1
|
Kang H, Kim N, Ryu J. Attentional decoder networks for chest X-ray image recognition on high-resolution features. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2024; 251:108198. [PMID: 38718718 DOI: 10.1016/j.cmpb.2024.108198] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 01/17/2024] [Revised: 03/31/2024] [Accepted: 04/21/2024] [Indexed: 05/31/2024]
Abstract
BACKGROUND AND OBJECTIVE This paper introduces an encoder-decoder-based attentional decoder network to recognize small-size lesions in chest X-ray images. In the encoder-only network, small-size lesions disappear during the down-sampling steps or are indistinguishable in the low-resolution feature maps. To address these issues, the proposed network processes images in the encoder-decoder architecture similar to U-Net families and classifies lesions by globally pooling high-resolution feature maps. However, two challenging obstacles prohibit U-Net families from being extended to classification: (1) the up-sampling procedure consumes considerable resources, and (2) there needs to be an effective pooling approach for the high-resolution feature maps. METHODS Therefore, the proposed network employs a lightweight attentional decoder and harmonic magnitude transform. The attentional decoder up-samples the given features with the low-resolution features as the key and value while the high-resolution features as the query. Since multi-scaled features interact, up-sampled features embody global context at a high resolution, maintaining pathological locality. In addition, harmonic magnitude transform is devised for pooling high-resolution feature maps in the frequency domain. We borrow the shift theorem of the Fourier transform to preserve the translation invariant property and further reduce the parameters of the pooling layer by an efficient embedding strategy. RESULTS The proposed network achieves state-of-the-art classification performance on the three public chest X-ray datasets, such as NIH, CheXpert, and MIMIC-CXR. CONCLUSIONS In conclusion, the proposed efficient encoder-decoder network recognizes small-size lesions well in chest X-ray images by efficiently up-sampling feature maps through an attentional decoder and processing high-resolution feature maps with harmonic magnitude transform. We open-source our implementation at https://github.com/Lab-LVM/ADNet.
Collapse
Affiliation(s)
- Hankyul Kang
- Department of Artificial Intelligence, Ajou University, Suwon, Republic of Korea
| | - Namkug Kim
- Department of Convergence Medicine, Ulsan University, Seoul, Republic of Korea
| | - Jongbin Ryu
- Department of Artificial Intelligence, Ajou University, Suwon, Republic of Korea; Department of Software and Computer Engineering, Ajou University, Suwon, Republic of Korea.
| |
Collapse
|
2
|
Li D, Huo H, Jiao S, Sun X, Chen S. Automated thorax disease diagnosis using multi-branch residual attention network. Sci Rep 2024; 14:11865. [PMID: 38789592 PMCID: PMC11126636 DOI: 10.1038/s41598-024-62813-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/30/2024] [Accepted: 05/21/2024] [Indexed: 05/26/2024] Open
Abstract
Chest X-ray (CXR) is an extensively utilized radiological modality for supporting the diagnosis of chest diseases. However, existing research approaches suffer from limitations in effectively integrating multi-scale CXR image features and are also hindered by imbalanced datasets. Therefore, there is a pressing need for further advancement in computer-aided diagnosis (CAD) of thoracic diseases. To tackle these challenges, we propose a multi-branch residual attention network (MBRANet) for thoracic disease diagnosis. MBRANet comprises three components. Firstly, to address the issue of inadequate extraction of spatial and positional information by the convolutional layer, a novel residual structure incorporating a coordinate attention (CA) module is proposed to extract features at multiple scales. Next, based on the concept of a Feature Pyramid Network (FPN), we perform multi-scale feature fusion in the following manner. Thirdly, we propose a novel Multi-Branch Feature Classifier (MFC) approach, which leverages the class-specific residual attention (CSRA) module for classification instead of relying solely on the fully connected layer. In addition, the designed BCEWithLabelSmoothing loss function improves the generalization ability and mitigates the problem of class imbalance by introducing a smoothing factor. We evaluated MBRANet on the ChestX-Ray14, CheXpert, MIMIC-CXR, and IU X-Ray datasets and achieved average AUCs of 0.841, 0.895, 0.805, and 0.745, respectively. Our method outperformed state-of-the-art baselines on these benchmark datasets.
Collapse
Affiliation(s)
- Dongfang Li
- School of Information Engineering, Henan University of Science and Technology, Luoyang, 471000, Henan, China
| | - Hua Huo
- School of Information Engineering, Henan University of Science and Technology, Luoyang, 471000, Henan, China.
| | - Shupei Jiao
- School of Information Engineering, Henan University of Science and Technology, Luoyang, 471000, Henan, China
| | - Xiaowei Sun
- School of Information Engineering, Henan University of Science and Technology, Luoyang, 471000, Henan, China
| | - Shuya Chen
- School of Information Engineering, Henan University of Science and Technology, Luoyang, 471000, Henan, China
| |
Collapse
|
3
|
Hung-Nguyen M. Patch-Level Feature Selection for Thoracic Disease Classification by Chest X-ray Images Using Information Bottleneck. Bioengineering (Basel) 2024; 11:316. [PMID: 38671737 PMCID: PMC11047950 DOI: 10.3390/bioengineering11040316] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/28/2024] [Revised: 03/20/2024] [Accepted: 03/23/2024] [Indexed: 04/28/2024] Open
Abstract
Chest X-ray (CXR) examination serves as a widely employed clinical test in medical diagnostics. Many studied have tried to apply artificial intelligence (AI) programs to analyze CXR images. Despite numerous positive outcomes, assessing the applicability of AI models for comprehensive diagnostic support remains a formidable challenge. We observed that, even when AI models exhibit high accuracy on one dataset, their performance may deteriorate when tested on another. To address this issue, we propose incorporating a variational information bottleneck (VIB) at the patch level to enhance the generalizability of diagnostic support models. The VIB introduces a probabilistic model aimed at approximating the posterior distribution of latent variables given input data, thereby enhancing the model's generalization capabilities on unseen data. Unlike the conventional VIB approaches that flatten features and use a re-parameterization trick to sample a new latent feature, our method applies the trick to 2D feature maps. This design allows only important pixels to respond, and the model will select important patches in an image. Moreover, the proposed patch-level VIB seamlessly integrates with various convolutional neural networks, offering a versatile solution to improve performance. Experimental results illustrate enhanced accuracy in standard experiment settings. In addition, the method shows robust improvement when training and testing on different datasets.
Collapse
Affiliation(s)
- Manh Hung-Nguyen
- Faculty of Electrical and Electronics Engineering, HCMC University of Technology and Education, Ho Chi Minh City 7000, Vietnam
| |
Collapse
|
4
|
Fan W, Yang Y, Qi J, Zhang Q, Liao C, Wen L, Wang S, Wang G, Xia Y, Wu Q, Fan X, Chen X, He M, Xiao J, Yang L, Liu Y, Chen J, Wang B, Zhang L, Yang L, Gan H, Zhang S, Liu G, Ge X, Cai Y, Zhao G, Zhang X, Xie M, Xu H, Zhang Y, Chen J, Li J, Han S, Mu K, Xiao S, Xiong T, Nian Y, Zhang D. A deep-learning-based framework for identifying and localizing multiple abnormalities and assessing cardiomegaly in chest X-ray. Nat Commun 2024; 15:1347. [PMID: 38355644 PMCID: PMC10867134 DOI: 10.1038/s41467-024-45599-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/19/2022] [Accepted: 01/30/2024] [Indexed: 02/16/2024] Open
Abstract
Accurate identification and localization of multiple abnormalities are crucial steps in the interpretation of chest X-rays (CXRs); however, the lack of a large CXR dataset with bounding boxes severely constrains accurate localization research based on deep learning. We created a large CXR dataset named CXR-AL14, containing 165,988 CXRs and 253,844 bounding boxes. On the basis of this dataset, a deep-learning-based framework was developed to identify and localize 14 common abnormalities and calculate the cardiothoracic ratio (CTR) simultaneously. The mean average precision values obtained by the model for 14 abnormalities reached 0.572-0.631 with an intersection-over-union threshold of 0.5, and the intraclass correlation coefficient of the CTR algorithm exceeded 0.95 on the held-out, multicentre and prospective test datasets. This framework shows an excellent performance, good generalization ability and strong clinical applicability, which is superior to senior radiologists and suitable for routine clinical settings.
Collapse
Affiliation(s)
- Weijie Fan
- Department of Radiology, Second Affiliated Hospital, Army Medical University, Chongqing, 400037, P. R. China
| | - Yi Yang
- Department of Digital Medicine, School of Biomedical Engineering and Imaging Medicine, Army Medical University, Chongqing, 400038, P. R. China
| | - Jing Qi
- Department of Digital Medicine, School of Biomedical Engineering and Imaging Medicine, Army Medical University, Chongqing, 400038, P. R. China
| | - Qichuan Zhang
- Department of Radiology, Second Affiliated Hospital, Army Medical University, Chongqing, 400037, P. R. China
| | - Cuiwei Liao
- Department of Radiology, Second Affiliated Hospital, Army Medical University, Chongqing, 400037, P. R. China
| | - Li Wen
- Department of Radiology, Second Affiliated Hospital, Army Medical University, Chongqing, 400037, P. R. China
| | - Shuang Wang
- Department of Radiology, Second Affiliated Hospital, Army Medical University, Chongqing, 400037, P. R. China
| | - Guangxian Wang
- Department of Radiology, People's Hospital of Banan, Chongqing Medical University, Chongqing, 401320, P. R. China
| | - Yu Xia
- Department of Radiology, Xishui hospital of Traditional Chinese Medicine, Zunyi of Guizhou province, 564600, P. R. China
| | - Qihua Wu
- Department of Radiology, People's Hospital of Nanchuan, Chongqing, 408400, P. R. China
| | - Xiaotao Fan
- Department of Radiology, Fengdu People's Hospital, Chongqing, 408200, P. R. China
| | - Xingcai Chen
- Department of Digital Medicine, School of Biomedical Engineering and Imaging Medicine, Army Medical University, Chongqing, 400038, P. R. China
| | - Mi He
- Department of Digital Medicine, School of Biomedical Engineering and Imaging Medicine, Army Medical University, Chongqing, 400038, P. R. China
| | - JingJing Xiao
- Department of Medical Engineering, Second Affiliated Hospital, Army Medical University, Chongqing, 400037, P. R. China
| | - Liu Yang
- Department of Radiology, Second Affiliated Hospital, Army Medical University, Chongqing, 400037, P. R. China
| | - Yun Liu
- Department of Radiology, Second Affiliated Hospital, Army Medical University, Chongqing, 400037, P. R. China
| | - Jia Chen
- Department of Radiology, Second Affiliated Hospital, Army Medical University, Chongqing, 400037, P. R. China
| | - Bing Wang
- Department of Radiology, Second Affiliated Hospital, Army Medical University, Chongqing, 400037, P. R. China
| | - Lei Zhang
- Department of Radiology, Second Affiliated Hospital, Army Medical University, Chongqing, 400037, P. R. China
| | - Liuqing Yang
- Department of Radiology, Second Affiliated Hospital, Army Medical University, Chongqing, 400037, P. R. China
| | - Hui Gan
- Department of Radiology, Second Affiliated Hospital, Army Medical University, Chongqing, 400037, P. R. China
| | - Shushu Zhang
- Department of Radiology, Second Affiliated Hospital, Army Medical University, Chongqing, 400037, P. R. China
| | - Guofang Liu
- Department of Radiology, Second Affiliated Hospital, Army Medical University, Chongqing, 400037, P. R. China
| | - Xiaodong Ge
- Department of Radiology, Second Affiliated Hospital, Army Medical University, Chongqing, 400037, P. R. China
| | - Yuanqing Cai
- Department of Radiology, Second Affiliated Hospital, Army Medical University, Chongqing, 400037, P. R. China
| | - Gang Zhao
- Department of Radiology, Second Affiliated Hospital, Army Medical University, Chongqing, 400037, P. R. China
| | - Xi Zhang
- Department of Radiology, Second Affiliated Hospital, Army Medical University, Chongqing, 400037, P. R. China
| | - Mingxun Xie
- Department of Radiology, Second Affiliated Hospital, Army Medical University, Chongqing, 400037, P. R. China
| | - Huilin Xu
- Department of Radiology, Second Affiliated Hospital, Army Medical University, Chongqing, 400037, P. R. China
| | - Yi Zhang
- Department of Radiology, Second Affiliated Hospital, Army Medical University, Chongqing, 400037, P. R. China
| | - Jiao Chen
- Department of Radiology, Second Affiliated Hospital, Army Medical University, Chongqing, 400037, P. R. China
| | - Jun Li
- Department of Radiology, Second Affiliated Hospital, Army Medical University, Chongqing, 400037, P. R. China
| | - Shuang Han
- Department of Radiology, Second Affiliated Hospital, Army Medical University, Chongqing, 400037, P. R. China
| | - Ke Mu
- Department of Radiology, Second Affiliated Hospital, Army Medical University, Chongqing, 400037, P. R. China
| | - Shilin Xiao
- Department of Radiology, Second Affiliated Hospital, Army Medical University, Chongqing, 400037, P. R. China
| | - Tingwei Xiong
- Department of Radiology, Second Affiliated Hospital, Army Medical University, Chongqing, 400037, P. R. China
| | - Yongjian Nian
- Department of Digital Medicine, School of Biomedical Engineering and Imaging Medicine, Army Medical University, Chongqing, 400038, P. R. China.
| | - Dong Zhang
- Department of Radiology, Second Affiliated Hospital, Army Medical University, Chongqing, 400037, P. R. China.
| |
Collapse
|
5
|
Gao X, Jiang B, Wang X, Huang L, Tu Z. Chest x-ray diagnosis via spatial-channel high-order attention representation learning. Phys Med Biol 2024; 69:045026. [PMID: 38347732 DOI: 10.1088/1361-6560/ad2014] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/15/2023] [Accepted: 01/18/2024] [Indexed: 02/15/2024]
Abstract
Objective. Chest x-ray image representation and learning is an important problem in computer-aided diagnostic area. Existing methods usually adopt CNN or Transformers for feature representation learning and focus on learning effective representations for chest x-ray images. Although good performance can be obtained, however, these works are still limited mainly due to the ignorance of mining the correlations of channels and pay little attention on the local context-aware feature representation of chest x-ray image.Approach. To address these problems, in this paper, we propose a novel spatial-channel high-order attention model (SCHA) for chest x-ray image representation and diagnosis. The proposed network architecture mainly contains three modules, i.e. CEBN, SHAM and CHAM. To be specific, firstly, we introduce a context-enhanced backbone network by employing multi-head self-attention to extract initial features for the input chest x-ray images. Then, we develop a novel SCHA which contains both spatial and channel high-order attention learning branches. For the spatial branch, we develop a novel local biased self-attention mechanism which can capture both local and long-range global dependences of positions to learn rich context-aware representation. For the channel branch, we employ Brownian Distance Covariance to encode the correlation information of channels and regard it as the image representation. Finally, the two learning branches are integrated together for the final multi-label diagnosis classification and prediction.Main results. Experiments on the commonly used datasets including ChestX-ray14 and CheXpert demonstrate that our proposed SCHA approach can obtain better performance when comparing many related approaches.Significance. This study obtains a more discriminative method for chest x-ray classification and provides a technique for computer-aided diagnosis.
Collapse
Affiliation(s)
- Xinyue Gao
- The School of Computer Science and Technology, Anhui University, Hefei 230601, People's Republic of China
| | - Bo Jiang
- The School of Computer Science and Technology, Anhui University, Hefei 230601, People's Republic of China
| | - Xixi Wang
- The School of Computer Science and Technology, Anhui University, Hefei 230601, People's Republic of China
| | - Lili Huang
- The School of Computer Science and Technology, Anhui University, Hefei 230601, People's Republic of China
| | - Zhengzheng Tu
- The School of Computer Science and Technology, Anhui University, Hefei 230601, People's Republic of China
| |
Collapse
|
6
|
Liu C, Wu Z, Wang B, Zhu M. Pulmonary nodule detection in x-ray images by feature augmentation and context aggregation. Phys Med Biol 2024; 69:045002. [PMID: 38237183 DOI: 10.1088/1361-6560/ad2013] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/02/2023] [Accepted: 01/18/2024] [Indexed: 02/06/2024]
Abstract
Recent developments in x-ray image based pulmonary nodule detection have achieved remarkable results. However, existing methods are focused on transferring off-the-shelf coarse-grained classification models and fine-grained detection models rather than developing a dedicated framework optimized for nodule detection. In this paper, we propose PN-DetX, which as we know is the first dedicated pulmonary nodule detection framework. PN-DetX incorporates feature fusion and self-attention into x-ray based pulmonary nodule detection tasks, achieving improved detection performance. Specifically, PN-DetX adopts CSPDarknet backbone to extract features, and utilizes feature augmentation module to fuse features from different levels followed by context aggregation module to aggregate semantic information. To evaluate the efficacy of our method, we collect aLArge-scalePulmonaryNOduleDetection dataset,LAPNOD, comprising 2954 x-ray images along with expert-annotated ground truths. As we know, this is the first large-scale chest x-ray pulmonary nodule detection dataset. Experiments demonstrates that our method outperforms baseline by 3.8% mAP and 5.1%AP0.5. The generality of our approach is also evaluated on the publicly available dataset NODE21. We aspire for our method to serve as an inspiration for future research in the field of pulmonary nodule detection. The dataset and codes will be made in public.
Collapse
Affiliation(s)
- Chenglin Liu
- Department of Automation, University of Science and Technology of China, Hefei, People's Republic of China
| | - Zhi Wu
- School of Cyber Science and Technology, University of Science and Technology of China, Hefei, People's Republic of China
| | - Binquan Wang
- School of Cyber Science and Technology, University of Science and Technology of China, Hefei, People's Republic of China
| | - Ming Zhu
- Department of Automation, University of Science and Technology of China, Hefei, People's Republic of China
| |
Collapse
|
7
|
Chen Y, Guo X, Pan Y, Xia Y, Yuan Y. Dynamic feature splicing for few-shot rare disease diagnosis. Med Image Anal 2023; 90:102959. [PMID: 37757644 DOI: 10.1016/j.media.2023.102959] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/18/2022] [Revised: 09/03/2023] [Accepted: 09/05/2023] [Indexed: 09/29/2023]
Abstract
Annotated images for rare disease diagnosis are extremely hard to collect. Therefore, identifying rare diseases under a few-shot learning (FSL) setting is significant. Existing FSL methods transfer useful and global knowledge from base classes with abundant training samples to enrich features of novel classes with few training samples, but still face difficulties when being applied to medical images due to the complex lesion characteristics and large intra-class variance. In this paper, we propose a dynamic feature splicing (DNFS) framework for few-shot rare disease diagnosis. Under DNFS, both low-level features (i.e., the output of three convolutional blocks) and high-level features (i.e., the output of the last fully connected layer) of novel classes are dynamically enriched. We construct the position coherent DNFS (P-DNFS) module to perform low-level feature splicing, where a lesion-oriented Transformer is designed to detect lesion regions. Thus, novel-class channels are replaced by similar base-class channels within the detected lesion regions to achieve disease-related feature enrichment. We also devise a semantic coherent DNFS (S-DNFS) module to perform high-level feature splicing. It explores cross-image channel relations and selects base-class channels with semantic consistency for explicit knowledge transfer. Both low-level and high-level feature splicings are performed dynamically and iteratively. Consequently, abundant spliced features are generated for disease diagnosis, leading to more accurate decision boundary and improved diagnosis performance. Extensive experiments have been conducted on three medical image classification datasets. Our results suggest that the proposed DNFS achieves superior performance against state-of-the-art approaches.
Collapse
Affiliation(s)
- Yuanyuan Chen
- National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, School of Computer Science and Engineering, Northwestern Polytechnical University, Xi'an 710072, China
| | - Xiaoqing Guo
- Department of Engineering Science, University of Oxford, Oxford, UK
| | - Yongsheng Pan
- National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, School of Computer Science and Engineering, Northwestern Polytechnical University, Xi'an 710072, China
| | - Yong Xia
- National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, School of Computer Science and Engineering, Northwestern Polytechnical University, Xi'an 710072, China.
| | - Yixuan Yuan
- Department of Electronic Engineering, Chinese University of Hong Kong, Hong Kong Special Administrative Region of China; CUHK Shenzhen Research Institute, Shenzhen 518172, China.
| |
Collapse
|
8
|
Ahmad Z, Malik AK, Qamar N, Islam SU. Efficient Thorax Disease Classification and Localization Using DCNN and Chest X-ray Images. Diagnostics (Basel) 2023; 13:3462. [PMID: 37998598 PMCID: PMC10669971 DOI: 10.3390/diagnostics13223462] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/31/2023] [Revised: 11/05/2023] [Accepted: 11/09/2023] [Indexed: 11/25/2023] Open
Abstract
Thorax disease is a life-threatening disease caused by bacterial infections that occur in the lungs. It could be deadly if not treated at the right time, so early diagnosis of thoracic diseases is vital. The suggested study can assist radiologists in more swiftly diagnosing thorax disorders and in the rapid airport screening of patients with a thorax disease, such as pneumonia. This paper focuses on automatically detecting and localizing thorax disease using chest X-ray images. It provides accurate detection and localization using DenseNet-121 which is foundation of our proposed framework, called Z-Net. The proposed framework utilizes the weighted cross-entropy loss function (W-CEL) that manages class imbalance issue in the ChestX-ray14 dataset, which helped in achieving the highest performance as compared to the previous models. The 112,120 images contained in the ChestX-ray14 dataset (60,412 images are normal, and the rest contain thorax diseases) were preprocessed and then trained for classification and localization. This work uses computer-aided diagnosis (CAD) system that supports development of highly accurate and precise computer-aided systems. We aim to develop a CAD system using a deep learning approach. Our quantitative results show high AUC scores in comparison with the latest research works. The proposed approach achieved the highest mean AUC score of 85.8%. This is the highest accuracy documented in the literature for any related model.
Collapse
Affiliation(s)
- Zeeshan Ahmad
- Department of Computer Science, COMSATS University Islamabad, Islamabad 45550, Pakistan;
| | - Ahmad Kamran Malik
- Department of Computer Science, COMSATS University Islamabad, Islamabad 45550, Pakistan;
| | - Nafees Qamar
- School of Health and Behavioral Sciences, Bryant University, Smithfield, RI 02917, USA;
| | - Saif ul Islam
- Department of Computer Science, Institute of Space Technology, Islamabad 44000, Pakistan
| |
Collapse
|
9
|
Dai Y, Qian Y, Lu F, Wang B, Gu Z, Wang W, Wan J, Zhang Y. Improving adversarial robustness of medical imaging systems via adding global attention noise. Comput Biol Med 2023; 164:107251. [PMID: 37480679 DOI: 10.1016/j.compbiomed.2023.107251] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/17/2023] [Revised: 06/14/2023] [Accepted: 07/07/2023] [Indexed: 07/24/2023]
Abstract
Recent studies have found that medical images are vulnerable to adversarial attacks. However, it is difficult to protect medical imaging systems from adversarial examples in that the lesion features of medical images are more complex with high resolution. Therefore, a simple and effective method is needed to address these issues to improve medical imaging systems' robustness. We find that the attackers generate adversarial perturbations corresponding to the lesion characteristics of different medical image datasets, which can shift the model's attention to other places. In this paper, we propose global attention noise (GATN) injection, including global noise in the example layer and attention noise in the feature layers. Global noise enhances the lesion features of the medical images, thus keeping the examples away from the sharp areas where the model is vulnerable. The attention noise further locally smooths the model from small perturbations. According to the characteristic of medical image datasets, we introduce Global attention lesion-unrelated noise (GATN-UR) for datasets with unclear lesion boundaries and Global attention lesion-related noise (GATN-R) for datasets with clear lesion boundaries. Extensive experiments on ChestX-ray, Dermatology, and Fundoscopy datasets show that GATN improves the robustness of medical diagnosis models against a variety of powerful attacks and significantly outperforms the existing adversarial defense methods. To be specific, the robust accuracy is 86.66% on ChestX-ray, 72.49% on Dermatology, and 90.17% on Fundoscopy under PGD attack. Under the AA attack, it achieves robust accuracy of 87.70% on ChestX-ray, 66.85% on Dermatology, and 87.83% on Fundoscopy.
Collapse
Affiliation(s)
- Yinyao Dai
- Zhejiang University of Science and Technology, Hangzhou 310023, China
| | - Yaguan Qian
- Zhejiang University of Science and Technology, Hangzhou 310023, China.
| | - Fang Lu
- Zhejiang University of Science and Technology, Hangzhou 310023, China
| | - Bin Wang
- Zhejiang Key Laboratory of Multidimensional Perception Technology, Application, and Cybersecurity, Hangzhou 310052, China.
| | - Zhaoquan Gu
- School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen 518071, China
| | - Wei Wang
- Beijing Key Laboratory of Security and Privacy in Intelligent Transportation, Beijing Jiaotong University, Beijing 100091, China
| | - Jian Wan
- Zhejiang University of Science and Technology, Hangzhou 310023, China
| | | |
Collapse
|
10
|
Liu Z, Cheng Y, Tamura S. Multi-Label Local to Global Learning: A Novel Learning Paradigm for Chest X-Ray Abnormality Classification. IEEE J Biomed Health Inform 2023; 27:4409-4420. [PMID: 37252867 DOI: 10.1109/jbhi.2023.3281466] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 06/01/2023]
Abstract
Deep neural network (DNN) approaches have shown remarkable progress in automatic Chest X-rays classification. However, existing methods use a training scheme that simultaneously trains all abnormalities without considering their learning priority. Inspired by the clinical practice of radiologists progressively recognizing more abnormalities and the observation that existing curriculum learning (CL) methods based on image difficulty may not be suitable for disease diagnosis, we propose a novel CL paradigm, named multi-label local to global (ML-LGL). This approach iteratively trains DNN models on gradually increasing abnormalities within the dataset, i,e, from fewer abnormalities (local) to more ones (global). At each iteration, we first build the local category by adding high-priority abnormalities for training, and the abnormality's priority is determined by our three proposed clinical knowledge-leveraged selection functions. Then, images containing abnormalities in the local category are gathered to form a new training set. The model is lastly trained on this set using a dynamic loss. Additionally, we demonstrate the superiority of ML-LGL from the perspective of the model's initial stability during training. Experimental results on three open-source datasets, PLCO, ChestX-ray14 and CheXpert show that our proposed learning paradigm outperforms baselines and achieves comparable results to state-of-the-art methods. The improved performance promises potential applications in multi-label Chest X-ray classification.
Collapse
|
11
|
Horry MJ, Chakraborty S, Pradhan B, Paul M, Zhu J, Loh HW, Barua PD, Acharya UR. Development of Debiasing Technique for Lung Nodule Chest X-ray Datasets to Generalize Deep Learning Models. SENSORS (BASEL, SWITZERLAND) 2023; 23:6585. [PMID: 37514877 PMCID: PMC10385599 DOI: 10.3390/s23146585] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/14/2023] [Revised: 07/16/2023] [Accepted: 07/20/2023] [Indexed: 07/30/2023]
Abstract
Screening programs for early lung cancer diagnosis are uncommon, primarily due to the challenge of reaching at-risk patients located in rural areas far from medical facilities. To overcome this obstacle, a comprehensive approach is needed that combines mobility, low cost, speed, accuracy, and privacy. One potential solution lies in combining the chest X-ray imaging mode with federated deep learning, ensuring that no single data source can bias the model adversely. This study presents a pre-processing pipeline designed to debias chest X-ray images, thereby enhancing internal classification and external generalization. The pipeline employs a pruning mechanism to train a deep learning model for nodule detection, utilizing the most informative images from a publicly available lung nodule X-ray dataset. Histogram equalization is used to remove systematic differences in image brightness and contrast. Model training is then performed using combinations of lung field segmentation, close cropping, and rib/bone suppression. The resulting deep learning models, generated through this pre-processing pipeline, demonstrate successful generalization on an independent lung nodule dataset. By eliminating confounding variables in chest X-ray images and suppressing signal noise from the bone structures, the proposed deep learning lung nodule detection algorithm achieves an external generalization accuracy of 89%. This approach paves the way for the development of a low-cost and accessible deep learning-based clinical system for lung cancer screening.
Collapse
Affiliation(s)
- Michael J Horry
- Centre for Advanced Modelling and Geospatial Information Systems (CAMGIS), Faculty of Engineering and Information Technology, University of Technology Sydney, Ultimo, NSW 2007, Australia
- IBM Australia Limited, Sydney, NSW 2000, Australia
| | - Subrata Chakraborty
- Centre for Advanced Modelling and Geospatial Information Systems (CAMGIS), Faculty of Engineering and Information Technology, University of Technology Sydney, Ultimo, NSW 2007, Australia
- Faculty of Science, Agriculture, Business and Law, University of New England, Armidale, NSW 2351, Australia
| | - Biswajeet Pradhan
- Centre for Advanced Modelling and Geospatial Information Systems (CAMGIS), Faculty of Engineering and Information Technology, University of Technology Sydney, Ultimo, NSW 2007, Australia
- Earth Observation Center, Institute of Climate Change, Universiti Kebangsaan Malaysia, Bangi 43600, Malaysia
| | - Manoranjan Paul
- Machine Vision and Digital Health (MaViDH), School of Computing and Mathematics, Charles Sturt University, Bathurst, NSW 2795, Australia
| | - Jing Zhu
- Department of Radiology, Westmead Hospital, Westmead, NSW 2145, Australia
| | - Hui Wen Loh
- School of Science and Technology, Singapore University of Social Sciences, Singapore 599494, Singapore
| | - Prabal Datta Barua
- Centre for Advanced Modelling and Geospatial Information Systems (CAMGIS), Faculty of Engineering and Information Technology, University of Technology Sydney, Ultimo, NSW 2007, Australia
- Faculty of Science, Agriculture, Business and Law, University of New England, Armidale, NSW 2351, Australia
- Cogninet Brain Team, Cogninet Australia, Sydney, NSW 2010, Australia
- School of Business (Information Systems), Faculty of Business, Education, Law & Arts, University of Southern Queensland, Toowoomba, QLD 4350, Australia
| | - U Rajendra Acharya
- School of Mathematics, Physics and Computing, University of Southern Queensland, Springfield, QLD 4300, Australia
| |
Collapse
|
12
|
Sugibayashi T, Walston SL, Matsumoto T, Mitsuyama Y, Miki Y, Ueda D. Deep learning for pneumothorax diagnosis: a systematic review and meta-analysis. Eur Respir Rev 2023; 32:32/168/220259. [PMID: 37286217 DOI: 10.1183/16000617.0259-2022] [Citation(s) in RCA: 9] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/23/2022] [Accepted: 03/16/2023] [Indexed: 06/09/2023] Open
Abstract
BACKGROUND Deep learning (DL), a subset of artificial intelligence (AI), has been applied to pneumothorax diagnosis to aid physician diagnosis, but no meta-analysis has been performed. METHODS A search of multiple electronic databases through September 2022 was performed to identify studies that applied DL for pneumothorax diagnosis using imaging. Meta-analysis via a hierarchical model to calculate the summary area under the curve (AUC) and pooled sensitivity and specificity for both DL and physicians was performed. Risk of bias was assessed using a modified Prediction Model Study Risk of Bias Assessment Tool. RESULTS In 56 of the 63 primary studies, pneumothorax was identified from chest radiography. The total AUC was 0.97 (95% CI 0.96-0.98) for both DL and physicians. The total pooled sensitivity was 84% (95% CI 79-89%) for DL and 85% (95% CI 73-92%) for physicians and the pooled specificity was 96% (95% CI 94-98%) for DL and 98% (95% CI 95-99%) for physicians. More than half of the original studies (57%) had a high risk of bias. CONCLUSIONS Our review found the diagnostic performance of DL models was similar to that of physicians, although the majority of studies had a high risk of bias. Further pneumothorax AI research is needed.
Collapse
Affiliation(s)
- Takahiro Sugibayashi
- Department of Diagnostic and Interventional Radiology, Graduate School of Medicine, Osaka Metropolitan University, Osaka, Japan
| | - Shannon L Walston
- Department of Diagnostic and Interventional Radiology, Graduate School of Medicine, Osaka Metropolitan University, Osaka, Japan
| | - Toshimasa Matsumoto
- Department of Diagnostic and Interventional Radiology, Graduate School of Medicine, Osaka Metropolitan University, Osaka, Japan
- Smart Life Science Lab, Center for Health Science Innovation, Osaka Metropolitan University, Osaka, Japan
| | - Yasuhito Mitsuyama
- Department of Diagnostic and Interventional Radiology, Graduate School of Medicine, Osaka Metropolitan University, Osaka, Japan
| | - Yukio Miki
- Department of Diagnostic and Interventional Radiology, Graduate School of Medicine, Osaka Metropolitan University, Osaka, Japan
| | - Daiju Ueda
- Department of Diagnostic and Interventional Radiology, Graduate School of Medicine, Osaka Metropolitan University, Osaka, Japan
- Smart Life Science Lab, Center for Health Science Innovation, Osaka Metropolitan University, Osaka, Japan
| |
Collapse
|
13
|
Li Q, Chen M, Geng J, Adamu MJ, Guan X. High-Resolution Network with Dynamic Convolution and Coordinate Attention for Classification of Chest X-ray Images. Diagnostics (Basel) 2023; 13:2165. [PMID: 37443559 DOI: 10.3390/diagnostics13132165] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/09/2023] [Revised: 06/12/2023] [Accepted: 06/21/2023] [Indexed: 07/15/2023] Open
Abstract
The development of automatic chest X-ray (CXR) disease classification algorithms is significant for diagnosing thoracic diseases. Owing to the characteristics of lesions in CXR images, including high similarity in appearance of the disease, varied sizes, and different occurrence locations, most existing convolutional neural network-based methods have insufficient feature extraction for thoracic lesions and struggle to adapt to changes in lesion size and location. To address these issues, this study proposes a high-resolution classification network with dynamic convolution and coordinate attention (HRCC-Net). In the method, this study suggests a parallel multi-resolution network in which a high-resolution branch acquires essential detailed features of the lesion and multi-resolution feature swapping and fusion to obtain multiple receptive fields to extract complicated disease features adequately. Furthermore, this study proposes dynamic convolution to enhance the network's ability to represent multi-scale information to accommodate lesions of diverse scales. In addition, this study introduces a coordinate attention mechanism, which enables automatic focus on pathologically relevant regions and capturing the variations in lesion location. The proposed method is evaluated on ChestX-ray14 and CheXpert datasets. The average AUC (area under ROC curve) values reach 0.845 and 0.913, respectively, indicating this method's advantages compared with the currently available methods. Meanwhile, with its specificity and sensitivity to measure the performance of medical diagnostic systems, the network can improve diagnostic efficiency while reducing the rate of misdiagnosis. The proposed algorithm has great potential for thoracic disease diagnosis and treatment.
Collapse
Affiliation(s)
- Qiang Li
- School of Microelectronics, Tianjin University, Tianjin 300072, China
| | - Mingyu Chen
- School of Microelectronics, Tianjin University, Tianjin 300072, China
| | - Jingjing Geng
- School of Microelectronics, Tianjin University, Tianjin 300072, China
| | | | - Xin Guan
- School of Microelectronics, Tianjin University, Tianjin 300072, China
| |
Collapse
|
14
|
Tsuji T, Hirata Y, Kusunose K, Sata M, Kumagai S, Shiraishi K, Kotoku J. Classification of chest X-ray images by incorporation of medical domain knowledge into operation branch networks. BMC Med Imaging 2023; 23:62. [PMID: 37161392 PMCID: PMC10169130 DOI: 10.1186/s12880-023-01019-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/23/2022] [Accepted: 05/02/2023] [Indexed: 05/11/2023] Open
Abstract
BACKGROUND This study was conducted to alleviate a common difficulty in chest X-ray image diagnosis: The attention region in a convolutional neural network (CNN) does not often match the doctor's point of focus. The method presented herein, which guides the area of attention in CNN to a medically plausible region, can thereby improve diagnostic capabilities. METHODS The model is based on an attention branch network, which has excellent interpretability of the classification model. This model has an additional new operation branch that guides the attention region to the lung field and heart in chest X-ray images. We also used three chest X-ray image datasets (Teikyo, Tokushima, and ChestX-ray14) to evaluate the CNN attention area of interest in these fields. Additionally, after devising a quantitative method of evaluating improvement of a CNN's region of interest, we applied it to evaluation of the proposed model. RESULTS Operation branch networks maintain or improve the area under the curve to a greater degree than conventional CNNs do. Furthermore, the network better emphasizes reasonable anatomical parts in chest X-ray images. CONCLUSIONS The proposed network better emphasizes the reasonable anatomical parts in chest X-ray images. This method can enhance capabilities for image interpretation based on judgment.
Collapse
Affiliation(s)
- Takumasa Tsuji
- Graduate School of Medical Care and Technology, Teikyo University, 2-11-1 Kaga, Itabashi-Ku, Tokyo, 173-8605, Japan
| | - Yukina Hirata
- Ultrasound Examination Center, Tokushima University Hospital, 2-50-1, Kuramoto, Tokushima, Japan
| | - Kenya Kusunose
- Department of Cardiovascular Medicine, Tokushima University Hospital, 2-50-1, Kuramoto, Tokushima, Japan
| | - Masataka Sata
- Department of Cardiovascular Medicine, Tokushima University Hospital, 2-50-1, Kuramoto, Tokushima, Japan
| | - Shinobu Kumagai
- Central Radiology Division, Teikyo University Hospital, 2-11-1 Kaga, Itabashi-Ku, Tokyo, 173-8606, Japan
| | - Kenshiro Shiraishi
- Department of Radiology, Teikyo University School of Medicine, 2-11-1 Kaga, Itabashi-Ku, Tokyo, 173-8605, Japan
| | - Jun'ichi Kotoku
- Graduate School of Medical Care and Technology, Teikyo University, 2-11-1 Kaga, Itabashi-Ku, Tokyo, 173-8605, Japan.
- Central Radiology Division, Teikyo University Hospital, 2-11-1 Kaga, Itabashi-Ku, Tokyo, 173-8606, Japan.
| |
Collapse
|
15
|
Wang X, Cheng L, Zhang D, Liu Z, Jiang L. Broad learning solution for rapid diagnosis of COVID-19. Biomed Signal Process Control 2023; 83:104724. [PMID: 36811035 PMCID: PMC9935280 DOI: 10.1016/j.bspc.2023.104724] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/08/2022] [Revised: 01/27/2023] [Accepted: 02/14/2023] [Indexed: 02/19/2023]
Abstract
COVID-19 has put all of humanity in a health dilemma as it spreads rapidly. For many infectious diseases, the delay of detection results leads to the spread of infection and an increase in healthcare costs. COVID-19 diagnostic methods rely on a large number of redundant labeled data and time-consuming data training processes to obtain satisfactory results. However, as a new epidemic, obtaining large clinical datasets is still challenging, which will inhibit the training of deep models. And a model that can really rapidly diagnose COVID-19 at all stages of the model has still not been proposed. To address these limitations, we combine feature attention and broad learning to propose a diagnostic system (FA-BLS) for COVID-19 pulmonary infection, which introduces a broad learning structure to address the slow diagnosis speed of existing deep learning methods. In our network, transfer learning is performed with ResNet50 convolutional modules with fixed weights to extract image features, and the attention mechanism is used to enhance feature representation. After that, feature nodes and enhancement nodes are generated by broad learning with random weights to adaptly select features for diagnosis. Finally, three publicly accessible datasets were used to evaluate our optimization model. It was determined that the FA-BLS model had a 26-130 times faster training speed than deep learning with a similar level of accuracy, which can achieve a fast and accurate diagnosis, achieve effective isolation from COVID-19 and the proposed method also opens up a new method for other types of chest CT image recognition problems.
Collapse
Affiliation(s)
- Xiaowei Wang
- School of Physical Science and Technology, Shenyang Normal University, Shenyang, 110034, China
| | - Liying Cheng
- School of Physical Science and Technology, Shenyang Normal University, Shenyang, 110034, China
| | - Dan Zhang
- Navigation College, Dalian Maritime University, Dalian, 116026, China
| | - Zuchen Liu
- School of Physical Science and Technology, Shenyang Normal University, Shenyang, 110034, China
| | - Longtao Jiang
- School of Physical Science and Technology, Shenyang Normal University, Shenyang, 110034, China
| |
Collapse
|
16
|
Wu J, Xia Y, Wang X, Wei Y, Liu A, Innanje A, Zheng M, Chen L, Shi J, Wang L, Zhan Y, Zhou XS, Xue Z, Shi F, Shen D. uRP: An integrated research platform for one-stop analysis of medical images. FRONTIERS IN RADIOLOGY 2023; 3:1153784. [PMID: 37492386 PMCID: PMC10365282 DOI: 10.3389/fradi.2023.1153784] [Citation(s) in RCA: 17] [Impact Index Per Article: 17.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 01/30/2023] [Accepted: 03/31/2023] [Indexed: 07/27/2023]
Abstract
Introduction Medical image analysis is of tremendous importance in serving clinical diagnosis, treatment planning, as well as prognosis assessment. However, the image analysis process usually involves multiple modality-specific software and relies on rigorous manual operations, which is time-consuming and potentially low reproducible. Methods We present an integrated platform - uAI Research Portal (uRP), to achieve one-stop analyses of multimodal images such as CT, MRI, and PET for clinical research applications. The proposed uRP adopts a modularized architecture to be multifunctional, extensible, and customizable. Results and Discussion The uRP shows 3 advantages, as it 1) spans a wealth of algorithms for image processing including semi-automatic delineation, automatic segmentation, registration, classification, quantitative analysis, and image visualization, to realize a one-stop analytic pipeline, 2) integrates a variety of functional modules, which can be directly applied, combined, or customized for specific application domains, such as brain, pneumonia, and knee joint analyses, 3) enables full-stack analysis of one disease, including diagnosis, treatment planning, and prognosis assessment, as well as full-spectrum coverage for multiple disease applications. With the continuous development and inclusion of advanced algorithms, we expect this platform to largely simplify the clinical scientific research process and promote more and better discoveries.
