Advancing eye disease detection: A comprehensive study on computer-aided diagnosis with vision transformers and SHAP explainability techniques

• Autorzy: Balaha Hossam Magdy , Hassan Asmaa El-Sayed , Ahmed Rawan Ayman , Balaha Magdy Hassan

Identyfikatory

DOI

10.1016/j.bbe.2024.11.005

• Języki publikacji: EN

Abstrakty

EN

Eye diseases such as age-related macular degeneration (AMD) and diabetic retinopathy are common worldwide and affect millions of people. These conditions can cause severe vision problems and even lead to blindness if not treated promptly. Therefore, accurate and timely diagnosis is crucial to manage these diseases effectively and prevent irreversible vision loss. This study introduces a computer-aided diagnosis (CAD) framework for automatically detecting various eye diseases via advanced methodologies and datasets. The main focus is on classifying fundus images, which is essential for precise diagnosis and prognosis. By incorporating cutting-edge techniques such as Vision Transformers (ViTs), this study aims to improve the performance and interpretability of traditional Convolutional Neural Networks (CNNs). ViTs can capture complex patterns and long-range dependencies in fundus images, helping distinguish between different eye diseases and healthy conditions. Furthermore, the study integrates SHapley additive exPlanations (SHAP) explainability techniques to provide insights into the model’s decision-making process, enhancing trust and understanding of its predictions. The results demonstrate significant performance enhancements compared with the baseline models, with an overall accuracy of 95%. This method outperforms previous state-of-the-art methods by a considerable margin. Additionally, metrics such as precision, recall, intersection over union (IoU), and the Matthews correlation coefficient (MCC) show superior performance across various eye diseases, such as diabetic retinopathy, glaucoma, and age-related macular degeneration. These findings underscore the effectiveness and reliability of the proposed approach in automated eye disease detection, indicating its potential for clinical integration and widespread adoption in healthcare settings.

Słowa kluczowe

EN

computer aided diagnosis; CAD; deep learning; DL; optical coherence tomography; OCT; Shapley additive explanations; vision transformer; ViT

PL

diagnostyka komputerowa; CAD; uczenie głębokie; DL; optyczna tomografia koherentna; OCT; transformator wizyjny

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2025
• Tom: Vol. 45, iss. 1
• Strony: 23--33
• Opis fizyczny: Bibliogr. 44 poz., rys., tab., wykr.

Twórcy

autor

Balaha Hossam Magdy

• Bioengineering Department, J.B. Speed School of Engineering, University of Louisville, Louisville, KY, USA
• Computer Science and Systems Department, Faculty of Engineering, Mansoura University, Mansoura, Egypt

• https://orcid.org/0000-0002-0686-4411

autor

Hassan Asmaa El-Sayed

• Mathematics and Engineering Physics Department, Faculty of Engineering, Mansoura University, Mansoura, Egypt

• https://orcid.org/0000-0002-4042-5519

autor

Ahmed Rawan Ayman

• Bioengineering Department, J.B. Speed School of Engineering, University of Louisville, Louisville, KY, USA

autor

Balaha Magdy Hassan

• Department of Obstetrics and Gynecology, Faculty of Medicine, Tanta University, Tanta, Egypt

• https://orcid.org/0000-0003-0504-0565

Bibliografia

• [1] Ong J, Waisberg E, Masalkhi M, Suh A, Kamran SA, Paladugu P, etal. ‘‘Spaceflight-to-eye clinic’’: Terrestrial advances in ophthalmic healthcare delivery from space-based innovations. Life Sci Space Res 2024;41:100-9.
• [2] Allied Market Research. Explore how AMR can help you stay ahead of the curve.2023, Allied Market Research.
• [3] He J, Wang J, Han Z, Ma J, Wang C, Qi M. An interpretable transformer network for the retinal disease classification using optical coherence tomography. Sci Rep2023;13(1):3637.
• [4] Li Z, Han Y, Yang X. Multi-fundus diseases classification using retinal optical coherence tomography images with swin transformer V2. J Imaging2023;9(10):203.
• [5] Abd El-Khalek AA, Balaha HM, Alghamdi NS, Ghazal M, Khalil AT, Abo-Elsoud MEA, et al. A concentrated machine learning-based classification system for Age-related Macular Degeneration (AMD) diagnosis using fundus images. SciRep 2024;14(1):2434.
• [6] Wang Y, Zhang Y, Yao Z, Zhao R, Zhou F. Machine learning based detection of Age-related Macular Degeneration (AMD) and Diabetic Macular Edema(DME) from Optical Coherence Tomography (OCT) images. Biomed Opt Express2016;7(12):4928-40.
• [7] Minakaran N, de Carvalho ER, Petzold A, Wong SH. Optical CoherenceTomography (OCT) in neuro-ophthalmology. Eye 2021;35(1):17-32.
• [8] Yan Q, Weeks DE, Xin H, Swaroop A, Chew EY, Huang H, et al. Deep-learning-based prediction of late age-related macular degeneration progression. Nat Mach Intell 2020;2(2):141-50.
• [9] Lee CS, Baughman DM, Lee AY. Deep learning is effective for classifying normal versus age-related macular degeneration OCT images. Ophthalmol Retina2017;1(4):322-7.
• [10] Treder M, Lauermann JL, Eter N. Automated detection of exudative age-related macular degeneration in spectral domain optical coherence tomography using deep learning. Graefes Arch Clin Exp 2018;256(2):259-65.
• [11] Surya. Eye disease detection dataset. 2023, URL:https://www.kaggle.com/datasets/ysnreddy/eye-disease-detection-dataset.
• [12] Hasan N. Diabetic eye disease retina dataset. 2023, URL:https://www.kaggle.com/datasets/najibhasan/diabetic-eye-disease-retina-dataset.
• [13] Gamal M. Eye diseases. 2024, URL: https://www.kaggle.com/datasets/mohamedgamal295/eye-diseases.
• [14] Liu Y, Zhang Y, Wang Y, Hou F, Yuan J, Tian J, et al. A survey of visual transformers. IEEE Trans Neural Netw Learn Syst 2023;1-21.
• [15] Raghu M, Unterthiner T, Kornblith S, Zhang C, Dosovitskiy A. Do vision transformers see like convolutional neural networks? Adv Neural Inf Process Syst2021;34:12116-28.
• [16] Cao YH, Yu H, Wu J. Training vision transformers with only 2040 images. In:Computer vision - ECCV 2022. Switzerland: Springer Nature; 2022, p. 220-37.
• [17] Zhou D, Yu Z, Xie E, Xiao C, Anandkumar A, Feng J, et al. Understanding the robustness in vision transformers. In: Proceedings of the 39th international conference on machine learning. 2022, p. 27378-94.
• [18] Kim Y, Kim Y. Explainable heat-related mortality with random forest and SHapley Additive exPlanations (SHAP) models. Sustainable Cities Soc 2022;79:103677.
• [19] Nohara Y, Matsumoto K, Soejima H, Nakashima N. Explanation of machine learning models using SHapley Additive exPlanations and application for real data in hospital. Comput Methods Programs Biomed 2022;214:106584.
• [20] Younisse R, Ahmad A, Abu Al-Haija Q. Explaining intrusion detection-based convolutional neural networks using SHapley Additive exPlanations (SHAP). BigData Cogn Comput 2022;6(4):126.
• [21] Gebreyesus Y, Dalton D, Nixon S, De Chiara D, Chinnici M. Machine learning for data center optimizations: Feature selection using SHapley Additive exPlanations (SHAP). Future Internet 2023;15(3):88.
• [22] Balaha H, Antar E, Saafan M, El-Gendy E. A comprehensive framework towards segmenting and classifying breast cancer patients using deep learning and Aquila optimizer. J Ambient Intell Humaniz Comput 2023;14:7897-917.
• [23] Balaha HM, Hassan AE. Comprehensive machine and deep learning analysis of sensor-based human activity recognition. Neural Comput Appl2023;35(17):12793-831.
• [24] Badawy M, Balaha HM, Maklad AS, Almars AM, Elhosseini MA. Revolutionizing oral cancer detection: An approach using Aquila and Gorilla algorithms optimized transfer learning-based CNNs. Biomimetics 2023;8(6):499.
