An Explainable Deep Learning Ensemble Model for Robust Diagnosis of Diabetic Retinopathy Grading

Mohammad Shorfuzzaman; M. Shamim Hossain; Abdulmotaleb El Saddik

doi:10.1145/3469841

journal article Oct 26, 2021

An Explainable Deep Learning Ensemble Model for Robust Diagnosis of Diabetic Retinopathy Grading

Mohammad Shorfuzzaman

M. Shamim Hossain

Abdulmotaleb El Saddik

ACM Transactions on Multimedia Computing, Communications, and Applications Vol. 17 No. 3s pp. 1-24 · Association for Computing Machinery (ACM)

View at Publisher Save 10.1145/3469841

Abstract

Diabetic retinopathy (DR)
is one of the most common causes of vision loss in people who have diabetes for a prolonged period.
Convolutional neural networks (CNNs)
have become increasingly popular for computer-aided DR diagnosis using retinal fundus images. While these CNNs are highly reliable, their lack of sufficient explainability prevents them from being widely used in medical practice. In this article, we propose a novel explainable deep learning ensemble model where weights from different models are fused into a single model to extract salient features from various retinal lesions found on fundus images. The extracted features are then fed to a custom classifier for the final diagnosis of DR severity level. The model is trained on an APTOS dataset containing retinal fundus images of various DR grades using a cyclical learning rates strategy with an automatic learning rate finder for decaying the learning rate to improve model accuracy. We develop an explainability approach by leveraging gradient-weighted class activation mapping and shapely adaptive explanations to highlight the areas of fundus images that are most indicative of different DR stages. This allows ophthalmologists to view our model's decision in a way that they can understand. Evaluation results using three different datasets (APTOS, MESSIDOR, IDRiD) show the effectiveness of our model, achieving superior classification rates with a high degree of precision (0.970), sensitivity (0.980), and AUC (0.978). We believe that the proposed model, which jointly offers state-of-the-art diagnosis performance and explainability, will address the black-box nature of deep CNN models in robust detection of DR grading.

Topics

No keywords indexed for this article. Browse by subject →

References

46

[1]

10.1007/s10654-019-00560-z

[2]

10.1016/s0140-6736(09)62124-3

[3]

L. Carson, Y. Darvin, G. Margaret, and L. Tony. 2017. Automated detection of diabetic retinopathy using deep learning. In Proceedings of AMIA Joint Summits on Translational Science 2017, 147–155.

[4]

10.1016/j.imu.2020.100377

[5]

J. Krause V. Gulshan E. Rahimy P. Karth K. Widner G. S. Corrado L. Peng and D. R. Webster. 2017. Grader variability and the importance of reference standards for evaluating machine learning models for diabetic retinopathy 2017 CoRR abs/1710.01711.

[6]

M. A. Rahman, M. S. Hossain, N. A. Alrajeh, and B. B. Gupta. 2021. A multimodal, multimedia point-of-care deep learning framework for COVID-19 diagnosis. ACM Trans. Multimedia Comput. Commun. 17, 1s, Article 18 (2021), 24 pages. DOI:https://doi.org/10.1145/3421725

[7]

10.1016/j.procs.2016.07.014

[8]

10.1145/3415155

[9]

10.1145/3239576.3239589

[10]

Acceleration of Stochastic Approximation by Averaging

B. T. Polyak, A. B. Juditsky

SIAM Journal on Control and Optimization 10.1137/0330046

[11]

10.1109/wacv.2017.58

[12]

APTOS. 2019. APTOS 2019 blindness detection. https://www.kaggle.com/c/aptos2019-blindness-detectionLast. accessed October 25 2020.

[13]

10.5566/ias.1155

[14]

10.1016/j.media.2019.101561

[15]

10.1145/3241056

[16]

G. Muhammad, M. S. Hossain, and N. Kumar. 2021. EEG-Based pathology detection for home health monitoring. IEEE Journal on Selected Areas in Communications 39, 2 (2021), 603–610. DOI:10.1109/JSAC.2020.3020654

[17]

10.5120/5503-7503

[18]

10.1007/978-3-319-11071-4_11

[19]

P. P. Conde, J. de la Calleja, A. Benitez, and M. A. Medina. 2012. Image-based classification of diabetic retinopathy using machine learning. In Proceedings of the 12th International Conference on Intelligent Systems Design and Applications (ISDA). 826–830.

[20]

10.3390/s20041005

[21]

10.1109/mnet.011.2000458

[22]

M. S. Hossain, M. Al-Hammadi, and G. Muhammad. 2019. Automatic fruit classification using deep learning for industrial applications. IEEE Transactions on Industrial Informatics 15, 2 (2019), 1027–1034.

