1
|
Ding X, Zhou Q, Liu Z, Hammad Kowah JA, Wang L, Huang X, Liu X. A Novel Approach to the Technique of Lung Region Segmentation Based on a Deep Learning Model to Diagnose COVID-19 X-ray Images. Curr Med Imaging 2024; 20:1-11. [PMID: 38389381 DOI: 10.2174/0115734056271185231121074341] [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: 07/27/2023] [Revised: 09/17/2023] [Accepted: 10/19/2023] [Indexed: 02/24/2024]
Abstract
BACKGROUND The novel coronavirus pandemic has caused a global health crisis, placing immense strain on healthcare systems worldwide. Chest X-ray technology has emerged as a critical tool for the diagnosis and treatment of COVID-19. However, the manual interpretation of chest X-ray films has proven to be inefficient and time-consuming, necessitating the development of an automated classification system. OBJECTIVE In response to the challenges posed by the COVID-19 pandemic, we aimed to develop a deep learning model that accurately classifies chest X-ray images, specifically focusing on lung regions, to enhance the efficiency and accuracy of COVID-19 and pneumonia diagnosis. METHODS We have proposed a novel deep network called "FocusNet" for precise segmentation of lung regions in chest radiographs. This segmentation allows for the accurate extraction of lung contours from chest X-ray images, which are then input into the classification network, ResNet18. By training the model on these segmented lung datasets, we sought to improve the accuracy of classification. RESULTS The performance of our proposed system was evaluated on three types of lung regions in normal individuals, COVID-19 patients, and those with pneumonia. The average accuracy of the segmentation model (FocusNet) in segmenting lung regions was found to be above 90%. After reclassification of the segmented lung images, the specificities and sensitivities for normal, COVID-19, and pneumonia were excellent, with values of 98.00%, 99.00%, 99.50%, and 98.50%, 100.00%, and 99.00%, respectively. ResNet18 achieved impressive area under the curve (AUC) values of 0.99, 1.00, and 0.99 for classifying normal, COVID-19, and pneumonia, respectively, on the segmented lung datasets. Moreover, the AUC values of the three groups increased by 0.02, 0.02, and 0.06, respectively, when compared to the direct classification of unsegmented original images. Overall, the accuracy of lung region classification after processing the datasets was 99.3%. CONCLUSION Our deep learning-based automated chest X-ray classification system, incorporating lung region segmentation using FocusNet and subsequent classification with ResNet18, has significantly improved the accuracy of diagnosing respiratory lung diseases, including COVID-19. The proposed approach has great potential to revolutionize the diagnosis of COVID-19 and other respiratory lung diseases, offering a valuable tool to support healthcare professionals during health crises.
Collapse
Affiliation(s)
- Xuejie Ding
- College of Medicine, Guangxi University, Nanning 530004, China
| | - Qi Zhou
- College of Medicine, Guangxi University, Nanning 530004, China
| | - Zifan Liu
- College of Medicine, Guangxi University, Nanning 530004, China
| | | | - Lisheng Wang
- College of Chemistry and Chemical Engineering, Guangxi University, Nanning 530004, China
| | - Xialing Huang
- Department of Radiology, The First Affiliated Hospital of Guangxi Medical University, No. 6 Shuangyong Road, Nanning 530004, Guangxi, China
| | - Xu Liu
- College of Medicine, Guangxi University, Nanning 530004, China
| |
Collapse
|
2
|
Rajaraman S, Yang F, Zamzmi G, Xue Z, Antani S. Can Deep Adult Lung Segmentation Models Generalize to the Pediatric Population? Expert Syst Appl 2023; 229:120531. [PMID: 37397242 PMCID: PMC10310063 DOI: 10.1016/j.eswa.2023.120531] [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: 07/04/2023]
Abstract
Lung segmentation in chest X-rays (CXRs) is an important prerequisite for improving the specificity of diagnoses of cardiopulmonary diseases in a clinical decision support system. Current deep learning models for lung segmentation are trained and evaluated on CXR datasets in which the radiographic projections are captured predominantly from the adult population. However, the shape of the lungs is reported to be significantly different across the developmental stages from infancy to adulthood. This might result in age-related data domain shifts that would adversely impact lung segmentation performance when the models trained on the adult population are deployed for pediatric lung segmentation. In this work, our goal is to (i) analyze the generalizability of deep adult lung segmentation models to the pediatric population and (ii) improve performance through a stage-wise, systematic approach consisting of CXR modality-specific weight initializations, stacked ensembles, and an ensemble of stacked ensembles. To evaluate segmentation performance and generalizability, novel evaluation metrics consisting of mean lung contour distance (MLCD) and average hash score (AHS) are proposed in addition to the multi-scale structural similarity index measure (MS-SSIM), the intersection of union (IoU), Dice score, 95% Hausdorff distance (HD95), and average symmetric surface distance (ASSD). Our results showed a significant improvement (p < 0.05) in cross-domain generalization through our approach. This study could serve as a paradigm to analyze the cross-domain generalizability of deep segmentation models for other medical imaging modalities and applications.
Collapse
Affiliation(s)
- Sivaramakrishnan Rajaraman
- Computational Health Research Branch, National Library of Medicine, National Institutes of Health, Bethesda, MD 20894, USA
| | - Feng Yang
- Computational Health Research Branch, National Library of Medicine, National Institutes of Health, Bethesda, MD 20894, USA
| | - Ghada Zamzmi
- Computational Health Research Branch, National Library of Medicine, National Institutes of Health, Bethesda, MD 20894, USA
| | - Zhiyun Xue
- Computational Health Research Branch, National Library of Medicine, National Institutes of Health, Bethesda, MD 20894, USA
| | - Sameer Antani
- Computational Health Research Branch, National Library of Medicine, National Institutes of Health, Bethesda, MD 20894, USA
| |
Collapse
|
3
|
熊 亮, 秦 小, 刘 欣. [Non-local attention and multi-task learning based lung segmentation in chest X-ray]. Sheng Wu Yi Xue Gong Cheng Xue Za Zhi 2023; 40:912-919. [PMID: 37879920 PMCID: PMC10600435 DOI: 10.7507/1001-5515.202211079] [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] [Subscribe] [Scholar Register] [Received: 11/29/2022] [Revised: 09/14/2023] [Indexed: 10/27/2023]
Abstract
Precise segmentation of lung field is a crucial step in chest radiographic computer-aided diagnosis system. With the development of deep learning, fully convolutional network based models for lung field segmentation have achieved great effect but are poor at accurate identification of the boundary and preserving lung field consistency. To solve this problem, this paper proposed a lung segmentation algorithm based on non-local attention and multi-task learning. Firstly, an encoder-decoder convolutional network based on residual connection was used to extract multi-scale context and predict the boundary of lung. Secondly, a non-local attention mechanism to capture the long-range dependencies between pixels in the boundary regions and global context was proposed to enrich feature of inconsistent region. Thirdly, a multi-task learning to predict lung field based on the enriched feature was conducted. Finally, experiments to evaluate this algorithm were performed on JSRT and Montgomery dataset. The maximum improvement of Dice coefficient and accuracy were 1.99% and 2.27%, respectively, comparing with other representative algorithms. Results show that by enhancing the attention of boundary, this algorithm can improve the accuracy and reduce false segmentation.
Collapse
Affiliation(s)
- 亮 熊
- 中国科学院成都计算机应用研究所(成都 610041)Chengdu Institute of Computer Application, Chinese Academy of Sciences, Chengdu 610041, P. R. China
- 中国科学院大学(北京 100049)University of Chinese Academy of Sciences, Beijing 100049, P. R. China
| | - 小林 秦
- 中国科学院成都计算机应用研究所(成都 610041)Chengdu Institute of Computer Application, Chinese Academy of Sciences, Chengdu 610041, P. R. China
- 中国科学院大学(北京 100049)University of Chinese Academy of Sciences, Beijing 100049, P. R. China
| | - 欣 刘
- 中国科学院成都计算机应用研究所(成都 610041)Chengdu Institute of Computer Application, Chinese Academy of Sciences, Chengdu 610041, P. R. China
| |
Collapse
|
4
|
Ghali R, Akhloufi MA. Vision Transformers for Lung Segmentation on CXR Images. SN Comput Sci 2023; 4:414. [PMID: 37252339 PMCID: PMC10206550 DOI: 10.1007/s42979-023-01848-4] [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] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 12/20/2022] [Accepted: 04/17/2023] [Indexed: 05/31/2023]
Abstract
Accurate segmentation of the lungs in CXR images is the basis for an automated CXR image analysis system. It helps radiologists in detecting lung areas, subtle signs of disease and improving the diagnosis process for patients. However, precise semantic segmentation of lungs is considered a challenging case due to the presence of the edge rib cage, wide variation of lung shape, and lungs affected by diseases. In this paper, we address the problem of lung segmentation in healthy and unhealthy CXR images. Five models were developed and used in detecting and segmenting lung regions. Two loss functions and three benchmark datasets were employed to evaluate these models. Experimental results showed that the proposed models were able to extract salient global and local features from the input CXR images. The best performing model achieved an F1 score of 97.47%, outperforming recent published models. They proved their ability to separate lung regions from the rib cage and clavicle edges and segment varying lung shape depending on age and gender, as well as challenging cases of lungs affected by anomalies such as tuberculosis and the presence of nodules.
Collapse
Affiliation(s)
- Rafik Ghali
- Perception, Robotics, and Intelligent Machines (PRIME), Department of Computer Science, Université de Moncton, Moncton, NB E1A 3E9 Canada
| | - Moulay A. Akhloufi
- Perception, Robotics, and Intelligent Machines (PRIME), Department of Computer Science, Université de Moncton, Moncton, NB E1A 3E9 Canada
| |
Collapse
|
5
|
Gupta A, Mishra S, Sahu SC, Srinivasarao U, Naik KJ. Application of Convolutional Neural Networks for COVID-19 Detection in X-ray Images Using InceptionV3 and U-Net. New Gener Comput 2023; 41:475-502. [PMID: 37229179 PMCID: PMC10173914 DOI: 10.1007/s00354-023-00217-2] [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] [Subscribe] [Scholar Register] [Received: 05/18/2022] [Accepted: 04/25/2023] [Indexed: 05/27/2023]
Abstract
COVID-19 has expanded overall across the globe after its initial cases were discovered in December 2019 in Wuhan-China. Because the virus has impacted people's health worldwide, its fast identification is essential for preventing disease spread and reducing mortality rates. The reverse transcription polymerase chain reaction (RT-PCR) is the primary leading method for detecting COVID-19 disease; it has high costs and long turnaround times. Hence, quick and easy-to-use innovative diagnostic instruments are required. According to a new study, COVID-19 is linked to discoveries in chest X-ray pictures. The suggested approach includes a stage of pre-processing with lung segmentation, removing the surroundings that do not provide information pertinent to the task and may result in biased results. The InceptionV3 and U-Net deep learning models used in this work process the X-ray photo and classifies them as COVID-19 negative or positive. The CNN model that uses a transfer learning approach was trained. Finally, the findings are analyzed and interpreted through different examples. The obtained COVID-19 detection accuracy is around 99% for the best models.
