Papers › Optic-Net: A Novel Convolutional Neural Network for Diagnosis of Retinal Diseases from...

Optic-Net: A Novel Convolutional Neural Network for Diagnosis of Retinal Diseases from Optical Tomography Images

13 Oct 2019arXiv:1910.05672archive 2025-07-28

Sharif Amit Kamran, Sourajit Saha, Ali Shihab Sabbir, Alireza Tavakkoli

Diagnosing different retinal diseases from Spectral Domain Optical Coherence Tomography (SD-OCT) images is a challenging task. Different automated approaches such as image processing, machine learning and deep learning algorithms have been used for early detection and diagnosis of retinal diseases. Unfortunately, these are prone to error and computational inefficiency, which requires further intervention from human experts. In this paper, we propose a novel convolution neural network architecture to successfully distinguish between different degeneration of retinal layers and their underlying causes. The proposed novel architecture outperforms other classification models while addressing the issue of gradient explosion. Our approach reaches near perfect accuracy of 99.8% and 100% for two separately available Retinal SD-OCT data-set respectively. Additionally, our architecture predicts retinal diseases in real time while outperforming human diagnosticians.

PaperPDFCode

Code

SharifAmit/OCT_Classification officialmentioned in papermentioned on GitHubtf report
SharifAmit/OpticNet-71 mentioned on GitHubtf report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Retinal OCT Disease Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Retinal OCT Disease Classification OCT2017 OpticNet-71 Acc 99.8 #2 of 16 Archive leaderboard report
Retinal OCT Disease Classification OCT2017 OpticNet-71 Sensitivity 99.8 #2 of 16 Archive leaderboard report
Retinal OCT Disease Classification OCT2017 Xception Acc 99.7 #3 of 16 Archive leaderboard report
Retinal OCT Disease Classification OCT2017 Xception Sensitivity 99.7 #3 of 16 Archive leaderboard report
Retinal OCT Disease Classification OCT2017 MobileNet-v2 Acc 99.4 #5 of 16 Archive leaderboard report
Retinal OCT Disease Classification OCT2017 MobileNet-v2 Sensitivity 99.4 #5 of 16 Archive leaderboard report
Retinal OCT Disease Classification OCT2017 ResNet50-v1 Acc 99.3 #7 of 16 Archive leaderboard report
Retinal OCT Disease Classification OCT2017 ResNet50-v1 Sensitivity 99.3 #7 of 16 Archive leaderboard report
Retinal OCT Disease Classification OCT2017 InceptionV3 Acc 96.6 #10 of 16 Archive leaderboard report
Retinal OCT Disease Classification OCT2017 InceptionV3 Sensitivity 97.8 #10 of 16 Archive leaderboard report
Retinal OCT Disease Classification OCT2017 InceptionV3 (limited) Acc 93.4 #13 of 16 Archive leaderboard report
Retinal OCT Disease Classification OCT2017 InceptionV3 (limited) Sensitivity 96.6 #13 of 16 Archive leaderboard report
Retinal OCT Disease Classification Srinivasan2014 OpticNet-71 Acc 100 #1 of 14 Archive leaderboard report
Retinal OCT Disease Classification Srinivasan2014 Xception Acc 99.36 #6 of 14 Archive leaderboard report
Retinal OCT Disease Classification Srinivasan2014 MobileNet-v2 Acc 97.46 #8 of 14 Archive leaderboard report
Retinal OCT Disease Classification Srinivasan2014 Karri et al. Acc 96 #9 of 14 Archive leaderboard report
Retinal OCT Disease Classification Srinivasan2014 ResNet50-v1 Acc 94.92 #11 of 14 Archive leaderboard report
Retinal OCT Disease Classification Srinivasan2014 Awais et al. Acc 93 #12 of 14 Archive leaderboard report
Retinal OCT Disease Classification Srinivasan2014 Lee et al. Acc 87.63 #14 of 14 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Convolution

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections