1
|
Nimitha U, Ameer PM. MRI super-resolution using similarity distance and multi-scale receptive field based feature fusion GAN and pre-trained slice interpolation network. Magn Reson Imaging 2024:S0730-725X(24)00134-6. [PMID: 38653336 DOI: 10.1016/j.mri.2024.04.021] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/19/2023] [Revised: 03/04/2024] [Accepted: 04/14/2024] [Indexed: 04/25/2024]
Abstract
Challenges arise in achieving high-resolution Magnetic Resonance Imaging (MRI) to improve disease diagnosis accuracy due to limitations in hardware, patient discomfort, long acquisition times, and high costs. While Convolutional Neural Networks (CNNs) have shown promising results in MRI super-resolution, they often don't look into the structural similarity and prior information available in consecutive MRI slices. By leveraging information from sequential slices, more robust features can be obtained, potentially leading to higher-quality MRI slices. We propose a multi-slice two-dimensional (2D) MRI super-resolution network that combines a Generative Adversarial Network (GAN) with feature fusion and a pre-trained slice interpolation network to achieve three-dimensional (3D) super-resolution. The proposed model requires consecutively acquired three low-resolution (LR) MRI slices along a specific axis, and achieves the reconstruction of the MRI slices in the remaining two axes. The network effectively enhances both in-plane and out-of-plane resolution along the sagittal axis while addressing computational and memory constraints in 3D super-resolution. The proposed generator has a in-plane and out-of-plane Attention (IOA) network that fuses both in-plane and out-plane features of MRI dynamically. In terms of out-of-plane attention, the network merges features by considering the similarity distance between features and for in-plane attention, the network employs a two-level pyramid structure with varying receptive fields to extract features at different scales, ensuring the inclusion of both global and local features. Subsequently, to achieve 3D MRI super-resolution, a pre-trained slice interpolation network is used that takes two consecutive super-resolved MRI slices to generate a new intermediate slice. To further enhance the network performance and perceptual quality, we introduce a feature up-sampling layer and a feature extraction block with Scaled Exponential Linear Unit (SeLU). Moreover, our super-resolution network incorporates VGG loss from a fine-tuned VGG-19 network to provide additional enhancement. Through experimental evaluations on the IXI dataset and BRATS dataset, using the peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM) and the number of training parameters, we demonstrate the superior performance of our method compared to the existing techniques. Also, the proposed model can be adapted or modified to achieve super-resolution for both 2D and 3D MRI data.
Collapse
Affiliation(s)
- U Nimitha
- Department of Electronics and Communication Engineering, National Institute of Technology Calicut, Kerala 673601, India.
| | - P M Ameer
- Department of Electronics and Communication Engineering, National Institute of Technology Calicut, Kerala 673601, India
| |
Collapse
|
2
|
Dai S, Guo X, Liu S, Tu L, Hu X, Cui J, Ruan Q, Tan X, Lu H, Jiang T, Xu J. Application of intelligent tongue image analysis in Conjunction with microbiomes in the diagnosis of MAFLD. Heliyon 2024; 10:e29269. [PMID: 38617943 PMCID: PMC11015139 DOI: 10.1016/j.heliyon.2024.e29269] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/15/2023] [Revised: 03/22/2024] [Accepted: 04/03/2024] [Indexed: 04/16/2024] Open
Abstract
Background Metabolic associated fatty liver disease (MAFLD) is a widespread liver disease that can lead to liver fibrosis and cirrhosis. Therefore, it is essential to develop early diagnosic and screening methods. Methods We performed a cross-sectional observational study. In this study, based on data from 92 patients with MAFLD and 74 healthy individuals, we observed the characteristics of tongue images, tongue coating and intestinal flora. A generative adversarial network was used to extract tongue image features, and 16S rRNA sequencing was performed using the tongue coating and intestinal flora. We then applied tongue image analysis technology combined with microbiome technology to obtain an MAFLD early screening model with higher accuracy. In addition, we compared different modelling methods, including Extreme Gradient Boosting (XGBoost), random forest, neural networks(MLP), stochastic gradient descent(SGD), and support vector machine(SVM). Results The results show that tongue-coating Streptococcus and Rothia, intestinal Blautia, and Streptococcus are potential biomarkers for MAFLD. The diagnostic model jointly incorporating tongue image features, basic information (gender, age, BMI), and tongue coating marker flora (Streptococcus, Rothia), can have an accuracy of 96.39%, higher than the accuracy value except for bacteria. Conclusion Combining computer-intelligent tongue diagnosis with microbiome technology enhances MAFLD diagnostic accuracy and provides a convenient early screening reference.
Collapse
Affiliation(s)
- Shixuan Dai
- Department of College of Traditional Chinese Medicine, Shanghai University of Traditional Chinese Medicine, 1200 Road, Shanghai, 201203, China
| | - Xiaojing Guo
- Department of Anesthesiology, Naval Medical University, No. 800, Xiangyin Road, Shanghai,200433, China
| | - Shi Liu
- Department of College of Traditional Chinese Medicine, Shanghai University of Traditional Chinese Medicine, 1200 Road, Shanghai, 201203, China
| | - Liping Tu
- Department of College of Traditional Chinese Medicine, Shanghai University of Traditional Chinese Medicine, 1200 Road, Shanghai, 201203, China
| | - Xiaojuan Hu
- Department of College of Traditional Chinese Medicine, Shanghai University of Traditional Chinese Medicine, 1200 Road, Shanghai, 201203, China
| | - Ji Cui
- Department of College of Traditional Chinese Medicine, Shanghai University of Traditional Chinese Medicine, 1200 Road, Shanghai, 201203, China
| | - QunSheng Ruan
- Department of Software, Xiamen University, No. 422, Siming South Road, Siming District, Xiamen City, Fujian Province, 361005, China
| | - Xin Tan
- Department of Computer Science and Technology, East China Normal University, No. 3663, Zhongshan North Road, Shanghai, 200062, China
| | - Hao Lu
- Department of Endocrinology, Shuguang Hospital Affiliated to Shanghai University of Traditional Chinese Medicine, No. 528, Zhangheng Road, Shanghai,200021, China
| | - Tao Jiang
- Department of College of Traditional Chinese Medicine, Shanghai University of Traditional Chinese Medicine, 1200 Road, Shanghai, 201203, China
| | - Jiatuo Xu
- Department of College of Traditional Chinese Medicine, Shanghai University of Traditional Chinese Medicine, 1200 Road, Shanghai, 201203, China
| |
Collapse
|
3
|
Hao L, Bakkes THGF, van Diepen A, Chennakeshava N, Bouwman RA, De Bie Dekker AJR, Woerlee PH, Mojoli F, Mischi M, Shi Y, Turco S. An adversarial learning approach to generate pressure support ventilation waveforms for asynchrony detection. Comput Methods Programs Biomed 2024; 250:108175. [PMID: 38640840 DOI: 10.1016/j.cmpb.2024.108175] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 01/08/2024] [Revised: 04/11/2024] [Accepted: 04/11/2024] [Indexed: 04/21/2024]
Abstract
BACKGROUND AND OBJECTIVE Mechanical ventilation is a life-saving treatment for critically-ill patients. During treatment, patient-ventilator asynchrony (PVA) can occur, which can lead to pulmonary damage, complications, and higher mortality. While traditional detection methods for PVAs rely on visual inspection by clinicians, in recent years, machine learning models are being developed to detect PVAs automatically. However, training these models requires large labeled datasets, which are difficult to obtain, as labeling is a labour-intensive and time-consuming task, requiring clinical expertise. Simulating the lung-ventilator interactions has been proposed to obtain large labeled datasets to train machine learning classifiers. However, the obtained data lacks the influence of different hardware, of servo-controlled algorithms, and different sources of noise. Here, we propose VentGAN, an adversarial learning approach to improve simulated data by learning the ventilator fingerprints from unlabeled clinical data. METHODS In VentGAN, the loss functions are designed to add characteristics of clinical waveforms to the generated results, while preserving the labels of the simulated waveforms. To validate VentGAN, we compare the performance for detection and classification of PVAs when training a previously developed machine learning algorithm with the original simulated data and with the data generated by VentGAN. Testing is performed on independent clinical data labeled by experts. The McNemar test is applied to evaluate statistical differences in the obtained classification accuracy. RESULTS VentGAN significantly improves the classification accuracy for late cycling, early cycling and normal breaths (p< 0.01); no significant difference in accuracy was observed for delayed inspirations (p = 0.2), while the accuracy decreased for ineffective efforts (p< 0.01). CONCLUSIONS Generation of realistic synthetic data with labels by the proposed framework is feasible and represents a promising avenue for improving training of machine learning models.
Collapse
Affiliation(s)
- L Hao
- Electrical Engineering, Eindhoven University of Technology, Eindhoven University of Technology, Den Dolech 12, Eindhoven 5612AZ, the Netherlands
| | - T H G F Bakkes
- Electrical Engineering, Eindhoven University of Technology, Eindhoven University of Technology, Den Dolech 12, Eindhoven 5612AZ, the Netherlands
| | - A van Diepen
- Electrical Engineering, Eindhoven University of Technology, Eindhoven University of Technology, Den Dolech 12, Eindhoven 5612AZ, the Netherlands
| | - N Chennakeshava
- Electrical Engineering, Eindhoven University of Technology, Eindhoven University of Technology, Den Dolech 12, Eindhoven 5612AZ, the Netherlands
| | - R A Bouwman
- Catharina Hospital, Michelangelolaan 2, Eindhoven, Noord-Brabant, EJ 5623, the Netherlands
| | - A J R De Bie Dekker
- Catharina Hospital, Michelangelolaan 2, Eindhoven, Noord-Brabant, EJ 5623, the Netherlands
| | - P H Woerlee
- Catharina Hospital, Michelangelolaan 2, Eindhoven, Noord-Brabant, EJ 5623, the Netherlands
| | - F Mojoli
- Fondazione I.R.C.C.S. Policlinico San Matteo and the University of Pavia, S.da Nuova, 65, Pavia 27100, Italy
| | - M Mischi
- Electrical Engineering, Eindhoven University of Technology, Eindhoven University of Technology, Den Dolech 12, Eindhoven 5612AZ, the Netherlands
| | - Y Shi
- School of Automation Science and Electrical Engineering, Beihang University, Beijing 100191, China
| | - S Turco
- Electrical Engineering, Eindhoven University of Technology, Eindhoven University of Technology, Den Dolech 12, Eindhoven 5612AZ, the Netherlands.
| |
Collapse
|
4
|
Islam M, Zunair H, Mohammed N. CosSIF: Cosine similarity-based image filtering to overcome low inter-class variation in synthetic medical image datasets. Comput Biol Med 2024; 172:108317. [PMID: 38492455 DOI: 10.1016/j.compbiomed.2024.108317] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/08/2023] [Revised: 01/27/2024] [Accepted: 03/12/2024] [Indexed: 03/18/2024]
Abstract
Crafting effective deep learning models for medical image analysis is a complex task, particularly in cases where the medical image dataset lacks significant inter-class variation. This challenge is further aggravated when employing such datasets to generate synthetic images using generative adversarial networks (GANs), as the output of GANs heavily relies on the input data. In this research, we propose a novel filtering algorithm called Cosine Similarity-based Image Filtering (CosSIF). We leverage CosSIF to develop two distinct filtering methods: Filtering Before GAN Training (FBGT) and Filtering After GAN Training (FAGT). FBGT involves the removal of real images that exhibit similarities to images of other classes before utilizing them as the training dataset for a GAN. On the other hand, FAGT focuses on eliminating synthetic images with less discriminative features compared to real images used for training the GAN. The experimental results reveal that the utilization of either the FAGT or FBGT method reduces low inter-class variation in clinical image classification datasets and enables GANs to generate synthetic images with greater discriminative features. Moreover, modern transformer and convolutional-based models, trained with datasets that utilize these filtering methods, lead to less bias toward the majority class, more accurate predictions of samples in the minority class, and overall better generalization capabilities. Code and implementation details are available at: https://github.com/mominul-ssv/cossif.
Collapse
Affiliation(s)
- Mominul Islam
- Department of Electrical and Computer Engineering, North South University, Bashundhara, Dhaka, Bangladesh.
| | - Hasib Zunair
- Concordia Institute for Information Systems Engineering, Concordia University, Montreal, QC, Canada.
| | - Nabeel Mohammed
- Department of Electrical and Computer Engineering, North South University, Bashundhara, Dhaka, Bangladesh.
| |
Collapse
|
5
|
Hu X, Lin C, Chen T, Chen W. Interactive design generation and optimization from generative adversarial networks in spatial computing. Sci Rep 2024; 14:5154. [PMID: 38431717 PMCID: PMC10908823 DOI: 10.1038/s41598-024-54783-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/09/2023] [Accepted: 02/16/2024] [Indexed: 03/05/2024] Open
Abstract
This paper focuses on exploring the application possibilities and optimization problems of Generative Adversarial Networks (GANs) in spatial computing to improve design efficiency and creativity and achieve a more intelligent design process. A method for icon generation is proposed, and a basic architecture for icon generation is constructed. A system with generation and optimization capabilities is constructed to meet various requirements in spatial design by introducing the concept of interactive design and the characteristics of requirement conditions. Next, the generated icons can effectively maintain diversity and innovation while meeting the conditional features by integrating multi-feature recognition modules into the discriminator and optimizing the structure of conditional features. The experiment uses publicly available icon datasets, including LLD-Icon and Icons-50. The icon shape generated by the model proposed here is more prominent, and the color of colored icons can be more finely controlled. The Inception Score (IS) values under different models are compared, and it is found that the IS value of the proposed model is 7.05, which is higher than that of other GAN models. The multi-feature icon generation model based on Auxiliary Classifier GANs performs well in presenting multiple feature representations of icons. After introducing multi-feature recognition modules into the network model, the peak error of the recognition network is only 2.000 in the initial stage, while the initial error of the ordinary GAN without multi-feature recognition modules is as high as 5.000. It indicates that the improved model effectively helps the discriminative network recognize the core information of icon images more quickly. The research results provide a reference basis for achieving more efficient and innovative interactive space design.
Collapse
Affiliation(s)
- Xiaochen Hu
- School of Design and Innovation, China Academy of Art, Hangzhou, 310000, Zhejiang, China.
| | - Cun Lin
- School of Design and Innovation, China Academy of Art, Hangzhou, 310000, Zhejiang, China
| | - Tianyi Chen
- School of Design and Innovation, China Academy of Art, Hangzhou, 310000, Zhejiang, China
| | - Weibo Chen
- School of Design and Innovation, China Academy of Art, Hangzhou, 310000, Zhejiang, China
| |
Collapse
|
6
|
Wei K, Kong W, Liu L, Wang J, Li B, Zhao B, Li Z, Zhu J, Yu G. CT synthesis from MR images using frequency attention conditional generative adversarial network. Comput Biol Med 2024; 170:107983. [PMID: 38286104 DOI: 10.1016/j.compbiomed.2024.107983] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/24/2023] [Revised: 12/24/2023] [Accepted: 01/13/2024] [Indexed: 01/31/2024]
Abstract
Magnetic resonance (MR) image-guided radiotherapy is widely used in the treatment planning of malignant tumors, and MR-only radiotherapy, a representative of this technique, requires synthetic computed tomography (sCT) images for effective radiotherapy planning. Convolutional neural networks (CNN) have shown remarkable performance in generating sCT images. However, CNN-based models tend to synthesize more low-frequency components and the pixel-wise loss function usually used to optimize the model can result in blurred images. To address these problems, a frequency attention conditional generative adversarial network (FACGAN) is proposed in this paper. Specifically, a frequency cycle generative model (FCGM) is designed to enhance the inter-mapping between MR and CT and extract more rich tissue structure information. Additionally, a residual frequency channel attention (RFCA) module is proposed and incorporated into the generator to enhance its ability in perceiving the high-frequency image features. Finally, high-frequency loss (HFL) and cycle consistency high-frequency loss (CHFL) are added to the objective function to optimize the model training. The effectiveness of the proposed model is validated on pelvic and brain datasets and compared with state-of-the-art deep learning models. The results show that FACGAN produces higher-quality sCT images while retaining clearer and richer high-frequency texture information.
Collapse
Affiliation(s)
- Kexin Wei
- Shandong Key Laboratory of Medical Physics and Image Processing, Shandong Institute of Industrial Technology for Health Sciences and Precision Medicine, School of Physics and Electronics, Shandong Normal University, Jinan, China
| | - Weipeng Kong
- Shandong Key Laboratory of Medical Physics and Image Processing, Shandong Institute of Industrial Technology for Health Sciences and Precision Medicine, School of Physics and Electronics, Shandong Normal University, Jinan, China
| | - Liheng Liu
- Department of Radiology, Zhongshan Hospital, Fudan University, Shanghai, China
| | - Jian Wang
- Department of Radiology, Central Hospital Affiliated to Shandong First Medical University, Jinan, China
| | - Baosheng Li
- Shandong Cancer Hospital and Institute, Shandong First Medical University and Shandong Academy of Medical Sciences, No.440, Jiyan Road, Jinan, 250117, Shandong Province, China
| | - Bo Zhao
- Shandong Key Laboratory of Medical Physics and Image Processing, Shandong Institute of Industrial Technology for Health Sciences and Precision Medicine, School of Physics and Electronics, Shandong Normal University, Jinan, China
| | - Zhenjiang Li
- Shandong Cancer Hospital and Institute, Shandong First Medical University and Shandong Academy of Medical Sciences, No.440, Jiyan Road, Jinan, 250117, Shandong Province, China
| | - Jian Zhu
- Shandong Cancer Hospital and Institute, Shandong First Medical University and Shandong Academy of Medical Sciences, No.440, Jiyan Road, Jinan, 250117, Shandong Province, China.
| | - Gang Yu
- Shandong Key Laboratory of Medical Physics and Image Processing, Shandong Institute of Industrial Technology for Health Sciences and Precision Medicine, School of Physics and Electronics, Shandong Normal University, Jinan, China.
| |
Collapse
|
7
|
Wen N, Liu Z, Wang W, Wang S. Feedback linearization control for uncertain nonlinear systems via generative adversarial networks. ISA Trans 2024; 146:555-566. [PMID: 38172034 DOI: 10.1016/j.isatra.2023.12.033] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/28/2022] [Revised: 09/30/2023] [Accepted: 12/22/2023] [Indexed: 01/05/2024]
Abstract
This article presents a novel approach to leverage generative adversarial networks(GANs) techniques to learn a feedback linearization controller(FLC) for a class of uncertain nonlinear systems. By estimating uncertainty through the adversarial process, where ground truth samples are exclusively obtained from a predefined integral model, the feedback linearization controller, learned through a minimax two-player optimization framework, enhances the reference tracking performance of the input-output uncertain nonlinear system. Furthermore, we provide theoretical guarantee of convergence and stability, demonstrating the safe recovery of robust FLC. We also address the common challenge of mode collapse in GANs training through the strict convexity of our synthesized generator structure and an enhanced adversarial loss. Comprehensive simulations and practical experiments are conducted to underscore the superiority and efficacy of our proposed approach.
Collapse
Affiliation(s)
- Nuan Wen
- School of Automation Science and Electrical Engineering, Beihang University, 37 XueYuan Road, Haidian District, Beijing 100191, China
| | - Zhenghua Liu
- School of Automation Science and Electrical Engineering, Beihang University, 37 XueYuan Road, Haidian District, Beijing 100191, China.
| | - Weihong Wang
- School of Automation Science and Electrical Engineering, Beihang University, 37 XueYuan Road, Haidian District, Beijing 100191, China
| | - Shaoping Wang
- School of Automation Science and Electrical Engineering, Beihang University, 37 XueYuan Road, Haidian District, Beijing 100191, China
| |
Collapse
|
8
|
Lu X, Liang X, Liu W, Miao X, Guan X. ReeGAN: MRI image edge-preserving synthesis based on GANs trained with misaligned data. Med Biol Eng Comput 2024:10.1007/s11517-024-03035-w. [PMID: 38396277 DOI: 10.1007/s11517-024-03035-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/20/2023] [Accepted: 01/27/2024] [Indexed: 02/25/2024]
Abstract
As a crucial medical examination technique, different modalities of magnetic resonance imaging (MRI) complement each other, offering multi-angle and multi-dimensional insights into the body's internal information. Therefore, research on MRI cross-modality conversion is of great significance, and many innovative techniques have been explored. However, most methods are trained on well-aligned data, and the impact of misaligned data has not received sufficient attention. Additionally, many methods focus on transforming the entire image and ignore crucial edge information. To address these challenges, we propose a generative adversarial network based on multi-feature fusion, which effectively preserves edge information while training on noisy data. Notably, we consider images with limited range random transformations as noisy labels and use an additional small auxiliary registration network to help the generator adapt to the noise distribution. Moreover, we inject auxiliary edge information to improve the quality of synthesized target modality images. Our goal is to find the best solution for cross-modality conversion. Comprehensive experiments and ablation studies demonstrate the effectiveness of the proposed method.
Collapse
Affiliation(s)
- Xiangjiang Lu
- Guangxi Key Lab of Multi-Source Information Mining & Security, School of Computer Science and Engineering & School of Software, Guangxi Normal University, Guilin, 541004, China.
| | - Xiaoshuang Liang
- Guangxi Key Lab of Multi-Source Information Mining & Security, School of Computer Science and Engineering & School of Software, Guangxi Normal University, Guilin, 541004, China
| | - Wenjing Liu
- Guangxi Key Lab of Multi-Source Information Mining & Security, School of Computer Science and Engineering & School of Software, Guangxi Normal University, Guilin, 541004, China
| | - Xiuxia Miao
- Guangxi Key Lab of Multi-Source Information Mining & Security, School of Computer Science and Engineering & School of Software, Guangxi Normal University, Guilin, 541004, China
| | - Xianglong Guan
- Guangxi Key Lab of Multi-Source Information Mining & Security, School of Computer Science and Engineering & School of Software, Guangxi Normal University, Guilin, 541004, China
| |
Collapse
|
9
|
Mishra AK, Paliwal S, Srivastava G. Anomaly detection using deep convolutional generative adversarial networks in the internet of things. ISA Trans 2024; 145:493-504. [PMID: 38105170 DOI: 10.1016/j.isatra.2023.12.005] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/03/2023] [Revised: 11/15/2023] [Accepted: 12/01/2023] [Indexed: 12/19/2023]
Abstract
Advanced 5 G and 6 G technologies have accelerated the adoption of the Internet of Things (IoT) and are a priority in providing support for high-speed communication and fast data analysis. One of IoT networks benefits is automated networking, which unfortunately increases the risk of security, integrity, and privacy breaches. Therefore, in this paper, we propose a weighted stacked ensemble model combining deep convolutional generative adversarial and bidirectional long short-term memory networks. The proposed model has been regularized, and hyperparameter tuning has been performed. The tuned model is then evaluated on four publicly available current IoT datasets. The proposed model exhibits significant improvement in standard performance measures for both binary and multiclass classification. Generalization error has been reduced by a rate of 0.005% and to overcome the issue of overfitting, a L2 regularization technique has been deployed. The overall Accuracy of the model on various datasets is 99.99% for BOT-IoT, 99.08% for IoT23, 99.82% for UNSWNB15, and 99.96% for ToN_IoT, respectively, alongside improvements in Precision, Recall, and F1-score.
Collapse
Affiliation(s)
- Amit Kumar Mishra
- Department of Computer Science & Engineering, Jain University, Bengaluru, Karnataka, India.
| | - Shweta Paliwal
- Institute of Innovation in Technology and Management, Delhi, India
| | - Gautam Srivastava
- Department of Math and Computer Science, Brandon University, Canada; Research Centre for Interneural Computing, China Medical University, Taichung, Taiwan; Department of Computer Science and Math, Lebanese American University, Beirut, Lebanon.
| |
Collapse
|
10
|
Santos da Silva G, Casanova D, Oliva JT, Rodrigues EO. Cardiac fat segmentation using computed tomography and an image-to-image conditional generative adversarial neural network. Med Eng Phys 2024; 124:104104. [PMID: 38418017 DOI: 10.1016/j.medengphy.2024.104104] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/15/2022] [Revised: 08/17/2023] [Accepted: 01/09/2024] [Indexed: 03/01/2024]
Abstract
In recent years, research has highlighted the association between increased adipose tissue surrounding the human heart and elevated susceptibility to cardiovascular diseases such as atrial fibrillation and coronary heart disease. However, the manual segmentation of these fat deposits has not been widely implemented in clinical practice due to the substantial workload it entails for medical professionals and the associated costs. Consequently, the demand for more precise and time-efficient quantitative analysis has driven the emergence of novel computational methods for fat segmentation. This study presents a novel deep learning-based methodology that offers autonomous segmentation and quantification of two distinct types of cardiac fat deposits. The proposed approach leverages the pix2pix network, a generative conditional adversarial network primarily designed for image-to-image translation tasks. By applying this network architecture, we aim to investigate its efficacy in tackling the specific challenge of cardiac fat segmentation, despite not being originally tailored for this purpose. The two types of fat deposits of interest in this study are referred to as epicardial and mediastinal fats, which are spatially separated by the pericardium. The experimental results demonstrated an average accuracy of 99.08% and f1-score 98.73 for the segmentation of the epicardial fat and 97.90% of accuracy and f1-score of 98.40 for the mediastinal fat. These findings represent the high precision and overlap agreement achieved by the proposed methodology. In comparison to existing studies, our approach exhibited superior performance in terms of f1-score and run time, enabling the images to be segmented in real time.
Collapse
Affiliation(s)
- Guilherme Santos da Silva
- Academic Department of Informatics, Universidade Tecnológica Federal do Paraná (UTFPR), Pato Branco, 85503-390, Brazil
| | - Dalcimar Casanova
- Academic Department of Informatics, Universidade Tecnológica Federal do Paraná (UTFPR), Pato Branco, 85503-390, Brazil
| | - Jefferson Tales Oliva
- Academic Department of Informatics, Universidade Tecnológica Federal do Paraná (UTFPR), Pato Branco, 85503-390, Brazil
| | - Erick Oliveira Rodrigues
- Academic Department of Informatics, Universidade Tecnológica Federal do Paraná (UTFPR), Pato Branco, 85503-390, Brazil; Graduate Program of Production and Systems Engineering, Universidade Tecnológica Federal do Paraná (UTFPR), Pato Branco, 85503-390, Brazil.
| |
Collapse
|
11
|
Kucukler OF, Amira A, Malekmohamadi H. EEG dataset for energy data visualizations. Data Brief 2024; 52:109933. [PMID: 38125371 PMCID: PMC10733112 DOI: 10.1016/j.dib.2023.109933] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/23/2023] [Revised: 11/20/2023] [Accepted: 12/05/2023] [Indexed: 12/23/2023] Open
Abstract
User behavior plays a substantial role in shaping household energy use. Nevertheless, the methodologies employed by researchers to examine user behavior exhibit certain limitations in terms of their reach. The present article introduces an openly accessible collection of electroencephalography (EEG) recordings, comprising EEG data collected from individuals who were subjected to energy data visualizations. The dataset comprises EEG recordings obtained from 28 individuals who were in good health. The EEG recordings were collected using a 32-channel EMOTIV EEG device, and the international 10-20 electrode system was employed for precise electrode placement. The energy data visualizations were generated and showcased utilizing the PsychoPy software. To ascertain the participants' affective state, they were requested to rate the valence and arousal of each stimulus through the utilization of a self-assessment manikin (SAM). Additionally, three inquiries were posed for every stimulation. The dataset includes both original data visualizations and ratings. Additionally, the raw EEG data has been divided into segments consisting of data visualizations and neutral images, with the use of event markers, in order to assist analysis. The EEG recordings were recorded and stored utilizing the EMOTIVPro application, whereas the subjective reactions were captured and preserved using the PsychoPy application. Furthermore, the generation of synthetic EEG data is accomplished by employing the Generative Adversarial Network (GAN) architecture on the acquired EEG dataset. The synthetic EEG data created is integrated with empirical EEG data, and afterwards subjected to qualitative and quantitative analysis in order to improve performance. The dataset presented herein showcases a pioneering utilization of EEG investigation and offers a valuable foundation for scholars in the domains of computer science, energy conservation, artificial intelligence, brain-computer interfaces, and human-computer interaction.
Collapse
Affiliation(s)
| | - Abbes Amira
- Institute of Artificial Intelligence, De Montfort University, Leicester, UK
- Department of Computer Science, University of Sharjah, Sharjah, UAE
| | | |
Collapse
|
12
|
Wang Q, Li Z, Zhang S, Chi N, Dai Q. A versatile Wavelet-Enhanced CNN-Transformer for improved fluorescence microscopy image restoration. Neural Netw 2024; 170:227-241. [PMID: 37992510 DOI: 10.1016/j.neunet.2023.11.039] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/07/2023] [Revised: 11/06/2023] [Accepted: 11/17/2023] [Indexed: 11/24/2023]
Abstract
Fluorescence microscopes are indispensable tools for the life science research community. Nevertheless, the presence of optical component limitations, coupled with the maximum photon budget that the specimen can tolerate, inevitably leads to a decline in imaging quality and a lack of useful signals. Therefore, image restoration becomes essential for ensuring high-quality and accurate analyses. This paper presents the Wavelet-Enhanced Convolutional-Transformer (WECT), a novel deep learning technique developed specifically for the purpose of reducing noise in microscopy images and attaining super-resolution. Unlike traditional approaches, WECT integrates wavelet transform and inverse-transform for multi-resolution image decomposition and reconstruction, resulting in an expanded receptive field for the network without compromising information integrity. Subsequently, multiple consecutive parallel CNN-Transformer modules are utilized to collaboratively model local and global dependencies, thus facilitating the extraction of more comprehensive and diversified deep features. In addition, the incorporation of generative adversarial networks (GANs) into WECT enhances its capacity to generate high perceptual quality microscopic images. Extensive experiments have demonstrated that the WECT framework outperforms current state-of-the-art restoration methods on real fluorescence microscopy data under various imaging modalities and conditions, in terms of quantitative and qualitative analysis.
Collapse
Affiliation(s)
- Qinghua Wang
- School of Information Science and Technology, Fudan University, Shanghai, 200433, China.
| | - Ziwei Li
- School of Information Science and Technology, Fudan University, Shanghai, 200433, China; Shanghai ERC of LEO Satellite Communication and Applications, Shanghai CIC of LEO Satellite Communication Technology, Fudan University, Shanghai, 200433, China; Pujiang Laboratory, Shanghai, China.
| | - Shuqi Zhang
- School of Information Science and Technology, Fudan University, Shanghai, 200433, China.
| | - Nan Chi
- School of Information Science and Technology, Fudan University, Shanghai, 200433, China; Shanghai ERC of LEO Satellite Communication and Applications, Shanghai CIC of LEO Satellite Communication Technology, Fudan University, Shanghai, 200433, China; Shanghai Collaborative Innovation Center of Low-Earth-Orbit Satellite Communication Technology, Shanghai, 200433, China.
| | - Qionghai Dai
- School of Information Science and Technology, Fudan University, Shanghai, 200433, China; Department of Automation, Tsinghua University, Beijing, 100084, China.
| |
Collapse
|
13
|
Ravaee H, Manshaei MH, Safayani M, Sartakhti JS. Intelligent phenotype-detection and gene expression profile generation with generative adversarial networks. J Theor Biol 2024; 577:111636. [PMID: 37944593 DOI: 10.1016/j.jtbi.2023.111636] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/16/2023] [Revised: 08/11/2023] [Accepted: 10/05/2023] [Indexed: 11/12/2023]
Abstract
Gene expression analysis is valuable for cancer type classification and identifying diverse cancer phenotypes. The latest high-throughput RNA sequencing devices have enabled access to large volumes of gene expression data. However, we face several challenges, such as data security and privacy, when we develop machine learning-based classifiers for categorizing cancer types with these datasets. To address these issues, we propose IP3G (Intelligent Phenotype-detection and Gene expression profile Generation with Generative adversarial network), a model based on Generative Adversarial Networks. IP3G tackles two major problems: augmenting gene expression data and unsupervised phenotype discovery. By converting gene expression profiles into 2-Dimensional images and leveraging IP3G, we generate new profiles for specific phenotypes. IP3G learns disentangled representations of gene expression patterns and identifies phenotypes without labeled data. We improve the objective function of the GAN used in IP3G by employing the earth mover distance and a novel mutual information function. IP3G outperforms clustering methods like k-Means, DBSCAN, and GMM in unsupervised phenotype discovery, while also surpassing SVM and CNN classification accuracy by up to 6% through gene expression profile augmentation. The source code for the developed IP3G is accessible to the public on GitHub.