Collapse
Affiliation(s)
- Aman Gupta
- Department of Computer Science and Engineering, National Institute of Technology Raipur, Raipur , Chhattisgarh India
| | - Shashank Mishra
- Department of Computer Science and Engineering, National Institute of Technology Raipur, Raipur , Chhattisgarh India
| | - Sourav Chandan Sahu
- Department of Computer Science and Engineering, National Institute of Technology Raipur, Raipur , Chhattisgarh India
| | - Ulligaddala Srinivasarao
- Department of Computer Science and Engineering, National Institute of Technology Raipur, Raipur , Chhattisgarh India
| | - K. Jairam Naik
- Department of Computer Science and Engineering, National Institute of Technology Raipur, Raipur , Chhattisgarh India
| |
Collapse
|
6
|
Murugappan M, Bourisly AK, Prakash NB, Sumithra MG, Acharya UR. Automated semantic lung segmentation in chest CT images using deep neural network. Neural Comput Appl 2023; 35:15343-15364. [PMID: 37273912 PMCID: PMC10088735 DOI: 10.1007/s00521-023-08407-1] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/11/2022] [Accepted: 02/13/2023] [Indexed: 06/06/2023]
Abstract
Lung segmentation algorithms play a significant role in segmenting theinfected regions in the lungs. This work aims to develop a computationally efficient and robust deep learning model for lung segmentation using chest computed tomography (CT) images with DeepLabV3 + networks for two-class (background and lung field) and four-class (ground-glass opacities, background, consolidation, and lung field). In this work, we investigate the performance of the DeepLabV3 + network with five pretrained networks: Xception, ResNet-18, Inception-ResNet-v2, MobileNet-v2 and ResNet-50. A publicly available database for COVID-19 that contains 750 chest CT images and corresponding pixel-labeled images are used to develop the deep learning model. The segmentation performance has been assessed using five performance measures: Intersection of Union (IoU), Weighted IoU, Balance F1 score, pixel accu-racy, and global accuracy. The experimental results of this work confirm that the DeepLabV3 + network with ResNet-18 and a batch size of 8 have a higher performance for two-class segmentation. DeepLabV3 + network coupled with ResNet-50 and a batch size of 16 yielded better results for four-class segmentation compared to other pretrained networks. Besides, the ResNet with a fewer number of layers is highly adequate for developing a more robust lung segmentation network with lesser computational complexity compared to the conventional DeepLabV3 + network with Xception. This present work proposes a unified DeepLabV3 + network to delineate the two and four different regions automatically using CT images for CoVID-19 patients. Our developed automated segmented model can be further developed to be used as a clinical diagnosis system for CoVID-19 as well as assist clinicians in providing an accurate second opinion CoVID-19 diagnosis.
Collapse
Affiliation(s)
- M. Murugappan
- Intelligent Signal Processing (ISP) Research Lab, Department of Electronics and Communication Engineering, Kuwait College of Science and Technology, Block 4, Doha, Kuwait
- Department of Electronics and Communication Engineering, School of Engineering, Vels Institute of Science, Technology, and Advanced Studies, Chennai, India
- Centre of Excellence for Unmanned Aerial Systems (CoEUAS), Universiti Malaysia Perlis, 02600 Perlis, Malaysia
| | - Ali K. Bourisly
- Department of Physiology, Kuwait University, Kuwait City, Kuwait
| | - N. B. Prakash
- Department of Electrical and Electronics and Engineering, National Engineering College, Kovilpatti, Tamil Nadu India
| | - M. G. Sumithra
- Department of Biomedical Engineering, Dr. N. G. P. Institute of Technology, Coimbatore, Tamilnadu India
| | - U. Rajendra Acharya
- Department of Electronics and Computer Engineering, Ngee Ann Polytechnic, Singapore, Singapore
- Department of Biomedical Engineering, School of Science and Technology, Singapore School of Social Sciences, Singapore, Singapore
- Department of Bioinformatics and Medical Engineering, Asia University, Taichung, Taiwan
| |
Collapse
|
7
|
Rezaei SR, Ahmadi A. A hierarchical GAN method with ensemble CNN for accurate nodule detection. Int J Comput Assist Radiol Surg 2023; 18:695-705. [PMID: 36522545 PMCID: PMC9754998 DOI: 10.1007/s11548-022-02807-9] [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: 04/11/2022] [Accepted: 11/30/2022] [Indexed: 12/23/2022]
Abstract
PURPOSE Lung cancer can evolve into one of the deadliest diseases whose early detection is one of the major survival factors. However, early detection is a challenging task due to the unclear structure, shape, and the size of the nodule. Hence, radiologists need automated tools to make accurate decisions. METHODS This paper develops a new approach based on generative adversarial network (GAN) architecture for nodule detection to propose a two-step GAN model containing lung segmentation and nodule localization. The first generator comprises a U-net network, while the second utilizes a mask R-CNN. The task of lung segmentation involves a two-class classification of the pixels in each image, categorizing lung pixels in one class and the rest in the other. The classifier becomes imbalanced due to numerous non-lung pixels, decreasing the model performance. This problem is resolved by using the focal loss function for training the generator. Moreover, a new loss function is developed as the nodule localization generator to enhance the diagnosis quality. Discriminator nets are implemented in GANs as an ensemble of convolutional neural networks (ECNNs), using multiple CNNs and connecting their outputs to make a final decision. RESULTS Several experiments are designed to assess the model on the well-known LUNA dataset. The experiments indicate that the proposed model can reduce the error of the state-of-the-art models on the IoU criterion by about 35 and 16% for lung segmentation and nodule localization, respectively. CONCLUSION Unlike recent studies, the proposed method considers two loss functions for generators, further promoting the goal achievements. Moreover, the network of discriminators is regarded as ECNNs, generating rich features for decisions.
Collapse
Affiliation(s)
- Seyed Reza Rezaei
- Department of Industrial Engineering and Management Systems, Amirkabir University of Technology, Tehran, Iran
| | - Abbas Ahmadi
- Department of Industrial Engineering and Management Systems, Amirkabir University of Technology, Tehran, Iran.
| |
Collapse
|
8
|
Sharma A, Mishra PK. Covid-MANet: Multi-task attention network for explainable diagnosis and severity assessment of COVID-19 from CXR images. Pattern Recognit 2022; 131:108826. [PMID: 35698723 PMCID: PMC9170279 DOI: 10.1016/j.patcog.2022.108826] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/21/2021] [Revised: 04/24/2022] [Accepted: 06/02/2022] [Indexed: 05/17/2023]
Abstract
The devastating outbreak of Coronavirus Disease (COVID-19) cases in early 2020 led the world to face health crises. Subsequently, the exponential reproduction rate of COVID-19 disease can only be reduced by early diagnosis of COVID-19 infection cases correctly. The initial research findings reported that radiological examinations using CT and CXR modality have successfully reduced false negatives by RT-PCR test. This research study aims to develop an explainable diagnosis system for the detection and infection region quantification of COVID-19 disease. The existing research studies successfully explored deep learning approaches with higher performance measures but lacked generalization and interpretability for COVID-19 diagnosis. In this study, we address these issues by the Covid-MANet network, an automated end-to-end multi-task attention network that works for 5 classes in three stages for COVID-19 infection screening. The first stage of the Covid-MANet network localizes attention of the model to the relevant lungs region for disease recognition. The second stage of the Covid-MANet network differentiates COVID-19 cases from bacterial pneumonia, viral pneumonia, normal and tuberculosis cases, respectively. To improve the interpretation and explainability, three experiments have been conducted in exploration of the most coherent and appropriate classification approach. Moreover, the multi-scale attention model MA-DenseNet201 proposed for the classification of COVID-19 cases. The final stage of the Covid-MANet network quantifies the proportion of infection and severity of COVID-19 in the lungs. The COVID-19 cases are graded into more specific severity levels such as mild, moderate, severe, and critical as per the score assigned by the RALE scoring system. The MA-DenseNet201 classification model outperforms eight state-of-the-art CNN models, in terms of sensitivity and interpretation with lung localization network. The COVID-19 infection segmentation by UNet with DenseNet121 encoder achieves dice score of 86.15% outperforming UNet, UNet++, AttentionUNet, R2UNet, with VGG16, ResNet50 and DenseNet201 encoder. The proposed network not only classifies images based on the predicted label but also highlights the infection by segmentation/localization of model-focused regions to support explainable decisions. MA-DenseNet201 model with a segmentation-based cropping approach achieves maximum interpretation of 96% with COVID-19 sensitivity of 97.75%. Finally, based on class-varied sensitivity analysis Covid-MANet ensemble network of MA-DenseNet201, ResNet50 and MobileNet achieve 95.05% accuracy and 98.75% COVID-19 sensitivity. The proposed model is externally validated on an unseen dataset, yields 98.17% COVID-19 sensitivity.
Collapse
Affiliation(s)
- Ajay Sharma
- Department of Computer Science, Institute of Science, Banaras Hindu University, Varanasi 221005, India
| | - Pramod Kumar Mishra
- Department of Computer Science, Institute of Science, Banaras Hindu University, Varanasi 221005, India
| |
Collapse
|
9
|
Owais M, Baek NR, Park KR. DMDF-Net: Dual multiscale dilated fusion network for accurate segmentation of lesions related to COVID-19 in lung radiographic scans. Expert Syst Appl 2022; 202:117360. [PMID: 35529253 PMCID: PMC9057951 DOI: 10.1016/j.eswa.2022.117360] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/13/2021] [Revised: 01/24/2022] [Accepted: 04/25/2022] [Indexed: 05/14/2023]
Abstract
The recent disaster of COVID-19 has brought the whole world to the verge of devastation because of its highly transmissible nature. In this pandemic, radiographic imaging modalities, particularly, computed tomography (CT), have shown remarkable performance for the effective diagnosis of this virus. However, the diagnostic assessment of CT data is a human-dependent process that requires sufficient time by expert radiologists. Recent developments in artificial intelligence have substituted several personal diagnostic procedures with computer-aided diagnosis (CAD) methods that can make an effective diagnosis, even in real time. In response to COVID-19, various CAD methods have been developed in the literature, which can detect and localize infectious regions in chest CT images. However, most existing methods do not provide cross-data analysis, which is an essential measure for assessing the generality of a CAD method. A few studies have performed cross-data analysis in their methods. Nevertheless, these methods show limited results in real-world scenarios without addressing generality issues. Therefore, in this study, we attempt to address generality issues and propose a deep learning-based CAD solution for the diagnosis of COVID-19 lesions from chest CT images. We propose a dual multiscale dilated fusion network (DMDF-Net) for the robust segmentation of small lesions in a given CT image. The proposed network mainly utilizes the strength of multiscale deep features fusion inside the encoder and decoder modules in a mutually beneficial manner to achieve superior segmentation performance. Additional pre- and post-processing steps are introduced in the proposed method to address the generality issues and further improve the diagnostic performance. Mainly, the concept of post-region of interest (ROI) fusion is introduced in the post-processing step, which reduces the number of false-positives and provides a way to accurately quantify the infected area of lung. Consequently, the proposed framework outperforms various state-of-the-art methods by accomplishing superior infection segmentation results with an average Dice similarity coefficient of 75.7%, Intersection over Union of 67.22%, Average Precision of 69.92%, Sensitivity of 72.78%, Specificity of 99.79%, Enhance-Alignment Measure of 91.11%, and Mean Absolute Error of 0.026.
Collapse
Affiliation(s)
- Muhammad Owais
- Division of Electronics and Electrical Engineering, Dongguk University, 30 Pildong-ro 1-gil, Jung-gu, Seoul 04620, South Korea
| | - Na Rae Baek
- Division of Electronics and Electrical Engineering, Dongguk University, 30 Pildong-ro 1-gil, Jung-gu, Seoul 04620, South Korea
| | - Kang Ryoung Park
- Division of Electronics and Electrical Engineering, Dongguk University, 30 Pildong-ro 1-gil, Jung-gu, Seoul 04620, South Korea
| |
Collapse
|
10
|
Qayyum A, Lalande A, Meriaudeau F. Effective multiscale deep learning model for COVID19 segmentation tasks: A further step towards helping radiologist. Neurocomputing 2022; 499:63-80. [PMID: 35578654 PMCID: PMC9095500 DOI: 10.1016/j.neucom.2022.05.009] [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: 10/04/2021] [Revised: 01/28/2022] [Accepted: 05/02/2022] [Indexed: 12/14/2022]
Abstract
Infection by the SARS-CoV-2 leading to COVID-19 disease is still rising and techniques to either diagnose or evaluate the disease are still thoroughly investigated. The use of CT as a complementary tool to other biological tests is still under scrutiny as the CT scans are prone to many false positives as other lung diseases display similar characteristics on CT scans. However, fully investigating CT images is of tremendous interest to better understand the disease progression and therefore thousands of scans need to be segmented by radiologists to study infected areas. Over the last year, many deep learning models for segmenting CT-lungs were developed. Unfortunately, the lack of large and shared annotated multicentric datasets led to models that were either under-tested (small dataset) or not properly compared (own metrics, none shared dataset), often leading to poor generalization performance. To address, these issues, we developed a model that uses a multiscale and multilevel feature extraction strategy for COVID19 segmentation and extensively validated it on several datasets to assess its generalization capability for other segmentation tasks on similar organs. The proposed model uses a novel encoder and decoder with a proposed kernel-based atrous spatial pyramid pooling module that is used at the bottom of the model to extract small features with a multistage skip connection concatenation approach. The results proved that our proposed model could be applied on a small-scale dataset and still produce generalizable performances on other segmentation tasks. The proposed model produced an efficient Dice score of 90% on a 100 cases dataset, 95% on the NSCLC dataset, 88.49% on the COVID19 dataset, and 97.33 on the StructSeg 2019 dataset as compared to existing state-of-the-art models. The proposed solution could be used for COVID19 segmentation in clinic applications. The source code is publicly available at https://github.com/RespectKnowledge/Mutiscale-based-Covid-_segmentation-usingDeep-Learning-models.
Collapse
Affiliation(s)
- Abdul Qayyum
- ImViA Laboratory, University of Bourgogne Franche-Comt́e, Dijon, France
| | - Alain Lalande
- ImViA Laboratory, University of Bourgogne Franche-Comt́e, Dijon, France
- Medical Imaging Department, University Hospital of Dijon, Dijon, France
| | | |
Collapse
|
11
|
Agarwal M, Agarwal S, Saba L, Chabert GL, Gupta S, Carriero A, Pasche A, Danna P, Mehmedovic A, Faa G, Shrivastava S, Jain K, Jain H, Jujaray T, Singh IM, Turk M, Chadha PS, Johri AM, Khanna NN, Mavrogeni S, Laird JR, Sobel DW, Miner M, Balestrieri A, Sfikakis PP, Tsoulfas G, Misra DP, Agarwal V, Kitas GD, Teji JS, Al-Maini M, Dhanjil SK, Nicolaides A, Sharma A, Rathore V, Fatemi M, Alizad A, Krishnan PR, Yadav RR, Nagy F, Kincses ZT, Ruzsa Z, Naidu S, Viskovic K, Kalra MK, Suri JS. Eight pruning deep learning models for low storage and high-speed COVID-19 computed tomography lung segmentation and heatmap-based lesion localization: A multicenter study using COVLIAS 2.0. Comput Biol Med 2022; 146:105571. [PMID: 35751196 PMCID: PMC9123805 DOI: 10.1016/j.compbiomed.2022.105571] [Citation(s) in RCA: 16] [Impact Index Per Article: 8.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/26/2022] [Revised: 04/05/2022] [Accepted: 04/26/2022] [Indexed: 12/12/2022]
Abstract
BACKGROUND COVLIAS 1.0: an automated lung segmentation was designed for COVID-19 diagnosis. It has issues related to storage space and speed. This study shows that COVLIAS 2.0 uses pruned AI (PAI) networks for improving both storage and speed, wiliest high performance on lung segmentation and lesion localization. METHOD ology: The proposed study uses multicenter ∼9,000 CT slices from two different nations, namely, CroMed from Croatia (80 patients, experimental data), and NovMed from Italy (72 patients, validation data). We hypothesize that by using pruning and evolutionary optimization algorithms, the size of the AI models can be reduced significantly, ensuring optimal performance. Eight different pruning techniques (i) differential evolution (DE), (ii) genetic algorithm (GA), (iii) particle swarm optimization algorithm (PSO), and (iv) whale optimization algorithm (WO) in two deep learning frameworks (i) Fully connected network (FCN) and (ii) SegNet were designed. COVLIAS 2.0 was validated using "Unseen NovMed" and benchmarked against MedSeg. Statistical tests for stability and reliability were also conducted. RESULTS Pruning algorithms (i) FCN-DE, (ii) FCN-GA, (iii) FCN-PSO, and (iv) FCN-WO showed improvement in storage by 92.4%, 95.3%, 98.7%, and 99.8% respectively when compared against solo FCN, and (v) SegNet-DE, (vi) SegNet-GA, (vii) SegNet-PSO, and (viii) SegNet-WO showed improvement by 97.1%, 97.9%, 98.8%, and 99.2% respectively when compared against solo SegNet. AUC > 0.94 (p < 0.0001) on CroMed and > 0.86 (p < 0.0001) on NovMed data set for all eight EA model. PAI <0.25 s per image. DenseNet-121-based Grad-CAM heatmaps showed validation on glass ground opacity lesions. CONCLUSIONS Eight PAI networks that were successfully validated are five times faster, storage efficient, and could be used in clinical settings.
Collapse
Affiliation(s)
- Mohit Agarwal
- Department of Computer Science Engineering, Bennett University, India
| | - Sushant Agarwal
- Department of Computer Science Engineering, PSIT, Kanpur, India; Advanced Knowledge Engineering Centre, Global Biomedical Technologies, Inc., Roseville, CA 95661, USA
| | - Luca Saba
- Department of Radiology, Azienda Ospedaliero Universitaria (A.O.U.), Cagliari, Italy
| | - Gian Luca Chabert
- Department of Radiology, Azienda Ospedaliero Universitaria (A.O.U.), Cagliari, Italy
| | - Suneet Gupta
- Department of Computer Science Engineering, Bennett University, India
| | - Alessandro Carriero
- Department of Radiology, Azienda Ospedaliero Universitaria (A.O.U.), Cagliari, Italy
| | - Alessio Pasche
- Depart of Radiology, "Maggiore della Carità" Hospital, University of Piemonte Orientale, Via Solaroli 17, 28100, Novara, Italy
| | - Pietro Danna
- Depart of Radiology, "Maggiore della Carità" Hospital, University of Piemonte Orientale, Via Solaroli 17, 28100, Novara, Italy
| | | | - Gavino Faa
- Department of Pathology - AOU of Cagliari, Italy
| | - Saurabh Shrivastava
- College of Computing Sciences and IT, Teerthanker Mahaveer University, Moradabad, 244001, India
| | - Kanishka Jain
- College of Computing Sciences and IT, Teerthanker Mahaveer University, Moradabad, 244001, India
| | - Harsh Jain
- College of Computing Sciences and IT, Teerthanker Mahaveer University, Moradabad, 244001, India
| | - Tanay Jujaray
- Dept of Molecular, Cell and Developmental Biology, University of California, Santa Cruz, CA, USA
| | | | - Monika Turk
- The Hanse-Wissenschaftskolleg Institute for Advanced Study, Delmenhorst, Germany
| | | | - Amer M Johri
- Division of Cardiology, Queen's University, Kingston, Ontario, Canada
| | - Narendra N Khanna
- Department of Cardiology, Indraprastha APOLLO Hospitals, New Delhi, India
| | - Sophie Mavrogeni
- Cardiology Clinic, Onassis Cardiac Surgery Center, Athens, Greece
| | - John R Laird
- Heart and Vascular Institute, Adventist Health St. Helena, St Helena, CA, USA
| | - David W Sobel
- Minimally Invasive Urology Institute, Brown University, Providence, RI, USA
| | - Martin Miner
- Men's Health Center, Miriam Hospital Providence, Rhode Island, USA
| | - Antonella Balestrieri
- Department of Radiology, Azienda Ospedaliero Universitaria (A.O.U.), Cagliari, Italy
| | - Petros P Sfikakis
- Rheumatology Unit, National Kapodistrian University of Athens, Greece
| | - George Tsoulfas
- Aristoteleion University of Thessaloniki, Thessaloniki, Greece
| | | | | | - George D Kitas
- Academic Affairs, Dudley Group NHS Foundation Trust, Dudley, UK; Arthritis Research UK Epidemiology Unit, Manchester University, Manchester, UK
| | - Jagjit S Teji
- Ann and Robert H. Lurie Children's Hospital of Chicago, Chicago, USA
| | - Mustafa Al-Maini
- Allergy, Clinical Immunology and Rheumatology Institute, Toronto, Canada
| | | | - Andrew Nicolaides
- Vascular Screening and Diagnostic Centre and Univ. of Nicosia Medical School, Cyprus
| | - Aditya Sharma
- Division of Cardiovascular Medicine, University of Virginia, Charlottesville, VA, USA
| | | | - Mostafa Fatemi
- Dept. of Physiology & Biomedical Engg., Mayo Clinic College of Medicine and Science, MN, USA
| | - Azra Alizad
- Dept. of Radiology, Mayo Clinic College of Medicine and Science, MN, USA
| | | | | | - Frence Nagy
- Department of Radiology, University of Szeged, 6725, Hungary
| | | | - Zoltan Ruzsa
- Invasive Cardiology Division, University of Szeged, Budapest, Hungary
| | - Subbaram Naidu
- Electrical Engineering Department, University of Minnesota, Duluth, MN, USA
| | | | - Manudeep K Kalra
- Department of Radiology, Massachusetts General Hospital, Boston, MA, USA
| | - Jasjit S Suri
- College of Computing Sciences and IT, Teerthanker Mahaveer University, Moradabad, 244001, India; Stroke Diagnostic and Monitoring Division, AtheroPoint™, Roseville, CA, USA.
| |
Collapse
|
12
|
Abstract
Chest radiography (X-ray) is the most common diagnostic method for pulmonary disorders. A trained radiologist is required for interpreting the radiographs. But sometimes, even experienced radiologists can misinterpret the findings. This leads to the need for computer-aided detection diagnosis. For decades, researchers were automatically detecting pulmonary disorders using the traditional computer vision (CV) methods. Now the availability of large annotated datasets and computing hardware has made it possible for deep learning to dominate the area. It is now the modus operandi for feature extraction, segmentation, detection, and classification tasks in medical imaging analysis. This paper focuses on the research conducted using chest X-rays for the lung segmentation and detection/classification of pulmonary disorders on publicly available datasets. The studies performed using the Generative Adversarial Network (GAN) models for segmentation and classification on chest X-rays are also included in this study. GAN has gained the interest of the CV community as it can help with medical data scarcity. In this study, we have also included the research conducted before the popularity of deep learning models to have a clear picture of the field. Many surveys have been published, but none of them is dedicated to chest X-rays. This study will help the readers to know about the existing techniques, approaches, and their significance.
Collapse
Affiliation(s)
- Tarun Agrawal
- Department of Computer Science and Engineering, National Institute of Technology Hamirpur, Hamirpur, Himachal Pradesh 177005 India
| | - Prakash Choudhary
- Department of Computer Science and Engineering, National Institute of Technology Hamirpur, Hamirpur, Himachal Pradesh 177005 India
| |
Collapse
|
13
|
Abstract
With the advances in technology, assistive medical systems are emerging with rapid growth and helping healthcare professionals. The proactive diagnosis of diseases with artificial intelligence (AI) and its aligned technologies has been an exciting research area in the last decade. Doctors usually detect tuberculosis (TB) by checking the lungs' X-rays. Classification using deep learning algorithms is successfully able to achieve accuracy almost similar to a doctor in detecting TB. It is found that the probability of detecting TB increases if classification algorithms are implemented on segmented lungs instead of the whole X-ray. The paper's novelty lies in detailed analysis and discussion of U-Net + + results and implementation of U-Net + + in lung segmentation using X-ray. A thorough comparison of U-Net + + with three other benchmark segmentation architectures and segmentation in diagnosing TB or other pulmonary lung diseases is also made in this paper. To the best of our knowledge, no prior research tried to implement U-Net + + for lung segmentation. Most of the papers did not even use segmentation before classification, which causes data leakage. Very few used segmentations before classification, but they only used U-Net, which U-Net + + can easily replace because accuracy and mean_iou of U-Net + + are greater than U-Net accuracy and mean_iou , discussed in results, which can minimize data leakage. The authors achieved more than 98% lung segmentation accuracy and mean_iou 0.95 using U-Net + + , and the efficacy of such comparative analysis is validated.
Collapse
Affiliation(s)
- Shilpa Gite
- Computer Science Engineering Department, Symbiosis Institute of Technology, Symbiosis International (Deemed University), Pune, 412115 India
- Symbiosis Centre for Applied Artificial Intelligence (SCAAI), Symbiosis International (Deemed University), Pune, 412115 India
| | - Abhinav Mishra
- Computer Science Engineering Department, Symbiosis Institute of Technology, Symbiosis International (Deemed University), Pune, 412115 India
| | - Ketan Kotecha
- Computer Science Engineering Department, Symbiosis Institute of Technology, Symbiosis International (Deemed University), Pune, 412115 India
- Symbiosis Centre for Applied Artificial Intelligence (SCAAI), Symbiosis International (Deemed University), Pune, 412115 India
| |
Collapse
|
14
|
Tsuchiya N, Tsubakimoto M, Nishie A, Murayama S. Kerley A-lines represent thickened septal plates between lung segments in patients with lymphangitic carcinomatosis: confirmation using 3D-CT lung segmentation analysis. Jpn J Radiol 2021. [PMID: 34750736 DOI: 10.1007/s11604-021-01215-4] [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] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/26/2021] [Accepted: 10/25/2021] [Indexed: 11/26/2022]
Abstract
Purpose Kerley A-lines are generally apparent in patients with pulmonary edema or lymphangitic carcinomatosis. There are two main thoughts regarding the etiology of Kerley A-lines, but no general agreement. Specifically, the lines are caused by thickened interlobular septa or dilated anastomotic lymphatics. Our purpose was to determine the anatomic structure represented as Kerley A-lines using 3D-CT lung segmentation analysis. Materials and methods We reviewed 139 charts of patients with lymphangitic carcinomatosis of the lung who had CT and X-ray exams with a maximum interval of 7 days. The presence of Kerley A-lines on X-ray was assessed by a radiologist. The A-lines on X-ray were defined as follows: dense; fine (< 1 mm thick); ≥ 2 cm in length, radiating from the hilum; no bifurcation; and not adjacent to the pleura. For cases with Kerley A-lines on X-ray, three radiologists agreed that the lines on CT corresponded with Kerley A-lines. The incidence of A-lines and the characteristics of the lines were investigated. The septal lines between lung segments were identified using a 3D-CT lung segmentation analysis workstation. The percentage of agreement between the A-lines on CT and lung segmental lines was assessed. Results On chest X-ray, 37 Kerley A-lines (right, 16; left, 21) were identified in the 22 cases (16%). Of these, 4 lungs with 12 lines were excluded from analysis due to technical reasons. Nineteen of the 25 lines (76%) corresponded to the septal lines on CT. Of these, 11 lines matched with automatically segmented lines (intersegmental septa, 4; intersubsegmental septa, 7) by the workstation. Two lines (8%) represented fissures. Four lines corresponded to the bronchial wall/artery (3 lines, 12%) or vein (1 line, 4%). Conclusion Kerley A-lines primarily represented thickened and continued interlobular septal lines that corresponded to the septa between lung segments and subsegments.
Supplementary Information The online version contains supplementary material available at 10.1007/s11604-021-01215-4.
Collapse
|
15
|
Pennisi M, Kavasidis I, Spampinato C, Schinina V, Palazzo S, Salanitri FP, Bellitto G, Rundo F, Aldinucci M, Cristofaro M, Campioni P, Pianura E, Di Stefano F, Petrone A, Albarello F, Ippolito G, Cuzzocrea S, Conoci S. An explainable AI system for automated COVID-19 assessment and lesion categorization from CT-scans. Artif Intell Med 2021; 118:102114. [PMID: 34412837 PMCID: PMC8139171 DOI: 10.1016/j.artmed.2021.102114] [Citation(s) in RCA: 7] [Impact Index Per Article: 2.3] [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: 09/25/2020] [Revised: 05/06/2021] [Accepted: 05/12/2021] [Indexed: 01/20/2023]
Abstract
COVID-19 infection caused by SARS-CoV-2 pathogen has been a catastrophic pandemic outbreak all over the world, with exponential increasing of confirmed cases and, unfortunately, deaths. In this work we propose an AI-powered pipeline, based on the deep-learning paradigm, for automated COVID-19 detection and lesion categorization from CT scans. We first propose a new segmentation module aimed at automatically identifying lung parenchyma and lobes. Next, we combine the segmentation network with classification networks for COVID-19 identification and lesion categorization. We compare the model's classification results with those obtained by three expert radiologists on a dataset of 166 CT scans. Results showed a sensitivity of 90.3% and a specificity of 93.5% for COVID-19 detection, at least on par with those yielded by the expert radiologists, and an average lesion categorization accuracy of about 84%. Moreover, a significant role is played by prior lung and lobe segmentation, that allowed us to enhance classification performance by over 6 percent points. The interpretation of the trained AI models reveals that the most significant areas for supporting the decision on COVID-19 identification are consistent with the lesions clinically associated to the virus, i.e., crazy paving, consolidation and ground glass. This means that the artificial models are able to discriminate a positive patient from a negative one (both controls and patients with interstitial pneumonia tested negative to COVID) by evaluating the presence of those lesions into CT scans. Finally, the AI models are integrated into a user-friendly GUI to support AI explainability for radiologists, which is publicly available at http://perceivelab.com/covid-ai. The whole AI system is unique since, to the best of our knowledge, it is the first AI-based software, publicly available, that attempts to explain to radiologists what information is used by AI methods for making decisions and that proactively involves them in the decision loop to further improve the COVID-19 understanding.
Collapse
Affiliation(s)
| | | | | | - Vincenzo Schinina
- National Institute for infectious disease, "Lazzaro Spallanzani" Department, Rome, Italy
| | | | | | | | | | - Marco Aldinucci
- Department of Computer Science, University of Turin, Turin, Italy
| | - Massimo Cristofaro
- National Institute for infectious disease, "Lazzaro Spallanzani" Department, Rome, Italy
| | - Paolo Campioni
- National Institute for infectious disease, "Lazzaro Spallanzani" Department, Rome, Italy
| | - Elisa Pianura
- National Institute for infectious disease, "Lazzaro Spallanzani" Department, Rome, Italy
| | - Federica Di Stefano
- National Institute for infectious disease, "Lazzaro Spallanzani" Department, Rome, Italy
| | - Ada Petrone
- National Institute for infectious disease, "Lazzaro Spallanzani" Department, Rome, Italy
| | - Fabrizio Albarello
- National Institute for infectious disease, "Lazzaro Spallanzani" Department, Rome, Italy
| | - Giuseppe Ippolito
- National Institute for infectious disease, "Lazzaro Spallanzani" Department, Rome, Italy
| | | | - Sabrina Conoci
- ChimBioFaram Department, University of Messina, Messina, Italy
| |
Collapse
|
16
|
Acar E, Şahin E, Yılmaz İ. Improving effectiveness of different deep learning-based models for detecting COVID-19 from computed tomography (CT) images. Neural Comput Appl 2021; 33:17589-17609. [PMID: 34345118 PMCID: PMC8321007 DOI: 10.1007/s00521-021-06344-5] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [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: 05/26/2020] [Accepted: 07/18/2021] [Indexed: 12/12/2022]
Abstract
COVID-19 has caused a pandemic crisis that threatens the world in many areas, especially in public health. For the diagnosis of COVID-19, computed tomography has a prognostic role in the early diagnosis of COVID-19 as it provides both rapid and accurate results. This is crucial to assist clinicians in making decisions for rapid isolation and appropriate patient treatment. Therefore, many researchers have shown that the accuracy of COVID-19 patient detection from chest CT images using various deep learning systems is extremely optimistic. Deep learning networks such as convolutional neural networks (CNNs) require substantial training data. One of the biggest problems for researchers is accessing a significant amount of training data. In this work, we combine methods such as segmentation, data augmentation and generative adversarial network (GAN) to increase the effectiveness of deep learning models. We propose a method that generates synthetic chest CT images using the GAN method from a limited number of CT images. We test the performance of experiments (with and without GAN) on internal and external dataset. When the CNN is trained on real images and synthetic images, a slight increase in accuracy and other results are observed in the internal dataset, but between \documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{mathrsfs}
\usepackage{upgreek}
\setlength{\oddsidemargin}{-69pt}
\begin{document}$$3\%$$\end{document}3% and \documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{mathrsfs}
\usepackage{upgreek}
\setlength{\oddsidemargin}{-69pt}
\begin{document}$$9\%$$\end{document}9% in the external dataset. It is promising according to the performance results that the proposed method will accelerate the detection of COVID-19 and lead to more robust systems.
Collapse
Affiliation(s)
- Erdi Acar
- Department of Computer Engineering, Çanakkale Onsekiz Mart University, 17100 Çanakkale, Turkey
| | - Engin Şahin
- Department of Computer Engineering, Çanakkale Onsekiz Mart University, 17100 Çanakkale, Turkey
| | - İhsan Yılmaz
- Department of Computer Engineering, Çanakkale Onsekiz Mart University, 17100 Çanakkale, Turkey
| |
Collapse
|
17
|
Lizancos Vidal P, de Moura J, Novo J, Ortega M. Multi-stage transfer learning for lung segmentation using portable X-ray devices for patients with COVID-19. Expert Syst Appl 2021; 173:114677. [PMID: 33612998 PMCID: PMC7879025 DOI: 10.1016/j.eswa.2021.114677] [Citation(s) in RCA: 17] [Impact Index Per Article: 5.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/03/2020] [Revised: 01/02/2021] [Accepted: 01/30/2021] [Indexed: 05/09/2023]
Abstract
One of the main challenges in times of sanitary emergency is to quickly develop computer aided diagnosis systems with a limited number of available samples due to the novelty, complexity of the case and the urgency of its implementation. This is the case during the current pandemic of COVID-19. This pathogen primarily infects the respiratory system of the afflicted, resulting in pneumonia and in a severe case of acute respiratory distress syndrome. This results in the formation of different pathological structures in the lungs that can be detected by the use of chest X-rays. Due to the overload of the health services, portable X-ray devices are recommended during the pandemic, preventing the spread of the disease. However, these devices entail different complications (such as capture quality) that, together with the subjectivity of the clinician, make the diagnostic process more difficult and suggest the necessity for computer-aided diagnosis methodologies despite the scarcity of samples available to do so. To solve this problem, we propose a methodology that allows to adapt the knowledge from a well-known domain with a high number of samples to a new domain with a significantly reduced number and greater complexity. We took advantage of a pre-trained segmentation model from brain magnetic resonance imaging of a unrelated pathology and performed two stages of knowledge transfer to obtain a robust system able to segment lung regions from portable X-ray devices despite the scarcity of samples and lesser quality. This way, our methodology obtained a satisfactory accuracy of 0.9761 ± 0.0100 for patients with COVID-19, 0.9801 ± 0.0104 for normal patients and 0.9769 ± 0.0111 for patients with pulmonary diseases with similar characteristics as COVID-19 (such as pneumonia) but not genuine COVID-19.
