1
|
Lu Z, She C, Wang W, Huang Q. LM-Net: A light-weight and multi-scale network for medical image segmentation. Comput Biol Med 2024; 168:107717. [PMID: 38007973 DOI: 10.1016/j.compbiomed.2023.107717] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/15/2023] [Revised: 11/07/2023] [Accepted: 11/15/2023] [Indexed: 11/28/2023]
Abstract
Current medical image segmentation approaches have limitations in deeply exploring multi-scale information and effectively combining local detail textures with global contextual semantic information. This results in over-segmentation, under-segmentation, and blurred segmentation boundaries. To tackle these challenges, we explore multi-scale feature representations from different perspectives, proposing a novel, lightweight, and multi-scale architecture (LM-Net) that integrates advantages of both Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) to enhance segmentation accuracy. LM-Net employs a lightweight multi-branch module to capture multi-scale features at the same level. Furthermore, we introduce two modules to concurrently capture local detail textures and global semantics with multi-scale features at different levels: the Local Feature Transformer (LFT) and Global Feature Transformer (GFT). The LFT integrates local window self-attention to capture local detail textures, while the GFT leverages global self-attention to capture global contextual semantics. By combining these modules, our model achieves complementarity between local and global representations, alleviating the problem of blurred segmentation boundaries in medical image segmentation. To evaluate the feasibility of LM-Net, extensive experiments have been conducted on three publicly available datasets with different modalities. Our proposed model achieves state-of-the-art results, surpassing previous methods, while only requiring 4.66G FLOPs and 5.4M parameters. These state-of-the-art results on three datasets with different modalities demonstrate the effectiveness and adaptability of our proposed LM-Net for various medical image segmentation tasks.
Collapse
Affiliation(s)
- Zhenkun Lu
- College of Electronic Information, Guangxi Minzu University, Nanning, China
| | - Chaoyin She
- College of Electronic Information, Guangxi Minzu University, Nanning, China. https://github.com/Asunatan/LM-Net
| | - Wei Wang
- Department of Medical Ultrasonics, Institute of Diagnostic and Interventional Ultrasound, The First Affiliated Hospital of Sun Yat-Sen University, Guangzhou, China
| | - Qinghua Huang
- School of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University, Xi'an, China.
| |
Collapse
|
2
|
Gao J, Xu L, Wan M. Incremental learning for an evolving stream of medical ultrasound images via counterfactual thinking. Comput Med Imaging Graph 2023; 109:102290. [PMID: 37647830 DOI: 10.1016/j.compmedimag.2023.102290] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/20/2023] [Revised: 07/27/2023] [Accepted: 08/16/2023] [Indexed: 09/01/2023]
Abstract
Despite the fact that traditional deep learning (DL) approaches provide promising accuracy and efficiency in medical ultrasound image analysis, they cannot replace the physician in making a diagnosis since the DL model is only appropriate in static application scenarios. Currently, most DL-based models are incapable of learning new tasks in the dynamic clinical environments due to the catastrophic forgetting of old tasks. To address the above problem, we propose an incremental classifier that is sequentially trained on evolving tasks for medical ultrasound images by counterfactual thinking. Specifically, the proposed model consists of a feature extractor and a classifier that can add new classes at any time during training. Toward a more discriminative model in the continual learning setting, a contrastive strategy is designed to leverage fine-grained information by generating a series of counterfactual regions. For model optimization, we design a multi-task loss made up of a knowledge distillation loss, a cross-entropy loss, and a contrasting loss. This objective jointly enjoys the merits of less forgetting, better accuracy, and fine-grained information utilization. A newly collected dataset with 52 medical ultrasound classification tasks is used to demonstrate the effectiveness of our method. The proposed approach achieves 76.59%, 11.67%, and 7.93% in terms of the average incremental accuracy, forgetting rate, and feature retention, respectively.
Collapse
Affiliation(s)
- Junling Gao
- The Key Laboratory of Biomedical Information Engineering of Ministry of Education, School of Life Science and Technology, Xi'an Jiaotong University, Xi'an 710049, PR China
| | - Lei Xu
- The Key Laboratory of Biomedical Information Engineering of Ministry of Education, School of Life Science and Technology, Xi'an Jiaotong University, Xi'an 710049, PR China; Xi'an Hospital of Traditional Chinese Medicine, Xi'an 710021, PR China
| | - Mingxi Wan
- The Key Laboratory of Biomedical Information Engineering of Ministry of Education, School of Life Science and Technology, Xi'an Jiaotong University, Xi'an 710049, PR China.
