Explainable Artificial Intelligence based Deep Learning for Retinal Disease Detection

Nitesh Sureja; Vruti Parikh; Ajaysinh Rathod; Priya Patel; Hemant Patel; Heli Sureja

doi:10.35882/jeeemi.v7i2.717

Nitesh Sureja Department of Computer Science and Engineering, Krishna School of Emerging Technology and Applied Research, KPGU, Vadodara, INDIA
Vruti Parikh Department of Computer Science & Engineering, Dr. Subhash University, Junagadh, INDIA
Ajaysinh Rathod Department of Computer Science and Engineering, Krishna School of Emerging Technology and Applied Research, KPGU, Vadodara, INDIA
Priya Patel Department of Computer Science & Design, Sardar Vallabhbhai Patel Institute of Technology, GTU, Vasad, INDIA
Hemant Patel Department of Computer Science & Engineering, Dr. Subhash University, Junagadh, INDIA
Heli Sureja Department of Computer & Data Science, Tagliatela College of Engineering, University of New Haven, CT, USA

DOI: https://doi.org/10.35882/jeeemi.v7i2.717

Keywords: Convolution neural network, Deep learning, Explainable artificial intelligence, Machine learning, Medical image analysis, Retinal diseases

Abstract

This research focuses on the automated identification of retinal diseases. To address this challenge, an artificial intelligence-based approach developed utilizing five deep learning models namely Xception, InceptionV4, EfficientNet-B4, SqueezeNet, and ResNet-264. The model leverages transfer learning to enhance its performance. It is trained on a dataset of optical coherence tomography (OCT) images to classify retinal conditions into four categories: (1) diabetic macular edema, (2) choroidal neovascularization, (3) drusen, and (4) normal. The training dataset, sourced from publicly available repositories, comprises 1,08,312 OCT retinal images covering all four categories. The proposed models achieved good results. InceptionV4 outperformed other models across multiple metrics, achieving the highest accuracy (99.50%), precision (100%), recall (100%), AUC (100%), and F1 score (100%). It surpassed SqueezeNet (accuracy: 98.00%, precision: 98.00%, recall: 98.00%), EfficientNet-B4 (accuracy: 98.50%, precision: 98.50%, recall: 98.50%), Xception (accuracy: 78.25%, precision: 80.36%, recall: 77.75%, F1 score: 99.50%), and ResNet-264 (accuracy: 87.75%, precision: 87.94%, recall: 87.50%, F1 score: 87.98%). The results highlight the effectiveness of deep learning models combined with transfer learning in achieving accurate and efficient retinal disease detection. Future research could focus on expanding the dataset and exploring hybrid architectures to enhance classification accuracy and improve generalization across various retinal conditions

Downloads

Download data is not yet available.

References

K. L. Pennington and M. M. DeAngelis, “Epidemiology of age-related macular degeneration (AMD): associations with cardiovascular disease phenotypes and lipid factors,” Eye And Vision, vol. 3, no. 1, Dec. 2016, doi: 10.1186/s40662-016-0063-5.

G. Atteia, N. A. Samee, and H. Z. Hassan, “DFTSA-Net: Deep Feature Transfer-Based Stacked Autoencoder Network for DME diagnosis,” Entropy, vol. 23, no. 10, p. 1251, Sep. 2021, doi: 10.3390/e23101251.

Q. D. Nguyen, S. M. Shah, E. Van Anden, J. U. Sung, S. Vitale, and P. A. Campochiaro, “Supplemental oxygen improves diabetic macular edema: a pilot study,” Investigative Ophthalmology & Visual Science, vol. 45, no. 2, p. 617, Jan. 2004, doi: 10.1167/iovs.03-0557.

G. Rajesh, X. M. Raajini, K. M. Sagayam, and H. Dang, “A statistical approach for high order epistasis interaction detection for prediction of diabetic macular edema,” Informatics in Medicine Unlocked, vol. 20, p. 100362, Jan. 2020, doi: 10.1016/j.imu.2020.100362.

J. W. Crabb et al., “Drusen proteome analysis: An approach to the etiology of age-related macular degeneration,” Proceedings of the National Academy of Sciences, vol. 99, no. 23, pp. 14682–14687, Oct. 2002, doi: 10.1073/pnas.222551899.