Collapse
Affiliation(s)
- Plácido Lizancos Vidal
- Centro de investigación CITIC, Universidade da Coruña, Campus de Elviña, s/n, 15071 A Coruña, Spain
- Grupo VARPA, Instituto de Investigación Biomédica de A Coruña (INIBIC), Universidade da Coruña, Xubias de Arriba, 84, 15006 A Coruña, Spain
| | - Joaquim de Moura
- Centro de investigación CITIC, Universidade da Coruña, Campus de Elviña, s/n, 15071 A Coruña, Spain
- Grupo VARPA, Instituto de Investigación Biomédica de A Coruña (INIBIC), Universidade da Coruña, Xubias de Arriba, 84, 15006 A Coruña, Spain
| | - Jorge Novo
- Centro de investigación CITIC, Universidade da Coruña, Campus de Elviña, s/n, 15071 A Coruña, Spain
- Grupo VARPA, Instituto de Investigación Biomédica de A Coruña (INIBIC), Universidade da Coruña, Xubias de Arriba, 84, 15006 A Coruña, Spain
| | - Marcos Ortega
- Centro de investigación CITIC, Universidade da Coruña, Campus de Elviña, s/n, 15071 A Coruña, Spain
- Grupo VARPA, Instituto de Investigación Biomédica de A Coruña (INIBIC), Universidade da Coruña, Xubias de Arriba, 84, 15006 A Coruña, Spain
| |
Collapse
|
18
|
Diniz JOB, Quintanilha DBP, Santos Neto AC, da Silva GLF, Ferreira JL, Netto SMB, Araújo JDL, Da Cruz LB, Silva TFB, da S. Martins CM, Ferreira MM, Rego VG, Boaro JMC, Cipriano CLS, Silva AC, de Paiva AC, Junior GB, de Almeida JDS, Nunes RA, Mogami R, Gattass M. Segmentation and quantification of COVID-19 infections in CT using pulmonary vessels extraction and deep learning. Multimed Tools Appl 2021; 80:29367-29399. [PMID: 34188605 PMCID: PMC8224997 DOI: 10.1007/s11042-021-11153-y] [Citation(s) in RCA: 11] [Impact Index Per Article: 3.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/16/2020] [Revised: 05/26/2021] [Accepted: 06/03/2021] [Indexed: 05/07/2023]
Abstract
At the end of 2019, the World Health Organization (WHO) reported pneumonia that started in Wuhan, China, as a global emergency problem. Researchers quickly advanced in research to try to understand this COVID-19 and sough solutions for the front-line professionals fighting this fatal disease. One of the tools to aid in the detection, diagnosis, treatment, and prevention of this disease is computed tomography (CT). CT images provide valuable information on how this new disease affects the lungs of patients. However, the analysis of these images is not trivial, especially when researchers are searching for quick solutions. Detecting and evaluating this disease can be tiring, time-consuming, and susceptible to errors. Thus, in this study, we aim to automatically segment infections caused by COVID19 and provide quantitative measures of these infections to specialists, thus serving as a support tool. We use a database of real clinical cases from Pedro Ernesto University Hospital of the State of Rio de Janeiro, Brazil. The method involves five steps: lung segmentation, segmentation and extraction of pulmonary vessels, infection segmentation, infection classification, and infection quantification. For the lung segmentation and infection segmentation tasks, we propose modifications to the traditional U-Net, including batch normalization, leaky ReLU, dropout, and residual block techniques, and name it as Residual U-Net. The proposed method yields an average Dice value of 77.1% and an average specificity of 99.76%. For quantification of infectious findings, the proposed method achieves results like that of specialists, and no measure presented a value of ρ < 0.05 in the paired t-test. The results demonstrate the potential of the proposed method as a tool to help medical professionals combat COVID-19. fight the COVID-19.
Collapse
Affiliation(s)
- João O. B. Diniz
- Federal Institute of Maranhão, BR-226, SN, Campus Grajaú, Vila Nova, Grajaú, MA 65940-00 Brazil
- Federal University of Maranhão, Av. dos Portugueses, SN, Campus do Bacanga, Bacanga, São Luís, MA 65085-580 Brazil
| | - Darlan B. P. Quintanilha
- Federal University of Maranhão, Av. dos Portugueses, SN, Campus do Bacanga, Bacanga, São Luís, MA 65085-580 Brazil
| | - Antonino C. Santos Neto
- Federal University of Maranhão, Av. dos Portugueses, SN, Campus do Bacanga, Bacanga, São Luís, MA 65085-580 Brazil
| | - Giovanni L. F. da Silva
- Federal University of Maranhão, Av. dos Portugueses, SN, Campus do Bacanga, Bacanga, São Luís, MA 65085-580 Brazil
- Dom Bosco Higher Education Unit (UNDB), Av. Colares Moreira, 443 - Jardim Renascença, São Luís, MA 65075-441 Brazil
| | - Jonnison L. Ferreira
- Federal University of Maranhão, Av. dos Portugueses, SN, Campus do Bacanga, Bacanga, São Luís, MA 65085-580 Brazil
- Federal Institute of Amazonas (IFAM), BR-226, SN, Campus Grajaú, Vila Nova, Grajaú, MA 65940-00 Brazil
| | - Stelmo M. B. Netto
- Federal University of Maranhão, Av. dos Portugueses, SN, Campus do Bacanga, Bacanga, São Luís, MA 65085-580 Brazil
| | - José D. L. Araújo
- Federal University of Maranhão, Av. dos Portugueses, SN, Campus do Bacanga, Bacanga, São Luís, MA 65085-580 Brazil
| | - Luana B. Da Cruz
- Federal University of Maranhão, Av. dos Portugueses, SN, Campus do Bacanga, Bacanga, São Luís, MA 65085-580 Brazil
| | - Thamila F. B. Silva
- Federal University of Maranhão, Av. dos Portugueses, SN, Campus do Bacanga, Bacanga, São Luís, MA 65085-580 Brazil
| | - Caio M. da S. Martins
- Federal University of Maranhão, Av. dos Portugueses, SN, Campus do Bacanga, Bacanga, São Luís, MA 65085-580 Brazil
| | - Marcos M. Ferreira
- Federal University of Maranhão, Av. dos Portugueses, SN, Campus do Bacanga, Bacanga, São Luís, MA 65085-580 Brazil
| | - Venicius G. Rego
- Federal University of Maranhão, Av. dos Portugueses, SN, Campus do Bacanga, Bacanga, São Luís, MA 65085-580 Brazil
| | - José M. C. Boaro
- Federal University of Maranhão, Av. dos Portugueses, SN, Campus do Bacanga, Bacanga, São Luís, MA 65085-580 Brazil
| | - Carolina L. S. Cipriano
- Federal University of Maranhão, Av. dos Portugueses, SN, Campus do Bacanga, Bacanga, São Luís, MA 65085-580 Brazil
| | - Aristófanes C. Silva
- Federal University of Maranhão, Av. dos Portugueses, SN, Campus do Bacanga, Bacanga, São Luís, MA 65085-580 Brazil
| | - Anselmo C. de Paiva
- Federal University of Maranhão, Av. dos Portugueses, SN, Campus do Bacanga, Bacanga, São Luís, MA 65085-580 Brazil
| | - Geraldo Braz Junior
- Federal University of Maranhão, Av. dos Portugueses, SN, Campus do Bacanga, Bacanga, São Luís, MA 65085-580 Brazil
| | - João D. S. de Almeida
- Federal University of Maranhão, Av. dos Portugueses, SN, Campus do Bacanga, Bacanga, São Luís, MA 65085-580 Brazil
| | - Rodolfo A. Nunes
- Rio de Janeiro State University, Boulevard 28 de Setembro, 77, Vila Isabel, Rio de Janeiro, RJ 20551-030 Brazil
| | - Roberto Mogami
- Rio de Janeiro State University, Boulevard 28 de Setembro, 77, Vila Isabel, Rio de Janeiro, RJ 20551-030 Brazil
| | - M. Gattass
- Pontifical Catholic University of Rio de Janeiro, R. São Vicente, 225, Gávea, Rio de Janeiro, RJ 22453-900 Brazil
| |
Collapse
|
19
|
Berta L, Rizzetto F, De Mattia C, Lizio D, Felisi M, Colombo PE, Carrazza S, Gelmini S, Bianchi L, Artioli D, Travaglini F, Vanzulli A, Torresin A. Automatic lung segmentation in COVID-19 patients: Impact on quantitative computed tomography analysis. Phys Med 2021; 87:115-122. [PMID: 34139383 PMCID: PMC9188767 DOI: 10.1016/j.ejmp.2021.06.001] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/31/2021] [Revised: 05/05/2021] [Accepted: 06/04/2021] [Indexed: 12/04/2022] Open
Abstract
Purpose To assess the impact of lung segmentation accuracy in an automatic pipeline for quantitative analysis of CT images. Methods Four different platforms for automatic lung segmentation based on convolutional neural network (CNN), region-growing technique and atlas-based algorithm were considered. The platforms were tested using CT images of 55 COVID-19 patients with severe lung impairment. Four radiologists assessed the segmentations using a 5-point qualitative score (QS). For each CT series, a manually revised reference segmentation (RS) was obtained. Histogram-based quantitative metrics (QM) were calculated from CT histogram using lung segmentationsfrom all platforms and RS. Dice index (DI) and differences of QMs (ΔQMs) were calculated between RS and other segmentations. Results Highest QS and lower ΔQMs values were associated to the CNN algorithm. However, only 45% CNN segmentations were judged to need no or only minimal corrections, and in only 17 cases (31%), automatic segmentations provided RS without manual corrections. Median values of the DI for the four algorithms ranged from 0.993 to 0.904. Significant differences for all QMs calculated between automatic segmentations and RS were found both when data were pooled together and stratified according to QS, indicating a relationship between qualitative and quantitative measurements. The most unstable QM was the histogram 90th percentile, with median ΔQMs values ranging from 10HU and 158HU between different algorithms. Conclusions None of tested algorithms provided fully reliable segmentation. Segmentation accuracy impacts differently on different quantitative metrics, and each of them should be individually evaluated according to the purpose of subsequent analyses.
Collapse
Affiliation(s)
- L Berta
- Department of Medical Physics, ASST Grande Ospedale Metropolitano Niguarda, Piazza Ospedale Maggiore 3, 20162 Milan, Italy
| | - F Rizzetto
- Department of Radiology, ASST Grande Ospedale Metropolitano Niguarda, Piazza Ospedale Maggiore 3, 20162 Milan, Italy; Postgraduate School of Diagnostic and Interventional Radiology, Università degli Studi di Milano, via Festa del Perdono 7, 20122, Milan, Italy
| | - C De Mattia
- Department of Medical Physics, ASST Grande Ospedale Metropolitano Niguarda, Piazza Ospedale Maggiore 3, 20162 Milan, Italy
| | - D Lizio
- Department of Medical Physics, ASST Grande Ospedale Metropolitano Niguarda, Piazza Ospedale Maggiore 3, 20162 Milan, Italy
| | - M Felisi
- Department of Medical Physics, ASST Grande Ospedale Metropolitano Niguarda, Piazza Ospedale Maggiore 3, 20162 Milan, Italy
| | - P E Colombo
- Department of Medical Physics, ASST Grande Ospedale Metropolitano Niguarda, Piazza Ospedale Maggiore 3, 20162 Milan, Italy
| | - S Carrazza
- Department of Physics, Università degli Studi di Milano, via Giovanni Celoria 16, 20133 Milan, Italy; Department of Physics, INFN Sezione di Milano, via Giovanni Celoria 16, 20133 Milan, Italy
| | - S Gelmini
- Department of Physics, Università degli Studi di Milano, via Giovanni Celoria 16, 20133 Milan, Italy
| | - L Bianchi
- Department of Radiology, ASST Grande Ospedale Metropolitano Niguarda, Piazza Ospedale Maggiore 3, 20162 Milan, Italy; Postgraduate School of Diagnostic and Interventional Radiology, Università degli Studi di Milano, via Festa del Perdono 7, 20122, Milan, Italy
| | - D Artioli
- Department of Radiology, ASST Grande Ospedale Metropolitano Niguarda, Piazza Ospedale Maggiore 3, 20162 Milan, Italy
| | - F Travaglini
- Department of Radiology, ASST Grande Ospedale Metropolitano Niguarda, Piazza Ospedale Maggiore 3, 20162 Milan, Italy
| | - A Vanzulli
- Department of Radiology, ASST Grande Ospedale Metropolitano Niguarda, Piazza Ospedale Maggiore 3, 20162 Milan, Italy; Department of Oncology and Hemato-Oncology, Università degli Studi di Milano, via Festa del Perdono 7, 20122, Milan, Italy
| | - A Torresin
- Department of Medical Physics, ASST Grande Ospedale Metropolitano Niguarda, Piazza Ospedale Maggiore 3, 20162 Milan, Italy; Department of Physics, Università degli Studi di Milano, via Giovanni Celoria 16, 20133 Milan, Italy.