Collapse
Affiliation(s)
- Jiaojiao Wu
- Department of Research and Development, Shanghai United Imaging Intelligence Co., Ltd., Shanghai, China
| | - Yuwei Xia
- Department of Research and Development, Shanghai United Imaging Intelligence Co., Ltd., Shanghai, China
| | - Xuechun Wang
- Department of Research and Development, Shanghai United Imaging Intelligence Co., Ltd., Shanghai, China
| | - Ying Wei
- Department of Research and Development, Shanghai United Imaging Intelligence Co., Ltd., Shanghai, China
| | - Aie Liu
- Department of Research and Development, Shanghai United Imaging Intelligence Co., Ltd., Shanghai, China
| | - Arun Innanje
- Department of Research and Development, United Imaging Intelligence Co., Ltd., Cambridge, MA, United States
| | - Meng Zheng
- Department of Research and Development, United Imaging Intelligence Co., Ltd., Cambridge, MA, United States
| | - Lei Chen
- Department of Research and Development, Shanghai United Imaging Intelligence Co., Ltd., Shanghai, China
| | - Jing Shi
- Department of Research and Development, Shanghai United Imaging Intelligence Co., Ltd., Shanghai, China
| | - Liye Wang
- Department of Research and Development, Shanghai United Imaging Intelligence Co., Ltd., Shanghai, China
| | - Yiqiang Zhan
- Department of Research and Development, Shanghai United Imaging Intelligence Co., Ltd., Shanghai, China
| | - Xiang Sean Zhou
- Department of Research and Development, Shanghai United Imaging Intelligence Co., Ltd., Shanghai, China
| | - Zhong Xue
- Department of Research and Development, Shanghai United Imaging Intelligence Co., Ltd., Shanghai, China
| | - Feng Shi
- Department of Research and Development, Shanghai United Imaging Intelligence Co., Ltd., Shanghai, China
| | - Dinggang Shen
- Department of Research and Development, Shanghai United Imaging Intelligence Co., Ltd., Shanghai, China
- School of Biomedical Engineering, ShanghaiTech University, Shanghai, China
- Shanghai Clinical Research and Trial Center, Shanghai, China
| |
Collapse
|
17
|
You H, Yu L, Tian S, Cai W. A stereo spatial decoupling network for medical image classification. COMPLEX INTELL SYST 2023; 9:1-10. [PMID: 37361963 PMCID: PMC10107597 DOI: 10.1007/s40747-023-01049-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/01/2022] [Accepted: 03/09/2023] [Indexed: 06/28/2023]
Abstract
Deep convolutional neural network (CNN) has made great progress in medical image classification. However, it is difficult to establish effective spatial associations, and always extracts similar low-level features, resulting in redundancy of information. To solve these limitations, we propose a stereo spatial discoupling network (TSDNets), which can leverage the multi-dimensional spatial details of medical images. Then, we use an attention mechanism to progressively extract the most discriminative features from three directions: horizontal, vertical, and depth. Moreover, a cross feature screening strategy is used to divide the original feature maps into three levels: important, secondary and redundant. Specifically, we design a cross feature screening module (CFSM) and a semantic guided decoupling module (SGDM) to model multi-dimension spatial relationships, thereby enhancing the feature representation capabilities. The extensive experiments conducted on multiple open source baseline datasets demonstrate that our TSDNets outperforms previous state-of-the-art models.
Collapse
Affiliation(s)
- Hongfeng You
- School of Information Science and Engineering, Xinjiang University, Urumqi, 830000 China
| | - Long Yu
- Network Center, Xinjiang University, Urumqi, 830000 China
| | - Shengwei Tian
- Software College, Xinjiang University, Urumqi, 830000 China
| | - Weiwei Cai
- School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, 214122 China
| |
Collapse
|
18
|
Rehman A, Khan A, Fatima G, Naz S, Razzak I. Review on chest pathogies detection systems using deep learning techniques. Artif Intell Rev 2023; 56:1-47. [PMID: 37362896 PMCID: PMC10027283 DOI: 10.1007/s10462-023-10457-9] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/29/2023]
Abstract
Chest radiography is the standard and most affordable way to diagnose, analyze, and examine different thoracic and chest diseases. Typically, the radiograph is examined by an expert radiologist or physician to decide about a particular anomaly, if exists. Moreover, computer-aided methods are used to assist radiologists and make the analysis process accurate, fast, and more automated. A tremendous improvement in automatic chest pathologies detection and analysis can be observed with the emergence of deep learning. The survey aims to review, technically evaluate, and synthesize the different computer-aided chest pathologies detection systems. The state-of-the-art of single and multi-pathologies detection systems, which are published in the last five years, are thoroughly discussed. The taxonomy of image acquisition, dataset preprocessing, feature extraction, and deep learning models are presented. The mathematical concepts related to feature extraction model architectures are discussed. Moreover, the different articles are compared based on their contributions, datasets, methods used, and the results achieved. The article ends with the main findings, current trends, challenges, and future recommendations.
Collapse
Affiliation(s)
- Arshia Rehman
- COMSATS University Islamabad, Abbottabad-Campus, Abbottabad, Pakistan
| | - Ahmad Khan
- COMSATS University Islamabad, Abbottabad-Campus, Abbottabad, Pakistan
| | - Gohar Fatima
- The Islamia University of Bahawalpur, Bahawal Nagar Campus, Bahawal Nagar, Pakistan
| | - Saeeda Naz
- Govt Girls Post Graduate College No.1, Abbottabad, Pakistan
| | - Imran Razzak
- School of Computer Science and Engineering, University of New South Wales, Sydney, Australia
| |
Collapse
|
19
|
Mao N, Zhang H, Dai Y, Li Q, Lin F, Gao J, Zheng T, Zhao F, Xie H, Xu C, Ma H. Attention-based deep learning for breast lesions classification on contrast enhanced spectral mammography: a multicentre study. Br J Cancer 2023; 128:793-804. [PMID: 36522478 PMCID: PMC9977865 DOI: 10.1038/s41416-022-02092-y] [Citation(s) in RCA: 9] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/01/2022] [Revised: 11/21/2022] [Accepted: 11/24/2022] [Indexed: 12/23/2022] Open
Abstract
BACKGROUND This study aims to develop an attention-based deep learning model for distinguishing benign from malignant breast lesions on CESM. METHODS Preoperative CESM images of 1239 patients, which were definitely diagnosed on pathology in a multicentre cohort, were divided into training and validation sets, internal and external test sets. The regions of interest of the breast lesions were outlined manually by a senior radiologist. We adopted three conventional convolutional neural networks (CNNs), namely, DenseNet 121, Xception, and ResNet 50, as the backbone architectures and incorporated the convolutional block attention module (CBAM) into them for classification. The performance of the models was analysed in terms of the receiver operating characteristic (ROC) curve, accuracy, the positive predictive value (PPV), the negative predictive value (NPV), the F1 score, the precision recall curve (PRC), and heat maps. The final models were compared with the diagnostic performance of conventional CNNs, radiomics models, and two radiologists with specialised breast imaging experience. RESULTS The best-performing deep learning model, that is, the CBAM-based Xception, achieved an area under the ROC curve (AUC) of 0.970, a sensitivity of 0.848, a specificity of 1.000, and an accuracy of 0.891 on the external test set, which was higher than those of other CNNs, radiomics models, and radiologists. The PRC and the heat maps also indicated the favourable predictive performance of the attention-based CNN model. The diagnostic performance of two radiologists improved with deep learning assistance. CONCLUSIONS Using an attention-based deep learning model based on CESM images can help to distinguishing benign from malignant breast lesions, and the diagnostic performance of radiologists improved with deep learning assistance.
Collapse
Affiliation(s)
- Ning Mao
- Department of Radiology, Yantai Yuhuangding Hospital, Qingdao University, 264000, Yantai, Shandong, P. R. China
- Big Data and Artificial Intelligence Laboratory, Yantai Yuhuangding Hospital, Qingdao University, 264000, Yantai, Shandong, P. R. China
| | - Haicheng Zhang
- Big Data and Artificial Intelligence Laboratory, Yantai Yuhuangding Hospital, Qingdao University, 264000, Yantai, Shandong, P. R. China
| | - Yi Dai
- Department of Radiology, Peking University Shenzhen Hospital, 518000, Shenzhen, P. R. China
| | - Qin Li
- Department of Radiology, Fudan University Cancer Center, 200433, Shanghai, P. R. China
| | - Fan Lin
- Department of Radiology, Yantai Yuhuangding Hospital, Qingdao University, 264000, Yantai, Shandong, P. R. China
| | - Jing Gao
- Department of Radiology, Yantai Yuhuangding Hospital, Qingdao University, 264000, Yantai, Shandong, P. R. China
| | - Tiantian Zheng
- Department of Radiology, Yantai Yuhuangding Hospital, Qingdao University, 264000, Yantai, Shandong, P. R. China
| | - Feng Zhao
- School of Computer Science and Technology, Shandong Technology and Business University, 264005, Yantai, Shandong, P. R. China
| | - Haizhu Xie
- Department of Radiology, Yantai Yuhuangding Hospital, Qingdao University, 264000, Yantai, Shandong, P. R. China
| | - Cong Xu
- Physical Examination Center, Yantai Yuhuangding Hospital, Qingdao University, 264000, Yantai, Shandong, P. R. China.
| | - Heng Ma
- Department of Radiology, Yantai Yuhuangding Hospital, Qingdao University, 264000, Yantai, Shandong, P. R. China.
| |
Collapse
|
20
|
Domain-ensemble learning with cross-domain mixup for thoracic disease classification in unseen domains. Biomed Signal Process Control 2023. [DOI: 10.1016/j.bspc.2022.104488] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/15/2022]
|
21
|
Ahmad HK, Milne MR, Buchlak QD, Ektas N, Sanderson G, Chamtie H, Karunasena S, Chiang J, Holt X, Tang CHM, Seah JCY, Bottrell G, Esmaili N, Brotchie P, Jones C. Machine Learning Augmented Interpretation of Chest X-rays: A Systematic Review. Diagnostics (Basel) 2023; 13:diagnostics13040743. [PMID: 36832231 PMCID: PMC9955112 DOI: 10.3390/diagnostics13040743] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/19/2023] [Revised: 02/13/2023] [Accepted: 02/14/2023] [Indexed: 02/18/2023] Open
Abstract
Limitations of the chest X-ray (CXR) have resulted in attempts to create machine learning systems to assist clinicians and improve interpretation accuracy. An understanding of the capabilities and limitations of modern machine learning systems is necessary for clinicians as these tools begin to permeate practice. This systematic review aimed to provide an overview of machine learning applications designed to facilitate CXR interpretation. A systematic search strategy was executed to identify research into machine learning algorithms capable of detecting >2 radiographic findings on CXRs published between January 2020 and September 2022. Model details and study characteristics, including risk of bias and quality, were summarized. Initially, 2248 articles were retrieved, with 46 included in the final review. Published models demonstrated strong standalone performance and were typically as accurate, or more accurate, than radiologists or non-radiologist clinicians. Multiple studies demonstrated an improvement in the clinical finding classification performance of clinicians when models acted as a diagnostic assistance device. Device performance was compared with that of clinicians in 30% of studies, while effects on clinical perception and diagnosis were evaluated in 19%. Only one study was prospectively run. On average, 128,662 images were used to train and validate models. Most classified less than eight clinical findings, while the three most comprehensive models classified 54, 72, and 124 findings. This review suggests that machine learning devices designed to facilitate CXR interpretation perform strongly, improve the detection performance of clinicians, and improve the efficiency of radiology workflow. Several limitations were identified, and clinician involvement and expertise will be key to driving the safe implementation of quality CXR machine learning systems.
Collapse
Affiliation(s)
- Hassan K. Ahmad
- Annalise.ai, Sydney, NSW 2000, Australia
- Department of Emergency Medicine, Royal North Shore Hospital, Sydney, NSW 2065, Australia
- Correspondence:
| | | | - Quinlan D. Buchlak
- Annalise.ai, Sydney, NSW 2000, Australia
- School of Medicine, University of Notre Dame Australia, Sydney, NSW 2007, Australia
- Department of Neurosurgery, Monash Health, Melbourne, VIC 3168, Australia
| | | | | | | | | | - Jason Chiang
- Annalise.ai, Sydney, NSW 2000, Australia
- Department of General Practice, University of Melbourne, Melbourne, VIC 3010, Australia
- Westmead Applied Research Centre, University of Sydney, Sydney, NSW 2006, Australia
| | | | | | - Jarrel C. Y. Seah
- Annalise.ai, Sydney, NSW 2000, Australia
- Department of Radiology, Alfred Health, Melbourne, VIC 3004, Australia
| | | | - Nazanin Esmaili
- School of Medicine, University of Notre Dame Australia, Sydney, NSW 2007, Australia
- Faculty of Engineering and Information Technology, University of Technology Sydney, Sydney, NSW 2007, Australia
| | - Peter Brotchie
- Annalise.ai, Sydney, NSW 2000, Australia
- Department of Radiology, St Vincent’s Health Australia, Melbourne, VIC 3065, Australia
| | - Catherine Jones
- Annalise.ai, Sydney, NSW 2000, Australia
- I-MED Radiology Network, Brisbane, QLD 4006, Australia
- School of Public and Preventive Health, Monash University, Clayton, VIC 3800, Australia
- Department of Clinical Imaging Science, University of Sydney, Sydney, NSW 2006, Australia
| |
Collapse
|
22
|
Ibragimov B, Arzamasov K, Maksudov B, Kiselev S, Mongolin A, Mustafaev T, Ibragimova D, Evteeva K, Andreychenko A, Morozov S. A 178-clinical-center experiment of integrating AI solutions for lung pathology diagnosis. Sci Rep 2023; 13:1135. [PMID: 36670118 PMCID: PMC9859802 DOI: 10.1038/s41598-023-27397-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/02/2021] [Accepted: 01/02/2023] [Indexed: 01/22/2023] Open
Abstract
In 2020, an experiment testing AI solutions for lung X-ray analysis on a multi-hospital network was conducted. The multi-hospital network linked 178 Moscow state healthcare centers, where all chest X-rays from the network were redirected to a research facility, analyzed with AI, and returned to the centers. The experiment was formulated as a public competition with monetary awards for participating industrial and research teams. The task was to perform the binary detection of abnormalities from chest X-rays. For the objective real-life evaluation, no training X-rays were provided to the participants. This paper presents one of the top-performing AI frameworks from this experiment. First, the framework used two EfficientNets, histograms of gradients, Haar feature ensembles, and local binary patterns to recognize whether an input image represents an acceptable lung X-ray sample, meaning the X-ray is not grayscale inverted, is a frontal chest X-ray, and completely captures both lung fields. Second, the framework extracted the region with lung fields and then passed them to a multi-head DenseNet, where the heads recognized the patient's gender, age and the potential presence of abnormalities, and generated the heatmap with the abnormality regions highlighted. During one month of the experiment from 11.23.2020 to 12.25.2020, 17,888 cases have been analyzed by the framework with 11,902 cases having radiological reports with the reference diagnoses that were unequivocally parsed by the experiment organizers. The performance measured in terms of the area under receiving operator curve (AUC) was 0.77. The AUC for individual diseases ranged from 0.55 for herniation to 0.90 for pneumothorax.
Collapse
Affiliation(s)
- Bulat Ibragimov
- Department of Computer Science, University of Copenhagen, Copenhagen, Denmark.
| | - Kirill Arzamasov
- Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies of the Moscow Healthcare Department, Moscow, Russia
| | - Bulat Maksudov
- School of Electronic Engineering, Dublin City University, Dublin, Ireland
| | | | - Alexander Mongolin
- Innopolis University, Innopolis, Russia
- Nova Information Management School, Universidade Nova de Lisboa, Lisbon, Portugal
| | - Tamerlan Mustafaev
- Innopolis University, Innopolis, Russia
- University Clinic Kazan State University, Kazan, Russia
| | | | - Ksenia Evteeva
- Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies of the Moscow Healthcare Department, Moscow, Russia
| | - Anna Andreychenko
- Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies of the Moscow Healthcare Department, Moscow, Russia
| | - Sergey Morozov
- Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies of the Moscow Healthcare Department, Moscow, Russia
- Osimis SA, Liege, Belgium
| |
Collapse
|
23
|
Chaddad A, Peng J, Xu J, Bouridane A. Survey of Explainable AI Techniques in Healthcare. SENSORS (BASEL, SWITZERLAND) 2023; 23:s23020634. [PMID: 36679430 PMCID: PMC9862413 DOI: 10.3390/s23020634] [Citation(s) in RCA: 33] [Impact Index Per Article: 33.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/07/2022] [Revised: 12/14/2022] [Accepted: 12/29/2022] [Indexed: 05/27/2023]
Abstract
Artificial intelligence (AI) with deep learning models has been widely applied in numerous domains, including medical imaging and healthcare tasks. In the medical field, any judgment or decision is fraught with risk. A doctor will carefully judge whether a patient is sick before forming a reasonable explanation based on the patient's symptoms and/or an examination. Therefore, to be a viable and accepted tool, AI needs to mimic human judgment and interpretation skills. Specifically, explainable AI (XAI) aims to explain the information behind the black-box model of deep learning that reveals how the decisions are made. This paper provides a survey of the most recent XAI techniques used in healthcare and related medical imaging applications. We summarize and categorize the XAI types, and highlight the algorithms used to increase interpretability in medical imaging topics. In addition, we focus on the challenging XAI problems in medical applications and provide guidelines to develop better interpretations of deep learning models using XAI concepts in medical image and text analysis. Furthermore, this survey provides future directions to guide developers and researchers for future prospective investigations on clinical topics, particularly on applications with medical imaging.
Collapse
Affiliation(s)
- Ahmad Chaddad
- School of Artificial Intelligence, Guilin University of Electronic Technology, Jinji Road, Guilin 541004, China
- The Laboratory for Imagery Vision and Artificial Intelligence, Ecole de Technologie Superieure, 1100 Rue Notre Dame O, Montreal, QC H3C 1K3, Canada
| | - Jihao Peng
- School of Artificial Intelligence, Guilin University of Electronic Technology, Jinji Road, Guilin 541004, China
| | - Jian Xu
- School of Artificial Intelligence, Guilin University of Electronic Technology, Jinji Road, Guilin 541004, China
| | - Ahmed Bouridane
- Centre for Data Analytics and Cybersecurity, University of Sharjah, Sharjah 27272, United Arab Emirates
| |
Collapse
|
24
|
Pei Y, Mu L, Xu C, Li Q, Sen G, Sun B, Li X, Li X. Learning-based landmark detection in pelvis x-rays with attention mechanism: data from the osteoarthritis initiative. Biomed Phys Eng Express 2023; 9. [PMID: 36070671 DOI: 10.1088/2057-1976/ac8ffa] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/23/2022] [Accepted: 09/07/2022] [Indexed: 01/07/2023]
Abstract
Patients with developmental dysplasia of the hip can have this problem throughout their lifetime. The problem is difficult to detect by radiologists throughout x-ray because of an abrasion of anatomical structures. Thus, the landmarks should be automatically and precisely located. In this paper, we propose an attention mechanism of combining multi-dimension information on the basis of separating spatial dimension. The proposed attention mechanism decouples spatial dimension and forms width-channel dimension and height-channel dimension by 1D pooling operations in the height and width of spatial dimension. Then non-local means operations are performed to capture the correlation between long-range pixels in width-channel dimension, as well as that in height-channel dimension at different resolutions. The proposed attention mechanism modules are inserted into the skipped connections of U-Net to form a novel landmark detection structure. This landmark detection method was trained and evaluated through five-fold cross-validation on an open-source dataset, including 524 pelvis x-ray, each containing eight landmarks in pelvis, and achieved excellent performance compared to other landmark detection models. The average point-to-point errors of U-Net, HR-Net, CE-Net, and the proposed network were 3.5651 mm, 3.6118 mm, 3.3914 mm and 3.1350 mm, respectively. The results indicate that the proposed method has the highest detection accuracy. Furthermore, an open-source pelvis dataset is annotated and released for open research.
Collapse
Affiliation(s)
- Yun Pei
- State Key Laboratory of Integrated Optoelectronics, College of Electronic Science and Engineering, Jilin University, Changchun, 130012, People's Republic of China
| | - Lin Mu
- Department of Radiology, The First Hospital of Jilin University, Changchun, 130021, People's Republic of China
| | - Chuanxin Xu
- School of Electrical Engineering and Computer, Jilin Jianzhu University, Changchun, 130118, People's Republic of China
| | - Qiang Li
- Department of Orthopedics, the Second Hospital of Jilin University, Changchun, 130041, People's Republic of China
| | - Gan Sen
- Department of Medical Engineering and Technology, Xinjiang Medical University, Urumqi, 830011, People's Republic of China
| | - Bin Sun
- Department of Medical Engineering and Technology, Xinjiang Medical University, Urumqi, 830011, People's Republic of China
| | - Xiuying Li
- State Key Laboratory of Integrated Optoelectronics, College of Electronic Science and Engineering, Jilin University, Changchun, 130012, People's Republic of China
| | - Xueyan Li
- State Key Laboratory of Integrated Optoelectronics, College of Electronic Science and Engineering, Jilin University, Changchun, 130012, People's Republic of China.,Peng Cheng Laboratory, Shenzhen, 518000, People's Republic of China
| |
Collapse
|
25
|
Mostafa FA, Elrefaei LA, Fouda MM, Hossam A. A Survey on AI Techniques for Thoracic Diseases Diagnosis Using Medical Images. Diagnostics (Basel) 2022; 12:diagnostics12123034. [PMID: 36553041 PMCID: PMC9777249 DOI: 10.3390/diagnostics12123034] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/10/2022] [Revised: 11/20/2022] [Accepted: 11/22/2022] [Indexed: 12/12/2022] Open
Abstract
Thoracic diseases refer to disorders that affect the lungs, heart, and other parts of the rib cage, such as pneumonia, novel coronavirus disease (COVID-19), tuberculosis, cardiomegaly, and fracture. Millions of people die every year from thoracic diseases. Therefore, early detection of these diseases is essential and can save many lives. Earlier, only highly experienced radiologists examined thoracic diseases, but recent developments in image processing and deep learning techniques are opening the door for the automated detection of these diseases. In this paper, we present a comprehensive review including: types of thoracic diseases; examination types of thoracic images; image pre-processing; models of deep learning applied to the detection of thoracic diseases (e.g., pneumonia, COVID-19, edema, fibrosis, tuberculosis, chronic obstructive pulmonary disease (COPD), and lung cancer); transfer learning background knowledge; ensemble learning; and future initiatives for improving the efficacy of deep learning models in applications that detect thoracic diseases. Through this survey paper, researchers may be able to gain an overall and systematic knowledge of deep learning applications in medical thoracic images. The review investigates a performance comparison of various models and a comparison of various datasets.
Collapse
Affiliation(s)
- Fatma A. Mostafa
- Department of Electrical Engineering, Faculty of Engineering at Shoubra, Benha University, Cairo 11672, Egypt
| | - Lamiaa A. Elrefaei
- Department of Electrical Engineering, Faculty of Engineering at Shoubra, Benha University, Cairo 11672, Egypt
| | - Mostafa M. Fouda
- Department of Electrical and Computer Engineering, College of Science and Engineering, Idaho State University, Pocatello, ID 83209, USA
- Correspondence:
| | - Aya Hossam
- Department of Electrical Engineering, Faculty of Engineering at Shoubra, Benha University, Cairo 11672, Egypt
| |
Collapse
|
26
|
Karri M, Annavarapu CSR, Acharya UR. Explainable multi-module semantic guided attention based network for medical image segmentation. Comput Biol Med 2022; 151:106231. [PMID: 36335811 DOI: 10.1016/j.compbiomed.2022.106231] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/23/2022] [Revised: 10/05/2022] [Accepted: 10/11/2022] [Indexed: 12/27/2022]
Abstract
Automated segmentation of medical images is crucial for disease diagnosis and treatment planning. Medical image segmentation has been improved based on the convolutional neural networks (CNNs) models. Unfortunately, they are still limited by scenarios in which the segmentation objective has large variations in size, boundary, position, and shape. Moreover, current CNNs have low explainability, restricting their use in clinical decisions. In this paper, we involve substantial use of various attentions in a CNN model and present an explainable multi-module semantic guided attention based network (MSGA-Net) for explainable and highly accurate medical image segmentation, which involves considering the most significant spatial regions, boundaries, scales, and channels. Specifically, we present a multi-scale attention module (MSA) to extract the most salient features at various scales from medical images. Then, we propose a semantic region-guided attention mechanism (SRGA) including location attention (LAM), channel-wise attention (CWA), and edge attention (EA) modules to extract the most important spatial, channel-wise, boundary-related features for interested regions. Moreover, we present a sequence of fine-tuning steps with the SRGA module to gradually weight the significance of interesting regions while simultaneously reducing the noise. In this work, we experimented with three different types of medical images such as dermoscopic images (HAM10000 dataset), multi-organ CT images (CHAOS 2019 dataset), and Brain tumor MRI images (BraTS 2020 dataset). Extensive experiments on all types of medical images revealed that our proposed MSGA-Net substantially increased the overall performance of all metrics over the existing models. Moreover, displaying the attention feature maps has more explainability than state-of-the-art models.
Collapse
Affiliation(s)
- Meghana Karri
- Computer Science and Engineering Department, Indian Institute of Technology (ISM), Dhanbad, 826004, Jharkhand, India.
| | | | - U Rajendra Acharya
- Ngee Ann Polytechnic, Department of Electronics and Computer Engineering, 599489, Singapore; Department of Biomedical Engineering, School of science and Technology, SUSS university, Singapore; Department of Biomedical Informatics and Medical Engineering, Asia university, Taichung, Taiwan.
| |
Collapse
|
27
|
Zhu X, Pang S, Zhang X, Huang J, Zhao L, Tang K, Feng Q. PCAN: Pixel-wise classification and attention network for thoracic disease classification and weakly supervised localization. Comput Med Imaging Graph 2022; 102:102137. [PMID: 36308870 DOI: 10.1016/j.compmedimag.2022.102137] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/04/2022] [Revised: 09/23/2022] [Accepted: 10/05/2022] [Indexed: 11/06/2022]
Abstract
Automatic chest X-ray (CXR) disease classification has drawn increasing public attention as CXR is widely used in thoracic disease diagnosis. Existing classification networks typically employ a global average pooling layer to produce the final feature for the subsequent classifier. This limits the classification performance owing to the characteristics of lesions in CXR images, including small relative sizes, varied absolute sizes, and different occurrence locations. In this study, we propose a pixel-wise classification and attention network (PCAN) to simultaneously perform disease classification and weakly supervised localization, which provides interpretability for disease classification. The PCAN comprises a backbone network for extracting mid-level features, a pixel-wise classification branch (pc-branch) for generating pixel-wise diagnoses, and a pixel-wise attention branch (pa-branch) for producing pixel-wise weights. The pc-branch is capable of explicitly detecting small lesions, and the pa-branch is capable of adaptively focusing on different regions when classifying different thoracic diseases. Then, the pixel-wise diagnoses are multiplied with the pixel-wise weights to obtain the disease localization map, which provides the sizes and locations of lesions in a manner of weakly supervised learning. The final image-wise diagnosis is obtained by summing up the disease localization map at the spatial dimension. Comprehensive experiments conducted on the ChestX-ray14 and CheXpert datasets demonstrate the effectiveness of the proposed PCAN, which has great potential for thoracic disease diagnosis and treatment. The source codes are available at https://github.com/fzfs/PCAN.