• [25] Azzam MT, Alksas A, Balaha HM, Hassan A, Shehata M, Mekky NE, et al. A novel textural and morphological-based CAD system for early and accurate diagnosis of vertebral tumors. In: 2023 IEEE 20th international symposium on biomedical imaging. 2023, p. 1-4.
• [26] Balaha HM, Ayyad SM, Alksas A, Elsorougy A, Badawy MA, Shehata M, et al.Early diagnosis of prostate cancer using parametric estimation of IVIM from DW-MRI. In: 2023 IEEE international conference on image processing. 2023, p. 2910-4.
• [27] Balaha HM, Shaban AO, El-Gendy EM, Saafan MM. Prostate cancer grading framework based on deep transfer learning and Aquila optimizer. Neural Comput Appl 2024.
• [28] Balaha HM, Hassan AE. A variate brain tumor segmentation, optimization, and recognition framework. Artif Intell Rev 2023;56(7):7403-56.
• [29] Balaha HM, Hassan AE, El-Gendy EM, ZainEldin H, Saafan MM. An aseptic approach towards skin lesion localization and grading using deep learning and Harris Hawks Optimization. Multimedia Tools Appl 2024;83(7):19787-815.
• [30] Wu B, Xu C, Dai X, Wan A, Zhang P, Yan Z, et al. Visual transformers:Token-based image representation and processing for computer vision. 2020.
• [31] Deng J, Dong W, Socher R, Li L, Li K, Fei-Fei L. Imagenet: A large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition. 2009, p. 248-55.
• [32] Abd El-Khalek A, Balaha H, Mahmoud A, Alghamdi N, Ghazal M, Khalil A, et al.A novel machine learning-based classification framework for Age-related Macular Degeneration (AMD) diagnosis from fundus images. In: 2024 IEEE international symposium on biomedical imaging. 2024, p. 1-4.
• [33] Bhuiyan A, Wong TY, Ting DSW, Govindaiah A, Souied EH, Smith RT. Artificial intelligence to stratify severity of Age-related Macular Degeneration (AMD) and predict risk of progression to late AMD. Transl Vis Sci Technol 2020;9(2):25.
• [34] Burlina P, Freund DE, Joshi N, Wolfson Y, Bressler NM. Detection of age-related macular degeneration via deep learning. In: 2016 IEEE 13th international symposium on biomedical imaging. 2016, p. 184-8.
• [35] Motozawa N, An G, Takagi S, Kitahata S, Mandai M, Hirami Y, et al. Optical coherence tomography-based deep-learning models for classifying normal and age-related macular degeneration and exudative and non-exudative age-related macular degeneration changes. Ophthalmol Ther 2019;8:527-39.
• [36] Ajana S, Cougnard-Grégoire A, Colijn JM, Merle BMJ, Verzijden T, deJong PTVM, et al. Predicting progression to advanced age-related macular degeneration from clinical, genetic, and lifestyle factors using machine learning.Ophthalmology 2021;128(4):587-97.
• [37] Kadry S, Rajinikanth V, González Crespo R, Verdú E. Automated detection of age-related macular degeneration using a pre-trained deep-learning scheme. J Supercomput 2022;78(5):7321-40.
• [38] Sarki R, Ahmed K, Wang H, Zhang Y, Wang K. Convolutional neural network for multi-class classification of diabetic eye disease. EAI Endorsed Trans Scalable Inf Syst 2021;9(4).
• [39] Umer MJ, Sharif M, Raza M, Kadry S. A deep feature fusion and selection-based retinal eye disease detection from OCT images. Expert Syst 2023;40(6):e13232.
• [40] Wassel M, Hamdi A, Adly N, Torki M. Vision transformers based classification for glaucomatous eye condition. In: 2022 26th international conference on pattern recognition. 2022, p. 5082-8.
• [41] Yu S, Ma K, Bi Q, Bian C, Ning M, He N, et al. Mil-vt: Multiple instance learning enhanced vision transformer for fundus image classification. In: Medical image computing and computer assisted intervention-MICCAI 2021: 24th international conference, Strasbourg, France, September 27-October 1 2021, proceedings, partVIII 24. 2021, p. 45-54
• [42] Mohan N, Murugan R, Goel T, Roy P. Vit-dr: Vision transformers in diabetic retinopathy grading using fundus images. In: 2022 IEEE 10th region 10 humanitarian technology conference. 2022, p. 167-72.
• [43] Zapata MA, Royo-Fibla D, Font O, Vela JI, Marcantonio I, Moya-Sánchez EU,et al. Artificial intelligence to identify retinal fundus images, quality validation, laterality evaluation, macular degeneration, and suspected glaucoma. ClinOphthalmol 2020;419-29.
• [44] Muthukannan P. Optimized convolution neural network based multiple eye disease detection. Comput Biol Med 2022;146:105648.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025).