| | | |
Collapse
|
20
|
Guo F, Capaldi DP, McCormack DG, Fenster A, Parraga G. Ultra-short echo-time magnetic resonance imaging lung segmentation with under-Annotations and domain shift. Med Image Anal 2021; 72:102107. [PMID: 34153626 DOI: 10.1016/j.media.2021.102107] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Key Words] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/21/2020] [Revised: 03/22/2021] [Accepted: 05/19/2021] [Indexed: 12/12/2022]
Abstract
Ultra-short echo-time (UTE) magnetic resonance imaging (MRI) provides enhanced visualization of pulmonary structural and functional abnormalities and has shown promise in phenotyping lung disease. Here, we describe the development and evaluation of a lung segmentation approach to facilitate UTE MRI methods for patient-based imaging. The proposed approach employs a k-means algorithm in kernel space for pair-wise feature clustering and imposes image domain continuous regularization, coined as continuous kernel k-means (CKKM). The high-order CKKM algorithm was simplified through upper bound relaxation and solved within an iterative continuous max-flow framework. We combined the CKKM with U-net and atlas-based approaches and comprehensively evaluated the performance on 100 images from 25 patients with asthma and bronchial pulmonary dysplasia enrolled at Robarts Research Institute (Western University, London, Canada) and Centre Hospitalier Universitaire (Sainte-Justine, Montreal, Canada). For U-net, we trained the network five times on a mixture of five different images with under-annotations and applied the model to 64 images from the two centres. We also trained a U-net on five images with full and brush annotations from one centre, and tested the model on 32 images from the other centre. For an atlas-based approach, we employed three atlas images to segment 64 target images from the two centres through straightforward atlas registration and label fusion. We applied the CKKM algorithm to the baseline U-net and atlas outputs and refined the initial segmentation through multi-volume image fusion. The integration of CKKM substantially improved baseline results and yielded, with minimal computational cost, segmentation accuracy, and precision that were greater than some state-of-the-art deep learning models and similar to experienced observer manual segmentation. This suggests that deep learning and atlas-based approaches may be utilized to segment UTE MRI datasets using relatively small training datasets with under-annotations.
Collapse
|
21
|
Rahman T, Khandakar A, Qiblawey Y, Tahir A, Kiranyaz S, Abul Kashem SB, Islam MT, Al Maadeed S, Zughaier SM, Khan MS, Chowdhury ME. Exploring the effect of image enhancement techniques on COVID-19 detection using chest X-ray images. Comput Biol Med 2021; 132:104319. [PMID: 33799220 PMCID: PMC7946571 DOI: 10.1016/j.compbiomed.2021.104319] [Citation(s) in RCA: 220] [Impact Index Per Article: 73.3] [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: 11/24/2020] [Revised: 03/03/2021] [Accepted: 03/04/2021] [Indexed: 02/06/2023]
Abstract
Computer-aided diagnosis for the reliable and fast detection of coronavirus disease (COVID-19) has become a necessity to prevent the spread of the virus during the pandemic to ease the burden on the healthcare system. Chest X-ray (CXR) imaging has several advantages over other imaging and detection techniques. Numerous works have been reported on COVID-19 detection from a smaller set of original X-ray images. However, the effect of image enhancement and lung segmentation of a large dataset in COVID-19 detection was not reported in the literature. We have compiled a large X-ray dataset (COVQU) consisting of 18,479 CXR images with 8851 normal, 6012 non-COVID lung infections, and 3616 COVID-19 CXR images and their corresponding ground truth lung masks. To the best of our knowledge, this is the largest public COVID positive database and the lung masks. Five different image enhancement techniques: histogram equalization (HE), contrast limited adaptive histogram equalization (CLAHE), image complement, gamma correction, and balance contrast enhancement technique (BCET) were used to investigate the effect of image enhancement techniques on COVID-19 detection. A novel U-Net model was proposed and compared with the standard U-Net model for lung segmentation. Six different pre-trained Convolutional Neural Networks (CNNs) (ResNet18, ResNet50, ResNet101, InceptionV3, DenseNet201, and ChexNet) and a shallow CNN model were investigated on the plain and segmented lung CXR images. The novel U-Net model showed an accuracy, Intersection over Union (IoU), and Dice coefficient of 98.63%, 94.3%, and 96.94%, respectively for lung segmentation. The gamma correction-based enhancement technique outperforms other techniques in detecting COVID-19 from the plain and the segmented lung CXR images. Classification performance from plain CXR images is slightly better than the segmented lung CXR images; however, the reliability of network performance is significantly improved for the segmented lung images, which was observed using the visualization technique. The accuracy, precision, sensitivity, F1-score, and specificity were 95.11%, 94.55%, 94.56%, 94.53%, and 95.59% respectively for the segmented lung images. The proposed approach with very reliable and comparable performance will boost the fast and robust COVID-19 detection using chest X-ray images.
Collapse
Affiliation(s)
- Tawsifur Rahman
- Department of Electrical Engineering, Qatar University, Doha, 2713, Qatar
| | - Amith Khandakar
- Department of Electrical Engineering, Qatar University, Doha, 2713, Qatar
| | - Yazan Qiblawey
- Department of Electrical Engineering, Qatar University, Doha, 2713, Qatar
| | - Anas Tahir
- Department of Electrical Engineering, Qatar University, Doha, 2713, Qatar
| | - Serkan Kiranyaz
- Department of Electrical Engineering, Qatar University, Doha, 2713, Qatar
| | - Saad Bin Abul Kashem
- Faculty of Robotics and Advanced Computing, Qatar Armed Forces Academic Bridge Program, Qatar Foundation, Doha, 24404, Qatar
| | - Mohammad Tariqul Islam
- Dept. of Electrical, Electronics and Systems Engineering, Universiti Kebangsaan Malaysia, Bangi, Selangor, 43600, Malaysia
| | - Somaya Al Maadeed
- Department of Computer Science and Engineering, Qatar University, Doha, 2713, Qatar
| | - Susu M. Zughaier
- Department of Basic Medical Sciences, College of Medicine, Biomedical and Pharmaceutical Research Unit, QU Health, Qatar University, Doha, 2713, Qatar
| | - Muhammad Salman Khan
- Department of Electrical Engineering (JC), University of Engineering and Technology, Peshawar, Pakistan
| | - Muhammad E.H. Chowdhury
- Department of Electrical Engineering, Qatar University, Doha, 2713, Qatar,Corresponding author
| |
Collapse
|
22
|
Park B, Park H, Lee SM, Seo JB, Kim N. Lung Segmentation on HRCT and Volumetric CT for Diffuse Interstitial Lung Disease Using Deep Convolutional Neural Networks. J Digit Imaging 2019; 32:1019-26. [PMID: 31396776 DOI: 10.1007/s10278-019-00254-8] [Citation(s) in RCA: 40] [Impact Index Per Article: 13.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/17/2022] Open
Abstract
A robust lung segmentation method using a deep convolutional neural network (CNN) was developed and evaluated on high-resolution computed tomography (HRCT) and volumetric CT of various types of diffuse interstitial lung disease (DILD). Chest CT images of 617 patients with various types of DILD, including cryptogenic organizing pneumonia (COP), usual interstitial pneumonia (UIP), and nonspecific interstitial pneumonia (NSIP), were scanned using HRCT (1-2-mm slices, 5-10-mm intervals) and volumetric CT (sub-millimeter thickness without intervals). Each scan was segmented using a conventional image processing method and then manually corrected by an expert thoracic radiologist to create gold standards. The lung regions in the HRCT images were then segmented using a two-dimensional U-Net architecture with the deep CNN, using separate training, validation, and test sets. In addition, 30 independent volumetric CT images of UIP patients were used to further evaluate the model. The segmentation results for both conventional and deep-learning methods were compared quantitatively with the gold standards using four accuracy metrics: the Dice similarity coefficient (DSC), Jaccard similarity coefficient (JSC), mean surface distance (MSD), and Hausdorff surface distance (HSD). The mean and standard deviation values of those metrics for the HRCT images were 98.84 ± 0.55%, 97.79 ± 1.07%, 0.27 ± 0.18 mm, and 25.47 ± 13.63 mm, respectively. Our deep-learning method showed significantly better segmentation performance (p < 0.001), and its segmentation accuracies for volumetric CT were similar to those for HRCT. We have developed an accurate and robust U-Net-based DILD lung segmentation method that can be used for patients scanned with different clinical protocols, including HRCT and volumetric CT.
Collapse
|
23
|
Chen C, Xiao R, Zhang T, Lu Y, Guo X, Wang J, Chen H, Wang Z. Pathological lung segmentation in chest CT images based on improved random walker. Comput Methods Programs Biomed 2021; 200:105864. [PMID: 33280937 DOI: 10.1016/j.cmpb.2020.105864] [Citation(s) in RCA: 12] [Impact Index Per Article: 4.0] [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: 12/02/2019] [Accepted: 11/16/2020] [Indexed: 06/12/2023]
Abstract
BACKGROUND AND OBJECTIVE Pathological lung segmentation as a pretreatment step in the diagnosis of lung diseases has been widely explored. Because of the complexity of pathological lung structures and gray blur of the border, accurate lung segmentation in clinical 3D computed tomography images is a challenging task. In view of the current situation, the work proposes a fast and accurate pathological lung segmentation method. The following contributions have been made: First, the edge weights introduce spatial information and clustering information, so that walkers can use more image information during walking. Second, a Gaussian Distribution of seed point set is established to further expand the possibility of selection between fake seed points and real seed points. Finally, the pre-parameter is calculated using original seed points, and the final results are fitted with new seed points. METHODS This study proposes a segmentation method based on an improved random walker algorithm. The proposed method consists of the following steps: First, a gray value is used as the sample distribution. Gaussian mixture model is used to obtain the clustering probability of an image. Thus, the spatial distance and clustering result are added as new weights, and the new edge weights are used to construct a random walker map. Second, a large number of marked points are automatically selected, and the intermediate results are obtained from the newly constructed map and retained only as pre-parameters. When new seed points are introduced, the probability value of the walker is quickly calculated from the new parameters and pre-parameters, and the final segmentation result can be obtained. RESULTS The proposed method was tested on 65 sets of CT cases. Quantitative evaluation with different methods confirms the high accuracy on our dataset (98.55%) and LOLA11 dataset (97.41%). Similarly, the average segmentation time (10.5s) is faster than random walker (1,332.5s). CONCLUSIONS The comparison of the experimental results show that the proposed method can accurately and quickly obtain pathological lung processing results. Therefore, it has potential clinical applications.
Collapse
Affiliation(s)
- Cheng Chen
- School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, 100083, China
| | - Ruoxiu Xiao
- School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, 100083, China; Institute of Artificial Intelligence, University of Science and Technology Beijing, Beijing 100083, China.
| | - Tao Zhang
- Department of Thoracic Surgery, Chinese PLA General Hospital, Beijing, 100853, China.
| | - Yuanyuan Lu
- Department of Ultrasound, Chinese PLA General Hospital, Beijing, 100853, China
| | - Xiaoyu Guo
- School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, 100083, China
| | - Jiayu Wang
- School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, 100083, China
| | - Hongyu Chen
- School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, 100083, China
| | - Zhiliang Wang
- School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, 100083, China
| |
Collapse
|
24
|
Abstract
Our work expands the use of capsule networks to the task of object segmentation for the first time in the literature. This is made possible via the introduction of locally-constrained routing and transformation matrix sharing, which reduces the parameter/memory burden and allows for the segmentation of objects at large resolutions. To compensate for the loss of global information in constraining the routing, we propose the concept of "deconvolutional" capsules to create a deep encoder-decoder style network, called SegCaps. We extend the masked reconstruction regularization to the task of segmentation and perform thorough ablation experiments on each component of our method. The proposed convolutional-deconvolutional capsule network, SegCaps, shows state-of-the-art results while using a fraction of the parameters of popular segmentation networks. To validate our proposed method, we perform experiments segmenting pathological lungs from clinical and pre-clinical thoracic computed tomography (CT) scans and segmenting muscle and adipose (fat) tissue from magnetic resonance imaging (MRI) scans of human subjects' thighs. Notably, our experiments in lung segmentation represent the largest-scale study in pathological lung segmentation in the literature, where we conduct experiments across five extremely challenging datasets, containing both clinical and pre-clinical subjects, and nearly 2000 computed-tomography scans. Our newly developed segmentation platform outperforms other methods across all datasets while utilizing less than 5% of the parameters in the popular U-Net for biomedical image segmentation. Further, we demonstrate capsules' ability to generalize to unseen handling of rotations/reflections on natural images.