| |
Collapse
|
3
|
Mustafa Z, Nsour H. Using Computer Vision Techniques to Automatically Detect Abnormalities in Chest X-rays. Diagnostics (Basel) 2023; 13:2979. [PMID: 37761345 PMCID: PMC10530162 DOI: 10.3390/diagnostics13182979] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/14/2023] [Revised: 07/23/2023] [Accepted: 08/07/2023] [Indexed: 09/29/2023] Open
Abstract
Our research focused on creating an advanced machine-learning algorithm that accurately detects anomalies in chest X-ray images to provide healthcare professionals with a reliable tool for diagnosing various lung conditions. To achieve this, we analysed a vast collection of X-ray images and utilised sophisticated visual analysis techniques; such as deep learning (DL) algorithms, object recognition, and categorisation models. To create our model, we used a large training dataset of chest X-rays, which provided valuable information for visualising and categorising abnormalities. We also utilised various data augmentation methods; such as scaling, rotation, and imitation; to increase the diversity of images used for training. We adopted the widely used You Only Look Once (YOLO) v8 algorithm, an object recognition paradigm that has demonstrated positive outcomes in computer vision applications, and modified it to classify X-ray images into distinct categories; such as respiratory infections, tuberculosis (TB), and lung nodules. It was particularly effective in identifying unique and crucial outcomes that may, otherwise, be difficult to detect using traditional diagnostic methods. Our findings demonstrate that healthcare practitioners can reliably use machine learning (ML) algorithms to diagnose various lung disorders with greater accuracy and efficiency.
Collapse
Affiliation(s)
- Zaid Mustafa
- Department of Computer Information Systems, Prince Abdullah Bin Ghazi Faculty of Information and Communication Technology, Al-Balqa Applied University, Al-Salt 19117, Jordan
| | - Heba Nsour
- Department of Computer Science, Prince Abdullah Bin Ghazi Faculty of Information and Communication Technology, Al-Balqa Applied University, Al-Salt 19117, Jordan
| |
Collapse
|
4
|
Yang T, Yuan L, Li P, Liu P. Real-Time Automatic Assisted Detection of Uterine Fibroid in Ultrasound Images Using a Deep Learning Detector. ULTRASOUND IN MEDICINE & BIOLOGY 2023; 49:1616-1626. [PMID: 37121880 DOI: 10.1016/j.ultrasmedbio.2023.03.013] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/29/2022] [Revised: 03/07/2023] [Accepted: 03/18/2023] [Indexed: 05/17/2023]
Abstract
OBJECTIVE Uterine smooth muscle hyperplasia causes a tumor called a uterine fibroid. With an incidence of up to 30%, it is one of the most prevalent tumors in women and has the third highest prevalence of all gynecological illnesses. Although uterine fibroids are usually not accompanied by symptoms, there are physical effects, such as impairment of the ability to conceive. To reduce morbidity, early detection and treatment are crucial. Ultrasound imaging is a common method used for pre-operative guidance and interventional therapy. Many applications of object detection are performing well with the advancement of deep learning in the field of medical image analysis. To ensure accuracy, computer-assisted detection can further solve the subjective problem generated by different doctors when they read images. METHODS Our research provides an improved YOLOv3 that combines the properties of EfficientNet and YOLOv3, which use a convolutional neural network to extract features, to detect uterine fibroid ultrasound images. RESULTS Our approach attained an F1 score of 95% and an average precision of 98.38% and reached a detection speed of 0.28 s per image. We reviewed and analyzed several detection techniques and identified potential future research hotpots. CONCLUSION This technique offers enough supplementary diagnostic tools for amateur or expert ultrasonologists and sets a solid foundation for future medical care and surgical excision.
Collapse
Affiliation(s)
- Tiantian Yang
- College of Engineering, Huaqiao University, Quanzhou, China
| | - Linlin Yuan
- College of Physical Education, Huaqiao University, Xiamen, China
| | - Ping Li
- Department of Gynecology and Obstetrics, First Hospital of Quanzhou, Quanzhou, China
| | - Peizhong Liu
- College of Engineering, Huaqiao University, Quanzhou, China.
