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

13 Oct 2019  ·  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.

PDF Abstract

Datasets


  Add Datasets introduced or used in this paper
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Retinal OCT Disease Classification OCT2017 ResNet50-v1 Acc 99.3 # 5
Sensitivity 99.3 # 6
Retinal OCT Disease Classification OCT2017 InceptionV3 Acc 96.6 # 8
Sensitivity 97.8 # 8
Retinal OCT Disease Classification OCT2017 InceptionV3 (limited) Acc 93.4 # 11
Sensitivity 96.6 # 10
Retinal OCT Disease Classification OCT2017 OpticNet-71 Acc 99.8 # 1
Sensitivity 99.8 # 1
Retinal OCT Disease Classification OCT2017 Xception Acc 99.7 # 2
Sensitivity 99.7 # 2
Retinal OCT Disease Classification OCT2017 MobileNet-v2 Acc 99.4 # 4
Sensitivity 99.4 # 4
Retinal OCT Disease Classification Srinivasan2014 OpticNet-71 Acc 100 # 1
Retinal OCT Disease Classification Srinivasan2014 Karri et al. Acc 96 # 9
Retinal OCT Disease Classification Srinivasan2014 Xception Acc 99.36 # 4
Retinal OCT Disease Classification Srinivasan2014 MobileNet-v2 Acc 97.46 # 7
Retinal OCT Disease Classification Srinivasan2014 ResNet50-v1 Acc 94.92 # 10
Retinal OCT Disease Classification Srinivasan2014 Lee et al. Acc 87.63 # 13
Retinal OCT Disease Classification Srinivasan2014 Awais et al. Acc 93 # 12

Methods