Collapse
Affiliation(s)
- Rodney LaLonde
- Center for Research in Computer Vision (CRCV), University of Central Florida (UCF), Orlando, FL
| | | | | | - Sanjay Jain
- Johns Hopkins University, Baltimore, MD US State
| | - Ulas Bagci
- Center for Research in Computer Vision (CRCV), University of Central Florida (UCF), Orlando, FL.
| |
Collapse
|
25
|
Tan J, Jing L, Huo Y, Li L, Akin O, Tian Y. LGAN: Lung segmentation in CT scans using generative adversarial network. Comput Med Imaging Graph 2021; 87:101817. [PMID: 33278767 PMCID: PMC8477299 DOI: 10.1016/j.compmedimag.2020.101817] [Citation(s) in RCA: 21] [Impact Index Per Article: 7.0] [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: 01/07/2020] [Revised: 10/13/2020] [Accepted: 10/23/2020] [Indexed: 11/17/2022]
Abstract
Lung segmentation in Computerized Tomography (CT) images plays an important role in various lung disease diagnosis. Most of the current lung segmentation approaches are performed through a series of procedures with manually empirical parameter adjustments in each step. Pursuing an automatic segmentation method with fewer steps, we propose a novel deep learning Generative Adversarial Network (GAN)-based lung segmentation schema, which we denote as LGAN. The proposed schema can be generalized to different kinds of neural networks for lung segmentation in CT images. We evaluated the proposed LGAN schema on datasets including Lung Image Database Consortium image collection (LIDC-IDRI) and Quantitative Imaging Network (QIN) collection with two metrics: segmentation quality and shape similarity. Also, we compared our work with current state-of-the-art methods. The experimental results demonstrated that the proposed LGAN schema can be used as a promising tool for automatic lung segmentation due to its simplified procedure as well as its improved performance and efficiency.
Collapse
Affiliation(s)
- Jiaxing Tan
- The City University of New York, New York 10016, USA
| | - Longlong Jing
- The City University of New York, New York 10016, USA
| | - Yumei Huo
- The City University of New York, New York 10016, USA
| | - Lihong Li
- The City University of New York, New York 10016, USA
| | - Oguz Akin
- Memorial Sloan Kettering Cancer Center, New York 10065, USA
| | - Yingli Tian
- The City University of New York, New York 10016, USA.
| |
Collapse
|
26
|
Liu C, Pang M. Extracting Lungs from CT Images via Deep Convolutional Neural Network Based Segmentation and Two-Pass Contour Refinement. J Digit Imaging 2020; 33:1465-78. [PMID: 33057882 DOI: 10.1007/s10278-020-00388-0] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/13/2019] [Revised: 08/17/2020] [Accepted: 09/14/2020] [Indexed: 10/23/2022] Open
Abstract
Lung segmentation is a key step of thoracic computed tomography (CT) image processing, and it plays an important role in computer-aided pulmonary disease diagnostics. However, the presence of image noises, pathologies, vessels, individual anatomical varieties, and so on makes lung segmentation a complex task. In this paper, we present a fully automatic algorithm for segmenting lungs from thoracic CT images accurately. An input image is first spilt into a set of non-overlapping fixed-sized image patches, and a deep convolutional neural network model is constructed to extract initial lung regions by classifying image patches. Superpixel segmentation is then performed on the preprocessed thoracic CT image, and the lung contours are locally refined according to corresponding superpixel contours with our adjacent point statistics method. Segmented lung contours are further globally refined by an edge direction tracing technique for the inclusion of juxta-pleural lesions. Our algorithm is tested on a group of thoracic CT scans with interstitial lung diseases. Experiments show that our algorithm creates an average Dice similarity coefficient of 97.95% and Jaccard's similarity index of 94.48%, with 2.8% average over-segmentation rate and 3.3% under-segmentation rate compared with manually segmented results. Meanwhile, it shows better performance compared with several feature-based machine learning methods and current methods on lung segmentation.
Collapse
|
27
|
Reamaroon N, Sjoding MW, Derksen H, Sabeti E, Gryak J, Barbaro RP, Athey BD, Najarian K. Robust segmentation of lung in chest x-ray: applications in analysis of acute respiratory distress syndrome. BMC Med Imaging 2020; 20:116. [PMID: 33059612 PMCID: PMC7566051 DOI: 10.1186/s12880-020-00514-y] [Citation(s) in RCA: 14] [Impact Index Per Article: 3.5] [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: 04/24/2020] [Accepted: 09/27/2020] [Indexed: 03/12/2023] Open
Abstract
Background This study outlines an image processing algorithm for accurate and consistent lung segmentation in chest radiographs of critically ill adults and children typically obscured by medical equipment. In particular, this work focuses on applications in analysis of acute respiratory distress syndrome – a critical illness with a mortality rate of 40% that affects 200,000 patients in the United States and 3 million globally each year. Methods Chest radiographs were obtained from critically ill adults (n = 100), adults diagnosed with acute respiratory distress syndrome (ARDS) (n = 25), and children (n = 100) hospitalized at Michigan Medicine. Physicians annotated the lung field of each radiograph to establish the ground truth. A Total Variation-based Active Contour (TVAC) lung segmentation algorithm was developed and compared to multiple state-of-the-art methods including a deep learning model (U-Net), a random walker algorithm, and an active spline model, using the Sørensen–Dice coefficient to measure segmentation accuracy. Results The TVAC algorithm accurately segmented lung fields in all patients in the study. For the adult cohort, an averaged Dice coefficient of 0.86 ±0.04 (min: 0.76) was reported for TVAC, 0.89 ±0.12 (min: 0.01) for U-Net, 0.74 ±0.19 (min: 0.15) for the random walker algorithm, and 0.64 ±0.17 (min: 0.20) for the active spline model. For the pediatric cohort, a Dice coefficient of 0.85 ±0.04 (min: 0.75) was reported for TVAC, 0.87 ±0.09 (min: 0.56) for U-Net, 0.67 ±0.18 (min: 0.18) for the random walker algorithm, and 0.61 ±0.18 (min: 0.18) for the active spline model. Conclusion The proposed algorithm demonstrates the most consistent performance of all segmentation methods tested. These results suggest that TVAC can accurately identify lung fields in chest radiographs in critically ill adults and children.
Collapse
Affiliation(s)
- Narathip Reamaroon
- Department of Computational Medicine and Bioinformatics, University of Michigan, Ann Arbor, MI, USA.
| | - Michael W Sjoding
- Department of Internal Medicine, University of Michigan, Ann Arbor, MI, USA
| | - Harm Derksen
- Department of Mathematics, University of Michigan, Ann Arbor, MI, USA
| | - Elyas Sabeti
- Michigan Institute for Data Science, University of Michigan, Ann Arbor, MI, USA
| | - Jonathan Gryak
- Department of Computational Medicine and Bioinformatics, University of Michigan, Ann Arbor, MI, USA
| | - Ryan P Barbaro
- Department of Pediatrics, University of Michigan, Ann Arbor, MI, USA
| | - Brian D Athey
- Department of Computational Medicine and Bioinformatics, University of Michigan, Ann Arbor, MI, USA
| | - Kayvan Najarian
- Department of Computational Medicine and Bioinformatics, University of Michigan, Ann Arbor, MI, USA
| |
Collapse
|
28
|
Abstract
Lung cancer has become one of the life-threatening killers. Lung disease need to be assisted by CT images taken doctor's diagnosis, and the segmented CT image of the lung parenchyma is the first step to help doctor diagnosis. For the problem of accurately segmenting the lung parenchyma, this paper proposes a segmentation method based on the combination of VGG-16 and dilated convolution. First of all, we use the first three parts of VGG-16 network structure to convolution and pooling the input image. Secondly, using multiple sets of dilated convolutions make the network has a large enough receptive field. Finally, the multi-scale convolution features are fused, and each pixel is predicted using MLP to segment the parenchymal region. Experimental results were produced over state of the art on 137 images which key metrics Dice similarity coefficient (DSC) is 0.9867. Experimental results show that this method can effectively segment the lung parenchymal area, and compared to other conventional methods better.
Collapse
Affiliation(s)
- Lei Geng
- Tianjin Key Laboratory of Optoelectronic Detection Technology and System , Tianjin , China.,School of Electronics and Information Engineering, Tianjin Polytechnic University , Tianjin , China
| | - Siqi Zhang
- Tianjin Key Laboratory of Optoelectronic Detection Technology and System , Tianjin , China.,School of Electronics and Information Engineering, Tianjin Polytechnic University , Tianjin , China
| | - Jun Tong
- Tianjin Key Laboratory of Optoelectronic Detection Technology and System , Tianjin , China.,School of Electronics and Information Engineering, Tianjin Polytechnic University , Tianjin , China.,School of Electrical, Computer and Telecommunications Engineering, University of Wollongong , Wollongong , Australia
| | - Zhitao Xiao
- Tianjin Key Laboratory of Optoelectronic Detection Technology and System , Tianjin , China.,School of Electronics and Information Engineering, Tianjin Polytechnic University , Tianjin , China
| |
Collapse
|
29
|
Souza JC, Bandeira Diniz JO, Ferreira JL, França da Silva GL, Corrêa Silva A, de Paiva AC. An automatic method for lung segmentation and reconstruction in chest X-ray using deep neural networks. Comput Methods Programs Biomed 2019; 177:285-296. [PMID: 31319957 DOI: 10.1016/j.cmpb.2019.06.005] [Citation(s) in RCA: 89] [Impact Index Per Article: 17.8] [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: 03/11/2019] [Revised: 05/24/2019] [Accepted: 06/05/2019] [Indexed: 05/03/2023]
Abstract
BACKGROUND AND OBJECTIVE Chest X-ray (CXR) is one of the most used imaging techniques for detection and diagnosis of pulmonary diseases. A critical component in any computer-aided system, for either detection or diagnosis in digital CXR, is the automatic segmentation of the lung field. One of the main challenges inherent to this task is to include in the segmentation the lung regions overlapped by dense abnormalities, also known as opacities, which can be caused by diseases such as tuberculosis and pneumonia. This specific task is difficult because opacities frequently reach high intensity values which can be incorrectly interpreted by an automatic method as the lung boundary, and as a consequence, this creates a challenge in the segmentation process, because the chances of incomplete segmentations are increased considerably. The purpose of this work is to propose a method for automatic segmentation of lungs in CXR that addresses this problem by reconstructing the lung regions "lost" due to pulmonary abnormalities. METHODS The proposed method, which features two deep convolutional neural network models, consists of four steps main steps: (1) image acquisition, (2) initial segmentation, (3) reconstruction and (4) final segmentation. RESULTS The proposed method was experimented on 138 Chest X-ray images from Montgomery County's Tuberculosis Control Program, and has achieved as best result an average sensitivity of 97.54%, an average specificity of 96.79%, an average accuracy of 96.97%, an average Dice coefficient of 94%, and an average Jaccard index of 88.07%. CONCLUSIONS We demonstrate in our lung segmentation method that the problem of dense abnormalities in Chest X-rays can be efficiently addressed by performing a reconstruction step based on a deep convolutional neural network model.
