OctNET: A Lightweight CNN for Retinal Disease Classification from Optical Coherence Tomography Images.

Autor: A P S; Department of Electronics and Communication Engineering, National Institute of Technology Tiruchirappalli, Tamilnadu-620015, India. Electronic address: sunijaprabhakaran@gmail.com., Kar S; Department of Electronics and Communication Engineering, National Institute of Technology Tiruchirappalli, Tamilnadu-620015, India. Electronic address: research@saikatkar.me., S G; Department of Electronics and Communication Engineering, National Institute of Technology Tiruchirappalli, Tamilnadu-620015, India. Electronic address: gsgayathriunnithan@gmail.com., Gopi VP; Department of Electronics and Communication Engineering, National Institute of Technology Tiruchirappalli, Tamilnadu-620015, India. Electronic address: varun@nitt.edu., Palanisamy P; Department of Electronics and Communication Engineering, National Institute of Technology Tiruchirappalli, Tamilnadu-620015, India. Electronic address: palan@nitt.edu.
Jazyk: angličtina
Zdroj: Computer methods and programs in biomedicine [Comput Methods Programs Biomed] 2021 Mar; Vol. 200, pp. 105877. Date of Electronic Publication: 2020 Nov 28.
DOI: 10.1016/j.cmpb.2020.105877
Abstrakt: Background and Objective: Retinal diseases are becoming a major health problem in recent years. Their early detection and ensuing treatment are essential to prevent visual damage, as the number of people affected by diabetes is expected to grow exponentially. Retinal diseases progress slowly, without any discernible symptoms. Optical Coherence Tomography (OCT) is a diagnostic tool capable of analyzing and identifying the quantitative discrimination in the disease affected retinal layers with high resolution. This paper proposes a deep neural network-based classifier for the computer-aided classification of Diabetic Macular Edema (DME), drusen, Choroidal NeoVascularization (CNV) from normal OCT images of the retina.
Methods: In the proposed method, we demonstrate the feasibility of classifying and detecting severe retinal pathologies from OCT images using a deep convolutional neural network having six convolutional blocks. The classification results are explained using a gradient-based class activation mapping algorithm.
Results: Training and validation of the model are performed on a public dataset of 83,484 images with expert-level disease grading of CNV, DME, and drusen, in addition to normal retinal image. We achieved a precision of 99.69%, recall of 99.69%, and accuracy of 99.69% with only three misclassifications out of 968 test cases.
Conclusion: In the proposed work, downsampling and weight sharing were introduced to improve the training efficiency and were found to reduce the trainable parameters significantly. The class activation mapping was also performed, and the output image was similar to the retina's actual color OCT images. The proposed network used only 6.9% of learnable parameters compared to the existing ResNet-50 model and yet outperformed it in classification. The proposed work can be potentially employed in real-time applications due to reduced complexity and fewer learnable parameters over other models.
Competing Interests: Declaration of Competing Interest The authors declare that they have no conflict of interests.
(Copyright © 2020 Elsevier B.V. All rights reserved.)
Databáze: MEDLINE
Externí odkaz: