Multi-Scale Learning with Sparse Residual Network for Explainable Multi-Disease Diagnosis in OCT Images
In recent decades, medical imaging techniques have revolutionized the field of disease diagnosis, enabling healthcare professionals to noninvasively observe the internal structures of the human body. Among these techniques, optical coherence tomography (OCT) has emerged as a powerful and versatile t...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-10-01
|
| Series: | Bioengineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2306-5354/10/11/1249 |
| _version_ | 1797460132733386752 |
|---|---|
| author | Phuoc-Nguyen Bui Duc-Tai Le Junghyun Bum Seongho Kim Su Jeong Song Hyunseung Choo |
| author_facet | Phuoc-Nguyen Bui Duc-Tai Le Junghyun Bum Seongho Kim Su Jeong Song Hyunseung Choo |
| author_sort | Phuoc-Nguyen Bui |
| collection | DOAJ |
| description | In recent decades, medical imaging techniques have revolutionized the field of disease diagnosis, enabling healthcare professionals to noninvasively observe the internal structures of the human body. Among these techniques, optical coherence tomography (OCT) has emerged as a powerful and versatile tool that allows high-resolution, non-invasive, and real-time imaging of biological tissues. Deep learning algorithms have been successfully employed to detect and classify various retinal diseases in OCT images, enabling early diagnosis and treatment planning. However, existing deep learning algorithms are primarily designed for single-disease diagnosis, which limits their practical application in clinical settings where OCT images often contain symptoms of multiple diseases. In this paper, we propose an effective approach for multi-disease diagnosis in OCT images using a multi-scale learning (MSL) method and a sparse residual network (SRN). Specifically, the MSL method extracts and fuses useful features from images of different sizes to enhance the discriminative capability of a classifier and make the disease predictions interpretable. The SRN is a minimal residual network, where convolutional layers with large kernel sizes are replaced with multiple convolutional layers that have smaller kernel sizes, thereby reducing model complexity while achieving a performance similar to that of existing convolutional neural networks. The proposed multi-scale sparse residual network significantly outperforms existing methods, exhibiting 97.40% accuracy, 95.38% sensitivity, and 98.25% specificity. Experimental results show the potential of our method to improve explainable diagnosis systems for various eye diseases via visual discrimination. |
| first_indexed | 2024-03-09T17:01:42Z |
| format | Article |
| id | doaj.art-850c9c9c7c154c478d9d6b571f9cbffa |
| institution | Directory Open Access Journal |
| issn | 2306-5354 |
| language | English |
| last_indexed | 2024-03-09T17:01:42Z |
| publishDate | 2023-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Bioengineering |
| spelling | doaj.art-850c9c9c7c154c478d9d6b571f9cbffa2023-11-24T14:29:38ZengMDPI AGBioengineering2306-53542023-10-011011124910.3390/bioengineering10111249Multi-Scale Learning with Sparse Residual Network for Explainable Multi-Disease Diagnosis in OCT ImagesPhuoc-Nguyen Bui0Duc-Tai Le1Junghyun Bum2Seongho Kim3Su Jeong Song4Hyunseung Choo5Department of AI Systems Engineering, Sungkyunkwan University, Suwon 16419, Republic of KoreaCollege of Computing and Informatics, Sungkyunkwan University, Suwon 16419, Republic of KoreaSungkyun AI Research Institute, Sungkyunkwan University, Suwon 16419, Republic of KoreaDepartment of Ophthalmology, Kangbuk Samsung Hospital, School of Medicine, Sungkyunkwan University, Seoul 03181, Republic of KoreaDepartment of Ophthalmology, Kangbuk Samsung Hospital, School of Medicine, Sungkyunkwan University, Seoul 03181, Republic of KoreaDepartment of AI Systems Engineering, Sungkyunkwan University, Suwon 16419, Republic of KoreaIn recent decades, medical imaging techniques have revolutionized the field of disease diagnosis, enabling healthcare professionals to noninvasively observe the internal structures of the human body. Among these techniques, optical coherence tomography (OCT) has emerged as a powerful and versatile tool that allows high-resolution, non-invasive, and real-time imaging of biological tissues. Deep learning algorithms have been successfully employed to detect and classify various retinal diseases in OCT images, enabling early diagnosis and treatment planning. However, existing deep learning algorithms are primarily designed for single-disease diagnosis, which limits their practical application in clinical settings where OCT images often contain symptoms of multiple diseases. In this paper, we propose an effective approach for multi-disease diagnosis in OCT images using a multi-scale learning (MSL) method and a sparse residual network (SRN). Specifically, the MSL method extracts and fuses useful features from images of different sizes to enhance the discriminative capability of a classifier and make the disease predictions interpretable. The SRN is a minimal residual network, where convolutional layers with large kernel sizes are replaced with multiple convolutional layers that have smaller kernel sizes, thereby reducing model complexity while achieving a performance similar to that of existing convolutional neural networks. The proposed multi-scale sparse residual network significantly outperforms existing methods, exhibiting 97.40% accuracy, 95.38% sensitivity, and 98.25% specificity. Experimental results show the potential of our method to improve explainable diagnosis systems for various eye diseases via visual discrimination.https://www.mdpi.com/2306-5354/10/11/1249optical coherence tomographymedical image analysismulti-disease diagnosismulti-scale learningresidual network |
| spellingShingle | Phuoc-Nguyen Bui Duc-Tai Le Junghyun Bum Seongho Kim Su Jeong Song Hyunseung Choo Multi-Scale Learning with Sparse Residual Network for Explainable Multi-Disease Diagnosis in OCT Images Bioengineering optical coherence tomography medical image analysis multi-disease diagnosis multi-scale learning residual network |
| title | Multi-Scale Learning with Sparse Residual Network for Explainable Multi-Disease Diagnosis in OCT Images |
| title_full | Multi-Scale Learning with Sparse Residual Network for Explainable Multi-Disease Diagnosis in OCT Images |
| title_fullStr | Multi-Scale Learning with Sparse Residual Network for Explainable Multi-Disease Diagnosis in OCT Images |
| title_full_unstemmed | Multi-Scale Learning with Sparse Residual Network for Explainable Multi-Disease Diagnosis in OCT Images |
| title_short | Multi-Scale Learning with Sparse Residual Network for Explainable Multi-Disease Diagnosis in OCT Images |
| title_sort | multi scale learning with sparse residual network for explainable multi disease diagnosis in oct images |
| topic | optical coherence tomography medical image analysis multi-disease diagnosis multi-scale learning residual network |
| url | https://www.mdpi.com/2306-5354/10/11/1249 |
| work_keys_str_mv | AT phuocnguyenbui multiscalelearningwithsparseresidualnetworkforexplainablemultidiseasediagnosisinoctimages AT ductaile multiscalelearningwithsparseresidualnetworkforexplainablemultidiseasediagnosisinoctimages AT junghyunbum multiscalelearningwithsparseresidualnetworkforexplainablemultidiseasediagnosisinoctimages AT seonghokim multiscalelearningwithsparseresidualnetworkforexplainablemultidiseasediagnosisinoctimages AT sujeongsong multiscalelearningwithsparseresidualnetworkforexplainablemultidiseasediagnosisinoctimages AT hyunseungchoo multiscalelearningwithsparseresidualnetworkforexplainablemultidiseasediagnosisinoctimages |