1
|
Huang ML, Liao YC. Stacking Ensemble and ECA-EfficientNetV2 Convolutional Neural Networks on Classification of Multiple Chest Diseases Including COVID-19. Acad Radiol 2023; 30:1915-1935. [PMID: 36526533 PMCID: PMC9748720 DOI: 10.1016/j.acra.2022.11.027] [Citation(s) in RCA: 5] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/06/2022] [Revised: 11/15/2022] [Accepted: 11/20/2022] [Indexed: 11/27/2022]
Abstract
RATIONALE AND OBJECTIVES Early detection and treatment of COVID-19 patients is crucial. Convolutional neural networks have been proven to accurately extract features in medical images, which accelerates time required for testing and increases the effectiveness of COVID-19 diagnosis. This study proposes two classification models for multiple chest diseases including COVID-19. MATERIALS AND METHODS The first is Stacking-ensemble model, which stacks six pretrained models including EfficientNetV2-B0, EfficientNetV2-B1, EfficientNetV2-B2, EfficientNetV2-B3, EfficientNetV2-S and EfficientNetV2-M. The second model is self-designed model ECA-EfficientNetV2 based on ECA-Net and EfficientNetV2. Ten-fold cross validation was performed for each model on chest X-ray and CT images. One more dataset, COVID-CT dataset, was tested to verify the performance of the proposed Stacking-ensemble and ECA-EfficientNetV2 models. RESULTS The best performance comes from the proposed ECA-EfficientNetV2 model with the highest Accuracy of 99.21%, Precision of 99.23%, Recall of 99.25%, F1-score of 99.20%, and (area under the curve) AUC of 99.51% on chest X-ray dataset; the best performance comes from the proposed ECA-EfficientNetV2 model with the highest Accuracy of 99.81%, Precision of 99.80%, Recall of 99.80%, F1-score of 99.81%, and AUC of 99.87% on chest CT dataset. The differences for five metrics between Stacking-ensemble and ECA-EfficientNetV2 models are not significant. CONCLUSION Ensemble model achieves better performance than single pretrained models. Compared to the SOTA, Stacking-ensemble and ECA-EfficientNetV2 models proposed in this study demonstrate promising performance on classification of multiple chest diseases including COVID-19.
Collapse
Affiliation(s)
- Mei-Ling Huang
- Department of Industrial Engineering & Management, National Chin-Yi University of Technology, 57, Sec. 2, Zhongshan Rd., Taiping Dist., Taichung, 411030, Taiwan.
| | - Yu-Chieh Liao
- Department of Industrial Engineering & Management, National Chin-Yi University of Technology, 57, Sec. 2, Zhongshan Rd., Taiping Dist., Taichung, 411030, Taiwan
| |
Collapse
|
2
|
Santosh KC, GhoshRoy D, Nakarmi S. A Systematic Review on Deep Structured Learning for COVID-19 Screening Using Chest CT from 2020 to 2022. Healthcare (Basel) 2023; 11:2388. [PMID: 37685422 PMCID: PMC10486542 DOI: 10.3390/healthcare11172388] [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] [Received: 06/12/2023] [Revised: 08/16/2023] [Accepted: 08/22/2023] [Indexed: 09/10/2023] Open
Abstract
The emergence of the COVID-19 pandemic in Wuhan in 2019 led to the discovery of a novel coronavirus. The World Health Organization (WHO) designated it as a global pandemic on 11 March 2020 due to its rapid and widespread transmission. Its impact has had profound implications, particularly in the realm of public health. Extensive scientific endeavors have been directed towards devising effective treatment strategies and vaccines. Within the healthcare and medical imaging domain, the application of artificial intelligence (AI) has brought significant advantages. This study delves into peer-reviewed research articles spanning the years 2020 to 2022, focusing on AI-driven methodologies for the analysis and screening of COVID-19 through chest CT scan data. We assess the efficacy of deep learning algorithms in facilitating decision making processes. Our exploration encompasses various facets, including data collection, systematic contributions, emerging techniques, and encountered challenges. However, the comparison of outcomes between 2020 and 2022 proves intricate due to shifts in dataset magnitudes over time. The initiatives aimed at developing AI-powered tools for the detection, localization, and segmentation of COVID-19 cases are primarily centered on educational and training contexts. We deliberate on their merits and constraints, particularly in the context of necessitating cross-population train/test models. Our analysis encompassed a review of 231 research publications, bolstered by a meta-analysis employing search keywords (COVID-19 OR Coronavirus) AND chest CT AND (deep learning OR artificial intelligence OR medical imaging) on both the PubMed Central Repository and Web of Science platforms.