S. Loukovaara et al., “Indications of lymphatic endothelial differentiation and endothelial progenitor cell activation in the pathology of proliferative diabetic retinopathy,” Acta Ophthalmologica, vol. 93, no. 6, pp. 512–523, Apr. 2015, doi: 10.1111/aos.12741.

T. A. Ciulla, A. G. Amador, and B. Zinman, “Diabetic retinopathy and diabetic macular edema,” Diabetes Care, vol. 26, no. 9, pp. 2653–2664, Sep. 2003, doi: 10.2337/diacare.26.9.2653.

S. Saha et al., “Automated detection and classification of early AMD biomarkers using deep learning,” Scientific Reports, vol. 9, no. 1, Jul. 2019, doi: 10.1038/s41598-019-47390-3.

J. De Fauw et al., “Clinically applicable deep learning for diagnosis and referral in retinal disease,” Nature Medicine, vol. 24, no. 9, pp. 1342–1350, Aug. 2018, doi: 10.1038/s41591-018-0107-6.

W. Lu, Y. Tong, Y. Yu, Y. Xing, C. Chen, and Y. Shen, “Deep Learning-Based Automated Classification of Multi-Categorical Abnormalities from optical coherence tomography images,” Translational Vision Science & Technology, vol. 7, no. 6, p. 41, Dec. 2018, doi: 10.1167/tvst.7.6.41.

G. An et al., “Glaucoma Diagnosis with Machine Learning Based on Optical Coherence Tomography and Color Fundus Images,” Journal of Healthcare Engineering, vol. 2019, pp. 1–9, Feb. 2019, doi: 10.1155/2019/4061313.

L. Fang, C. Wang, S. Li, H. Rabbani, X. Chen, and Z. Liu, “Attention to Lesion: Lesion-Aware Convolutional Neural Network for Retinal Optical coherence Tomography image classification,” IEEE Transactions on Medical Imaging, vol. 38, no. 8, pp. 1959–1970, Feb. 2019, doi: 10.1109/tmi.2019.2898414.

J. Wang et al., “Automated diagnosis and segmentation of choroidal neovascularization in OCT angiography using deep learning,” Biomedical Optics Express, vol. 11, no. 2, p. 927, Jan. 2020, doi: 10.1364/boe.379977.

F. Y. Shih and H. Patel, “Deep Learning classification on optical coherence tomography retina images,” International Journal of Pattern Recognition and Artificial Intelligence, vol. 34, no. 08, p. 2052002, Sep. 2019, doi: 10.1142/s0218001420520023.

P. Sunija, V. P. Gopi, and P. Palanisamy, “Redundancy reduced depthwise separable convolution for glaucoma classification using OCT images,” Biomedical Signal Processing and Control, vol. 71, p. 103192, Oct. 2021, doi: 10.1016/j.bspc.2021.103192.

Adel, M. M. Soliman, N. E. M. Khalifa, and K. Mostafa, “Automatic classification of retinal eye diseases from optical coherence tomography using transfer learning,” 16th International Computer Engineering Conference, Cairo, Egypt, pp. 37–42, Dec. 2020, doi: 10.1109/icenco49778.2020.9357324.

M. Elsharkawy et al., “A novel Computer-Aided diagnostic System for early detection of diabetic retinopathy using 3D-OCT Higher-Order Spatial Appearance model,” Diagnostics, vol. 12, no. 2, p. 461, Feb. 2022, doi: 10.3390/diagnostics12020461.

M. Berrimi and A. Moussaoui, "Deep learning for identifying and classifying retinal diseases," 2020 2nd International Conference on Computer and Information Sciences (ICCIS), Sakaka, Saudi Arabia, 2020, pp. 1-6, doi: 10.1109/ICCIS49240.2020.9257674.

K. Jin et al., “Multimodal deep learning with feature level fusion for identification of choroidal neovascularization activity in age‐related macular degeneration,” Acta Ophthalmologica, vol. 100, no. 2, Jun. 2021, doi: 10.1111/aos.14928.

Y. Rong et al., “Surrogate-Assisted Retinal OCT image classification based on convolutional neural networks,” IEEE Journal of Biomedical and Health Informatics, vol. 23, no. 1, pp. 253–263, Feb. 2018, doi: 10.1109/jbhi.2018.2795545.

T. Daghistani, “Using Artificial Intelligence for Analyzing Retinal Images (OCT) in People with Diabetes: Detecting Diabetic Macular Edema Using Deep Learning Approach,” Transactions on Machine Learning and Artificial Intelligence, vol. 10, no. 1, pp. 41–49, Feb. 2022, doi: 10.14738/tmlai.101.11805.