Collapse
Affiliation(s)
- Hamid Ravaee
- Department of Electrical and Computer Engineering, Isfahan University of Technology, Isfahan, 84156-83111, Iran
| | - Mohammad Hossein Manshaei
- Department of Electrical and Computer Engineering, Isfahan University of Technology, Isfahan, 84156-83111, Iran.
| | - Mehran Safayani
- Department of Electrical and Computer Engineering, Isfahan University of Technology, Isfahan, 84156-83111, Iran
| | | |
Collapse
|
14
|
Weng X, Song H, Lin Y, Wu Y, Zhang X, Liu B, Yang J. A joint learning method for incomplete and imbalanced data in electronic health record based on generative adversarial networks. Comput Biol Med 2024; 168:107687. [PMID: 38007974 DOI: 10.1016/j.compbiomed.2023.107687] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/19/2023] [Revised: 10/07/2023] [Accepted: 11/06/2023] [Indexed: 11/28/2023]
Abstract
Electronic health records (EHR), present challenges of incomplete and imbalanced data in clinical predictions. Previous studies addressed these two issues with two-step separately, which caused the decrease in the performance of prediction tasks. In this paper, we propose a unified framework to simultaneously addresses the challenges of incomplete and imbalanced data in EHR. Based on the framework, we develop a model called Missing Value Imputation and Imbalanced Learning Generative Adversarial Network (MVIIL-GAN). We use MVIIL-GAN to perform joint learning on the imputation process of high missing rate data and the conditional generation process of EHR data. The joint learning is achieved by introducing two discriminators to distinguish the fake data from the generated data at sample-level and variable-level. MVIIL-GAN integrate the missing values imputation and data generation in one step, improving the consistency of parameter optimization and the performance of prediction tasks. We evaluate our framework using the public dataset MIMIC-IV with high missing rates data and imbalanced data. Experimental results show that MVIIL-GAN outperforms existing methods in prediction performance. The implementation of MVIIL-GAN can be found at https://github.com/Peroxidess/MVIIL-GAN.
Collapse
Affiliation(s)
- Xutao Weng
- School of Computer Science and Technology, Beijing Institute of Technology, Beijing, 100081, China
| | - Hong Song
- School of Computer Science and Technology, Beijing Institute of Technology, Beijing, 100081, China.
| | - Yucong Lin
- School of Optics and Photonics, Beijing Institute of Technology, Beijing, 100081, China
| | - You Wu
- School of Medical Technology, Beijing Institute of Technology, Beijing, 100081, China
| | - Xi Zhang
- School of Computer Science and Technology, Beijing Institute of Technology, Beijing, 100081, China
| | - Bowen Liu
- School of Medical Technology, Beijing Institute of Technology, Beijing, 100081, China
| | - Jian Yang
- School of Optics and Photonics, Beijing Institute of Technology, Beijing, 100081, China.
| |
Collapse
|
15
|
Kassab M, Jehanzaib M, Başak K, Demir D, Keles GE, Turan M. FFPE++: Improving the quality of formalin-fixed paraffin-embedded tissue imaging via contrastive unpaired image-to-image translation. Med Image Anal 2024; 91:102992. [PMID: 37852162 DOI: 10.1016/j.media.2023.102992] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/17/2022] [Revised: 04/29/2023] [Accepted: 10/02/2023] [Indexed: 10/20/2023]
Abstract
Formalin-fixation and paraffin-embedding (FFPE) is a technique for preparing and preserving tissue specimens that has been utilized in histopathology since the late 19th century. This process is further complicated by FFPE preparation steps such as fixation, processing, embedding, microtomy, staining, and coverslipping, which often results in artifacts due to the complex histological and cytological characteristics of a tissue specimen. The term "artifacts" includes, but is not limited to, staining inconsistencies, tissue folds, chattering, pen marks, blurring, air bubbles, and contamination. The presence of artifacts may interfere with pathological diagnosis in disease detection, subtyping, grading, and choice of therapy. In this study, we propose FFPE++, an unpaired image-to-image translation method based on contrastive learning with a mixed channel-spatial attention module and self-regularization loss that drastically corrects the aforementioned artifacts in FFPE tissue sections. Turing tests were performed by 10 board-certified pathologists with more than 10 years of experience. These tests which were performed for ovarian carcinoma, lung adenocarcinoma, lung squamous cell carcinoma, and papillary thyroid carcinoma, demonstrate the clear superiority of the proposed method in many clinical aspects compared with standard FFPE images. Based on the qualitative experiments and feedback from the Turing tests, we believe that FFPE++ can contribute to substantial diagnostic and prognostic accuracy in clinical pathology in the future and can also improve the performance of AI tools in digital pathology. The code and dataset are publicly available at https://github.com/DeepMIALab/FFPEPlus.
Collapse
Affiliation(s)
- Mohamad Kassab
- Department of Computer Engineering, Bogazici University, Istanbul, Turkey
| | - Muhammad Jehanzaib
- Department of Computer Engineering, Bogazici University, Istanbul, Turkey
| | - Kayhan Başak
- Sağlık Bilimleri University, Kartal Dr.Lütfi Kırdar City Hospital, Department of Pathology, Istanbul, Turkey
| | - Derya Demir
- Faculty of Medicine, Department of Pathology, Ege University, Izmir, Turkey
| | | | - Mehmet Turan
- Department of Computer Engineering, Bogazici University, Istanbul, Turkey.
| |
Collapse
|
16
|
Gou Y, Li M, Zhang Y, He Z, He Y. Few-shot image generation with reverse contrastive learning. Neural Netw 2024; 169:154-164. [PMID: 37890365 DOI: 10.1016/j.neunet.2023.10.026] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/10/2023] [Revised: 08/27/2023] [Accepted: 10/18/2023] [Indexed: 10/29/2023]
Abstract
Generative models, such as Generative Adversarial Networks (GANs), have recently shown remarkable capabilities in various generation tasks. However, the success of these models heavily depends on the availability of a large-scale training dataset. When the size of the training dataset is limited, the quality and diversity of the generated results suffer from severe degradation. In this paper, we propose a novel approach, Reverse Contrastive Learning (RCL), to address the problem of high-quality and diverse image generation under few-shot settings. The success of RCL benefits from a two-sided, powerful regularization. Our proposed regularization is designed based on the correlation between generated samples, which can effectively utilize the latent feature information between different levels of samples. It does not require any auxiliary information or augmentation techniques. A series of qualitative and quantitative results show that our proposed method is superior to the existing State-Of-The-Art (SOTA) methods under the few-shot setting and is still competitive under the low-shot setting, showcasing the effectiveness of RCL. Code will be released upon acceptance at https://github.com/gouayao/RCL.
Collapse
Affiliation(s)
- Yao Gou
- Xi'an High-Tech Research Institute, Xi'an, 710025, China.
| | - Min Li
- Xi'an High-Tech Research Institute, Xi'an, 710025, China.
| | - Yusen Zhang
- Xi'an High-Tech Research Institute, Xi'an, 710025, China.
| | - Zhuzhen He
- Xi'an High-Tech Research Institute, Xi'an, 710025, China.
| | - Yujie He
- Xi'an High-Tech Research Institute, Xi'an, 710025, China.
| |
Collapse
|
17
|
Deshpande S, Dawood M, Minhas F, Rajpoot N. SynCLay: Interactive synthesis of histology images from bespoke cellular layouts. Med Image Anal 2024; 91:102995. [PMID: 37898050 DOI: 10.1016/j.media.2023.102995] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/30/2022] [Revised: 09/27/2023] [Accepted: 10/02/2023] [Indexed: 10/30/2023]
Abstract
Automated synthesis of histology images has several potential applications in computational pathology. However, no existing method can generate realistic tissue images with a bespoke cellular layout or user-defined histology parameters. In this work, we propose a novel framework called SynCLay (Synthesis from Cellular Layouts) that can construct realistic and high-quality histology images from user-defined cellular layouts along with annotated cellular boundaries. Tissue image generation based on bespoke cellular layouts through the proposed framework allows users to generate different histological patterns from arbitrary topological arrangement of different types of cells (e.g., neutrophils, lymphocytes, epithelial cells and others). SynCLay generated synthetic images can be helpful in studying the role of different types of cells present in the tumor microenvironment. Additionally, they can assist in balancing the distribution of cellular counts in tissue images for designing accurate cellular composition predictors by minimizing the effects of data imbalance. We train SynCLay in an adversarial manner and integrate a nuclear segmentation and classification model in its training to refine nuclear structures and generate nuclear masks in conjunction with synthetic images. During inference, we combine the model with another parametric model for generating colon images and associated cellular counts as annotations given the grade of differentiation and cellularities (cell densities) of different cells. We assess the generated images quantitatively using the Frechet Inception Distance and report on feedback from trained pathologists who assigned realism scores to a set of images generated by the framework. The average realism score across all pathologists for synthetic images was as high as that for the real images. Moreover, with the assistance from pathologists, we showcase the ability of the generated images to accurately differentiate between benign and malignant tumors, thus reinforcing their reliability. We demonstrate that the proposed framework can be used to add new cells to a tissue images and alter cellular positions. We also show that augmenting limited real data with the synthetic data generated by our framework can significantly boost prediction performance of the cellular composition prediction task. The implementation of the proposed SynCLay framework is available at https://github.com/Srijay/SynCLay-Framework.
Collapse
Affiliation(s)
- Srijay Deshpande
- Tissue Image Analytics Centre, Department of Computer Science, University of Warwick, UK.
| | - Muhammad Dawood
- Tissue Image Analytics Centre, Department of Computer Science, University of Warwick, UK
| | - Fayyaz Minhas
- Tissue Image Analytics Centre, Department of Computer Science, University of Warwick, UK
| | - Nasir Rajpoot
- Tissue Image Analytics Centre, Department of Computer Science, University of Warwick, UK; The Alan Turing Institute, London, UK; Department of Pathology, University Hospitals Coventry & Warwickshire, UK; Histofy Ltd, Birmingham, UK.
| |
Collapse
|
18
|
Muffoletto M, Xu H, Kunze KP, Neji R, Botnar R, Prieto C, Rückert D, Young AA. Combining generative modelling and semi-supervised domain adaptation for whole heart cardiovascular magnetic resonance angiography segmentation. J Cardiovasc Magn Reson 2023; 25:80. [PMID: 38124106 PMCID: PMC10734115 DOI: 10.1186/s12968-023-00981-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/14/2023] [Accepted: 11/12/2023] [Indexed: 12/23/2023] Open
Abstract
BACKGROUND Quantification of three-dimensional (3D) cardiac anatomy is important for the evaluation of cardiovascular diseases. Changes in anatomy are indicative of remodeling processes as the heart tissue adapts to disease. Although robust segmentation methods exist for computed tomography angiography (CTA), few methods exist for whole-heart cardiovascular magnetic resonance angiograms (CMRA) which are more challenging due to variable contrast, lower signal to noise ratio and a limited amount of labeled data. METHODS Two state-of-the-art unsupervised generative deep learning domain adaptation architectures, generative adversarial networks and variational auto-encoders, were applied to 3D whole heart segmentation of both conventional (n = 20) and high-resolution (n = 45) CMRA (target) images, given segmented CTA (source) images for training. An additional supervised loss function was implemented to improve performance given 10%, 20% and 30% segmented CMRA cases. A fully supervised nn-UNet trained on the given CMRA segmentations was used as the benchmark. RESULTS The addition of a small number of segmented CMRA training cases substantially improved performance in both generative architectures in both standard and high-resolution datasets. Compared with the nn-UNet benchmark, the generative methods showed substantially better performance in the case of limited labelled cases. On the standard CMRA dataset, an average 12% (adversarial method) and 10% (variational method) improvement in Dice score was obtained. CONCLUSIONS Unsupervised domain-adaptation methods for CMRA segmentation can be boosted by the addition of a small number of supervised target training cases. When only few labelled cases are available, semi-supervised generative modelling is superior to supervised methods.
Collapse
Affiliation(s)
- Marica Muffoletto
- School of Biomedical Engineering and Imaging Sciences, King's College, St Thomas' Hospital, 4th Floor Lambeth Wing, Westminster Bridge, London, SW1 7EH, UK.
| | - Hao Xu
- School of Biomedical Engineering and Imaging Sciences, King's College, St Thomas' Hospital, 4th Floor Lambeth Wing, Westminster Bridge, London, SW1 7EH, UK
| | - Karl P Kunze
- School of Biomedical Engineering and Imaging Sciences, King's College, St Thomas' Hospital, 4th Floor Lambeth Wing, Westminster Bridge, London, SW1 7EH, UK
- MR Research Collaborations, Siemens Healthcare Limited, Frimley, UK
| | - Radhouene Neji
- School of Biomedical Engineering and Imaging Sciences, King's College, St Thomas' Hospital, 4th Floor Lambeth Wing, Westminster Bridge, London, SW1 7EH, UK
- MR Research Collaborations, Siemens Healthcare Limited, Frimley, UK
| | - René Botnar
- School of Biomedical Engineering and Imaging Sciences, King's College, St Thomas' Hospital, 4th Floor Lambeth Wing, Westminster Bridge, London, SW1 7EH, UK
| | - Claudia Prieto
- School of Biomedical Engineering and Imaging Sciences, King's College, St Thomas' Hospital, 4th Floor Lambeth Wing, Westminster Bridge, London, SW1 7EH, UK
| | - Daniel Rückert
- Biomedical Image Analysis Group, Department of Computing, Imperial College London, London, UK
- Institute for Artificial Intelligence and Informatics in Medicine, Klinikum Rechts der Isar, Technical University of Munich, Munich, Germany
| | - Alistair A Young
- School of Biomedical Engineering and Imaging Sciences, King's College, St Thomas' Hospital, 4th Floor Lambeth Wing, Westminster Bridge, London, SW1 7EH, UK
| |
Collapse
|
19
|
Zou J, Yu J, Hu P, Zhao L, Shi S. STAGAN: An approach for improve the stability of molecular graph generation based on generative adversarial networks. Comput Biol Med 2023; 167:107691. [PMID: 37976819 DOI: 10.1016/j.compbiomed.2023.107691] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/21/2022] [Revised: 09/18/2023] [Accepted: 11/06/2023] [Indexed: 11/19/2023]
Abstract
With the wide application of deep learning in Drug Discovery, deep generative model has shown its advantages in drug molecular generation. Generative adversarial networks can be used to learn the internal structure of molecules, but the training process may be unstable, such as gradient disappearance and model collapse, which may lead to the generation of molecules that do not conform to chemical rules or a single style. In this paper, a novel method called STAGAN was proposed to solve the difficulty of model training, by adding a new gradient penalty term in the discriminator and designing a parallel layer of batch normalization used in generator. As an illustration of method, STAGAN generated higher valid and unique molecules than previous models in training datasets from QM9 and ZINC-250K. This indicates that the proposed method can effectively solve the instability problem in the model training process, and can provide more instructive guidance for the further study of molecular graph generation.
Collapse
Affiliation(s)
- Jinping Zou
- Department of Mathematics, School of Mathematics and Computer Sciences, Nanchang University, Nanchang, 330031, China; Institute of Mathematics and Interdisciplinary Sciences, Nanchang University, Nanchang, 330031, China
| | - Jialin Yu
- Department of Mathematics, School of Mathematics and Computer Sciences, Nanchang University, Nanchang, 330031, China; Institute of Mathematics and Interdisciplinary Sciences, Nanchang University, Nanchang, 330031, China
| | - Pengwei Hu
- Department of Mathematics, School of Mathematics and Computer Sciences, Nanchang University, Nanchang, 330031, China; Institute of Mathematics and Interdisciplinary Sciences, Nanchang University, Nanchang, 330031, China
| | - Long Zhao
- Department of Mathematics, School of Mathematics and Computer Sciences, Nanchang University, Nanchang, 330031, China; Institute of Mathematics and Interdisciplinary Sciences, Nanchang University, Nanchang, 330031, China
| | - Shaoping Shi
- Department of Mathematics, School of Mathematics and Computer Sciences, Nanchang University, Nanchang, 330031, China; Institute of Mathematics and Interdisciplinary Sciences, Nanchang University, Nanchang, 330031, China.
| |
Collapse
|
20
|
Jin R, Li X. Backdoor attack and defense in federated generative adversarial network-based medical image synthesis. Med Image Anal 2023; 90:102965. [PMID: 37804585 DOI: 10.1016/j.media.2023.102965] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/19/2022] [Revised: 07/12/2023] [Accepted: 09/11/2023] [Indexed: 10/09/2023]
Abstract
Deep Learning-based image synthesis techniques have been applied in healthcare research for generating medical images to support open research and augment medical datasets. Training generative adversarial neural networks (GANs) usually require large amounts of training data. Federated learning (FL) provides a way of training a central model using distributed data while keeping raw data locally. However, given that the FL server cannot access the raw data, it is vulnerable to backdoor attacks, an adversarial by poisoning training data. Most backdoor attack strategies focus on classification models and centralized domains. It is still an open question if the existing backdoor attacks can affect GAN training and, if so, how to defend against the attack in the FL setting. In this work, we investigate the overlooked issue of backdoor attacks in federated GANs (FedGANs). The success of this attack is subsequently determined to be the result of some local discriminators overfitting the poisoned data and corrupting the local GAN equilibrium, which then further contaminates other clients when averaging the generator's parameters and yields high generator loss. Therefore, we proposed FedDetect, an efficient and effective way of defending against the backdoor attack in the FL setting, which allows the server to detect the client's adversarial behavior based on their losses and block the malicious clients. Our extensive experiments on two medical datasets with different modalities demonstrate the backdoor attack on FedGANs can result in synthetic images with low fidelity. After detecting and suppressing the detected malicious clients using the proposed defense strategy, we show that FedGANs can synthesize high-quality medical datasets (with labels) for data augmentation to improve classification models' performance.