[23]

10.1371/journal.pone.0138285

[24]

Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs

Varun Gulshan, Lily Peng, Marc Coram et al.

JAMA 10.1001/jama.2016.17216

[25]

Rethinking the Inception Architecture for Computer Vision

Christian Szegedy, Vincent Vanhoucke, Sergey Ioffe et al.

2016 IEEE Conference on Computer Vision and Patter... 10.1109/cvpr.2016.308

[26]

Diabetic Retinopathy Detection. https://www.kaggle.com/c/diabetic-retinopathy-detection/data Last accessed October 30 2020.

[27]

Messidor-2 DR Grades. https://www.kaggle.com/google-brain/messidor2-dr-grades Last accessed October 30 2020.

[28]

10.1016/j.ophtha.2017.02.008

[29]

Y.-H. Li, N.-N. Yeh, S.-J. Chen, and Y.-C. Chung. 2019. Computer-assisted diagnosis for diabetic retinopathy based on fundus images using deep convolutional neural network. Mobile Information Systems 2019, Article ID 6142839. https://doi.org/10.1155/2019/6142839

[30]

10.1109/jsyst.2015.2470644

[31]

B. Tymchenko P. Marchenko and D. Spodarets. 2020. Deep learning approach to diabetic retinopathy detection. arXiv:2003.02261 [cs.LG] 2020. 10.5220/0008970805010509

[32]

M. T. Hagos and S. Kant. 2019. Transfer learning based detection of diabetic retinopathy from small dataset. CoRR abs/1905.07203.

[33]

R. Sarki S. Michalska K. Ahmed H. Wang and Y. Zhang. 2019. Convolutional neural networks for mild diabetic retinopathy detection: An experimental study. bioRxiv 2019. 10.1101/763136

[34]

10.1167/tvst.9.2.41

[35]

10.1016/j.patrec.2020.04.009

[36]

10.1016/j.measurement.2018.12.032

[37]

10.1155/2020/5801870

[38]

10.1109/embc44109.2020.9175664

[39]

A. Kind and G. Azzopardi. 2019. An explainable AI-based computer aided detection system for diabetic retinopathy using retinal fundus images. CAIP (1) 2019, 457–468.

[40]

10.1016/j.media.2020.101742

[41]

ImageNet: A large-scale hierarchical image database

Jia Deng, Wei Dong, Richard Socher et al.

2009 IEEE Conference on Computer Vision and Patter... 10.1109/cvpr.2009.5206848

[42]

Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, and Andrew Rabinovich. 2015. Going deeper with convolutions. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1–9.

[43]

Learning Deep Features for Discriminative Localization

Bolei Zhou, Aditya Khosla, Agata Lapedriza et al.

2016 IEEE Conference on Computer Vision and Patter... 10.1109/cvpr.2016.319

[44]

10.1007/s11263-019-01228-7

[45]

10.5555/3295222.3295230

[46]

B. Kenstler. Cyclical Learning Rates Implementation. https://github.com/bckenstler/CLR.

Cited By

41

Bio-Inspired Watermarking Method for Authentication of Fundus Images in Computer-Aided Diagnosis of Retinopathy

Ernesto Moya-Albor, Sandra L. Gomez-Coronel · 2024

Mathematics

Survey of explainable artificial intelligence techniques for biomedical imaging with deep neural networks

Sajid Nazir, Diane M. Dickson · 2023

Computers in Biology and Medicine

Application of explainable artificial intelligence for healthcare: A systematic review of the last decade (2011–2022)

Hui Wen Loh, Chui Ping Ooi · 2022

Computer Methods and Programs in Bi...

Metrics

41

Citations

46

References

Details

Published: Oct 26, 2021
Vol/Issue: 17(3s)
Pages: 1-24
License: View

Authors

M

Mohammad Shorfuzzaman

Department of Computer Science, College of Computers and Information Technology, Taif University, Taif, Saudi Arabia

M

M. Shamim Hossain

Department of Software Engineering, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia

A

Abdulmotaleb El Saddik

University of Ottawa, Ottawa, Ontario, Canada

Funding

Taif University Researchers Award: TURSP-2020/79

Cite This Article

Mohammad Shorfuzzaman, M. Shamim Hossain, Abdulmotaleb El Saddik (2021). An Explainable Deep Learning Ensemble Model for Robust Diagnosis of Diabetic Retinopathy Grading. ACM Transactions on Multimedia Computing, Communications, and Applications, 17(3s), 1-24. https://doi.org/10.1145/3469841

An Explainable Deep Learning Ensemble Model for Robust Diagnosis of Diabetic Retinopathy Grading

You May Also Like