Collapse
|
30
|
Gordaliza PM, Muñoz-Barrutia A, Via LE, Sharpe S, Desco M, Vaquero JJ. Computed Tomography-Based Biomarker for Longitudinal Assessment of Disease Burden in Pulmonary Tuberculosis. Mol Imaging Biol 2019; 21:19-24. [PMID: 29845428 DOI: 10.1007/s11307-018-1215-x] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/13/2022]
Abstract
PURPOSE Computed tomography (CT) images enable capturing specific manifestations of tuberculosis (TB) that are undetectable using common diagnostic tests, which suffer from limited specificity. In this study, we aimed to automatically quantify the burden of Mycobacterium tuberculosis (Mtb) using biomarkers extracted from x-ray CT images. PROCEDURES Nine macaques were aerosol-infected with Mtb and treated with various antibiotic cocktails. Chest CT scans were acquired in all animals at specific times independently of disease progression. First, a fully automatic segmentation of the healthy lungs from the acquired chest CT volumes was performed and air-like structures were extracted. Next, unsegmented pulmonary regions corresponding to damaged parenchymal tissue and TB lesions were included. CT biomarkers were extracted by classification of the probability distribution of the intensity of the segmented images into three tissue types: (1) Healthy tissue, parenchyma free from infection; (2) soft diseased tissue, and (3) hard diseased tissue. The probability distribution of tissue intensities was assumed to follow a Gaussian mixture model. The thresholds identifying each region were automatically computed using an expectation-maximization algorithm. RESULTS The estimated longitudinal course of TB infection shows that subjects that have followed the same antibiotic treatment present a similar response (relative change in the diseased volume) with respect to baseline. More interestingly, the correlation between the diseased volume (soft tissue + hard tissue), which was manually delineated by an expert, and the automatically extracted volume with the proposed method was very strong (R2 ≈ 0.8). CONCLUSIONS We present a methodology that is suitable for automatic extraction of a radiological biomarker from CT images for TB disease burden. The method could be used to describe the longitudinal evolution of Mtb infection in a clinical trial devoted to the design of new drugs.
Collapse
Affiliation(s)
- P M Gordaliza
- Dpto. Bioingeniería e Ingeniería Aeroespacial, Universidad Carlos III de Madrid, Leganés, Spain.,Instituto de Investigación Sanitaria Gregorio Marañón, Madrid, Spain
| | - A Muñoz-Barrutia
- Dpto. Bioingeniería e Ingeniería Aeroespacial, Universidad Carlos III de Madrid, Leganés, Spain. .,Instituto de Investigación Sanitaria Gregorio Marañón, Madrid, Spain.
| | - L E Via
- Tuberculosis Research Section, LCIM, and Tuberculosis Imaging Program, DIR, NIAID, NIH, Bethesda, MD, USA
| | - S Sharpe
- National Infections Service, Public Health England, Porton Down, England
| | - M Desco
- Dpto. Bioingeniería e Ingeniería Aeroespacial, Universidad Carlos III de Madrid, Leganés, Spain.,Instituto de Investigación Sanitaria Gregorio Marañón, Madrid, Spain.,Centro Nacional de Investigaciones Cardiovasculares Carlos III, Madrid, Spain.,Centro de Investigación Biomédica en Red de Salud Mental, Madrid, Spain
| | - J J Vaquero
- Dpto. Bioingeniería e Ingeniería Aeroespacial, Universidad Carlos III de Madrid, Leganés, Spain.,Instituto de Investigación Sanitaria Gregorio Marañón, Madrid, Spain
| |
Collapse
|
31
|
Gill G, Beichel RR. An approach for reducing the error rate in automated lung segmentation. Comput Biol Med 2016; 76:143-53. [PMID: 27447897 DOI: 10.1016/j.compbiomed.2016.06.022] [Citation(s) in RCA: 13] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/15/2016] [Revised: 06/21/2016] [Accepted: 06/22/2016] [Indexed: 11/23/2022]
Abstract
Robust lung segmentation is challenging, especially when tens of thousands of lung CT scans need to be processed, as required by large multi-center studies. The goal of this work was to develop and assess a method for the fusion of segmentation results from two different methods to generate lung segmentations that have a lower failure rate than individual input segmentations. As basis for the fusion approach, lung segmentations generated with a region growing and model-based approach were utilized. The fusion result was generated by comparing input segmentations and selectively combining them using a trained classification system. The method was evaluated on a diverse set of 204 CT scans of normal and diseased lungs. The fusion approach resulted in a Dice coefficient of 0.9855±0.0106 and showed a statistically significant improvement compared to both input segmentation methods. In addition, the failure rate at different segmentation accuracy levels was assessed. For example, when requiring that lung segmentations must have a Dice coefficient of better than 0.97, the fusion approach had a failure rate of 6.13%. In contrast, the failure rate for region growing and model-based methods was 18.14% and 15.69%, respectively. Therefore, the proposed method improves the quality of the lung segmentations, which is important for subsequent quantitative analysis of lungs. Also, to enable a comparison with other methods, results on the LOLA11 challenge test set are reported.
Collapse
|
32
|
Lee WL, Chang K, Hsieh KS. Unsupervised segmentation of lung fields in chest radiographs using multiresolution fractal feature vector and deformable models. Med Biol Eng Comput 2015; 54:1409-22. [PMID: 26530048 DOI: 10.1007/s11517-015-1412-6] [Citation(s) in RCA: 6] [Impact Index Per Article: 0.7] [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: 02/11/2015] [Accepted: 10/19/2015] [Indexed: 10/22/2022]
Abstract
Segmenting lung fields in a chest radiograph is essential for automatically analyzing an image. We present an unsupervised method based on multiresolution fractal feature vector. The feature vector characterizes the lung field region effectively. A fuzzy c-means clustering algorithm is then applied to obtain a satisfactory initial contour. The final contour is obtained by deformable models. The results show the feasibility and high performance of the proposed method. Furthermore, based on the segmentation of lung fields, the cardiothoracic ratio (CTR) can be measured. The CTR is a simple index for evaluating cardiac hypertrophy. After identifying a suspicious symptom based on the estimated CTR, a physician can suggest that the patient undergoes additional extensive tests before a treatment plan is finalized.
Collapse
Affiliation(s)
- Wen-Li Lee
- Department of Healthcare Information and Management, Ming Chuan University, Taoyuan, 333, Taiwan, ROC.
| | - Koyin Chang
- Department of Healthcare Information and Management, Ming Chuan University, Taoyuan, 333, Taiwan, ROC
| | | |
Collapse
|
33
|
Shen S, Bui AAT, Cong J, Hsu W. An automated lung segmentation approach using bidirectional chain codes to improve nodule detection accuracy. Comput Biol Med 2014; 57:139-49. [PMID: 25557199 DOI: 10.1016/j.compbiomed.2014.12.008] [Citation(s) in RCA: 73] [Impact Index Per Article: 7.3] [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: 09/16/2014] [Revised: 12/06/2014] [Accepted: 12/10/2014] [Indexed: 11/18/2022]
Abstract
Computer-aided detection and diagnosis (CAD) has been widely investigated to improve radiologists׳ diagnostic accuracy in detecting and characterizing lung disease, as well as to assist with the processing of increasingly sizable volumes of imaging. Lung segmentation is a requisite preprocessing step for most CAD schemes. This paper proposes a parameter-free lung segmentation algorithm with the aim of improving lung nodule detection accuracy, focusing on juxtapleural nodules. A bidirectional chain coding method combined with a support vector machine (SVM) classifier is used to selectively smooth the lung border while minimizing the over-segmentation of adjacent regions. This automated method was tested on 233 computed tomography (CT) studies from the lung imaging database consortium (LIDC), representing 403 juxtapleural nodules. The approach obtained a 92.6% re-inclusion rate. Segmentation accuracy was further validated on 10 randomly selected CT series, finding a 0.3% average over-segmentation ratio and 2.4% under-segmentation rate when compared to manually segmented reference standards done by an expert.
Collapse
Affiliation(s)
- Shiwen Shen
- Department of Bioengineering, University of California, Los Angeles, CA, USA; Medical Imaging Informatics (MII) Group, Department of Radiological Sciences, University of California, Los Angeles, CA, USA.
| | - Alex A T Bui
- Medical Imaging Informatics (MII) Group, Department of Radiological Sciences, University of California, Los Angeles, CA, USA
| | - Jason Cong
- Department of Computer Science, University of California, Los Angeles, CA, USA
| | - William Hsu
- Medical Imaging Informatics (MII) Group, Department of Radiological Sciences, University of California, Los Angeles, CA, USA
| |
Collapse
|
34
|
Saien S, Hamid Pilevar A, Abrishami Moghaddam H. Refinement of lung nodule candidates based on local geometric shape analysis and Laplacian of Gaussian kernels. Comput Biol Med 2014; 54:188-98. [PMID: 25303113 DOI: 10.1016/j.compbiomed.2014.09.010] [Citation(s) in RCA: 19] [Impact Index Per Article: 1.9] [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: 02/14/2014] [Revised: 09/16/2014] [Accepted: 09/17/2014] [Indexed: 10/24/2022]
Abstract
This work is focused on application of a new technique in the first steps of computer-aided detection (CAD) of lung nodules. The scheme includes segmenting the lung volume and detecting most of the nodules with a low number of false positive (FP) objects. The juxtapleural nodules were properly included and the airways excluded in the lung segmentation. Among the suspicious regions obtained from the multiscale dot enhancement filter, those containing the center of nodule candidates, were determined. These center points were achieved from a 3D blob detector based on Laplacian of Gaussian kernels. Then the volumetric shape index (SI) that encodes the 3D local shape information was calculated for voxels in the determined regions. The performance of the scheme was evaluated by using 42 CT images from the Lung Image Database Consortium (LIDC). The results show that the average number of FPs reaches to 38.8 per scan with the sensitivity of 95.9% in the initial detections. The scheme is adaptable to detect nodules with wide variations in size, shape, intensity and location. Comparison of results with previously reported ones indicates that the proposed scheme can be satisfactory applied for initial detection of lung nodules in the chest CT images.
Collapse
Affiliation(s)
- Soudeh Saien
- Department of Computing Engineering, Bu-Ali Sina University, Hamedan, Iran.
| | | | - Hamid Abrishami Moghaddam
- Department of Biomedical Engineering, Faculty of Electrical Engineering, K.N. Toosi University of Technology, Tehran, Iran.
| |
Collapse
|
35
|
Özkan H, Osman O, Şahin S, Boz AF. A novel method for pulmonary embolism detection in CTA images. Comput Methods Programs Biomed 2014; 113:757-766. [PMID: 24440133 DOI: 10.1016/j.cmpb.2013.12.014] [Citation(s) in RCA: 14] [Impact Index Per Article: 1.4] [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: 07/02/2013] [Revised: 12/19/2013] [Accepted: 12/20/2013] [Indexed: 06/03/2023]
Abstract
In this paper, we propose a new computer-aided detection (CAD) - based method to detect pulmonary embolism (PE) in computed tomography angiography images (CTAI). Since lung vessel segmentation is the main objective to provide high sensitivity in PE detection, this method performs accurate lung vessel segmentation. To concatenate clogged vessels due to PEs, the starting region of PEs and some reference points (RPs) are determined. These RPs are detected according to the fixed anatomical structures. After lung vessel tree is segmented, the region, intensity, and size of PEs are used to distinguish them. We used the data sets that have heart disease or abnormal tissues because of lung disease except PE in this work. According to the results, 428 of 450 PEs, labeled by the radiologists from 33 patients, have been detected. The sensitivity of the developed system is 95.1% at 14.4 false positive per data set (FP/ds). With this performance, the proposed CAD system is found quite useful to use as a second reader by the radiologists.
Collapse
Affiliation(s)
- Haydar Özkan
- Fatih Sultan Mehmet Vakıf University, Department of Biomedical Engineering, Istanbul, Turkey.
| | - Onur Osman
- Arel University, Department of Electrical and Electronics Engineering, Istanbul, Turkey
| | - Sinan Şahin
- Dr. Siyami Ersek Thoracic and Cardiovascular Surgery Training and Research Hospital, Department of Radiology, Istanbul, Turkey
| | - Ali Fuat Boz
- Sakarya University Technology Faculty, Department of Electrical and Electronics Engineering, Sakarya, Turkey
| |
Collapse
|