Collapse
Affiliation(s)
- Xiongfeng Zhu
- School of Biomedical Engineering, Southern Medical University, Guangzhou, 510515, China; Guangdong Provincial Key Laboratory of Medical Image Processing, Southern Medical University, Guangzhou, 510515, China; Guangdong Province Engineering Laboratory for Medical Imaging and Diagnostic Technology, Southern Medical University, Guangzhou, 510515, China.
| | - Shumao Pang
- School of Biomedical Engineering, Southern Medical University, Guangzhou, 510515, China; Guangdong Provincial Key Laboratory of Medical Image Processing, Southern Medical University, Guangzhou, 510515, China; Guangdong Province Engineering Laboratory for Medical Imaging and Diagnostic Technology, Southern Medical University, Guangzhou, 510515, China
| | - Xiaoxuan Zhang
- School of Biomedical Engineering, Southern Medical University, Guangzhou, 510515, China; Guangdong Provincial Key Laboratory of Medical Image Processing, Southern Medical University, Guangzhou, 510515, China; Guangdong Province Engineering Laboratory for Medical Imaging and Diagnostic Technology, Southern Medical University, Guangzhou, 510515, China
| | - Junzhang Huang
- School of Biomedical Engineering, Southern Medical University, Guangzhou, 510515, China; Guangdong Provincial Key Laboratory of Medical Image Processing, Southern Medical University, Guangzhou, 510515, China; Guangdong Province Engineering Laboratory for Medical Imaging and Diagnostic Technology, Southern Medical University, Guangzhou, 510515, China
| | - Lei Zhao
- School of Biomedical Engineering, Southern Medical University, Guangzhou, 510515, China; Guangdong Provincial Key Laboratory of Medical Image Processing, Southern Medical University, Guangzhou, 510515, China; Guangdong Province Engineering Laboratory for Medical Imaging and Diagnostic Technology, Southern Medical University, Guangzhou, 510515, China
| | - Kai Tang
- School of Biomedical Engineering, Southern Medical University, Guangzhou, 510515, China; Guangdong Provincial Key Laboratory of Medical Image Processing, Southern Medical University, Guangzhou, 510515, China; Guangdong Province Engineering Laboratory for Medical Imaging and Diagnostic Technology, Southern Medical University, Guangzhou, 510515, China
| | - Qianjin Feng
- School of Biomedical Engineering, Southern Medical University, Guangzhou, 510515, China; Guangdong Provincial Key Laboratory of Medical Image Processing, Southern Medical University, Guangzhou, 510515, China; Guangdong Province Engineering Laboratory for Medical Imaging and Diagnostic Technology, Southern Medical University, Guangzhou, 510515, China.
| |
Collapse
|
28
|
Fan L, Yang W, Tu W, Zhou X, Zou Q, Zhang H, Feng Y, Liu S. Thoracic Imaging in China: Yesterday, Today, and Tomorrow. J Thorac Imaging 2022; 37:366-373. [PMID: 35980382 PMCID: PMC9592175 DOI: 10.1097/rti.0000000000000670] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/24/2022]
Abstract
Thoracic imaging has been revolutionized through advances in technology and research around the world, and so has China. Thoracic imaging in China has progressed from anatomic observation to quantitative and functional evaluation, from using traditional approaches to using artificial intelligence. This article will review the past, present, and future of thoracic imaging in China, in an attempt to establish new accepted strategies moving forward.
Collapse
Affiliation(s)
- Li Fan
- Second Affiliated Hospital, Naval Medical University
| | - Wenjie Yang
- Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China
| | - Wenting Tu
- Second Affiliated Hospital, Naval Medical University
| | - Xiuxiu Zhou
- Second Affiliated Hospital, Naval Medical University
| | - Qin Zou
- Second Affiliated Hospital, Naval Medical University
| | - Hanxiao Zhang
- Second Affiliated Hospital, Naval Medical University
| | - Yan Feng
- Second Affiliated Hospital, Naval Medical University
| | - Shiyuan Liu
- Second Affiliated Hospital, Naval Medical University
| |
Collapse
|
29
|
Dabass M, Vashisth S, Vig R. MTU: A multi-tasking U-net with hybrid convolutional learning and attention modules for cancer classification and gland Segmentation in Colon Histopathological Images. Comput Biol Med 2022; 150:106095. [PMID: 36179516 DOI: 10.1016/j.compbiomed.2022.106095] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/17/2022] [Revised: 08/31/2022] [Accepted: 09/10/2022] [Indexed: 11/17/2022]
Abstract
A clinically comparable multi-tasking computerized deep U-Net-based model is demonstrated in this paper. It intends to offer clinical gland morphometric information and cancer grade classification to be provided as referential opinions for pathologists in order to abate human errors. It embraces enhanced feature learning capability that aids in extraction of potent multi-scale features; efficacious semantic gap recovery during feature concatenation; and successful interception of resolution-degradation and vanishing gradient problems while performing moderate computations. It is proposed by integrating three unique novel structural components namely Hybrid Convolutional Learning Units in the encoder and decoder, Attention Learning Units in skip connection, and Multi-Scalar Dilated Transitional Unit as the transitional layer in the traditional U-Net architecture. These units are composed of the amalgamated phenomenon of multi-level convolutional learning through conventional, atrous, residual, depth-wise, and point-wise convolutions which are further incorporated with target-specific attention learning and enlarged effectual receptive field size. Also, pre-processing techniques of patch-sampling, augmentation (color and morphological), stain-normalization, etc. are employed to burgeon its generalizability. To build network invariance towards digital variability, exhaustive experiments are conducted using three public datasets (Colorectal Adenocarcinoma Gland (CRAG), Gland Segmentation (GlaS) challenge, and Lung Colon-25000 (LC-25K) dataset)) and then its robustness is verified using an in-house private dataset of Hospital Colon (HosC). For the cancer classification, the proposed model achieved results of Accuracy (CRAG(95%), GlaS(97.5%), LC-25K(99.97%), HosC(99.45%)), Precision (CRAG(0.9678), GlaS(0.9768), LC-25K(1), HosC(1)), F1-score (CRAG(0.968), GlaS(0.977), LC 25K(0.9997), HosC(0.9965)), and Recall (CRAG(0.9677), GlaS(0.9767), LC-25K(0.9994), HosC(0.9931)). For the gland detection and segmentation, the proposed model achieved competitive results of F1-score (CRAG(0.924), GlaS(Test A(0.949), Test B(0.918)), LC-25K(0.916), HosC(0.959)); Object-Dice Index (CRAG(0.959), GlaS(Test A(0.956), Test B(0.909)), LC-25K(0.929), HosC(0.922)), and Object-Hausdorff Distance (CRAG(90.47), GlaS(Test A(23.17), Test B(71.53)), LC-25K(96.28), HosC(85.45)). In addition, the activation mappings for testing the interpretability of the classification decision-making process are reported by utilizing techniques of Local Interpretable Model-Agnostic Explanations, Occlusion Sensitivity, and Gradient-Weighted Class Activation Mappings. This is done to provide further evidence about the model's self-learning capability of the comparable patterns considered relevant by pathologists without any pre-requisite for annotations. These activation mapping visualization outcomes are evaluated by proficient pathologists, and they delivered these images with a class-path validation score of (CRAG(9.31), GlaS(9.25), LC-25K(9.05), and HosC(9.85)). Furthermore, the seg-path validation score of (GlaS (Test A(9.40), Test B(9.25)), CRAG(9.27), LC-25K(9.01), HosC(9.19)) given by multiple pathologists is included for the final segmented outcomes to substantiate the clinical relevance and suitability for facilitation at the clinical level. The proposed model will aid pathologists to formulate an accurate diagnosis by providing a referential opinion during the morphology assessment of histopathology images. It will reduce unintentional human error in cancer diagnosis and consequently will enhance patient survival rate.
Collapse
Affiliation(s)
- Manju Dabass
- EECE Deptt, The NorthCap University, Gurugram, 122017, India.
| | - Sharda Vashisth
- EECE Deptt, The NorthCap University, Gurugram, 122017, India
| | - Rekha Vig
- EECE Deptt, The NorthCap University, Gurugram, 122017, India
| |
Collapse
|
30
|
Development and validation of an abnormality-derived deep-learning diagnostic system for major respiratory diseases. NPJ Digit Med 2022; 5:124. [PMID: 35999467 PMCID: PMC9395860 DOI: 10.1038/s41746-022-00648-z] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/12/2021] [Accepted: 07/04/2022] [Indexed: 01/05/2023] Open
Abstract
Respiratory diseases impose a tremendous global health burden on large patient populations. In this study, we aimed to develop DeepMRDTR, a deep learning-based medical image interpretation system for the diagnosis of major respiratory diseases based on the automated identification of a wide range of radiological abnormalities through computed tomography (CT) and chest X-ray (CXR) from real-world, large-scale datasets. DeepMRDTR comprises four networks (two CT-Nets and two CXR-Nets) that exploit contrastive learning to generate pre-training parameters that are fine-tuned on the retrospective dataset collected from a single institution. The performance of DeepMRDTR was evaluated for abnormality identification and disease diagnosis on data from two different institutions: one was an internal testing dataset from the same institution as the training data and the second was collected from an external institution to evaluate the model generalizability and robustness to an unrelated population dataset. In such a difficult multi-class diagnosis task, our system achieved the average area under the receiver operating characteristic curve (AUC) of 0.856 (95% confidence interval (CI):0.843–0.868) and 0.841 (95%CI:0.832–0.887) for abnormality identification, and 0.900 (95%CI:0.872–0.958) and 0.866 (95%CI:0.832–0.887) for major respiratory diseases’ diagnosis on CT and CXR datasets, respectively. Furthermore, to achieve a clinically actionable diagnosis, we deployed a preliminary version of DeepMRDTR into the clinical workflow, which was performed on par with senior experts in disease diagnosis, with an AUC of 0.890 and a Cohen’s k of 0.746–0.877 at a reasonable timescale; these findings demonstrate the potential to accelerate the medical workflow to facilitate early diagnosis as a triage tool for respiratory diseases which supports improved clinical diagnoses and decision-making.
Collapse
|
31
|
A convolution neural network with multi-level convolutional and attention learning for classification of cancer grades and tissue structures in colon histopathological images. Comput Biol Med 2022; 147:105680. [DOI: 10.1016/j.compbiomed.2022.105680] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/24/2022] [Revised: 05/06/2022] [Accepted: 05/30/2022] [Indexed: 12/15/2022]
|
32
|
Li ZC, Yan J, Zhang S, Liang C, Lv X, Zou Y, Zhang H, Liang D, Zhang Z, Chen Y. Glioma survival prediction from whole-brain MRI without tumor segmentation using deep attention network: a multicenter study. Eur Radiol 2022; 32:5719-5729. [PMID: 35278123 DOI: 10.1007/s00330-022-08640-7] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/29/2021] [Revised: 01/10/2022] [Accepted: 02/02/2022] [Indexed: 12/14/2022]
Abstract
OBJECTIVES To develop and validate a deep learning model for predicting overall survival from whole-brain MRI without tumor segmentation in patients with diffuse gliomas. METHODS In this multicenter retrospective study, two deep learning models were built for survival prediction from MRI, including a DeepRisk model built from whole-brain MRI, and an original ResNet model built from expert-segmented tumor images. Both models were developed using a training dataset (n = 935) and an internal tuning dataset (n = 156) and tested on two external test datasets (n = 194 and 150) and a TCIA dataset (n = 121). C-index, integrated Brier score (IBS), prediction error curves, and calibration curves were used to assess the model performance. RESULTS In total, 1556 patients were enrolled (age, 49.0 ± 13.1 years; 830 male). The DeepRisk score was an independent predictor and can stratify patients in each test dataset into three risk subgroups. The IBS and C-index for DeepRisk were 0.14 and 0.83 in external test dataset 1, 0.15 and 0.80 in external dataset 2, and 0.16 and 0.77 in TCIA dataset, respectively, which were comparable with those for original ResNet. The AUCs at 6, 12, 24, 26, and 48 months for DeepRisk ranged between 0.77 and 0.94. Combining DeepRisk score with clinicomolecular factors resulted in a nomogram with a better calibration and classification accuracy (net reclassification improvement 0.69, p < 0.001) than the clinical nomogram. CONCLUSIONS DeepRisk that obviated the need of tumor segmentation can predict glioma survival from whole-brain MRI and offers incremental prognostic value. KEY POINTS • DeepRisk can predict overall survival directly from whole-brain MRI without tumor segmentation. • DeepRisk achieves comparable accuracy in survival prediction with deep learning model built using expert-segmented tumor images. • DeepRisk has independent and incremental prognostic value over existing clinical parameters and IDH mutation status.
Collapse
Affiliation(s)
- Zhi-Cheng Li
- Institute of Biomedical and Health Engineering, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
- National Innovation Center for Advanced Medical Devices, Shenzhen, China
| | - Jing Yan
- Department of MRI, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China
| | - Shenghai Zhang
- Institute of Biomedical and Health Engineering, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
| | - Chaofeng Liang
- Department of Neurosurgery, The 3rd Affiliated Hospital of Sun Yat-Sen University, Guangzhou, China
| | - Xiaofei Lv
- Department of Medical Imaging, Sun Yat-Sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangzhou, China
| | - Yan Zou
- Department of Radiology, The 3rd Affiliated Hospital of Sun Yat-Sen University, Guangzhou, China
| | - Huailing Zhang
- School of Information Engineering, Guangdong Medical University, Dongguan, China
| | - Dong Liang
- Institute of Biomedical and Health Engineering, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
- National Innovation Center for Advanced Medical Devices, Shenzhen, China
| | - Zhenyu Zhang
- Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University, 1 Jian she Dong Road, Zhengzhou, 450052, Henan, China.
| | - Yinsheng Chen
- Department of Neurosurgery/Neuro-oncology, Sun Yat-Sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, 651 Dongfeng East Road, Guangzhou, 510060, China.
| |
Collapse
|
33
|
Çallı E, Murphy K, Scholten ET, Schalekamp S, van Ginneken B. Explainable emphysema detection on chest radiographs with deep learning. PLoS One 2022; 17:e0267539. [PMID: 35900979 PMCID: PMC9333227 DOI: 10.1371/journal.pone.0267539] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/17/2021] [Accepted: 04/12/2022] [Indexed: 12/02/2022] Open
Abstract
We propose a deep learning system to automatically detect four explainable emphysema signs on frontal and lateral chest radiographs. Frontal and lateral chest radiographs from 3000 studies were retrospectively collected. Two radiologists annotated these with 4 radiological signs of pulmonary emphysema identified from the literature. A patient with ≥2 of these signs present is considered emphysema positive. Using separate deep learning systems for frontal and lateral images we predict the presence of each of the four visual signs and use these to determine emphysema positivity. The ROC and AUC results on a set of 422 held-out cases, labeled by both radiologists, are reported. Comparison with a black-box model which predicts emphysema without the use of explainable visual features is made on the annotations from both radiologists, as well as the subset that they agreed on. DeLong’s test is used to compare with the black-box model ROC and McNemar’s test to compare with radiologist performance. In 422 test cases, emphysema positivity was predicted with AUCs of 0.924 and 0.946 using the reference standard from each radiologist separately. Setting model sensitivity equivalent to that of the second radiologist, our model has a comparable specificity (p = 0.880 and p = 0.143 for each radiologist respectively). Our method is comparable with the black-box model with AUCs of 0.915 (p = 0.407) and 0.935 (p = 0.291), respectively. On the 370 cases where both radiologists agreed (53 positives), our model achieves an AUC of 0.981, again comparable to the black-box model AUC of 0.972 (p = 0.289). Our proposed method can predict emphysema positivity on chest radiographs as well as a radiologist or a comparable black-box method. It additionally produces labels for four visual signs to ensure the explainability of the result. The dataset is publicly available at https://doi.org/10.5281/zenodo.6373392.