D. Rastogi, R. P. Padhy, and P. K. Sa, “Detection of Retinal Disorders in Optical Coherence Tomography using Deep Learning,” 2022 13th International Conference on Computing Communication and Networking Technologies (ICCCNT), pp. 1–7, Jul. 2019, doi: 10.1109/icccnt45670.2019.8944406.

D.-K. Hwang et al., “Artificial intelligence-based decision-making for age-related macular degeneration,” Theranostics, vol. 9, no. 1, pp. 232–245, Dec. 2018, doi: 10.7150/thno.28447.

F. Li et al., “Deep learning-based automated detection of retinal diseases using optical coherence tomography images,” Biomedical Optics Express, vol. 10, no. 12, p. 6204, Nov. 2019, doi: 10.1364/boe.10.006204.

N. Saleh, M. A. Wahed, and A. M. Salaheldin, “Transfer learning‐based platform for detecting multi‐classification retinal disorders using optical coherence tomography images,” International Journal of Imaging Systems and Technology, vol. 32, no. 3, pp. 740–752, Nov. 2021, doi: 10.1002/ima.22673.

Y. Yan et al., “Attention‐based deep learning system for automated diagnoses of age‐related macular degeneration in optical coherence tomography images,” Medical Physics, vol. 48, no. 9, pp. 4926–4934, May 2021, doi: 10.1002/mp.15002.

R. Gupta, V. Tripathi, and A. Gupta, “An Efficient Model for Detection and Classification of Internal Eye Diseases using Deep Learning,” 2021 International Conference on Computational Performance Evaluation (ComPE), pp. 045–053, Dec. 2021, doi: 10.1109/compe53109.2021.9752188.

Kermany, D.; Zhang, K.; Goldbaum, M. Large Dataset of Labeled Optical Coherence Tomography (OCT) and Chest X-ray Images. Mendeley Data 2018, 3, 10–17632.

Yang, J.; Fong, S.; Wang, H.; Hu, Q.; Lin, C.; Huang, S.; Zhao, Q. Artiﬁcial intelligence in ophthalmopathy and ultra-wide ﬁeld image: A survey. Expert Syst. Appl. 2021, 182, 115068. [CrossRef]

Szegedy et al., "Going deeper with convolutions," 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA, 2015, pp. 1-9, doi: 10.1109/CVPR.2015.7298594.

Szegedy, S. Ioffe, V. Vanhoucke, and A. Alemi, “Inception-V4, Inception-ResNet and the impact of residual connections on learning,” Proceedings of the AAAI Conference on Artificial Intelligence, vol. 31, no. 1, Feb. 2017, doi: 10.1609/aaai. v31i1.11231.

K. He, X. Zhang, S. Ren and J. Sun, "Deep Residual Learning for Image Recognition," 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 2016, pp. 770-778, doi: 10.1109/CVPR.2016.90.

F. Chollet, "Xception: Deep Learning with Depthwise Separable Convolutions," 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, 2017, pp. 1800-1807, doi: 10.1109/CVPR.2017.195.

F. N. Iandola, S. Han, M. W. Moskewicz, K. Ashraf, W. J. Dally, and K. Keutzer, “SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size,” arXiv (Cornell University), Jan. 2016, doi: 10.48550/arxiv.1602.07360.

R. Pillai, N. Sharma, and R. Gupta, “Fine-Tuned EfficientNeTB4 Transfer Learning Model for weather Classification,” 2023 3rd Asian Conference on Innovation in Technology (ASIANCON), Ravet IN, India, 2023, pp. 1–6, Aug. 2023, doi: 10.1109/asiancon58793.2023.10270698.

A. Adadi and M. Berrada, "Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI)," in IEEE Access, vol. 6, pp. 52138-52160, 2018, doi: 10.1109/ACCESS.2018.2870052.

A. B. Arrieta et al., “Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI,” Information Fusion, vol. 58, pp. 82–115, Dec. 2019, doi: 10.1016/j.inffus.2019.12.012.

Powers, David & Ailab., “Evaluation: From precision, recall and F-measure to ROC, informedness, markedness & correlation.”, J. Mach. Learn. Technol., Vol. 2, 2011, pp. 2229-3981, doi:10.9735/2229-3981.