Collapse
Affiliation(s)
- Ruinan Jin
- Computer Science Department, The University of British Columbia, BC, V6T 1Z4, Canada
| | - Xiaoxiao Li
- Electrical and Computer Engineering Department, The University of British Columbia, BC, V6T 1Z4, Canada.
| |
Collapse
|
21
|
Chen L, Jing XY, Hao Y, Liu W, Zhu X, Han W. A novel two-way rebalancing strategy for identifying carbonylation sites. BMC Bioinformatics 2023; 24:429. [PMID: 37957582 PMCID: PMC10644465 DOI: 10.1186/s12859-023-05551-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/10/2023] [Accepted: 10/30/2023] [Indexed: 11/15/2023] Open
Abstract
BACKGROUND As an irreversible post-translational modification, protein carbonylation is closely related to many diseases and aging. Protein carbonylation prediction for related patients is significant, which can help clinicians make appropriate therapeutic schemes. Because carbonylation sites can be used to indicate change or loss of protein function, integrating these protein carbonylation site data has been a promising method in prediction. Based on these protein carbonylation site data, some protein carbonylation prediction methods have been proposed. However, most data is highly class imbalanced, and the number of un-carbonylation sites greatly exceeds that of carbonylation sites. Unfortunately, existing methods have not addressed this issue adequately. RESULTS In this work, we propose a novel two-way rebalancing strategy based on the attention technique and generative adversarial network (Carsite_AGan) for identifying protein carbonylation sites. Specifically, Carsite_AGan proposes a novel undersampling method based on attention technology that allows sites with high importance value to be selected from un-carbonylation sites. The attention technique can obtain the value of each sample's importance. In the meanwhile, Carsite_AGan designs a generative adversarial network-based oversampling method to generate high-feasibility carbonylation sites. The generative adversarial network can generate high-feasibility samples through its generator and discriminator. Finally, we use a classifier like a nonlinear support vector machine to identify protein carbonylation sites. CONCLUSIONS Experimental results demonstrate that our approach significantly outperforms other resampling methods. Using our approach to resampling carbonylation data can significantly improve the effect of identifying protein carbonylation sites.
Collapse
Affiliation(s)
- Linjun Chen
- School of Computer Science, Wuhan University, Wuhan, China
| | - Xiao-Yuan Jing
- School of Computer Science, Wuhan University, Wuhan, China.
- Guangdong Provincial Key Laboratory of Petrochemical Equipment Fault Diagnosis and School of Computer, Guangdong University of Petrochemical Technology, Maoming, China.
- State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China.
| | - Yaru Hao
- School of Computer Science, Wuhan University, Wuhan, China
| | - Wei Liu
- School of Computer Science, Wuhan University, Wuhan, China
| | - Xiaoke Zhu
- School of Computer and Information Engineering, Henan University, Kaifeng, China
| | - Wei Han
- School of Computer Science, Wuhan University, Wuhan, China
| |
Collapse
|
22
|
Pan X, Feng T, Zhang N. PVGAN: A Pathological Voice Generation Model Incorporating a Progressive Nesting Strategy. J Voice 2023:S0892-1997(23)00315-6. [PMID: 37940422 DOI: 10.1016/j.jvoice.2023.10.006] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/07/2023] [Revised: 10/04/2023] [Accepted: 10/04/2023] [Indexed: 11/10/2023]
Abstract
The voice generation task is to solve the problem of limited samples in the voice dataset using computer technology. By increasing the number of samples, the accuracy of voice disorder diagnosis can be improved, which has a wide range of application value in medical diagnosis and other fields. At present, there are insufficient models for detailed features such as pitch, timbre, and different frequency components in pathological voice data. Therefore, this paper proposes a PVGAN network for learning different frequency information of audio to generate pathological voice data. The proposed network captures the multi-scale features and different periodic patterns of audio signals by designing multiscale perceptual residual blocks and periodic discriminators. At the same time, a progressive nesting strategy was proposed to combine the generator and the discriminator to improve the learning ability of different resolution information. In addition, a latent mapping network is designed to fuse the latent vector with the condition information to generate sound features related to specific diseases or pathological states. The loss function is optimized to further improve the model performance. On the Saarbruecken Voice Database(SVD), the average values of each index of the data generated after training with different pathological types as conditional information are similar to the original data. Finally, the generated data were used to expand the SVD dataset, and the accuracy of the two classification experiments was improved to a certain extent.
Collapse
Affiliation(s)
- Xiaoying Pan
- Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing, Xi'an University of Posts and Telecommunications, Xi'an 710121, China; School of Computer Science & Technology, Xi'an University of Posts and Telecommunications, Xi'an 710121, China.
| | - Tong Feng
- Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing, Xi'an University of Posts and Telecommunications, Xi'an 710121, China; School of Computer Science & Technology, Xi'an University of Posts and Telecommunications, Xi'an 710121, China
| | - Nijuan Zhang
- Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing, Xi'an University of Posts and Telecommunications, Xi'an 710121, China; School of Computer Science & Technology, Xi'an University of Posts and Telecommunications, Xi'an 710121, China
| |
Collapse
|
23
|
Song F, Zhang W, Zheng Y, Shi D, He M. A deep learning model for generating fundus autofluorescence images from color fundus photography. Adv Ophthalmol Pract Res 2023; 3:192-198. [PMID: 38059165 PMCID: PMC10696390 DOI: 10.1016/j.aopr.2023.11.001] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 08/29/2023] [Revised: 11/04/2023] [Accepted: 11/05/2023] [Indexed: 12/08/2023]
Abstract
Background Fundus Autofluorescence (FAF) is a valuable imaging technique used to assess metabolic alterations in the retinal pigment epithelium (RPE) associated with various age-related and disease-related changes. The practical uses of FAF are ever-growing. This study aimed to evaluate the effectiveness of a generative deep learning (DL) model in translating color fundus (CF) images into synthetic FAF images and explore its potential for enhancing screening of age-related macular degeneration (AMD). Methods A generative adversarial network (GAN) model was trained on pairs of CF and FAF images to generate synthetic FAF images. The quality of synthesized FAF images was assessed objectively by common generation metrics. Additionally, the clinical effectiveness of the generated FAF images in AMD classification was evaluated by measuring the area under the curve (AUC), using the LabelMe dataset. Results A total of 8410 FAF images from 2586 patients were analyzed. The synthesized FAF images exhibited an impressive objectively assessed quality, achieving a multi-scale structural similarity index (MS-SSIM) of 0.67. When evaluated on the LabelMe dataset, the combination of generated FAF images and CF images resulted in a noteworthy improvement in AMD classification accuracy, with the AUC increasing from 0.931 to 0.968. Conclusions This study presents the first attempt to use a generative deep learning model to create authentic and high-quality FAF images from CF images. The incorporation of the translated FAF images on top of CF images improved the accuracy of AMD classification. Overall, this study presents a promising approach to enhance large-scale AMD screening.
Collapse
Affiliation(s)
- Fan Song
- Experimental Ophthalmology, School of Optometry, The Hong Kong Polytechnic University, Hong Kong, China
- Research Centre for SHARP Vision, The Hong Kong Polytechnic University, Hong Kong, China
| | - Weiyi Zhang
- Experimental Ophthalmology, School of Optometry, The Hong Kong Polytechnic University, Hong Kong, China
- Research Centre for SHARP Vision, The Hong Kong Polytechnic University, Hong Kong, China
| | - Yingfeng Zheng
- State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangdong Provincial Key Laboratory of Ophthalmology and Visual Science, Guangdong Provincial Clinical Research Center for Ocular Diseases, Guangzhou, China
| | - Danli Shi
- Experimental Ophthalmology, School of Optometry, The Hong Kong Polytechnic University, Hong Kong, China
- Research Centre for SHARP Vision, The Hong Kong Polytechnic University, Hong Kong, China
| | - Mingguang He
- Experimental Ophthalmology, School of Optometry, The Hong Kong Polytechnic University, Hong Kong, China
- Research Centre for SHARP Vision, The Hong Kong Polytechnic University, Hong Kong, China
| |
Collapse
|
24
|
Liang D, Zhang S, Zhao Z, Wang G, Sun J, Zhao J, Li W, Xu LX. Two-stage generative adversarial networks for metal artifact reduction and visualization in ablation therapy of liver tumors. Int J Comput Assist Radiol Surg 2023; 18:1991-2000. [PMID: 37391537 DOI: 10.1007/s11548-023-02986-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/08/2023] [Accepted: 06/12/2023] [Indexed: 07/02/2023]
Abstract
PURPOSE The strong metal artifacts produced by the electrode needle cause poor image quality, thus preventing physicians from observing the surgical situation during the puncture process. To address this issue, we propose a metal artifact reduction and visualization framework for CT-guided ablation therapy of liver tumors. METHODS Our framework contains a metal artifact reduction model and an ablation therapy visualization model. A two-stage generative adversarial network is proposed to reduce the metal artifacts of intraoperative CT images and avoid image blurring. To visualize the puncture process, the axis and tip of the needle are localized, and then the needle is rebuilt in 3D space intraoperatively. RESULTS Experiments show that our proposed metal artifact reduction method achieves higher SSIM (0.891) and PSNR (26.920) values than the state-of-the-art methods. The accuracy of ablation needle reconstruction is 2.76 mm average in needle tip localization and 1.64° average in needle axis localization. CONCLUSION We propose a novel metal artifact reduction and an ablation therapy visualization framework for CT-guided ablation therapy of liver cancer. The experiment results indicate that our approach can reduce metal artifacts and improve image quality. Furthermore, our proposed method demonstrates the potential for displaying the relative position of the tumor and the needle intraoperatively.
Collapse
Affiliation(s)
- Duan Liang
- School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China
| | - Shunan Zhang
- School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China
| | - Ziqi Zhao
- School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China
| | - Guangzhi Wang
- School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China
| | - Jianqi Sun
- School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China.
| | - Jun Zhao
- School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China
| | - Wentao Li
- Department of Radiology, Fudan University Shanghai Cancer Center, Shanghai, 200240, China
| | - Lisa X Xu
- School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China
| |
Collapse
|
25
|
Leewiwatwong S, Lu J, Dummer I, Yarnall K, Mummy D, Wang Z, Driehuys B. Combining neural networks and image synthesis to enable automatic thoracic cavity segmentation of hyperpolarized 129Xe MRI without proton scans. Magn Reson Imaging 2023; 103:145-155. [PMID: 37406744 PMCID: PMC10528669 DOI: 10.1016/j.mri.2023.07.001] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/01/2023] [Revised: 07/01/2023] [Accepted: 07/02/2023] [Indexed: 07/07/2023]
Abstract
RATIONALE AND OBJECTIVES Quantification of 129Xe MRI relies on accurate segmentation of the thoracic cavity, typically performed manually using a combination of 1H and 129Xe scans. This can be accelerated by using Convolutional Neural Networks (CNNs) that segment only the 129Xe scan. However, this task is complicated by peripheral ventilation defects, which requires training CNNs with large, diverse datasets. Here, we accelerate the creation of training data by synthesizing 129Xe images with a variety of defects. We use this to train a 3D model to provide thoracic cavity segmentation from 129Xe ventilation MRI alone. MATERIALS AND METHODS Training and testing data consisted of 22 and 33 3D 129Xe ventilation images. Training data were expanded to 484 using Template-based augmentation while an additional 298 images were synthesized using the Pix2Pix model. This data was used to train both a 2D U-net and 3D V-net-based segmentation model using a combination of Dice-Focal and Anatomical Constraint loss functions. Segmentation performance was compared using Dice coefficients calculated over the entire lung and within ventilation defects. RESULTS Performance of both U-net and 3D segmentation was improved by including synthetic training data. The 3D models performed significantly better than U-net, and the 3D model trained with synthetic 129Xe images exhibited the highest overall Dice score of 0.929. Moreover, addition of synthetic training data improved the Dice score in ventilation defect regions from 0.545 to 0.588 for U-net and 0.739 to 0.765 for the 3D model. CONCLUSION It is feasible to obtain high-quality segmentations from 129Xe scan alone using 3D models trained with additional synthetic images.
Collapse
Affiliation(s)
- Suphachart Leewiwatwong
- Center for In Vivo Microscopy, Duke University Medical Center, Durham, NC, USA; Department of Biomedical Engineering, Duke University, Durham, NC, USA
| | - Junlan Lu
- Center for In Vivo Microscopy, Duke University Medical Center, Durham, NC, USA; Department of Medical Physics, Duke University, Durham, NC, USA
| | - Isabelle Dummer
- Department of Biomedical Engineering, McGill University, Montréal, QC, Canada
| | - Kevin Yarnall
- Department of Mechanical Engineering, Duke University, Durham, NC, USA
| | - David Mummy
- Center for In Vivo Microscopy, Duke University Medical Center, Durham, NC, USA; Department of Radiology, Duke University Medical Center, Durham, NC
| | - Ziyi Wang
- Center for In Vivo Microscopy, Duke University Medical Center, Durham, NC, USA; Department of Biomedical Engineering, Duke University, Durham, NC, USA
| | - Bastiaan Driehuys
- Center for In Vivo Microscopy, Duke University Medical Center, Durham, NC, USA; Department of Biomedical Engineering, Duke University, Durham, NC, USA; Department of Medical Physics, Duke University, Durham, NC, USA; Department of Radiology, Duke University Medical Center, Durham, NC,.
| |
Collapse
|
26
|
Khan U, Yasin A. Plane invariant segmentation of computed tomography images through weighted cross entropy optimized conditional GANs in compressed formats. Med Biol Eng Comput 2023; 61:2677-2697. [PMID: 37428300 DOI: 10.1007/s11517-023-02846-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/25/2022] [Accepted: 05/12/2023] [Indexed: 07/11/2023]
Abstract
Computed tomography (CT) scan provides first-hand knowledge to doctors to identify an ailment. Deep neural networks help enhance image understanding through segmentation and labeling. In this work, we implement two variants of Pix2Pix generative adversarial networks (GANs) with varying complexities of generator and discriminator networks for plane invariant segmentation of CT scan images and subsequently propose an effective generative adversarial network with a suitably weighted binary cross-entropy loss function followed by image processing layer necessary for getting high-quality output segmentation. Our conditional GAN is powered by a unique set of an encoder-decoder network that coupled with the image processing layer produces enhanced segmentation. The network can be extended to the complete set of Hounsfield units and can also be implemented on smartphones. Furthermore, we also demonstrate effects on accuracy, F-1 score, and Jaccard index by using the conditional GAN networks on the spine vertebrae dataset, thus achieving an average of 86.28 % accuracy, 90.5 % Jaccard index score, and 89.9 % F-1 score in predicting segmented maps for validation input images. In addition, an overall lifting of accuracy, F-1 score, and Jaccard index graph for validation images with better continuity has also been highlighted.
Collapse
Affiliation(s)
- Usman Khan
- SS-CASE-IT Islamabad, Islamabad, Pakistan.
| | | |
Collapse
|
27
|
Barrera K, Rodellar J, Alférez S, Merino A. Automatic normalized digital color staining in the recognition of abnormal blood cells using generative adversarial networks. Comput Methods Programs Biomed 2023; 240:107629. [PMID: 37301181 DOI: 10.1016/j.cmpb.2023.107629] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/07/2023] [Revised: 05/23/2023] [Accepted: 05/28/2023] [Indexed: 06/12/2023]
Abstract
BACKGROUND AND OBJECTIVES Combining knowledge of clinical pathologists and deep learning models is a growing trend in morphological analysis of cells circulating in blood to add objectivity, accuracy, and speed in diagnosing hematological and non-hematological diseases. However, the variability in staining protocols across different laboratories can affect the color of images and performance of automatic recognition models. The objective of this work is to develop, train and evaluate a new system for the normalization of color staining of peripheral blood cell images, so that it transforms images from different centers to map the color staining of a reference center (RC) while preserving the structural morphological features. METHODS The system has two modules, GAN1 and GAN2. GAN1 uses the PIX2PIX technique to fade original color images to an adaptive gray, while GAN2 transforms them into RGB normalized images. Both GANs have a similar structure, where the generator is a U-NET convolutional neural network with ResNet and the discriminator is a classifier with ResNet34 structure. Digitally stained images were evaluated using GAN metrics and histograms to assess the ability to modify color without altering cell morphology. The system was also evaluated as a pre-processing tool before cells undergo a classification process. For this purpose, a CNN classifier was designed for three classes: abnormal lymphocytes, blasts and reactive lymphocytes. RESULTS Training of all GANs and the classifier was performed using RC images, while evaluations were conducted using images from four other centers. Classification tests were performed before and after applying the stain normalization system. The overall accuracy reached a similar value around 96% in both cases for the RC images, indicating the neutrality of the normalization model for the reference images. On the contrary, it was a significant improvement in the classification performance when applying the stain normalization to the other centers. Reactive lymphocytes were the most sensitive to stain normalization, with true positive rates (TPR) increasing from 46.3% - 66% for the original images to 81.2% - 97.2% after digital staining. Abnormal lymphocytes TPR ranged from 31.9% - 95.7% with original images to 83% - 100% with digitally stained images. Blast class showed TPR ranges of 90.3% - 94.4% and 94.4% - 100%, for original and stained images, respectively. CONCLUSIONS The proposed GAN-based normalization staining approach improves the performance of classifiers with multicenter data sets by generating digitally stained images with a quality similar to the original images and adaptability to a reference staining standard. The system requires low computation cost and can help improve the performance of automatic recognition models in clinical settings.