| |
Collapse
|
5
|
Liu J, Feng Q, Miao Y, He W, Shi W, Jiang Z. COVID-19 disease identification network based on weakly supervised feature selection. MATHEMATICAL BIOSCIENCES AND ENGINEERING : MBE 2023; 20:9327-9348. [PMID: 37161245 DOI: 10.3934/mbe.2023409] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/11/2023]
Abstract
The coronavirus disease 2019 (COVID-19) outbreak has resulted in countless infections and deaths worldwide, posing increasing challenges for the health care system. The use of artificial intelligence to assist in diagnosis not only had a high accuracy rate but also saved time and effort in the sudden outbreak phase with the lack of doctors and medical equipment. This study aimed to propose a weakly supervised COVID-19 classification network (W-COVNet). This network was divided into three main modules: weakly supervised feature selection module (W-FS), deep learning bilinear feature fusion module (DBFF) and Grad-CAM++ based network visualization module (Grad-Ⅴ). The first module, W-FS, mainly removed redundant background features from computed tomography (CT) images, performed feature selection and retained core feature regions. The second module, DBFF, mainly used two symmetric networks to extract different features and thus obtain rich complementary features. The third module, Grad-Ⅴ, allowed the visualization of lesions in unlabeled images. A fivefold cross-validation experiment showed an average classification accuracy of 85.3%, and a comparison with seven advanced classification models showed that our proposed network had a better performance.
Collapse
Affiliation(s)
- Jingyao Liu
- School of Computer Science and Technology, Changchun University of Science and Technology, Changchun, Jilin 130022, China
- School of Computer and Information Engineering, Chuzhou University, Chuzhou 239000, China
| | - Qinghe Feng
- School of Intelligent Engineering, Henan Institute of Technology, Xinxiang 453003, China
| | - Yu Miao
- School of Computer Science and Technology, Changchun University of Science and Technology, Changchun, Jilin 130022, China
- Zhongshan Institute of Changchun University of Science and Technology, Zhongshan 528437, China
| | - Wei He
- School of Computer Science and Technology, Changchun University of Science and Technology, Changchun, Jilin 130022, China
| | - Weili Shi
- School of Computer Science and Technology, Changchun University of Science and Technology, Changchun, Jilin 130022, China
- Zhongshan Institute of Changchun University of Science and Technology, Zhongshan 528437, China
| | - Zhengang Jiang
- School of Computer Science and Technology, Changchun University of Science and Technology, Changchun, Jilin 130022, China
- Zhongshan Institute of Changchun University of Science and Technology, Zhongshan 528437, China
| |
Collapse
|
6
|
Huang ML, Liao YC. A lightweight CNN-based network on COVID-19 detection using X-ray and CT images. Comput Biol Med 2022; 146:105604. [PMID: 35576824 PMCID: PMC9090861 DOI: 10.1016/j.compbiomed.2022.105604] [Citation(s) in RCA: 8] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/22/2022] [Revised: 05/03/2022] [Accepted: 05/08/2022] [Indexed: 01/17/2023]
Abstract
BACKGROUND AND OBJECTIVES The traditional method of detecting COVID-19 disease mainly rely on the interpretation of computer tomography (CT) or X-ray images (X-ray) by doctors or professional researchers to identify whether it is COVID-19 disease, which is easy to cause identification mistakes. In this study, the technology of convolutional neural network is expected to be able to efficiently and accurately identify the COVID-19 disease. METHODS This study uses and fine-tunes seven convolutional neural networks including InceptionV3, ResNet50V2, Xception, DenseNet121, MobileNetV2, EfficientNet-B0, and EfficientNetV2 on COVID-19 detection. In addition, we proposes a lightweight convolutional neural network, LightEfficientNetV2, on small number of chest X-ray and CT images. Five-fold cross-validation was used to evaluate the performance of each model. To confirm the performance of the proposed model, LightEfficientNetV2 was carried out on three different datasets (NIH Chest X-rays, SARS-CoV-2 and COVID-CT). RESULTS On chest X-ray image dataset, the highest accuracy 96.50% was from InceptionV3 before fine-tuning; and the highest accuracy 97.73% was from EfficientNetV2 after fine-tuning. The accuracy of the LightEfficientNetV2 model proposed in this study is 98.33% on chest X-ray image. On CT images, the best transfer learning model before fine-tuning is MobileNetV2, with an accuracy of 94.46%; the best transfer learning model after fine-tuning is Xception, with an accuracy of 96.78%. The accuracy of the LightEfficientNetV2 model proposed in this study is 97.48% on CT image. CONCLUSIONS Compared with the SOTA, LightEfficientNetV2 proposed in this study demonstrates promising performance on chest X-ray images, CT images and three different datasets.
Collapse
Affiliation(s)
- Mei-Ling Huang
- Department of Industrial Engineering & Management, National Chin-Yi University of Technology, 57, Sec. 2, Zhongshan Rd., Taiping Dist., Taichung, 411030, Taiwan.
| | - Yu-Chieh Liao
- Department of Industrial Engineering & Management, National Chin-Yi University of Technology, 57, Sec. 2, Zhongshan Rd., Taiping Dist., Taichung, 411030, Taiwan
| |
Collapse
|