Collapse
Affiliation(s)
- Erdi Çallı
- Diagnostic Image Analysis Group, Radboudumc, Nijmegen, The Netherlands
- * E-mail:
| | - Keelin Murphy
- Diagnostic Image Analysis Group, Radboudumc, Nijmegen, The Netherlands
| | - Ernst T. Scholten
- Diagnostic Image Analysis Group, Radboudumc, Nijmegen, The Netherlands
| | - Steven Schalekamp
- Diagnostic Image Analysis Group, Radboudumc, Nijmegen, The Netherlands
| | - Bram van Ginneken
- Diagnostic Image Analysis Group, Radboudumc, Nijmegen, The Netherlands
| |
Collapse
|
34
|
Chandra TB, Singh BK, Jain D. Disease Localization and Severity Assessment in Chest X-Ray Images using Multi-Stage Superpixels Classification. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2022; 222:106947. [PMID: 35749885 PMCID: PMC9403875 DOI: 10.1016/j.cmpb.2022.106947] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/05/2022] [Revised: 05/25/2022] [Accepted: 06/08/2022] [Indexed: 05/13/2023]
Abstract
BACKGROUND AND OBJECTIVES Chest X-ray (CXR) is a non-invasive imaging modality used in the prognosis and management of chronic lung disorders like tuberculosis (TB), pneumonia, coronavirus disease (COVID-19), etc. The radiomic features associated with different disease manifestations assist in detection, localization, and grading the severity of infected lung regions. The majority of the existing computer-aided diagnosis (CAD) system used these features for the classification task, and only a few works have been dedicated to disease-localization and severity scoring. Moreover, the existing deep learning approaches use class activation map and Saliency map, which generate a rough localization. This study aims to generate a compact disease boundary, infection map, and grade the infection severity using proposed multistage superpixel classification-based disease localization and severity assessment framework. METHODS The proposed method uses a simple linear iterative clustering (SLIC) technique to subdivide the lung field into small superpixels. Initially, the different radiomic texture and proposed shape features are extracted and combined to train different benchmark classifiers in a multistage framework. Subsequently, the predicted class labels are used to generate an infection map, mark disease boundary, and grade the infection severity. The performance is evaluated using a publicly available Montgomery dataset and validated using Friedman average ranking and Holm and Nemenyi post-hoc procedures. RESULTS The proposed multistage classification approach achieved accuracy (ACC)= 95.52%, F-Measure (FM)= 95.48%, area under the curve (AUC)= 0.955 for Stage-I and ACC=85.35%, FM=85.20%, AUC=0.853 for Stage-II using calibration dataset and ACC = 93.41%, FM = 95.32%, AUC = 0.936 for Stage-I and ACC = 84.02%, FM = 71.01%, AUC = 0.795 for Stage-II using validation dataset. Also, the model has demonstrated the average Jaccard Index (JI) of 0.82 and Pearson's correlation coefficient (r) of 0.9589. CONCLUSIONS The obtained classification results using calibration and validation dataset confirms the promising performance of the proposed framework. Also, the average JI shows promising potential to localize the disease, and better agreement between radiologist score and predicted severity score (r) confirms the robustness of the method. Finally, the statistical test justified the significance of the obtained results.
Collapse
Affiliation(s)
- Tej Bahadur Chandra
- Department of Computer Applications, National Institute of Technology Raipur, Chhattisgarh, India.
| | - Bikesh Kumar Singh
- Department of Biomedical Engineering, National Institute of Technology Raipur, Chhattisgarh, India
| | - Deepak Jain
- Department of Radiodiagnosis, Pt. Jawahar Lal Nehru Memorial Medical College, Raipur, Chhattisgarh, India
| |
Collapse
|
35
|
Mondal AK. COVID-19 prognosis using limited chest X-ray images. Appl Soft Comput 2022; 122:108867. [PMID: 35494338 PMCID: PMC9035620 DOI: 10.1016/j.asoc.2022.108867] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/09/2021] [Revised: 01/18/2022] [Accepted: 04/09/2022] [Indexed: 01/31/2023]
Abstract
The COrona VIrus Disease 2019 (COVID-19) pandemic is an ongoing global pandemic that has claimed millions of lives till date. Detecting COVID-19 and isolating affected patients at an early stage is crucial to contain its rapid spread. Although accurate, the primary viral test 'Reverse Transcription Polymerase Chain Reaction' (RT-PCR) for COVID-19 diagnosis has an elaborate test kit, and the turnaround time is high. This has motivated the research community to develop CXR based automated COVID-19 diagnostic methodologies. However, COVID-19 being a novel disease, there is no annotated large-scale CXR dataset for this particular disease. To address the issue of limited data, we propose to exploit a large-scale CXR dataset collected in the pre-COVID era and train a deep neural network in a self-supervised fashion to extract CXR specific features. Further, we compute attention maps between the global and the local features of the backbone convolutional network while finetuning using a limited COVID-19 CXR dataset. We empirically demonstrate the effectiveness of the proposed method. We provide a thorough ablation study to understand the effect of each proposed component. Finally, we provide visualizations highlighting the critical patches instrumental to the predictive decision made by our model. These saliency maps are not only a stepping stone towards explainable AI but also aids radiologists in localizing the infected area.
Collapse
|
36
|
Zhang R, Yang F, Luo Y, Liu J, Wang C. Learning Invariant Representation for Unsupervised Domain Adaptive Thorax Disease Classification. Pattern Recognit Lett 2022. [DOI: 10.1016/j.patrec.2022.06.015] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022]
|
37
|
Wei W, Tao H, Chen W, Wu X. Automatic recognition of micronucleus by combining attention mechanism and AlexNet. BMC Med Inform Decis Mak 2022; 22:138. [PMID: 35585543 PMCID: PMC9116712 DOI: 10.1186/s12911-022-01875-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/28/2022] [Accepted: 05/05/2022] [Indexed: 11/19/2022] Open
Abstract
Background Micronucleus (MN) is an abnormal fragment in a human cell caused by disorders in the mechanism regulating chromosome segregation. It can be used as a biomarker for genotoxicity, tumor risk, and tumor malignancy. The in vitro micronucleus assay is a commonly used method to detect micronucleus. However, it is time-consuming and the visual scoring can be inconsistent. Methods To alleviate this issue, we proposed a computer-aided diagnosis method combining convolutional neural networks and visual attention for micronucleus recognition. The backbone of our model is AlexNet without any dense layers and it is pretrained on the ImageNet dataset. Two attention modules are applied to extract cell image features and generate attention maps highlighting the region of interest to improve the interpretability of the network. Given the problems in the data set, we leverage data augmentation and focal loss to alleviate the impact. Results Experiments show that the proposed network yields better performance with fewer parameters. The AP value, F1 value and AUC value reach 0.932, 0.811 and 0.995, respectively. Conclusion In conclusion, the proposed network can effectively recognize micronucleus, and it can play an auxiliary role in clinical diagnosis by doctors.
Collapse
Affiliation(s)
- Weiyi Wei
- College of Computer Science and Engineering, Northwest Normal University, Lanzhou, China
| | - Hong Tao
- College of Computer Science and Engineering, Northwest Normal University, Lanzhou, China.
| | - Wenxia Chen
- College of Computer Science and Engineering, Northwest Normal University, Lanzhou, China
| | - Xiaoqin Wu
- Radiology Department, Gansu Provincial Center For Disease Control And Prevention, Lanzhou, China
| |
Collapse
|
38
|
A Lightweight Attention-Based Network towards Distracted Driving Behavior Recognition. APPLIED SCIENCES-BASEL 2022. [DOI: 10.3390/app12094191] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/12/2023]
Abstract
Distracted driving is currently a global issue causing fatal traffic crashes and injuries. Although deep learning has achieved significant success in various fields, it still faces the trade-off between computation cost and overall accuracy in the field of distracted driving behavior recognition. This paper addresses this problem and proposes a novel lightweight attention-based (LWANet) network for image classification tasks. To reduce the computation cost and trainable parameters, we replace standard convolution layers with depthwise separable convolutions and optimize the classic VGG16 architecture by 98.16% trainable parameters reduction. Inspired by the attention mechanism in cognitive science, a lightweight inverted residual attention module (IRAM) is proposed to simulate human attention, extract more specific features, and improve the overall accuracy. LWANet achieved an accuracy of 99.37% on Statefarm’s dataset and 98.45% on American University in Cairo’s dataset. With only 1.22 M trainable parameters and a model file size of 4.68 MB, the quantitative experimental results demonstrate that the proposed LWANet obtains state-of-the-art overall performance in deep learning-based distracted driving behavior recognition.
Collapse
|
39
|
Song Y, Du X, Zhang Y, Li S. Two-stage segmentation network with feature aggregation and multi-level attention mechanism for multi-modality heart images. Comput Med Imaging Graph 2022; 97:102054. [PMID: 35339724 DOI: 10.1016/j.compmedimag.2022.102054] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/24/2021] [Revised: 12/06/2021] [Accepted: 03/05/2022] [Indexed: 11/17/2022]
Abstract
Accurate segmentation of cardiac substructures in multi-modality heart images is an important prerequisite for the diagnosis and treatment of cardiovascular diseases. However, the segmentation of cardiac images remains a challenging task due to (1) the interference of multiple targets, (2) the imbalance of sample size. Therefore, in this paper, we propose a novel two-stage segmentation network with feature aggregation and multi-level attention mechanism (TSFM-Net) to comprehensively solve these challenges. Firstly, in order to improve the effectiveness of multi-target features, we adopt the encoder-decoder structure as the backbone segmentation framework and design a feature aggregation module (FAM) to realize the multi-level feature representation (Stage1). Secondly, because the segmentation results obtained from Stage1 are limited to the decoding of single scale feature maps, we design a multi-level attention mechanism (MLAM) to assign more attention to the multiple targets, so as to get multi-level attention maps. We fuse these attention maps and concatenate the output of Stage1 to carry out the second segmentation to get the final segmentation result (Stage2). The proposed method has better segmentation performance and balance on 2017 MM-WHS multi-modality whole heart images than the state-of-the-art methods, which demonstrates the feasibility of TSFM-Net for accurate segmentation of heart images.
Collapse
Affiliation(s)
- Yuhui Song
- School of Computer Science and Technology, Anhui University, China
| | - Xiuquan Du
- Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, Anhui University, China; School of Computer Science and Technology, Anhui University, China.
| | - Yanping Zhang
- Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, Anhui University, China; School of Computer Science and Technology, Anhui University, China
| | - Shuo Li
- Department of Medical Imaging, Western University, London, ON N6A 3K7, Canada
| |
Collapse
|
40
|
Broad learning system stacking with multi-scale attention for the diagnosis of gastric intestinal metaplasia. Biomed Signal Process Control 2022. [DOI: 10.1016/j.bspc.2021.103476] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/01/2023]
|
41
|
Luo X, Zhang J, Li Z, Yang R. Diagnosis of ulcerative colitis from endoscopic images based on deep learning. Biomed Signal Process Control 2022. [DOI: 10.1016/j.bspc.2021.103443] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/11/2022]
|
42
|
Efficient Framework for Detecting COVID-19 and Pneumonia from Chest X-Ray Using Deep Convolutional Network. EGYPTIAN INFORMATICS JOURNAL 2022. [PMCID: PMC8806137 DOI: 10.1016/j.eij.2022.01.002] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Indexed: 12/01/2022]
Abstract
Recently, the COVID-19 pandemic is considered the most severe infectious disease because of its rapid spreading. Radiologists still lack sufficient knowledge and experience for accurate and fast detecting COVID-19. What exacerbates things is the significant overlap between Pneumonia symptoms and COVID-19, which confuses the radiologists. It’s widely agreed that the early detection of the infected patient increases his likelihood of recovery. Chest X-ray images are considered the cheapest radiology images, and their devices are available widely. This study introduces an effective Deep Convolutional Neural Network (DCNN) called “DeepChest” for fast and accurate detection for both COVID-19 and Pneumonia in chest X-ray images. “DeepChest” runs with a small number of convolutional layers, a small number of max-pooling layers, and a small number of training iterations compared with the recent approaches and the state-of-the-art of DCNN. We conducted the experimental evaluations of the proposed approach on a data set with 7512 chest X-ray images. The proposed approach achieves an accuracy of 96.56% overall, 99.40% in detecting COVID-19, and 99.32% in detecting Pneumonia. In actual practice, the presented approach can be used as a computer-aided diagnosis tool to get accurate results in detecting Pneumonia and COVID-19 in chest X-ray images.
Collapse
|
43
|
Zhao J, Zhou X, Shi G, Xiao N, Song K, Zhao J, Hao R, Li K. Semantic consistency generative adversarial network for cross-modality domain adaptation in ultrasound thyroid nodule classification. APPL INTELL 2022; 52:10369-10383. [PMID: 35039715 PMCID: PMC8754560 DOI: 10.1007/s10489-021-03025-7] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 11/18/2021] [Indexed: 12/22/2022]
Abstract
Deep convolutional networks have been widely used for various medical image processing tasks. However, the performance of existing learning-based networks is still limited due to the lack of large training datasets. When a general deep model is directly deployed to a new dataset with heterogeneous features, the effect of domain shifts is usually ignored, and performance degradation problems occur. In this work, by designing the semantic consistency generative adversarial network (SCGAN), we propose a new multimodal domain adaptation method for medical image diagnosis. SCGAN performs cross-domain collaborative alignment of ultrasound images and domain knowledge. Specifically, we utilize a self-attention mechanism for adversarial learning between dual domains to overcome visual differences across modal data and preserve the domain invariance of the extracted semantic features. In particular, we embed nested metric learning in the semantic information space, thus enhancing the semantic consistency of cross-modal features. Furthermore, the adversarial learning of our network is guided by a discrepancy loss for encouraging the learning of semantic-level content and a regularization term for enhancing network generalization. We evaluate our method on a thyroid ultrasound image dataset for benign and malignant diagnosis of nodules. The experimental results of a comprehensive study show that the accuracy of the SCGAN method for the classification of thyroid nodules reaches 94.30%, and the AUC reaches 97.02%. These results are significantly better than the state-of-the-art methods.
Collapse
|
44
|
Wong PK, Yan T, Wang H, Chan IN, Wang J, Li Y, Ren H, Wong CH. Automatic detection of multiple types of pneumonia: Open dataset and a multi-scale attention network. Biomed Signal Process Control 2021; 73:103415. [PMID: 34909050 PMCID: PMC8660060 DOI: 10.1016/j.bspc.2021.103415] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/11/2021] [Revised: 10/31/2021] [Accepted: 11/28/2021] [Indexed: 12/13/2022]
Abstract
The quick and precise identification of COVID-19 pneumonia, non-COVID-19 viral pneumonia, bacterial pneumonia, mycoplasma pneumonia, and normal lung on chest CT images play a crucial role in timely quarantine and medical treatment. However, manual identification is subject to potential misinterpretations and time-consumption issues owing the visual similarities of pneumonia lesions. In this study, we propose a novel multi-scale attention network (MSANet) based on a bag of advanced deep learning techniques for the automatic classification of COVID-19 and multiple types of pneumonia. The proposed method can automatically pay attention to discriminative information and multi-scale features of pneumonia lesions for better classification. The experimental results show that the proposed MSANet can achieve an overall precision of 97.31%, recall of 96.18%, F1-score of 96.71%, accuracy of 97.46%, and macro-average area under the receiver operating characteristic curve (AUC) of 0.9981 to distinguish between multiple classes of pneumonia. These promising results indicate that the proposed method can significantly assist physicians and radiologists in medical diagnosis. The dataset is publicly available at https://doi.org/10.17632/rf8x3wp6ss.1.
Collapse
Affiliation(s)
- Pak Kin Wong
- Department of Electromechanical Engineering, University of Macau, Taipa 999078, Macau
| | - Tao Yan
- School of Mechanical Engineering, Hubei University of Arts and Science, Xiangyang 441053, China
| | - Huaqiao Wang
- Xiangyang No.1 People's Hospital, Hubei University of Medicine, Xiangyang 441000, China
| | - In Neng Chan
- Department of Electromechanical Engineering, University of Macau, Taipa 999078, Macau
| | - Jiangtao Wang
- Xiangyang Central Hospital, Affiliated Hospital of Hubei University of Arts and Science, Xiangyang 441021, China
| | - Yang Li
- Xiangyang No.1 People's Hospital, Hubei University of Medicine, Xiangyang 441000, China
| | - Hao Ren
- Xiangyang Central Hospital, Affiliated Hospital of Hubei University of Arts and Science, Xiangyang 441021, China
| | - Chi Hong Wong
- Faculty of Medicine, Macau University of Science and Technology, Taipa 999078, Macau
| |
Collapse
|
45
|
Ali M, Ali R. Gender and age detection assist convolutional neural networks in classification of thorax diseases. PeerJ Comput Sci 2021; 7:e738. [PMID: 34825055 PMCID: PMC8592247 DOI: 10.7717/peerj-cs.738] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/15/2021] [Accepted: 09/14/2021] [Indexed: 06/13/2023]
Abstract
Conventionally, convolutional neural networks (CNNs) have been used to identify and detect thorax diseases on chest x-ray images. To identify thorax diseases, CNNs typically learn two types of information: disease-specific features and generic anatomical features. CNNs focus on disease-specific features while ignoring the rest of the anatomical features during their operation. There is no evidence that generic anatomical features improve or worsen the performance of convolutional neural networks for thorax disease classification in the current research. As a consequence, the relevance of general anatomical features in boosting the performance of CNNs for thorax disease classification is investigated in this study. We employ a dual-stream CNN model to learn anatomical features before training the model for thorax disease classification. The dual-stream technique is used to compel the model to learn structural information because initial layers of CNNs often learn features of edges and boundaries. As a result, a dual-stream model with minimal layers learns structural and anatomical features as a priority. To make the technique more comprehensive, we first train the model to identify gender and age and then classify thorax diseases using the information acquired. Only when the model learns the anatomical features can it detect gender and age. We also use Non-negative Matrix Factorization (NMF) and Contrast Limited Adaptive Histogram Equalization (CLAHE) to pre-process the training data, which suppresses disease-related information while amplifying general anatomical features, allowing the model to acquire anatomical features considerably faster. Finally, the model that was earlier trained for gender and age detection is retrained for thorax disease classification using original data. The proposed technique increases the performance of convolutional neural networks for thorax disease classification, as per experiments on the Chest X-ray14 dataset. We can also see the significant parts of the image that contribute more for gender, age, and a certain thorax disease by visualizing the features. The proposed study achieves two goals: first, it produces novel gender and age identification results on chest X-ray images that may be used in biometrics, forensics, and anthropology, and second, it highlights the importance of general anatomical features in thorax disease classification. In comparison to state-of-the-art results, the proposed work also produces competitive results.
Collapse
Affiliation(s)
- Mumtaz Ali
- Computer Science, Huazhong University of Science and Technology, Wuhan, Hubei, China
- Computer Systems Engineering, Sukkur IBA University, Sukkur, Sukkur, Sindh, Pakistan
| | - Riaz Ali
- Computer Sceince, Sukkur IBA University, Sukkur, Sukkur, Sindh, Pakistan
| |
Collapse
|
46
|
Horry MJ, Chakraborty S, Pradhan B, Fallahpoor M, Chegeni H, Paul M. Factors determining generalization in deep learning models for scoring COVID-CT images. MATHEMATICAL BIOSCIENCES AND ENGINEERING : MBE 2021; 18:9264-9293. [PMID: 34814345 DOI: 10.3934/mbe.2021456] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/13/2023]
Abstract
The COVID-19 pandemic has inspired unprecedented data collection and computer vision modelling efforts worldwide, focused on the diagnosis of COVID-19 from medical images. However, these models have found limited, if any, clinical application due in part to unproven generalization to data sets beyond their source training corpus. This study investigates the generalizability of deep learning models using publicly available COVID-19 Computed Tomography data through cross dataset validation. The predictive ability of these models for COVID-19 severity is assessed using an independent dataset that is stratified for COVID-19 lung involvement. Each inter-dataset study is performed using histogram equalization, and contrast limited adaptive histogram equalization with and without a learning Gabor filter. We show that under certain conditions, deep learning models can generalize well to an external dataset with F1 scores up to 86%. The best performing model shows predictive accuracy of between 75% and 96% for lung involvement scoring against an external expertly stratified dataset. From these results we identify key factors promoting deep learning generalization, being primarily the uniform acquisition of training images, and secondly diversity in CT slice position.
Collapse
Affiliation(s)
- Michael James Horry
- Center for Advanced Modelling and Geospatial Information Systems (CAMGIS), Faculty of Engineering and Information Technology, University of Technology Sydney, Australia
| | - Subrata Chakraborty
- Center for Advanced Modelling and Geospatial Information Systems (CAMGIS), Faculty of Engineering and Information Technology, University of Technology Sydney, Australia
| | - Biswajeet Pradhan
- Center for Advanced Modelling and Geospatial Information Systems (CAMGIS), Faculty of Engineering and Information Technology, University of Technology Sydney, Australia
- Center of Excellence for Climate Change Research, King Abdulaziz University, Jeddah 21589, Saudi Arabia
- Earth Observation Center, Institute of Climate Change, Universiti Kebangsaan Malaysia, Selangor 43600, Malaysia
| | - Maryam Fallahpoor
- Center for Advanced Modelling and Geospatial Information Systems (CAMGIS), Faculty of Engineering and Information Technology, University of Technology Sydney, Australia
| | - Hossein Chegeni
- Fellowship of Interventional Radiology Imaging Center, IranMehr General Hospital, Iran
| | - Manoranjan Paul
- Machine Vision and Digital Health (MaViDH), School of Computing, Mathematics, and Engineering, Charles Sturt University, Australia
| |
Collapse
|
47
|
Lee S, Summers RM. Clinical Artificial Intelligence Applications in Radiology: Chest and Abdomen. Radiol Clin North Am 2021; 59:987-1002. [PMID: 34689882 DOI: 10.1016/j.rcl.2021.07.001] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/19/2022]
Abstract
Organ segmentation, chest radiograph classification, and lung and liver nodule detections are some of the popular artificial intelligence (AI) tasks in chest and abdominal radiology due to the wide availability of public datasets. AI algorithms have achieved performance comparable to humans in less time for several organ segmentation tasks, and some lesion detection and classification tasks. This article introduces the current published articles of AI applied to chest and abdominal radiology, including organ segmentation, lesion detection, classification, and predicting prognosis.
Collapse
Affiliation(s)
- Sungwon Lee
- Imaging Biomarkers and Computer-Aided Diagnosis Laboratory, Department of Radiology and Imaging Sciences, National Institutes of Health Clinical Center, Building 10, Room 1C224D, 10 Center Drive, Bethesda, MD 20892-1182, USA
| | - Ronald M Summers
- Imaging Biomarkers and Computer-Aided Diagnosis Laboratory, Department of Radiology and Imaging Sciences, National Institutes of Health Clinical Center, Building 10, Room 1C224D, 10 Center Drive, Bethesda, MD 20892-1182, USA.
| |
Collapse
|
48
|
Segmentation-based multi-scale attention model for KRAS mutation prediction in rectal cancer. INT J MACH LEARN CYB 2021. [DOI: 10.1007/s13042-021-01447-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/20/2022]
|
49
|
Horry M, Chakraborty S, Pradhan B, Paul M, Gomes D, Ul-Haq A, Alamri A. Deep Mining Generation of Lung Cancer Malignancy Models from Chest X-ray Images. SENSORS 2021; 21:s21196655. [PMID: 34640976 PMCID: PMC8513105 DOI: 10.3390/s21196655] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 08/31/2021] [Revised: 09/28/2021] [Accepted: 10/05/2021] [Indexed: 12/19/2022]
Abstract
Lung cancer is the leading cause of cancer death and morbidity worldwide. Many studies have shown machine learning models to be effective in detecting lung nodules from chest X-ray images. However, these techniques have yet to be embraced by the medical community due to several practical, ethical, and regulatory constraints stemming from the “black-box” nature of deep learning models. Additionally, most lung nodules visible on chest X-rays are benign; therefore, the narrow task of computer vision-based lung nodule detection cannot be equated to automated lung cancer detection. Addressing both concerns, this study introduces a novel hybrid deep learning and decision tree-based computer vision model, which presents lung cancer malignancy predictions as interpretable decision trees. The deep learning component of this process is trained using a large publicly available dataset on pathological biomarkers associated with lung cancer. These models are then used to inference biomarker scores for chest X-ray images from two independent data sets, for which malignancy metadata is available. Next, multi-variate predictive models were mined by fitting shallow decision trees to the malignancy stratified datasets and interrogating a range of metrics to determine the best model. The best decision tree model achieved sensitivity and specificity of 86.7% and 80.0%, respectively, with a positive predictive value of 92.9%. Decision trees mined using this method may be considered as a starting point for refinement into clinically useful multi-variate lung cancer malignancy models for implementation as a workflow augmentation tool to improve the efficiency of human radiologists.
Collapse
Affiliation(s)
- Michael Horry
- Centre for Advanced Modelling and Geospatial Information Systems (CAMGIS), Faculty of Engineering and IT, University of Technology Sydney, Sydney, NSW 2007, Australia;
- IBM Australia Ltd., Sydney, NSW 2000, Australia
| | - Subrata Chakraborty
- Centre for Advanced Modelling and Geospatial Information Systems (CAMGIS), Faculty of Engineering and IT, University of Technology Sydney, Sydney, NSW 2007, Australia;
- Correspondence: (S.C.); (B.P.)
| | - Biswajeet Pradhan
- Centre for Advanced Modelling and Geospatial Information Systems (CAMGIS), Faculty of Engineering and IT, University of Technology Sydney, Sydney, NSW 2007, Australia;
- Earth Observation Centre, Institute of Climate Change, Universiti Kebangsaan Malaysia (UKM), Bangi 43600, Malaysia
- Correspondence: (S.C.); (B.P.)
| | - Manoranjan Paul
- Machine Vision and Digital Health (MaViDH), School of Computing and Mathematics, Charles Sturt University, Bathurst, NSW 2795, Australia; (M.P.); (D.G.); (A.U.-H.)
| | - Douglas Gomes
- Machine Vision and Digital Health (MaViDH), School of Computing and Mathematics, Charles Sturt University, Bathurst, NSW 2795, Australia; (M.P.); (D.G.); (A.U.-H.)
| | - Anwaar Ul-Haq
- Machine Vision and Digital Health (MaViDH), School of Computing and Mathematics, Charles Sturt University, Bathurst, NSW 2795, Australia; (M.P.); (D.G.); (A.U.-H.)
| | - Abdullah Alamri
- Department of Geology and Geophysics, College of Science, King Saud University, P.O. Box 2455, Riyadh 11451, Saudi Arabia;
| |
Collapse
|
50
|
Çallı E, Sogancioglu E, van Ginneken B, van Leeuwen KG, Murphy K. Deep learning for chest X-ray analysis: A survey. Med Image Anal 2021; 72:102125. [PMID: 34171622 DOI: 10.1016/j.media.2021.102125] [Citation(s) in RCA: 98] [Impact Index Per Article: 32.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/16/2021] [Revised: 05/17/2021] [Accepted: 05/27/2021] [Indexed: 12/14/2022]
Abstract
Recent advances in deep learning have led to a promising performance in many medical image analysis tasks. As the most commonly performed radiological exam, chest radiographs are a particularly important modality for which a variety of applications have been researched. The release of multiple, large, publicly available chest X-ray datasets in recent years has encouraged research interest and boosted the number of publications. In this paper, we review all studies using deep learning on chest radiographs published before March 2021, categorizing works by task: image-level prediction (classification and regression), segmentation, localization, image generation and domain adaptation. Detailed descriptions of all publicly available datasets are included and commercial systems in the field are described. A comprehensive discussion of the current state of the art is provided, including caveats on the use of public datasets, the requirements of clinically useful systems and gaps in the current literature.
Collapse
Affiliation(s)
- Erdi Çallı
- Radboud University Medical Center, Institute for Health Sciences, Department of Medical Imaging, Nijmegen, the Netherlands.
| | - Ecem Sogancioglu
- Radboud University Medical Center, Institute for Health Sciences, Department of Medical Imaging, Nijmegen, the Netherlands
| | - Bram van Ginneken
- Radboud University Medical Center, Institute for Health Sciences, Department of Medical Imaging, Nijmegen, the Netherlands
| | - Kicky G van Leeuwen
- Radboud University Medical Center, Institute for Health Sciences, Department of Medical Imaging, Nijmegen, the Netherlands
| | - Keelin Murphy
- Radboud University Medical Center, Institute for Health Sciences, Department of Medical Imaging, Nijmegen, the Netherlands
| |
Collapse
|