Collapse
Affiliation(s)
- Kevin Barrera
- Universitat Politècnica de Catalunya - BarcelonaTech (UPC), Barcelona East Engineering School, Department of Mathematics, Barcelona, Spain.
| | - José Rodellar
- Universitat Politècnica de Catalunya - BarcelonaTech (UPC), Barcelona East Engineering School, Department of Mathematics, Barcelona, Spain.
| | - Santiago Alférez
- Universitat Politècnica de Catalunya - BarcelonaTech (UPC), Barcelona East Engineering School, Department of Mathematics, Barcelona, Spain.
| | - Anna Merino
- Hospital Clínic of Barcelona-IDIBAPS, Biochemistry and Molecular Genetics Department, CORE Laboratory, Biomedical Diagnostic, Barcelona, Spain.
| |
Collapse
|
28
|
Liu Y, Dwivedi G, Boussaid F, Sanfilippo F, Yamada M, Bennamoun M. Inflating 2D convolution weights for efficient generation of 3D medical images. Comput Methods Programs Biomed 2023; 240:107685. [PMID: 37429247 DOI: 10.1016/j.cmpb.2023.107685] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/12/2023] [Revised: 06/13/2023] [Accepted: 06/19/2023] [Indexed: 07/12/2023]
Abstract
BACKGROUND AND OBJECTIVE The generation of three-dimensional (3D) medical images has great application potential since it takes into account the 3D anatomical structure. Two problems prevent effective training of a 3D medical generative model: (1) 3D medical images are expensive to acquire and annotate, resulting in an insufficient number of training images, and (2) a large number of parameters are involved in 3D convolution. METHODS We propose a novel GAN model called 3D Split&Shuffle-GAN. To address the 3D data scarcity issue, we first pre-train a two-dimensional (2D) GAN model using abundant image slices and inflate the 2D convolution weights to improve the initialization of the 3D GAN. Novel 3D network architectures are proposed for both the generator and discriminator of the GAN model to significantly reduce the number of parameters while maintaining the quality of image generation. Several weight inflation strategies and parameter-efficient 3D architectures are investigated. RESULTS Experiments on both heart (Stanford AIMI Coronary Calcium) and brain (Alzheimer's Disease Neuroimaging Initiative) datasets show that our method leads to improved 3D image generation quality (14.7 improvements on Frchet inception distance) with significantly fewer parameters (only 48.5% of the baseline method). CONCLUSIONS We built a parameter-efficient 3D medical image generation model. Due to the efficiency and effectiveness, it has the potential to generate high-quality 3D brain and heart images for real use cases.
Collapse
Affiliation(s)
- Yanbin Liu
- School of Computing, Australian National University, Canberra, ACT, AU
| | - Girish Dwivedi
- Harry Perkins Institute of Medical Research, The University of Western Australia, Perth, WA, AU; Cardiology Department, Fiona Stanley Hospital, Perth, WA, AU
| | - Farid Boussaid
- Department of Electrical, Electronic and Computer Engineering, The University of Western Australia, Perth, WA, AU
| | - Frank Sanfilippo
- School of Population and Global Health, The University of Western Australia, Perth, WA, AU
| | - Makoto Yamada
- Okinawa Institute of Science and Technology, Okinawa, JP
| | - Mohammed Bennamoun
- Department of Computer Science and Software Engineering, The University of Western Australia, Perth, WA, AU.
| |
Collapse
|
29
|
Zia T, Wahab A, Windridge D, Tirunagari S, Bhatti NB. Visual attribution using Adversarial Latent Transformations. Comput Biol Med 2023; 166:107521. [PMID: 37778213 DOI: 10.1016/j.compbiomed.2023.107521] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/20/2023] [Revised: 09/02/2023] [Accepted: 09/19/2023] [Indexed: 10/03/2023]
Abstract
The ability to accurately locate all indicators of disease within medical images is vital for comprehending the effects of the disease, as well as for weakly-supervised segmentation and localization of the diagnostic correlators of disease. Existing methods either use classifiers to make predictions based on class-salient regions or else use adversarial learning based image-to-image translation to capture such disease effects. However, the former does not capture all relevant features for visual attribution (VA) and are prone to data biases; the latter can generate adversarial (misleading) and inefficient solutions when dealing in pixel values. To address this issue, we propose a novel approach Visual Attribution using Adversarial Latent Transformations (VA2LT). Our method uses adversarial learning to generate counterfactual (CF) normal images from abnormal images by finding and modifying discrepancies in the latent space. We use cycle consistency between the query and CF latent representations to guide our training. We evaluate our method on three datasets including a synthetic dataset, the Alzheimer's Disease Neuroimaging Initiative dataset, and the BraTS dataset. Our method outperforms baseline and related methods on all datasets.
Collapse
Affiliation(s)
- Tehseen Zia
- COMSATS University Islamabad, Pakistan; Medical Imaging and Diagnostics Lab, National Center of Artificial Intelligence, Pakistan.
| | - Abdul Wahab
- COMSATS University Islamabad, Pakistan; Medical Imaging and Diagnostics Lab, National Center of Artificial Intelligence, Pakistan
| | | | | | | |
Collapse
|
30
|
Berger L, Haberbusch M, Moscato F. Generative adversarial networks in electrocardiogram synthesis: Recent developments and challenges. Artif Intell Med 2023; 143:102632. [PMID: 37673589 DOI: 10.1016/j.artmed.2023.102632] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/09/2023] [Revised: 07/25/2023] [Accepted: 08/08/2023] [Indexed: 09/08/2023]
Abstract
Training deep neural network classifiers for electrocardiograms (ECGs) requires sufficient data. However, imbalanced datasets pose a major problem for the training process and hence data augmentation is commonly performed. Generative adversarial networks (GANs) can create synthetic ECG data to augment such imbalanced datasets. This review aims at identifying the present literature concerning synthetic ECG signal generation using GANs to provide a comprehensive overview of architectures, quality evaluation metrics, and classification performances. Thirty publications from the years 2019 to 2022 were selected from three separate databases. Nine publications used a quality evaluation metric neglecting classification, eleven performed a classification but omitted a quality evaluation metric, and ten publications performed both. Twenty different quality evaluation metrics were observed. Overall, the classification performance of databases augmented with synthetically created ECG signals increased by 7 % to 98 % in accuracy and 6 % to 97 % in sensitivity. In conclusion, synthetic ECG signal generation using GANs represents a promising tool for data augmentation of imbalanced datasets. Consistent quality evaluation of generated signals remains challenging. Hence, future work should focus on the establishment of a gold standard for quality evaluation metrics for GANs.
Collapse
Affiliation(s)
- Laurenz Berger
- Center for Medical Physics and Biomedical Engineering, Medical University of Vienna, Währinger Gürtel 18-20, A-1090 Vienna, Austria; Ludwig Boltzmann Institute for Cardiovascular Research, Währinger Gürtel 18-20, A-1090 Vienna, Austria.
| | - Max Haberbusch
- Center for Medical Physics and Biomedical Engineering, Medical University of Vienna, Währinger Gürtel 18-20, A-1090 Vienna, Austria; Ludwig Boltzmann Institute for Cardiovascular Research, Währinger Gürtel 18-20, A-1090 Vienna, Austria
| | - Francesco Moscato
- Center for Medical Physics and Biomedical Engineering, Medical University of Vienna, Währinger Gürtel 18-20, A-1090 Vienna, Austria; Ludwig Boltzmann Institute for Cardiovascular Research, Währinger Gürtel 18-20, A-1090 Vienna, Austria; Austrian Cluster for Tissue Regeneration, Donaueschingenstraße 13, A-1200 Vienna, Austria
| |
Collapse
|
31
|
Mahey P, Toussi N, Purnomu G, Herdman AT. Generative Adversarial Network (GAN) for Simulating Electroencephalography. Brain Topogr 2023; 36:661-670. [PMID: 37410276 DOI: 10.1007/s10548-023-00986-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/24/2022] [Accepted: 06/22/2023] [Indexed: 07/07/2023]
Abstract
Electroencephalographs record the electrical activity of your brain through the scalp. Electroencephalography is difficult to obtain due to its sensitivity and variability. Applications of electroencephalography such as for diagnosis, education, brain-computer interfaces require large samples of electroencephalography recording, however, it is often difficult to obtain the required datasets. Generative adversarial networks are robust deep learning framework which have proven themselves to be capable of synthesizing data. The robust nature of a generative adversarial network was used to generate multi-channel electroencephalography data in order to see if generative adversarial networks could reconstruct the spatio-temporal aspects of multi-channel electroencephalography signals. We were able to find that the synthetic electroencephalography data was able to replicate fine details of electroencephalography data and could potentially help us to generate large sample synthetic resting-state electroencephalography data for use in simulation testing of neuroimaging analyses. Generative adversarial networks (GANs) are robust deep-learning frameworks that can be trained to be convincing replicants of real data GANs were capable of generating "fake" EEG data that replicated fine details and topographies of "real" resting-state EEG data.
Collapse
Affiliation(s)
| | - Nima Toussi
- University of British Columbia, Vancouver, BC, Canada
| | - Grace Purnomu
- University of British Columbia, Vancouver, BC, Canada
| | - Anthony Thomas Herdman
- University of British Columbia, Vancouver, BC, Canada
- School of Audiology & Speech Sciences, Faculty of Medicine, The University of British Columbia, Vancouver, Canada
| |
Collapse
|
32
|
Luleci F, Catbas FN. A brief introductory review to deep generative models for civil structural health monitoring. AI Civil Eng 2023; 2:9. [PMID: 37621778 PMCID: PMC10444648 DOI: 10.1007/s43503-023-00017-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 04/07/2023] [Revised: 07/25/2023] [Accepted: 07/27/2023] [Indexed: 08/26/2023]
Abstract
The use of deep generative models (DGMs) such as variational autoencoders, autoregressive models, flow-based models, energy-based models, generative adversarial networks, and diffusion models has been advantageous in various disciplines due to their high data generative skills. Using DGMs has become one of the most trending research topics in Artificial Intelligence in recent years. On the other hand, the research and development endeavors in the civil structural health monitoring (SHM) area have also been very progressive owing to the increasing use of Machine Learning techniques. As such, some of the DGMs have also been used in the civil SHM field lately. This short review communication paper aims to assist researchers in the civil SHM field in understanding the fundamentals of DGMs and, consequently, to help initiate their use for current and possible future engineering applications. On this basis, this study briefly introduces the concept and mechanism of different DGMs in a comparative fashion. While preparing this short review communication, it was observed that some DGMs had not been utilized or exploited fully in the SHM area. Accordingly, some representative studies presented in the civil SHM field that use DGMs are briefly overviewed. The study also presents a short comparative discussion on DGMs, their link to the SHM, and research directions.
Collapse
Affiliation(s)
- Furkan Luleci
- Department of Civil, Environmental, and Construction Engineering, University of Central Florida, Orlando, FL 32816 USA
| | - F. Necati Catbas
- Department of Civil, Environmental, and Construction Engineering, University of Central Florida, Orlando, FL 32816 USA
| |
Collapse
|
33
|
Lin J, Miao QI, Surawech C, Raman SS, Zhao K, Wu HH, Sung K. High-Resolution 3D MRI With Deep Generative Networks via Novel Slice-Profile Transformation Super-Resolution. IEEE Access 2023; 11:95022-95036. [PMID: 37711392 PMCID: PMC10501177 DOI: 10.1109/access.2023.3307577] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Indexed: 09/16/2023]
Abstract
High-resolution magnetic resonance imaging (MRI) sequences, such as 3D turbo or fast spin-echo (TSE/FSE) imaging, are clinically desirable but suffer from long scanning time-related blurring when reformatted into preferred orientations. Instead, multi-slice two-dimensional (2D) TSE imaging is commonly used because of its high in-plane resolution but is limited clinically by poor through-plane resolution due to elongated voxels and the inability to generate multi-planar reformations due to staircase artifacts. Therefore, multiple 2D TSE scans are acquired in various orthogonal imaging planes, increasing the overall MRI scan time. In this study, we propose a novel slice-profile transformation super-resolution (SPTSR) framework with deep generative learning for through-plane super-resolution (SR) of multi-slice 2D TSE imaging. The deep generative networks were trained by synthesized low-resolution training input via slice-profile downsampling (SP-DS), and the trained networks inferred on the slice profile convolved (SP-conv) testing input for 5.5x through-plane SR. The network output was further slice-profile deconvolved (SP-deconv) to achieve an isotropic super-resolution. Compared to SMORE SR method and the networks trained by conventional downsampling, our SPTSR framework demonstrated the best overall image quality from 50 testing cases, evaluated by two abdominal radiologists. The quantitative analysis cross-validated the expert reader study results. 3D simulation experiments confirmed the quantitative improvement of the proposed SPTSR and the effectiveness of the SP-deconv step, compared to 3D ground-truths. Ablation studies were conducted on the individual contributions of SP-DS and SP-conv, networks structure, training dataset size, and different slice profiles.
Collapse
Affiliation(s)
- Jiahao Lin
- Department of Radiological Sciences, University of California at Los Angeles, Los Angeles, CA 90095, USA
- Department of Electrical and Computer Engineering, University of California at Los Angeles, Los Angeles, CA 90095, USA
| | - Q I Miao
- Department of Radiological Sciences, University of California at Los Angeles, Los Angeles, CA 90095, USA
- Department of Radiology, The First Affiliated Hospital of China Medical University, Shenyang, Liaoning 110001, China
| | - Chuthaporn Surawech
- Department of Radiological Sciences, University of California at Los Angeles, Los Angeles, CA 90095, USA
- Department of Radiology, Faculty of Medicine, Chulalongkorn University, Bangkok 10330, Thailand
- Division of Diagnostic Radiology, Department of Radiology, King Chulalongkorn Memorial Hospital, Bangkok 10330, Thailand
| | - Steven S Raman
- Department of Radiological Sciences, University of California at Los Angeles, Los Angeles, CA 90095, USA
| | - Kai Zhao
- Department of Radiological Sciences, University of California at Los Angeles, Los Angeles, CA 90095, USA
| | - Holden H Wu
- Department of Radiological Sciences, University of California at Los Angeles, Los Angeles, CA 90095, USA
| | - Kyunghyun Sung
- Department of Radiological Sciences, University of California at Los Angeles, Los Angeles, CA 90095, USA
| |
Collapse
|
34
|
Luleci F, Necati Catbas F. Condition transfer between prestressed bridges using structural state translation for structural health monitoring. AI Civil Eng 2023; 2:7. [PMID: 37564103 PMCID: PMC10411104 DOI: 10.1007/s43503-023-00016-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 03/03/2023] [Revised: 06/02/2023] [Accepted: 07/01/2023] [Indexed: 08/12/2023]
Abstract
Implementing Structural Health Monitoring (SHM) systems with extensive sensing layouts on all civil structures is obviously expensive and unfeasible. Thus, estimating the state (condition) of dissimilar civil structures based on the information collected from other structures is regarded as a useful and essential way. For this purpose, Structural State Translation (SST) has been recently proposed to predict the response data of civil structures based on the information acquired from a dissimilar structure. This study uses the SST methodology to translate the state of one bridge (Bridge #1) to a new state based on the knowledge acquired from a structurally dissimilar bridge (Bridge #2). Specifically, the Domain-Generalized Cycle-Generative (DGCG) model is trained in the Domain Generalization learning approach on two distinct data domains obtained from Bridge #1; the bridges have two different conditions: State-H and State-D. Then, the model is used to generalize and transfer the knowledge on Bridge #1 to Bridge #2. In doing so, DGCG translates the state of Bridge #2 to the state that the model has learned after being trained. In one scenario, Bridge #2's State-H is translated to State-D; in another scenario, Bridge #2's State-D is translated to State-H. The translated bridge states are then compared with the real ones via modal identifiers and mean magnitude-squared coherence (MMSC), showing that the translated states are remarkably similar to the real ones. For instance, the modes of the translated and real bridge states are similar, with the maximum frequency difference of 1.12% and the minimum correlation of 0.923 in Modal Assurance Criterion values, as well as the minimum of 0.947 in Average MMSC values. In conclusion, this study demonstrates that SST is a promising methodology for research with data scarcity and population-based structural health monitoring (PBSHM). In addition, a critical discussion about the methodology adopted in this study is also offered to address some related concerns.
Collapse
Affiliation(s)
- Furkan Luleci
- Department of Civil, Environmental, and Construction Engineering, University of Central Florida, Orlando, FL 32816 USA
| | - F. Necati Catbas
- Department of Civil, Environmental, and Construction Engineering, University of Central Florida, Orlando, FL 32816 USA
| |
Collapse
|
35
|
Shin K, Lee JS, Lee JY, Lee H, Kim J, Byeon JS, Jung HY, Kim DH, Kim N. An Image Turing Test on Realistic Gastroscopy Images Generated by Using the Progressive Growing of Generative Adversarial Networks. J Digit Imaging 2023; 36:1760-1769. [PMID: 36914855 PMCID: PMC10406771 DOI: 10.1007/s10278-023-00803-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/05/2022] [Revised: 02/21/2023] [Accepted: 02/23/2023] [Indexed: 03/16/2023] Open
Abstract
Generative adversarial networks (GAN) in medicine are valuable techniques for augmenting unbalanced rare data, anomaly detection, and avoiding patient privacy issues. However, there were limits to generating high-quality endoscopic images with various characteristics, such as peristalsis, viewpoints, light sources, and mucous patterns. This study used the progressive growing of GAN (PGGAN) within the normal distribution dataset to confirm the ability to generate high-quality gastrointestinal images and investigated what barriers PGGAN has to generate endoscopic images. We trained the PGGAN with 107,060 gastroscopy images from 4165 normal patients to generate highly realistic 5122 pixel-sized images. For the evaluation, visual Turing tests were conducted on 100 real and 100 synthetic images to distinguish the authenticity of images by 19 endoscopists. The endoscopists were divided into three groups based on their years of clinical experience for subgroup analysis. The overall accuracy, sensitivity, and specificity of the 19 endoscopist groups were 61.3%, 70.3%, and 52.4%, respectively. The mean accuracy of the three endoscopist groups was 62.4 [Group I], 59.8 [Group II], and 59.1% [Group III], which was not considered a significant difference. There were no statistically significant differences in the location of the stomach. However, the real images with the anatomical landmark pylorus had higher detection sensitivity. The images generated by PGGAN showed highly realistic depictions that were difficult to distinguish, regardless of their expertise as endoscopists. However, it was necessary to establish GANs that could better represent the rugal folds and mucous membrane texture.
Collapse
Affiliation(s)
- Keewon Shin
- Biomedical Engineering Research Center, Asan Medical Center, Seoul, Republic of Korea
| | - Jung Su Lee
- Department of Gastroenterology, University of Ulsan College of Medicine, Asan Medical Center, Seoul, Republic of Korea
- Seoul Samsung Internal Medicine Clinic, Seoul, Republic of Korea
| | - Ji Young Lee
- Department of Health Screening and Promotion Center, University of Ulsan College of Medicine, Asan Medical Center, Seoul, Republic of Korea
| | - Hyunsu Lee
- Department of Medical Informatics, Keimyung University School of Medicine, Daegu, Republic of Korea
| | - Jeongseok Kim
- Department of Internal Medicine, Keimyung University School of Medicine, Daegu, Republic of Korea
| | - Jeong-Sik Byeon
- Department of Gastroenterology, University of Ulsan College of Medicine, Asan Medical Center, Seoul, Republic of Korea
| | - Hwoon-Yong Jung
- Department of Gastroenterology, University of Ulsan College of Medicine, Asan Medical Center, Seoul, Republic of Korea
| | - Do Hoon Kim
- Department of Gastroenterology, University of Ulsan College of Medicine, Asan Medical Center, Seoul, Republic of Korea.
| | - Namkug Kim
- Biomedical Engineering Research Center, Asan Medical Center, Seoul, Republic of Korea.
- Department of Convergence Medicine, University of Ulsan College of Medicine & Asan Medical Center, Seoul, Republic of Korea.
| |
Collapse
|
36
|
Kuo NIH, Garcia F, Sönnerborg A, Böhm M, Kaiser R, Zazzi M, Polizzotto M, Jorm L, Barbieri S. Generating synthetic clinical data that capture class imbalanced distributions with generative adversarial networks: Example using antiretroviral therapy for HIV. J Biomed Inform 2023; 144:104436. [PMID: 37451495 DOI: 10.1016/j.jbi.2023.104436] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/31/2023] [Revised: 06/24/2023] [Accepted: 06/30/2023] [Indexed: 07/18/2023]
Abstract
OBJECTIVE Clinical data's confidential nature often limits the development of machine learning models in healthcare. Generative adversarial networks (GANs) can synthesise realistic datasets, but suffer from mode collapse, resulting in low diversity and bias towards majority demographics and common clinical practices. This work proposes an extension to the classic GAN framework that includes a variational autoencoder (VAE) and an external memory mechanism to overcome these limitations and generate synthetic data accurately describing imbalanced class distributions commonly found in clinical variables. METHODS The proposed method generated a synthetic dataset related to antiretroviral therapy for human immunodeficiency virus (ART for HIV). We evaluated it based on five metrics: (1) accurately representing imbalanced class distribution; (2) the realism of the individual variables; (3) the realism among variables; (4) patient disclosure risk; and (5) the utility of the generated dataset for developing downstream machine learning models. RESULTS The proposed method overcomes the issue of mode collapse and generates a synthetic dataset that accurately describes imbalanced class distributions commonly found in clinical variables. The generated data has a patient disclosure risk of 0.095%, lower than the 9% threshold stated by Health Canada and the European Medicines Agency, making it suitable for distribution to the research community with high security. The generated data also has high utility, indicating the potential of the proposed method to enable the development of downstream machine learning algorithms for healthcare applications using synthetic data. CONCLUSION Our proposed extension to the classic GAN framework, which includes a VAE and an external memory mechanism, represents a promising approach towards generating synthetic data that accurately describe imbalanced class distributions commonly found in clinical variables. This method overcomes the limitations of GANs and creates more realistic datasets with higher patient cohort diversity, facilitating the development of downstream machine learning algorithms for healthcare applications.
Collapse
Affiliation(s)
- Nicholas I-Hsien Kuo
- Centre for Big Data Research in Health, the University of New South Wales, Sydney, Australia.
| | - Federico Garcia
- Instituto de Investigación Ibs.Granada, Spain; Hospital Universitario San Cecilio, Spain; CIBER de Enfermedades Infecciosas, Spain
| | | | | | - Rolf Kaiser
- Uniklinik Köln, Universität zu Köln, Germany
| | | | | | - Louisa Jorm
- Centre for Big Data Research in Health, the University of New South Wales, Sydney, Australia
| | - Sebastiano Barbieri
- Centre for Big Data Research in Health, the University of New South Wales, Sydney, Australia
| |
Collapse
|
37
|
Yamamoto S, Higaki A. Visual Turing test is not sufficient to evaluate the performance of medical generative models. Eur Radiol Exp 2023; 7:31. [PMID: 37423911 PMCID: PMC10329967 DOI: 10.1186/s41747-023-00347-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/21/2023] [Accepted: 04/21/2023] [Indexed: 07/11/2023] Open
Affiliation(s)
- Shoichiro Yamamoto
- Department of Cardiology, Pulmonology, Hypertension and Nephrology, Ehime University Graduate School of Medicine, 454 Shitsukawa, Toon, Ehime, 791-0295, Japan
| | - Akinori Higaki
- Department of Cardiology, Pulmonology, Hypertension and Nephrology, Ehime University Graduate School of Medicine, 454 Shitsukawa, Toon, Ehime, 791-0295, Japan.
| |
Collapse
|
38
|
Riley R, Mathieson I, Mathieson S. INTERPRETING GENERATIVE ADVERSARIAL NETWORKS TO INFER NATURAL SELECTION FROM GENETIC DATA. bioRxiv 2023:2023.03.07.531546. [PMID: 36945387 PMCID: PMC10028936 DOI: 10.1101/2023.03.07.531546] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 03/10/2023]
Abstract
Understanding natural selection in humans and other species is a major focus for the use of machine learning in population genetics. Existing methods rely on computationally intensive simulated training data. Unlike efficient neutral coalescent simulations for demographic inference, realistic simulations of selection typically requires slow forward simulations. Because there are many possible modes of selection, a high dimensional parameter space must be explored, with no guarantee that the simulated models are close to the real processes. Mismatches between simulated training data and real test data can lead to incorrect inference. Finally, it is difficult to interpret trained neural networks, leading to a lack of understanding about what features contribute to classification. Here we develop a new approach to detect selection that requires relatively few selection simulations during training. We use a Generative Adversarial Network (GAN) trained to simulate realistic neutral data. The resulting GAN consists of a generator (fitted demographic model) and a discriminator (convolutional neural network). For a genomic region, the discriminator predicts whether it is "real" or "fake" in the sense that it could have been simulated by the generator. As the "real" training data includes regions that experienced selection and the generator cannot produce such regions, regions with a high probability of being real are likely to have experienced selection. To further incentivize this behavior, we "fine-tune" the discriminator with a small number of selection simulations. We show that this approach has high power to detect selection in simulations, and that it finds regions under selection identified by state-of-the art population genetic methods in three human populations. Finally, we show how to interpret the trained networks by clustering hidden units of the discriminator based on their correlation patterns with known summary statistics. In summary, our approach is a novel, efficient, and powerful way to use machine learning to detect natural selection.
Collapse
Affiliation(s)
- Rebecca Riley
- Department of Computer Science, Haverford College, Haverford PA, 19041 USA
| | - Iain Mathieson
- Department of Genetics, Perelman School of Medicine, University of Pennsylvania, Philadelphia PA, 19104 USA
| | - Sara Mathieson
- Department of Computer Science, Haverford College, Haverford PA, 19041 USA
| |
Collapse
|
39
|
Frisch Y, Fuchs M, Mukhopadhyay A. Temporally consistent sequence-to-sequence translation of cataract surgeries. Int J Comput Assist Radiol Surg 2023:10.1007/s11548-023-02925-y. [PMID: 37219806 PMCID: PMC10329626 DOI: 10.1007/s11548-023-02925-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/14/2023] [Accepted: 04/17/2023] [Indexed: 05/24/2023]
Abstract
PURPOSE Image-to-image translation methods can address the lack of diversity in publicly available cataract surgery data. However, applying image-to-image translation to videos-which are frequently used in medical downstream applications-induces artifacts. Additional spatio-temporal constraints are needed to produce realistic translations and improve the temporal consistency of translated image sequences. METHODS We introduce a motion-translation module that translates optical flows between domains to impose such constraints. We combine it with a shared latent space translation model to improve image quality. Evaluations are conducted regarding translated sequences' image quality and temporal consistency, where we propose novel quantitative metrics for the latter. Finally, the downstream task of surgical phase classification is evaluated when retraining it with additional synthetic translated data. RESULTS Our proposed method produces more consistent translations than state-of-the-art baselines. Moreover, it stays competitive in terms of the per-image translation quality. We further show the benefit of consistently translated cataract surgery sequences for improving the downstream task of surgical phase prediction. CONCLUSION The proposed module increases the temporal consistency of translated sequences. Furthermore, imposed temporal constraints increase the usability of translated data in downstream tasks. This allows overcoming some of the hurdles of surgical data acquisition and annotation and enables improving models' performance by translating between existing datasets of sequential frames.
Collapse
Affiliation(s)
- Yannik Frisch
- Computer Science, Technical University Darmstadt, Fraunhoferstraße 5, 64283, Darmstadt, Hessen, Germany.
| | - Moritz Fuchs
- Computer Science, Technical University Darmstadt, Fraunhoferstraße 5, 64283, Darmstadt, Hessen, Germany
| | - Anirban Mukhopadhyay
- Computer Science, Technical University Darmstadt, Fraunhoferstraße 5, 64283, Darmstadt, Hessen, Germany
| |
Collapse
|
40
|
Rather IH, Kumar S. Generative adversarial network based synthetic data training model for lightweight convolutional neural networks. Multimed Tools Appl 2023:1-23. [PMID: 37362646 PMCID: PMC10199442 DOI: 10.1007/s11042-023-15747-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 02/07/2023] [Revised: 04/17/2023] [Accepted: 04/25/2023] [Indexed: 06/28/2023]
Abstract
Inadequate training data is a significant challenge for deep learning techniques, particularly in applications where data is difficult to get, and publicly available datasets are uncommon owing to ethical and privacy concerns. Various approaches, such as data augmentation and transfer learning, are employed to address this problem, which help to some extent in removing this limitation. However, after a certain amount of data augmentation, the quality of the generated data stalls, and transfer learning suffers from the issue of negative transfer. This paper proposes a novel generative adversarial network-based synthetic data training (GAN-ST) model to generate synthetic data for training a lightweight convolutional neural network (CNN). An enhanced generator is proposed to quickly saturate and cover the colour space of the training distribution. The GAN-ST model is based on Deep Convolutional Generative Adversarial Network(s) (DCGAN) and Conditional Generative Adversarial Network(s) (CGAN) models, which consist of an enhanced generator. The study evaluates the accuracy of a CNN model on the MNIST and CIFAR 10 datasets using both original and synthetic data. The results revealed an impressive classifier accuracy on the MNIST dataset, achieving an accuracy of 99.38% on GAN-ST-generated synthetic training data, which is only 0.05% lower than the performance on original data-based training. The classifier performance on the CIFAR dataset is also remarkable, achieving an accuracy of 90.23%. The performance of CNN trained using GAN-ST-based synthetic data is notable, with the most considerable improvement of 0.66% and 7.06%, over a single GAN-based synthetic data training for the MNIST and CIFAR datasets, respectively. By training two GANs independently, the GAN-ST model covers different parts of the original data distribution, resulting in a more diverse and realistic training data set for the classifier. This diverse set of synthetic data, when used to train a CNN, shows better generalization to new data, leading to improved classification accuracy.
Collapse
Affiliation(s)
- Ishfaq Hussain Rather
- School of Computer & Systems Sciences, Jawaharlal Nehru University, New Delhi, India
| | - Sushil Kumar
- School of Computer & Systems Sciences, Jawaharlal Nehru University, New Delhi, India
| |
Collapse
|
41
|
Rajabi MM, Komeilian P, Wan X, Farmani R. Leak detection and localization in water distribution networks using conditional deep convolutional generative adversarial networks. Water Res 2023; 238:120012. [PMID: 37150062 DOI: 10.1016/j.watres.2023.120012] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 01/15/2023] [Revised: 04/06/2023] [Accepted: 04/26/2023] [Indexed: 05/09/2023]
Abstract
This paper explores the use of 'conditional convolutional generative adversarial networks' (CDCGAN) for image-based leak detection and localization (LD&L) in water distribution networks (WDNs). The method employs pressure measurements and is based on four pillars: (1) hydraulic model-based generation of leak-free training data by taking into account the demand uncertainty, (2) conversion of hydraulic model input demand-output pressure pairs into images using kriging interpolation, (3) training of a CDCGAN model for image-to-image translation, and (4) using the structural similarity (SSIM) index for LD&L. SSIM, computed over the entire pressure distribution image is used for leak detection, and a local estimate of SSIM is employed for leak localization. The CDCGAN model employed in this paper is based on the pix2pix architecture. The effectiveness of the proposed methodology is demonstrated on leakage datasets under various scenarios. Results show that the method has an accuracy of approximately 70% for real-time leak detection. The proposed method is well-suited for real-time applications due to the low computational cost of CDCGAN predictions compared to WDN hydraulic models, is robust in presence of uncertainty due to the nature of generative adversarial networks, and scales well to large and variable-sized monitoring data due to the use of an image-based approach.
Collapse
Affiliation(s)
- Mohammad Mahdi Rajabi
- Civil and Environmental Engineering Faculty, Tarbiat Modares University, PO Box 14115-397, Tehran, Iran.
| | - Pooya Komeilian
- Department of Civil Engineering, Sharif University of Technology, Tehran, Iran
| | - Xi Wan
- Centre for Water Systems, Department of Engineering, University of Exeter, Exeter, Devon EX4 4QF, UK
| | - Raziyeh Farmani
- Centre for Water Systems, Department of Engineering, University of Exeter, Exeter, Devon EX4 4QF, UK
| |
Collapse
|
42
|
Lee J, Jeon J, Hong Y, Jeong D, Jang Y, Jeon B, Baek HJ, Cho E, Shim H, Chang HJ. Generative adversarial network with radiomic feature reproducibility analysis for computed tomography denoising. Comput Biol Med 2023; 159:106931. [PMID: 37116238 DOI: 10.1016/j.compbiomed.2023.106931] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/24/2022] [Revised: 04/04/2023] [Accepted: 04/13/2023] [Indexed: 04/30/2023]
Abstract
BACKGROUND Most computed tomography (CT) denoising algorithms have been evaluated using image quality analysis (IQA) methods developed for natural image, which do not adequately capture the texture details in medical imaging. Radiomics is an emerging image analysis technique that extracts texture information to provide a more objective basis for medical imaging diagnostics, overcoming the subjective nature of traditional methods. By utilizing the difficulty of reproducing radiomics features under different imaging protocols, we can more accurately evaluate the performance of CT denoising algorithms. METHOD We introduced radiomic feature reproducibility analysis as an evaluation metric for a denoising algorithm. Also, we proposed a low-dose CT denoising method based on a generative adversarial network (GAN), which outperformed well-known CT denoising methods. RESULTS Although the proposed model produced excellent results visually, the traditional image assessment metrics such as peak signal-to-noise ratio and structural similarity failed to show distinctive performance differences between the proposed method and the conventional ones. However, radiomic feature reproducibility analysis provided a distinctive assessment of the CT denoising performance. Furthermore, radiomic feature reproducibility analysis allowed fine-tuning of the hyper-parameters of the GAN. CONCLUSION We demonstrated that the well-tuned GAN architecture outperforms the well-known CT denoising methods. Our study is the first to introduce radiomics reproducibility analysis as an evaluation metric for CT denoising. We look forward that the study may bridge the gap between traditional objective and subjective evaluations in the clinical medical imaging field.
Collapse
Affiliation(s)
- Jina Lee
- CONNECT-AI Research Center, Yonsei University College of Medicine, Seoul, 03764, South Korea; Brain Korea 21 PLUS Project for Medical Science, Yonsei University, Seoul, 03722, South Korea
| | - Jaeik Jeon
- CONNECT-AI Research Center, Yonsei University College of Medicine, Seoul, 03764, South Korea
| | - Youngtaek Hong
- CONNECT-AI Research Center, Yonsei University College of Medicine, Seoul, 03764, South Korea; Ontact Health, Seoul, 03764, South Korea.
| | - Dawun Jeong
- CONNECT-AI Research Center, Yonsei University College of Medicine, Seoul, 03764, South Korea; Brain Korea 21 PLUS Project for Medical Science, Yonsei University, Seoul, 03722, South Korea
| | - Yeonggul Jang
- CONNECT-AI Research Center, Yonsei University College of Medicine, Seoul, 03764, South Korea; Brain Korea 21 PLUS Project for Medical Science, Yonsei University, Seoul, 03722, South Korea
| | - Byunghwan Jeon
- Division of Computer Engineering, Hankuk University of Foreign Studies, Yongin, 17035, South Korea
| | - Hye Jin Baek
- Department of Radiology, Gyeongsang National University Changwon Hospital, Gyeongsang National University School of Medicine, Changwon, 51472, South Korea
| | - Eun Cho
- Department of Radiology, Gyeongsang National University Changwon Hospital, Gyeongsang National University School of Medicine, Changwon, 51472, South Korea
| | - Hackjoon Shim
- CONNECT-AI Research Center, Yonsei University College of Medicine, Seoul, 03764, South Korea
| | - Hyuk-Jae Chang
- CONNECT-AI Research Center, Yonsei University College of Medicine, Seoul, 03764, South Korea; Division of Cardiology, Severance Cardiovascular Hospital, Yonsei University College of Medicine, Seoul, 03722, South Korea
| |
Collapse
|
43
|
Ko K, Yeom T, Lee M. SuperstarGAN: Generative adversarial networks for image-to-image translation in large-scale domains. Neural Netw 2023; 162:330-339. [PMID: 36940493 DOI: 10.1016/j.neunet.2023.02.042] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/31/2022] [Revised: 01/19/2023] [Accepted: 02/28/2023] [Indexed: 03/09/2023]
Abstract
Image-to-image translation with generative adversarial networks (GANs) has been extensively studied in recent years. Among the models, StarGAN has achieved image-to-image translation for multiple domains with a single generator, whereas conventional models require multiple generators. However, StarGAN has several limitations, including the lack of capacity to learn mappings among large-scale domains; furthermore, StarGAN can barely express small feature changes. To address the limitations, we propose an improved StarGAN, namely SuperstarGAN. We adopted the idea, first proposed in controllable GAN (ControlGAN), of training an independent classifier with the data augmentation techniques to handle the overfitting problem in the classification of StarGAN structures. Since the generator with a well-trained classifier can express small features belonging to the target domain, SuperstarGAN achieves image-to-image translation in large-scale domains. Evaluated with a face image dataset, SuperstarGAN demonstrated improved performance in terms of Fréchet Inception distance (FID) and learned perceptual image patch similarity (LPIPS). Specifically, compared to StarGAN, SuperstarGAN exhibited decreased FID and LPIPS by 18.1% and 42.5%, respectively. Furthermore, we conducted an additional experiment with interpolated and extrapolated label values, indicating the ability of SuperstarGAN to control the degree of expression of the target domain features in generated images. Additionally, SuperstarGAN was successfully adapted to an animal face dataset and a painting dataset, where it can translate styles of animal faces (i.e., a cat to a tiger) and styles of painters (i.e., Hassam to Picasso), respectively, which explains the generality of SuperstarGAN regardless of datasets.
Collapse
Affiliation(s)
- Kanghyeok Ko
- School of Electrical and Electronics Engineering, Chung-Ang University, 84 Heukseok-ro, Dongjak-gu, Seoul 06974, South Korea
| | - Taesun Yeom
- School of Mechanical Engineering, Chung-Ang University, 84 Heukseok-ro, Dongjak-gu, Seoul 06974, South Korea
| | - Minhyeok Lee
- School of Electrical and Electronics Engineering, Chung-Ang University, 84 Heukseok-ro, Dongjak-gu, Seoul 06974, South Korea.
| |
Collapse
|
44
|
Ren Z, Li Q, Cao K, Li MM, Zhou Y, Wang K. Model performance and interpretability of semi-supervised generative adversarial networks to predict oncogenic variants with unlabeled data. BMC Bioinformatics 2023; 24:43. [PMID: 36759776 PMCID: PMC9909865 DOI: 10.1186/s12859-023-05141-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/03/2023] [Accepted: 01/05/2023] [Indexed: 02/11/2023] Open
Abstract
BACKGROUND It remains an important challenge to predict the functional consequences or clinical impacts of genetic variants in human diseases, such as cancer. An increasing number of genetic variants in cancer have been discovered and documented in public databases such as COSMIC, but the vast majority of them have no functional or clinical annotations. Some databases, such as CiVIC are available with manual annotation of functional mutations, but the size of the database is small due to the use of human annotation. Since the unlabeled data (millions of variants) typically outnumber labeled data (thousands of variants), computational tools that take advantage of unlabeled data may improve prediction accuracy. RESULT To leverage unlabeled data to predict functional importance of genetic variants, we introduced a method using semi-supervised generative adversarial networks (SGAN), incorporating features from both labeled and unlabeled data. Our SGAN model incorporated features from clinical guidelines and predictive scores from other computational tools. We also performed comparative analysis to study factors that influence prediction accuracy, such as using different algorithms, types of features, and training sample size, to provide more insights into variant prioritization. We found that SGAN can achieve competitive performances with small labeled training samples by incorporating unlabeled samples, which is a unique advantage compared to traditional machine learning methods. We also found that manually curated samples can achieve a more stable predictive performance than publicly available datasets. CONCLUSIONS By incorporating much larger samples of unlabeled data, the SGAN method can improve the ability to detect novel oncogenic variants, compared to other machine-learning algorithms that use only labeled datasets. SGAN can be potentially used to predict the pathogenicity of more complex variants such as structural variants or non-coding variants, with the availability of more training samples and informative features.
Collapse
Affiliation(s)
- Zilin Ren
- grid.239552.a0000 0001 0680 8770Raymond G. Perelman Center for Cellular and Molecular Therapeutics, Children’s Hospital of Philadelphia, Philadelphia, PA 19104 USA
| | - Quan Li
- grid.239552.a0000 0001 0680 8770Raymond G. Perelman Center for Cellular and Molecular Therapeutics, Children’s Hospital of Philadelphia, Philadelphia, PA 19104 USA ,grid.17063.330000 0001 2157 2938Princess Margaret Cancer Centre, University Health Network, University of Toronto, Toronto, ON M5G2C1 Canada
| | - Kajia Cao
- grid.239552.a0000 0001 0680 8770Division of Genomic Diagnostics, Department of Pathology and Laboratory Medicine, Children’s Hospital of Philadelphia, Philadelphia, PA 19104 USA
| | - Marilyn M. Li
- grid.239552.a0000 0001 0680 8770Division of Genomic Diagnostics, Department of Pathology and Laboratory Medicine, Children’s Hospital of Philadelphia, Philadelphia, PA 19104 USA ,grid.25879.310000 0004 1936 8972Department of Pathology and Laboratory Medicine, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104 USA
| | - Yunyun Zhou
- Raymond G. Perelman Center for Cellular and Molecular Therapeutics, Children's Hospital of Philadelphia, Philadelphia, PA, 19104, USA.
| | - Kai Wang
- Raymond G. Perelman Center for Cellular and Molecular Therapeutics, Children's Hospital of Philadelphia, Philadelphia, PA, 19104, USA. .,Department of Pathology and Laboratory Medicine, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, 19104, USA.
| |
Collapse
|
45
|
Barrera K, Merino A, Molina A, Rodellar J. Automatic generation of artificial images of leukocytes and leukemic cells using generative adversarial networks (syntheticcellgan). Comput Methods Programs Biomed 2023; 229:107314. [PMID: 36565666 DOI: 10.1016/j.cmpb.2022.107314] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/29/2022] [Revised: 11/29/2022] [Accepted: 12/14/2022] [Indexed: 06/17/2023]
Abstract
BACKGROUND AND OBJECTIVES Visual analysis of cell morphology has an important role in the diagnosis of hematological diseases. Morphological cell recognition is a challenge that requires experience and in-depth review by clinical pathologists. Within the new trend of introducing computer-aided diagnostic tools in laboratory medicine, models based on deep learning are being developed for the automatic identification of different types of cells in peripheral blood. In general, well-annotated large image sets are needed to train the models to reach a desired classification performance. This is especially relevant when it comes to discerning between cell images in which morphological differences are subtle and when it comes to low prevalent diseases with the consequent difficulty in collecting cell images. The objective of this work is to develop, train and validate SyntheticCellGAN (SCG), a new system for the automatic generation of artificial images of white blood cells, maintaining morphological characteristics very close to real cells found in practice in clinical laboratories. METHODS SCG is designed with two sequential generative adversarial networks. First, a Wasserstein structure is used to transform random noise vectors into low resolution images of basic mononuclear cells. Second, the concept of image-to-image translation is used to build specific models that transform the basic images into high-resolution final images with the realistic morphology of each cell type target: 1) the five groups of normal leukocytes (lymphocytes, monocytes, eosinophils, neutrophils and basophils); 2) atypical promyelocytes and hairy cells, which are two relevant cell types of complex morphology with low abundance in blood smears. RESULTS The images of the SCG system are evaluated with four experimental tests. In the first test we evaluated the generated images with quantitative metrics for GANs. In the second test, morphological verification of the artificial images is performed by expert clinical pathologists with 100% accuracy. In the third test, two classifiers based on convolutional neural networks (CNN) previously trained with images of real cells are used. Two sets of artificial images of the SCG system are classified with an accuracy of 95.36% and 94%, respectively. In the fourth test, three CNN classifiers are trained with artificial images of the SCG system. Real cells are identified with an accuracy ranging from 87.7% to 100%. CONCLUSIONS The SCG system has proven effective in creating images of all normal leukocytes and two low-prevalence cell classes associated with diseases such as acute promyelocyte leukemia and hairy cell leukemia. Once trained, the system requires low computational cost and can help augment high-quality image datasets to improve automatic recognition model training for clinical laboratory practice.
Collapse
Affiliation(s)
- Kevin Barrera
- Technical University of Catalonia, Barcelona East Engineering School, Department of Mathematics, Barcelona, Spain.
| | - Anna Merino
- Hospital Clínic of Barcelona-IDIBAPS, Biochemistry and Molecular Genetics Department, CORE Laboratory, Biomedical Diagnostic, Barcelona, Spain.
| | - Angel Molina
- Hospital Clínic of Barcelona-IDIBAPS, Biochemistry and Molecular Genetics Department, CORE Laboratory, Biomedical Diagnostic, Barcelona, Spain.
| | - José Rodellar
- Technical University of Catalonia, Barcelona East Engineering School, Department of Mathematics, Barcelona, Spain.
| |
Collapse
|
46
|
Couteaux V, Zhang C, Mulé S, Milot L, Valette PJ, Raynaud C, Vlachomitrou AS, Ciofolo-Veit C, Lawrance L, Belkouchi Y, Vilgrain V, Lewin M, Trillaud H, Hoeffel C, Laurent V, Ammari S, Morand E, Faucoz O, Tenenhaus A, Talbot H, Luciani A, Lassau N, Lazarus C. Synthetic MR image generation of macrotrabecular-massive hepatocellular carcinoma using generative adversarial networks. Diagn Interv Imaging 2023; 104:243-247. [PMID: 36681532 DOI: 10.1016/j.diii.2023.01.003] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/20/2022] [Revised: 01/05/2023] [Accepted: 01/10/2023] [Indexed: 01/22/2023]
Abstract
PURPOSE The purpose of this study was to develop a method for generating synthetic MR images of macrotrabecular-massive hepatocellular carcinoma (MTM-HCC). MATERIALS AND METHODS A set of abdominal MR images including fat-saturated T1-weighted images obtained during the arterial and portal venous phases of enhancement and T2-weighted images of 91 patients with MTM-HCC, and another set of MR abdominal images from 67 other patients were used. Synthetic images were obtained using a 3-step pipeline that consisted in: (i), generating a synthetic MTM-HCC tumor on a neutral background; (ii), randomly selecting a background among the 67 patients and a position inside the liver; and (iii), merging the generated tumor in the background at the specified location. Synthetic images were qualitatively evaluated by three radiologists and quantitatively assessed using a mix of 1-nearest neighbor classifier metric and Fréchet inception distance. RESULTS A set of 1000 triplets of synthetic MTM-HCC images with consistent contrasts were successfully generated. Evaluation of selected synthetic images by three radiologists showed that the method gave realistic, consistent and diversified images. Qualitative and quantitative evaluation led to an overall score of 0.64. CONCLUSION This study shows the feasibility of generating realistic synthetic MR images with very few training data, by leveraging the wide availability of liver backgrounds. Further studies are needed to assess the added value of those synthetic images for automatic diagnosis of MTM-HCC.
