OView-AI Supporter for Classifying Pneumonia, Pneumothorax, Tuberculosis, Lung Cancer Chest X-ray Images Using Multi-Stage Superpixels Classification
The deep learning approach has recently attracted much attention for its outstanding performance to assist in clinical diagnostic tasks, notably in computer-aided solutions. Computer-aided solutions are being developed using chest radiography to identify lung diseases. A chest X-ray image is one of...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-04-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/13/9/1519 |
| _version_ | 1797602848378191872 |
|---|---|
| author | Joonho Oh Chanho Park Hongchang Lee Beanbonyka Rim Younggyu Kim Min Hong Jiwon Lyu Suha Han Seongjun Choi |
| author_facet | Joonho Oh Chanho Park Hongchang Lee Beanbonyka Rim Younggyu Kim Min Hong Jiwon Lyu Suha Han Seongjun Choi |
| author_sort | Joonho Oh |
| collection | DOAJ |
| description | The deep learning approach has recently attracted much attention for its outstanding performance to assist in clinical diagnostic tasks, notably in computer-aided solutions. Computer-aided solutions are being developed using chest radiography to identify lung diseases. A chest X-ray image is one of the most often utilized diagnostic imaging modalities in computer-aided solutions since it produces non-invasive standard-of-care data. However, the accurate identification of a specific illness in chest X-ray images still poses a challenge due to their high inter-class similarities and low intra-class variant abnormalities, especially given the complex nature of radiographs and the complex anatomy of the chest. In this paper, we proposed a deep-learning-based solution to classify four lung diseases (pneumonia, pneumothorax, tuberculosis, and lung cancer) and healthy lungs using chest X-ray images. In order to achieve a high performance, the EfficientNet B7 model with the pre-trained weights of ImageNet trained by Noisy Student was used as a backbone model, followed by our proposed fine-tuned layers and hyperparameters. Our study achieved an average test accuracy of 97.42%, sensitivity of 95.93%, and specificity of 99.05%. Additionally, our findings were utilized as diagnostic supporting software in OView-AI system (computer-aided application). We conducted 910 clinical trials and achieved an AUC confidence interval (95% CI) of the diagnostic results in the OView-AI system of 97.01%, sensitivity of 95.68%, and specificity of 99.34%. |
| first_indexed | 2024-03-11T04:21:13Z |
| format | Article |
| id | doaj.art-7d4ba7f86d6a44769f17b73ef87c1d00 |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-11T04:21:13Z |
| publishDate | 2023-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-7d4ba7f86d6a44769f17b73ef87c1d002023-11-17T22:44:46ZengMDPI AGDiagnostics2075-44182023-04-01139151910.3390/diagnostics13091519OView-AI Supporter for Classifying Pneumonia, Pneumothorax, Tuberculosis, Lung Cancer Chest X-ray Images Using Multi-Stage Superpixels ClassificationJoonho Oh0Chanho Park1Hongchang Lee2Beanbonyka Rim3Younggyu Kim4Min Hong5Jiwon Lyu6Suha Han7Seongjun Choi8Department of Mechanical System Engineering, Chosun University, Gwangju 61452, Republic of KoreaDepartment of Radiology, Soonchunhyang University Cheonan Hospital, Cheonan 31151, Republic of KoreaHaewootech Co., Ltd., Busan 46742, Republic of KoreaOTOM, Co., Ltd., Gwangju 61042, Republic of KoreaOTOM, Co., Ltd., Gwangju 61042, Republic of KoreaDepartment of Computer Software Engineering, Soonchunhyang University, Asan 31538, Republic of KoreaDivision of Respiratory Medicine, Department of Internal Medicine, Soonchunhyang University Cheonan Hospital, Cheonan 31151, Republic of KoreaDepartment of Nursing, Soonchunhyang University Cheonan Hospital, Cheonan 31151, Republic of KoreaDepartment of Otolaryngology-Head and Neck Surgery, Cheonan Hospital, Soonchunhyang University College of Medicine, Cheonan 31151, Republic of KoreaThe deep learning approach has recently attracted much attention for its outstanding performance to assist in clinical diagnostic tasks, notably in computer-aided solutions. Computer-aided solutions are being developed using chest radiography to identify lung diseases. A chest X-ray image is one of the most often utilized diagnostic imaging modalities in computer-aided solutions since it produces non-invasive standard-of-care data. However, the accurate identification of a specific illness in chest X-ray images still poses a challenge due to their high inter-class similarities and low intra-class variant abnormalities, especially given the complex nature of radiographs and the complex anatomy of the chest. In this paper, we proposed a deep-learning-based solution to classify four lung diseases (pneumonia, pneumothorax, tuberculosis, and lung cancer) and healthy lungs using chest X-ray images. In order to achieve a high performance, the EfficientNet B7 model with the pre-trained weights of ImageNet trained by Noisy Student was used as a backbone model, followed by our proposed fine-tuned layers and hyperparameters. Our study achieved an average test accuracy of 97.42%, sensitivity of 95.93%, and specificity of 99.05%. Additionally, our findings were utilized as diagnostic supporting software in OView-AI system (computer-aided application). We conducted 910 clinical trials and achieved an AUC confidence interval (95% CI) of the diagnostic results in the OView-AI system of 97.01%, sensitivity of 95.68%, and specificity of 99.34%.https://www.mdpi.com/2075-4418/13/9/1519deep learningEfficientNetpneumoniapneumothoraxtuberculosislung cancer |
| spellingShingle | Joonho Oh Chanho Park Hongchang Lee Beanbonyka Rim Younggyu Kim Min Hong Jiwon Lyu Suha Han Seongjun Choi OView-AI Supporter for Classifying Pneumonia, Pneumothorax, Tuberculosis, Lung Cancer Chest X-ray Images Using Multi-Stage Superpixels Classification Diagnostics deep learning EfficientNet pneumonia pneumothorax tuberculosis lung cancer |
| title | OView-AI Supporter for Classifying Pneumonia, Pneumothorax, Tuberculosis, Lung Cancer Chest X-ray Images Using Multi-Stage Superpixels Classification |
| title_full | OView-AI Supporter for Classifying Pneumonia, Pneumothorax, Tuberculosis, Lung Cancer Chest X-ray Images Using Multi-Stage Superpixels Classification |
| title_fullStr | OView-AI Supporter for Classifying Pneumonia, Pneumothorax, Tuberculosis, Lung Cancer Chest X-ray Images Using Multi-Stage Superpixels Classification |
| title_full_unstemmed | OView-AI Supporter for Classifying Pneumonia, Pneumothorax, Tuberculosis, Lung Cancer Chest X-ray Images Using Multi-Stage Superpixels Classification |
| title_short | OView-AI Supporter for Classifying Pneumonia, Pneumothorax, Tuberculosis, Lung Cancer Chest X-ray Images Using Multi-Stage Superpixels Classification |
| title_sort | oview ai supporter for classifying pneumonia pneumothorax tuberculosis lung cancer chest x ray images using multi stage superpixels classification |
| topic | deep learning EfficientNet pneumonia pneumothorax tuberculosis lung cancer |
| url | https://www.mdpi.com/2075-4418/13/9/1519 |
| work_keys_str_mv | AT joonhooh oviewaisupporterforclassifyingpneumoniapneumothoraxtuberculosislungcancerchestxrayimagesusingmultistagesuperpixelsclassification AT chanhopark oviewaisupporterforclassifyingpneumoniapneumothoraxtuberculosislungcancerchestxrayimagesusingmultistagesuperpixelsclassification AT hongchanglee oviewaisupporterforclassifyingpneumoniapneumothoraxtuberculosislungcancerchestxrayimagesusingmultistagesuperpixelsclassification AT beanbonykarim oviewaisupporterforclassifyingpneumoniapneumothoraxtuberculosislungcancerchestxrayimagesusingmultistagesuperpixelsclassification AT younggyukim oviewaisupporterforclassifyingpneumoniapneumothoraxtuberculosislungcancerchestxrayimagesusingmultistagesuperpixelsclassification AT minhong oviewaisupporterforclassifyingpneumoniapneumothoraxtuberculosislungcancerchestxrayimagesusingmultistagesuperpixelsclassification AT jiwonlyu oviewaisupporterforclassifyingpneumoniapneumothoraxtuberculosislungcancerchestxrayimagesusingmultistagesuperpixelsclassification AT suhahan oviewaisupporterforclassifyingpneumoniapneumothoraxtuberculosislungcancerchestxrayimagesusingmultistagesuperpixelsclassification AT seongjunchoi oviewaisupporterforclassifyingpneumoniapneumothoraxtuberculosislungcancerchestxrayimagesusingmultistagesuperpixelsclassification |