Collapse
Affiliation(s)
- KC Santosh
- 2AI: Applied Artificial Intelligence Research Lab, Vermillion, SD 57069, USA
| | - Debasmita GhoshRoy
- School of Automation, Banasthali Vidyapith, Tonk 304022, Rajasthan, India;
| | - Suprim Nakarmi
- Department of Computer Science, University of South Dakota, Vermillion, SD 57069, USA;
| |
Collapse
|
3
|
Xie P, Zhao X, He X. Improve the performance of CT-based pneumonia classification via source data reweighting. Sci Rep 2023; 13:9401. [PMID: 37296239 PMCID: PMC10251339 DOI: 10.1038/s41598-023-35938-3] [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: 10/09/2022] [Accepted: 05/26/2023] [Indexed: 06/12/2023] Open
Abstract
Pneumonia is a life-threatening disease. Computer tomography (CT) imaging is broadly used for diagnosing pneumonia. To assist radiologists in accurately and efficiently detecting pneumonia from CT scans, many deep learning methods have been developed. These methods require large amounts of annotated CT scans, which are difficult to obtain due to privacy concerns and high annotation costs. To address this problem, we develop a three-level optimization based method which leverages CT data from a source domain to mitigate the lack of labeled CT scans in a target domain. Our method automatically identifies and downweights low-quality source CT data examples which are noisy or have large domain discrepancy with target data, by minimizing the validation loss of a target model trained on reweighted source data. On a target dataset with 2218 CT scans and a source dataset with 349 CT images, our method achieves an F1 score of 91.8% in detecting pneumonia and an F1 score of 92.4% in detecting other types of pneumonia, which are significantly better than those achieved by state-of-the-art baseline methods.
Collapse
Affiliation(s)
- Pengtao Xie
- Department of Electrical and Computer Engineering, University of California San Diego, San Diego, USA.
| | - Xingchen Zhao
- Department of Electrical and Computer Engineering, Northeastern University, Boston, USA
| | - Xuehai He
- Department of Computer Science and Engineering, University of California Santa Cruz, Santa Cruz, USA
| |
Collapse
|
4
|
Motta PC, Cortez PC, Silva BRS, Yang G, de Albuquerque VHC. Automatic COVID-19 and Common-Acquired Pneumonia Diagnosis Using Chest CT Scans. Bioengineering (Basel) 2023; 10:529. [PMID: 37237599 PMCID: PMC10215490 DOI: 10.3390/bioengineering10050529] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/04/2023] [Revised: 04/22/2023] [Accepted: 04/24/2023] [Indexed: 05/28/2023] Open
Abstract
Even with over 80% of the population being vaccinated against COVID-19, the disease continues to claim victims. Therefore, it is crucial to have a secure Computer-Aided Diagnostic system that can assist in identifying COVID-19 and determining the necessary level of care. This is especially important in the Intensive Care Unit to monitor disease progression or regression in the fight against this epidemic. To accomplish this, we merged public datasets from the literature to train lung and lesion segmentation models with five different distributions. We then trained eight CNN models for COVID-19 and Common-Acquired Pneumonia classification. If the examination was classified as COVID-19, we quantified the lesions and assessed the severity of the full CT scan. To validate the system, we used Resnetxt101 Unet++ and Mobilenet Unet for lung and lesion segmentation, respectively, achieving accuracy of 98.05%, F1-score of 98.70%, precision of 98.7%, recall of 98.7%, and specificity of 96.05%. This was accomplished in just 19.70 s per full CT scan, with external validation on the SPGC dataset. Finally, when classifying these detected lesions, we used Densenet201 and achieved accuracy of 90.47%, F1-score of 93.85%, precision of 88.42%, recall of 100.0%, and specificity of 65.07%. The results demonstrate that our pipeline can correctly detect and segment lesions due to COVID-19 and Common-Acquired Pneumonia in CT scans. It can differentiate these two classes from normal exams, indicating that our system is efficient and effective in identifying the disease and assessing the severity of the condition.
Collapse
Affiliation(s)
- Pedro Crosara Motta
- Department of Teleinformatics Engineering, Federal University of Ceará, Fortaleza 60455-970, Brazil; (P.C.M.); (P.C.C.); (B.R.S.S.)
| | - Paulo César Cortez
- Department of Teleinformatics Engineering, Federal University of Ceará, Fortaleza 60455-970, Brazil; (P.C.M.); (P.C.C.); (B.R.S.S.)
| | - Bruno R. S. Silva
- Department of Teleinformatics Engineering, Federal University of Ceará, Fortaleza 60455-970, Brazil; (P.C.M.); (P.C.C.); (B.R.S.S.)
| | - Guang Yang
- National Heart and Lung Institute, Imperial College London, London SW7 2AZ, UK
| | - Victor Hugo C. de Albuquerque
- Department of Teleinformatics Engineering, Federal University of Ceará, Fortaleza 60455-970, Brazil; (P.C.M.); (P.C.C.); (B.R.S.S.)
| |
Collapse
|
5
|
da Silveira TLT, Pinto PGL, Lermen TS, Jung CR. Omnidirectional 2.5D representation for COVID-19 diagnosis using chest CTs. JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION 2023; 91:103775. [PMID: 36741546 PMCID: PMC9886432 DOI: 10.1016/j.jvcir.2023.103775] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 08/24/2022] [Revised: 01/18/2023] [Accepted: 01/27/2023] [Indexed: 06/18/2023]
Abstract
The Coronavirus Disease 2019 (COVID-19) has drastically overwhelmed most countries in the last two years, and image-based approaches using computerized tomography (CT) have been used to identify pulmonary infections. Recent methods based on deep learning either require time-consuming per-slice annotations (2D) or are highly data- and hardware-demanding (3D). This work proposes a novel omnidirectional 2.5D representation of volumetric chest CTs that allows exploring efficient 2D deep learning architectures while requiring volume-level annotations only. Our learning approach uses a siamese feature extraction backbone applied to each lung. It combines these features into a classification head that explores a novel combination of Squeeze-and-Excite strategies with Class Activation Maps. We experimented with public and in-house datasets and compared our results with state-of-the-art techniques. Our analyses show that our method provides better or comparable prediction quality and accurately distinguishes COVID-19 infections from other kinds of pneumonia and healthy lungs.
Collapse
Affiliation(s)
- Thiago L T da Silveira
- Institute of Informatics - Federal University of Rio Grande do Sul, Porto Alegre, 91501-970, Brazil
| | - Paulo G L Pinto
- Institute of Informatics - Federal University of Rio Grande do Sul, Porto Alegre, 91501-970, Brazil
| | - Thiago S Lermen
- Institute of Informatics - Federal University of Rio Grande do Sul, Porto Alegre, 91501-970, Brazil
| | - Cláudio R Jung
- Institute of Informatics - Federal University of Rio Grande do Sul, Porto Alegre, 91501-970, Brazil
| |
Collapse
|
6
|
Wu Y, Qi Q, Qi S, Yang L, Wang H, Yu H, Li J, Wang G, Zhang P, Liang Z, Chen R. Classification of COVID-19 from community-acquired pneumonia: Boosting the performance with capsule network and maximum intensity projection image of CT scans. Comput Biol Med 2023; 154:106567. [PMID: 36738705 PMCID: PMC9869624 DOI: 10.1016/j.compbiomed.2023.106567] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/30/2022] [Revised: 12/30/2022] [Accepted: 01/22/2023] [Indexed: 01/24/2023]
Abstract
BACKGROUND The coronavirus disease 2019 (COVID-19) and community-acquired pneumonia (CAP) present a high degree of similarity in chest computed tomography (CT) images. Therefore, a procedure for accurately and automatically distinguishing between them is crucial. METHODS A deep learning method for distinguishing COVID-19 from CAP is developed using maximum intensity projection (MIP) images from CT scans. LinkNet is employed for lung segmentation of chest CT images. MIP images are produced by superposing the maximum gray of intrapulmonary CT values. The MIP images are input into a capsule network for patient-level pred iction and diagnosis of COVID-19. The network is trained using 333 CT scans (168 COVID-19/165 CAP) and validated on three external datasets containing 3581 CT scans (2110 COVID-19/1471 CAP). RESULTS LinkNet achieves the highest Dice coefficient of 0.983 for lung segmentation. For the classification of COVID-19 and CAP, the capsule network with the DenseNet-121 feature extractor outperforms ResNet-50 and Inception-V3, achieving an accuracy of 0.970 on the training dataset. Without MIP or the capsule network, the accuracy decreases to 0.857 and 0.818, respectively. Accuracy scores of 0.961, 0.997, and 0.949 are achieved on the external validation datasets. The proposed method has higher or comparable sensitivity compared with ten state-of-the-art methods. CONCLUSIONS The proposed method illustrates the feasibility of applying MIP images from CT scans to distinguish COVID-19 from CAP using capsule networks. MIP images provide conspicuous benefits when exploiting deep learning to detect COVID-19 lesions from CT scans and the capsule network improves COVID-19 diagnosis.
Collapse
Affiliation(s)
- Yanan Wu
- College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, China; Key Laboratory of Intelligent Computing in Medical Image, Ministry of Education, Northeastern University, Shenyang, China.
| | - Qianqian Qi
- Research Center for Healthcare Data Science, Zhejiang Lab, Hangzhou, China.
| | - Shouliang Qi
- College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, China; Key Laboratory of Intelligent Computing in Medical Image, Ministry of Education, Northeastern University, Shenyang, China.
| | - Liming Yang
- Department of Radiology, The Affiliated Hospital of Guizhou Medical University, Guiyang, China.
| | - Hanlin Wang
- Department of Radiology, General Hospital of the Yangtze River Shipping, Wuhan, China.
| | - Hui Yu
- General Practice Center, The Seventh Affiliated Hospital, Southern Medical University, Guangzhou, China.
| | - Jianpeng Li
- Department of Radiology, Affiliated Dongguan Hospital, Southern Medical University, Dongguan, China.
| | - Gang Wang
- Department of Radiology, Affiliated Dongguan Hospital, Southern Medical University, Dongguan, China.
| | - Ping Zhang
- Department of Pulmonary and Critical Care Medicine, Affiliated Dongguan Hospital, Southern Medical University, Dongguan, China.
| | - Zhenyu Liang
- State Key Laboratory of Respiratory Disease, National Clinical Research Center for Respiratory Disease, Guangzhou Institute of Respiratory Health, The First Affiliated Hospital of Guangzhou Medical University, Guangzhou, China.
| | - Rongchang Chen
- Key Laboratory of Respiratory Disease of Shenzhen, Shenzhen Institute of Respiratory Disease, Shenzhen People's Hospital (Second Affiliated Hospital of Jinan University, First Affiliated Hospital of South University of Science and Technology of China), Shenzhen, China.
| |
Collapse
|
7
|
Wen C, Liu S, Liu S, Heidari AA, Hijji M, Zarco C, Muhammad K. ACSN: Attention capsule sampling network for diagnosing COVID-19 based on chest CT scans. Comput Biol Med 2023; 153:106338. [PMID: 36640529 PMCID: PMC9678829 DOI: 10.1016/j.compbiomed.2022.106338] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/10/2022] [Revised: 11/08/2022] [Accepted: 11/16/2022] [Indexed: 11/23/2022]
Abstract
Automated diagnostic techniques based on computed tomography (CT) scans of the chest for the coronavirus disease (COVID-19) help physicians detect suspected cases rapidly and precisely, which is critical in providing timely medical treatment and preventing the spread of epidemic outbreaks. Existing capsule networks have played a significant role in automatic COVID-19 detection systems based on small datasets. However, extracting key slices is difficult because CT scans typically show many scattered lesion sections. In addition, existing max pooling sampling methods cannot effectively fuse the features from multiple regions. Therefore, in this study, we propose an attention capsule sampling network (ACSN) to detect COVID-19 based on chest CT scans. A key slices enhancement method is used to obtain critical information from a large number of slices by applying attention enhancement to key slices. Then, the lost active and background features are retained by integrating two types of sampling. The results of experiments on an open dataset of 35,000 slices show that the proposed ACSN achieve high performance compared with state-of-the-art models and exhibits 96.3% accuracy, 98.8% sensitivity, 93.8% specificity, and 98.3% area under the receiver operating characteristic curve.
Collapse
Affiliation(s)
- Cuihong Wen
- College of Information Science and Engineering, Hunan Normal University, Changsha, 410081, China; State Key Laboratory for Turbulence and Complex Systems, Department of Advanced Manufacturing and Robotics, College of Engineering, Peking University, Beijing, 100871, China
| | - Shaowu Liu
- College of Information Science and Engineering, Hunan Normal University, Changsha, 410081, China
| | - Shuai Liu
- College of Information Science and Engineering, Hunan Normal University, Changsha, 410081, China; School of Educational Science, Hunan Normal University, Changsha, 410081, China; Key Laboratory of Big Data Research and Application for Basic Education, Hunan Normal University, Changsha, 410081, China.
| | - Ali Asghar Heidari
- School of Surveying and Geospatial Engineering, College of Engineering, University of Tehran, Tehran, 1439957131, Iran.
| | - Mohammad Hijji
- Faculty of Computers and Information Technology (FCIT), University of Tabuk, Tabuk, 47711, Saudi Arabia
| | - Carmen Zarco
- Andalusian Research Institute in Data Science and Computational Intelligence (DaSCI), University of Granada (UGR), Spain
| | - Khan Muhammad
- Visual Analytics for Knowledge Laboratory (VIS2KNOW Lab), Department of Applied AI, School of Convergence, College of Computing and Informatics, Sungkyunkwan University, Seoul, 03063, South Korea.
| |
Collapse
|
8
|
Ahuja S, Panigrahi BK, Dey N, Taneja A, Gandhi TK. McS-Net: Multi-class Siamese network for severity of COVID-19 infection classification from lung CT scan slices. Appl Soft Comput 2022; 131:109683. [PMID: 36277300 PMCID: PMC9573862 DOI: 10.1016/j.asoc.2022.109683] [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: 02/02/2022] [Revised: 08/25/2022] [Accepted: 09/22/2022] [Indexed: 11/29/2022]
Abstract
Worldwide COVID-19 is a highly infectious and rapidly spreading disease in almost all age groups. The Computed Tomography (CT) scans of lungs are found to be accurate for the timely diagnosis of COVID-19 infection. In the proposed work, a deep learning-based P-shot N-ways Siamese network along with prototypical nearest neighbor classifiers is implemented for the classification of COVID-19 infection from lung CT scan slices. For this, a Siamese network with an identical sub-network (weight sharing) is used for image classification with a limited dataset for each class. The feature vectors are obtained from the pre-trained sub-networks having weight sharing. The performance of the proposed methodology is evaluated on the benchmark MosMed dataset having categories zero (healthy control) and numerous COVID-19 infections. The proposed methodology is evaluated on (a) chest CT scans provided by medical hospitals in Moscow, Russia for 1110 patients, and (b) case study of low-dose CT scans of 42 patients provided by Avtaran healthcare in India. The deep learning-based Siamese network (15-shot 5-ways) obtained an accuracy of 98.07%, the sensitivity of 95.66%, specificity of 98.83%, and F1-score of 95.10%. The proposed work outperforms the COVID-19 infection severity classification with limited scans availability for numerous infection categories.
Collapse
Affiliation(s)
- Sakshi Ahuja
- Electrical Engineering Department, Indian Institute of Technology Delhi, New Delhi, 110016, India
| | - Bijaya Ketan Panigrahi
- Electrical Engineering Department, Indian Institute of Technology Delhi, New Delhi, 110016, India
| | - Nilanjan Dey
- Department of Computer Science and Engineering, Techno International New Town, Kolkata, 700156, India
| | - Arpit Taneja
- Department of Radiology, Avtaran Healthcare LLP, Kurukshetra, 136118, India
| | - Tapan Kumar Gandhi
- Electrical Engineering Department, Indian Institute of Technology Delhi, New Delhi, 110016, India
| |
Collapse
|
9
|
The Caliber of Segmental and Subsegmental Vessels in COVID-19 Pneumonia Is Enlarged: A Distinctive Feature in Comparison with Other Forms of Inflammatory and Thromboembolic Diseases. J Pers Med 2022; 12:jpm12091465. [PMID: 36143250 PMCID: PMC9505964 DOI: 10.3390/jpm12091465] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/12/2022] [Revised: 09/01/2022] [Accepted: 09/05/2022] [Indexed: 11/16/2022] Open
Abstract
Background: The purpose of this study was to compare COVID-19 patients’ vessel caliber with that of normal lungs and lungs affected by other inflammatory and thromboembolic processes. Methods: between March and April 2020, 42 patients affected by COVID-19 pneumonia (COV-P) underwent CT scans of the lungs at Verona University Hospital for clinical indications. The lung images of four different groups of patients were compared (normal lung (NL), distal thromboembolism (DTE), and bacterial and fungal pneumonia (Bact-P, Fung-P)) by a radiologist with four years of experience. Results: The COV-P patients’ segmental and subsegmental vessels, evaluated as the ratio with the corresponding bronchial branch (V/B ratio), were larger, with respect to the NL the DTE groups, in the apparently healthy parenchyma, a result confirmed in the zones of opacification with respect to the Bact-P and Fung-P groups. Conclusions: This was the first study to show, by comparative analysis, that COVID-19 patients’ segmental and subsegmental vessel calibers are significantly enlarged. This is a distinctive feature of COVID-19 pneumonia, suggesting its distinct pathophysiology as compared to other inflammatory and thromboembolic diseases and alerting radiologists to consider it when evaluating the CT scans of suspected patients.
Collapse
|
10
|
Detection and Prevention of Virus Infection. ADVANCES IN EXPERIMENTAL MEDICINE AND BIOLOGY 2022; 1368:21-52. [DOI: 10.1007/978-981-16-8969-7_2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 02/07/2023]
|