Collapse
Affiliation(s)
| | - Cheng Zhang
- Philips Research France, 92150 Suresnes, France
| | - Sébastien Mulé
- Medical Imaging Department, AP-HP, Henri Mondor University Hospital, 94000 Créteil, France; INSERM, U955, Team 18, 94000 Créteil, France
| | - Laurent Milot
- Body and VIR Radiology Department, Hospices Civils de Lyon, Hôpital Edouard Herriot, 69003 Lyon, France
| | - Pierre-Jean Valette
- Body and VIR Radiology Department, Hospices Civils de Lyon, Hôpital Edouard Herriot, 69003 Lyon, France
| | | | | | | | - Littisha Lawrance
- Laboratoire d'Imagerie Biomédicale Multimodale Paris-Saclay, BIOMAPS, UMR 1281, Université Paris-Saclay, Inserm, CNRS, CEA, 94800 Villejuif, France
| | - Younes Belkouchi
- Laboratoire d'Imagerie Biomédicale Multimodale Paris-Saclay, BIOMAPS, UMR 1281, Université Paris-Saclay, Inserm, CNRS, CEA, 94800 Villejuif, France; OPIS - Optimisation Imagerie et Santé, Université Paris-Saclay, Inria, CentraleSupélec, CVN - Centre de vision numérique, 91190 Gif-Sur-Yvette, France
| | - Valérie Vilgrain
- Department of Radiology, APHP, University Hospitals Paris Nord-Val de Seine, Hôpital Beaujon, 92210 Clichy, France; Université Paris Cité, CRI INSERM, 75006 Paris, France
| | - Maité Lewin
- Department of Radiology, AP-HP Hôpital Paul Brousse, 94800 Villejuif, France; Faculté de Médecine, Université Paris-Saclay, 94270 Le Kremlin-Bicêtre, France
| | - Hervé Trillaud
- CHU de Bordeaux, Department of Radiology, Université de Bordeaux, F-33000 Bordeaux, France
| | - Christine Hoeffel
- Department of Radiology, Reims University Hospital, 51092 Reims, France; CRESTIC, University of Reims Champagne-Ardenne, 51100 Reims, France
| | - Valérie Laurent
- Department of Radiology, Nancy University Hospital, University of Lorraine, 54500 Vandoeuvre-lès-Nancy, France
| | - Samy Ammari
- Laboratoire d'Imagerie Biomédicale Multimodale Paris-Saclay, BIOMAPS, UMR 1281, Université Paris-Saclay, Inserm, CNRS, CEA, 94800 Villejuif, France; Department of Imaging, Institut Gustave Roussy, Université Paris-Saclay, 94800 Villejuif, France
| | - Eric Morand
- Centre National d'Etudes Spatiales, Centre Spatial de Toulouse, 31000 Toulouse, France
| | - Orphee Faucoz
- Centre National d'Etudes Spatiales, Centre Spatial de Toulouse, 31000 Toulouse, France
| | - Arthur Tenenhaus
- Université Paris-Saclay, Centrale Supélec, Laboratoire des Signaux et Systèmes, 91190 Gif-sur-Yvette, France
| | - Hugues Talbot
- OPIS - Optimisation Imagerie et Santé, Université Paris-Saclay, Inria, CentraleSupélec, CVN - Centre de vision numérique, 91190 Gif-Sur-Yvette, France
| | - Alain Luciani
- Medical Imaging Department, AP-HP, Henri Mondor University Hospital, 94000 Créteil, France; INSERM, U955, Team 18, 94000 Créteil, France
| | - Nathalie Lassau
- Laboratoire d'Imagerie Biomédicale Multimodale Paris-Saclay, BIOMAPS, UMR 1281, Université Paris-Saclay, Inserm, CNRS, CEA, 94800 Villejuif, France; Department of Imaging, Institut Gustave Roussy, Université Paris-Saclay, 94800 Villejuif, France
| | | |
Collapse
|
47
|
Liu S, Hu W, Xu F, Chen W, Liu J, Yu X, Wang Z, Li Z, Li Z, Yang X, Song B, Wang S, Wang K, Wang X, Hong J, Zhang L, Li J. Prediction of OCT images of short-term response to anti-VEGF treatment for diabetic macular edema using different generative adversarial networks. Photodiagnosis Photodyn Ther 2023; 41:103272. [PMID: 36632873 DOI: 10.1016/j.pdpdt.2023.103272] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/08/2022] [Revised: 01/03/2023] [Accepted: 01/03/2023] [Indexed: 01/11/2023]
Abstract
PURPOSE This study sought to assess the predictive performance of optical coherence tomography (OCT) images for the response of diabetic macular edema (DME) patients to anti-vascular endothelial growth factor (VEGF) therapy generated from baseline images using generative adversarial networks (GANs). METHODS Patient information, including clinical and imaging data, was obtained from inpatients at the Ophthalmology Department of Qilu Hospital. 715 and 103 pairs of pre-and post-treatment OCT images of DME patients were included in the training and validation sets, respectively. The post-treatment OCT images were used to assess the validity of the generated images. Six different GAN models (CycleGAN, PairGAN, Pix2pixHD, RegGAN, SPADE, UNIT) were applied to predict the efficacy of anti-VEGF treatment by generating OCT images. Independent screening and evaluation experiments were conducted to validate the quality and comparability of images generated by different GAN models. RESULTS OCT images generated f GAN models exhibited high comparability to the real images, especially for edema absorption. RegGAN exhibited the highest prediction accuracy over the CycleGAN, PairGAN, Pix2pixHD, SPADE, and UNIT models. Further analyses were conducted based on the RegGAN. Most post-therapeutic OCT images (95/103) were difficult to differentiate from the real OCT images by retinal specialists. A mean absolute error of 26.74 ± 21.28 μm was observed for central macular thickness (CMT) between the synthetic and real OCT images. CONCLUSION Different generative adversarial networks have different prognostic efficacy for DME, and RegGAN yielded the best performance in our study. Different GAN models yielded good accuracy in predicting the OCT-based response to anti-VEGF treatment at one month. Overall, the application of GAN models can assist clinicians in prognosis prediction of patients with DME to design better treatment strategies and follow-up schedules.
Collapse
|
48
|
Mulé S, Lawrance L, Belkouchi Y, Vilgrain V, Lewin M, Trillaud H, Hoeffel C, Laurent V, Ammari S, Morand E, Faucoz O, Tenenhaus A, Cotten A, Meder JF, Talbot H, Luciani A, Lassau N. Generative adversarial networks (GAN)-based data augmentation of rare liver cancers: The SFR 2021 Artificial Intelligence Data Challenge. Diagn Interv Imaging 2023; 104:43-48. [PMID: 36207277 DOI: 10.1016/j.diii.2022.09.005] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/19/2022] [Accepted: 09/20/2022] [Indexed: 01/10/2023]
Abstract
PURPOSE The 2021 edition of the Artificial Intelligence Data Challenge was organized by the French Society of Radiology together with the Centre National d'Études Spatiales and CentraleSupélec with the aim to implement generative adversarial networks (GANs) techniques to provide 1000 magnetic resonance imaging (MRI) cases of macrotrabecular-massive (MTM) hepatocellular carcinoma (HCC), a rare and aggressive subtype of HCC, generated from a limited number of real cases from multiple French centers. MATERIALS AND METHODS A dedicated platform was used by the seven inclusion centers to securely upload their anonymized MRI examinations including all three cross-sectional images (one late arterial and one portal-venous phase T1-weighted images and one fat-saturated T2-weighted image) in compliance with general data protection regulation. The quality of the database was checked by experts and manual delineation of the lesions was performed by the expert radiologists involved in each center. Multidisciplinary teams competed between October 11th, 2021 and February 13th, 2022. RESULTS A total of 91 MTM-HCC datasets of three images each were collected from seven French academic centers. Six teams with a total of 28 individuals participated in this challenge. Each participating team was asked to generate one thousand 3-image cases. The qualitative evaluation was performed by three radiologists using the Likert scale on ten randomly selected cases generated by each participant. A quantitative evaluation was also performed using two metrics, the Frechet inception distance and a leave-one-out accuracy of a 1-Nearest Neighbor algorithm. CONCLUSION This data challenge demonstrates the ability of GANs techniques to generate a large number of images from a small sample of imaging examinations of a rare malignant tumor.
Collapse
Affiliation(s)
- Sébastien Mulé
- Medical Imaging Department, AP-HP, Henri Mondor University Hospital, Créteil 94000, France; INSERM, U955, Team 18, Créteil 94000, France.
| | - Littisha Lawrance
- Laboratoire d'Imagerie Biomédicale Multimodale Paris-Saclay, Inserm, CNRS, CEA, BIOMAPS, UMR 1281, Université Paris-Saclay, Villejuif 94800, France
| | - Younes Belkouchi
- Laboratoire d'Imagerie Biomédicale Multimodale Paris-Saclay, Inserm, CNRS, CEA, BIOMAPS, UMR 1281, Université Paris-Saclay, Villejuif 94800, France; OPIS-Optimisation Imagerie et Santé, Inria, CentraleSupélec, CVN-Centre de Vision Numérique, Université Paris-Saclay, Gif-Sur-Yvette 91190, France
| | - Valérie Vilgrain
- Department of Radiology, APHP, University Hospitals Paris Nord Val de Seine, Hôpital Beaujon, Clichy 92110, France; CRI INSERM, Université Paris Cité, Paris 75018, France
| | - Maité Lewin
- Department of Radiology, AP-HP Hôpital Paul Brousse, Villejuif 94800, France; Faculté de Médecine, Université Paris-Saclay, Le Kremlin-Bicêtre 94270, France
| | - Hervé Trillaud
- CHU de Bordeaux, Department of Radiology, Université de Bordeaux, Bordeaux 33000, France
| | - Christine Hoeffel
- Department of Radiology, Reims University Hospital, Reims 51092, France; CRESTIC, University of Reims Champagne-Ardenne, Reims 51100, France
| | - Valérie Laurent
- Department of Radiology, Nancy University Hospital, University of Lorraine, Vandoeuvre-ls-Nancy 54500, France
| | - Samy Ammari
- Laboratoire d'Imagerie Biomédicale Multimodale Paris-Saclay, Inserm, CNRS, CEA, BIOMAPS, UMR 1281, Université Paris-Saclay, Villejuif 94800, France; Department of Imaging, Institut Gustave Roussy, Université Paris-Saclay, Villejuif 94800, France
| | - Eric Morand
- Centre National d'Etudes Spatiales-CNES, Centre Spatial de Toulouse, Toulouse 31401 CEDEX 9 University, France
| | - Orphée Faucoz
- Centre National d'Etudes Spatiales-CNES, Centre Spatial de Toulouse, Toulouse 31401 CEDEX 9 University, France
| | - Arthur Tenenhaus
- CentraleSupélec, Laboratoire des Signaux et Systèmes, Université Paris-Saclay, Gif-sur-Yvette 91190, France
| | - Anne Cotten
- Department of Musculoskeletal Radiology, Centre de Consultations Et D'imagerie de L'appareil Locomoteur, Lille 59037, France; Lille University School of Medicine, Lille, France
| | - Jean-François Meder
- Department of Neuroimaging, Sainte-Anne Hospital, Paris 75013 University, France; Université Paris Cité, Paris 75006, France
| | - Hugues Talbot
- OPIS-Optimisation Imagerie et Santé, Inria, CentraleSupélec, CVN-Centre de Vision Numérique, Université Paris-Saclay, Gif-Sur-Yvette 91190, France
| | - Alain Luciani
- Medical Imaging Department, AP-HP, Henri Mondor University Hospital, Créteil 94000, France; INSERM, U955, Team 18, Créteil 94000, France
| | - Nathalie Lassau
- Laboratoire d'Imagerie Biomédicale Multimodale Paris-Saclay, Inserm, CNRS, CEA, BIOMAPS, UMR 1281, Université Paris-Saclay, Villejuif 94800, France; Department of Imaging, Institut Gustave Roussy, Université Paris-Saclay, Villejuif 94800, France
| |
Collapse
|
49
|
Celard P, Iglesias EL, Sorribes-Fdez JM, Romero R, Vieira AS, Borrajo L. A survey on deep learning applied to medical images: from simple artificial neural networks to generative models. Neural Comput Appl 2023; 35:2291-2323. [PMID: 36373133 PMCID: PMC9638354 DOI: 10.1007/s00521-022-07953-4] [Citation(s) in RCA: 9] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/23/2022] [Accepted: 10/12/2022] [Indexed: 11/06/2022]
Abstract
Deep learning techniques, in particular generative models, have taken on great importance in medical image analysis. This paper surveys fundamental deep learning concepts related to medical image generation. It provides concise overviews of studies which use some of the latest state-of-the-art models from last years applied to medical images of different injured body areas or organs that have a disease associated with (e.g., brain tumor and COVID-19 lungs pneumonia). The motivation for this study is to offer a comprehensive overview of artificial neural networks (NNs) and deep generative models in medical imaging, so more groups and authors that are not familiar with deep learning take into consideration its use in medicine works. We review the use of generative models, such as generative adversarial networks and variational autoencoders, as techniques to achieve semantic segmentation, data augmentation, and better classification algorithms, among other purposes. In addition, a collection of widely used public medical datasets containing magnetic resonance (MR) images, computed tomography (CT) scans, and common pictures is presented. Finally, we feature a summary of the current state of generative models in medical image including key features, current challenges, and future research paths.
Collapse
Affiliation(s)
- P. Celard
- Computer Science Department, Universidade de Vigo, Escuela Superior de Ingeniería Informática, Campus Universitario As Lagoas, 32004 Ourense, Spain ,CINBIO - Biomedical Research Centre, Universidade de Vigo, Campus Universitario Lagoas-Marcosende, 36310 Vigo, Spain ,SING Research Group, Galicia Sur Health Research Institute (IIS Galicia Sur), SERGAS-UVIGO, Vigo, Spain
| | - E. L. Iglesias
- Computer Science Department, Universidade de Vigo, Escuela Superior de Ingeniería Informática, Campus Universitario As Lagoas, 32004 Ourense, Spain ,CINBIO - Biomedical Research Centre, Universidade de Vigo, Campus Universitario Lagoas-Marcosende, 36310 Vigo, Spain ,SING Research Group, Galicia Sur Health Research Institute (IIS Galicia Sur), SERGAS-UVIGO, Vigo, Spain
| | - J. M. Sorribes-Fdez
- Computer Science Department, Universidade de Vigo, Escuela Superior de Ingeniería Informática, Campus Universitario As Lagoas, 32004 Ourense, Spain ,CINBIO - Biomedical Research Centre, Universidade de Vigo, Campus Universitario Lagoas-Marcosende, 36310 Vigo, Spain ,SING Research Group, Galicia Sur Health Research Institute (IIS Galicia Sur), SERGAS-UVIGO, Vigo, Spain
| | - R. Romero
- Computer Science Department, Universidade de Vigo, Escuela Superior de Ingeniería Informática, Campus Universitario As Lagoas, 32004 Ourense, Spain ,CINBIO - Biomedical Research Centre, Universidade de Vigo, Campus Universitario Lagoas-Marcosende, 36310 Vigo, Spain ,SING Research Group, Galicia Sur Health Research Institute (IIS Galicia Sur), SERGAS-UVIGO, Vigo, Spain
| | - A. Seara Vieira
- Computer Science Department, Universidade de Vigo, Escuela Superior de Ingeniería Informática, Campus Universitario As Lagoas, 32004 Ourense, Spain ,CINBIO - Biomedical Research Centre, Universidade de Vigo, Campus Universitario Lagoas-Marcosende, 36310 Vigo, Spain ,SING Research Group, Galicia Sur Health Research Institute (IIS Galicia Sur), SERGAS-UVIGO, Vigo, Spain
| | - L. Borrajo
- Computer Science Department, Universidade de Vigo, Escuela Superior de Ingeniería Informática, Campus Universitario As Lagoas, 32004 Ourense, Spain ,CINBIO - Biomedical Research Centre, Universidade de Vigo, Campus Universitario Lagoas-Marcosende, 36310 Vigo, Spain ,SING Research Group, Galicia Sur Health Research Institute (IIS Galicia Sur), SERGAS-UVIGO, Vigo, Spain
| |
Collapse
|
50
|
Wang F, Urquizo RC, Roberts P, Mohan V, Newenham C, Ivanov A, Dowling R. Biologically inspired robotic perception-action for soft fruit harvesting in vertical growing environments. Precis Agric 2023; 24:1072-1096. [PMID: 37152437 PMCID: PMC10010232 DOI: 10.1007/s11119-023-10000-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Accepted: 02/19/2023] [Indexed: 05/09/2023]
Abstract
Multiple interlinked factors like demographics, migration patterns, and economics are presently leading to the critical shortage of labour available for low-skilled, physically demanding tasks like soft fruit harvesting. This paper presents a biomimetic robotic solution covering the full 'Perception-Action' loop targeting harvesting of strawberries in a state-of-the-art vertical growing environment. The novelty emerges from both dealing with crop/environment variance as well as configuring the robot action system to deal with a range of runtime task constraints. Unlike the commonly used deep neural networks, the proposed perception system uses conditional Generative Adversarial Networks to identify the ripe fruit using synthetic data. The network can effectively train the synthetic data using the image-to-image translation concept, thereby avoiding the tedious work of collecting and labelling the real dataset. Once the harvest-ready fruit is localised using point cloud data generated by a stereo camera, our platform's action system can coordinate the arm to reach/cut the stem using the Passive Motion Paradigm framework inspired by studies on neural control of movement in the brain. Results from field trials for strawberry detection, reaching/cutting the stem of the fruit, and extension to analysing complex canopy structures/bimanual coordination (searching/picking) are presented. While this article focuses on strawberry harvesting, ongoing research towards adaptation of the architecture to other crops such as tomatoes and sweet peppers is briefly described. Supplementary Information The online version contains supplementary material available at 10.1007/s11119-023-10000-4.
Collapse
Affiliation(s)
- Fuli Wang
- School of Computer Science and Electronic Engineering, University of Essex, Colchester, CO4 3SQ UK
| | - Rodolfo Cuan Urquizo
- School of Computer Science and Electronic Engineering, University of Essex, Colchester, CO4 3SQ UK
| | - Penelope Roberts
- School of Computer Science and Electronic Engineering, University of Essex, Colchester, CO4 3SQ UK
| | - Vishwanathan Mohan
- School of Computer Science and Electronic Engineering, University of Essex, Colchester, CO4 3SQ UK
| | - Chris Newenham
- Wilkin & Sons Ltd, Factory Hill, Tiptree, Essex CO5 0RF UK
| | - Andrey Ivanov
- Wilkin & Sons Ltd, Factory Hill, Tiptree, Essex CO5 0RF UK
| | - Robin Dowling
- Wilkin & Sons Ltd, Factory Hill, Tiptree, Essex CO5 0RF UK
| |
Collapse
|