Fundus Image Analysis for Age Related Macular Degeneration: ADAM-2020\n Challenge Report

2020/09/03 by Sharath M Shankaranarayana, Shankaranarayana, Sharath M
Medicine · Computer Science · #Retinal Imaging and Analysis #Digital Imaging for Blood Diseases

paper · pdf · doi:10.48550/arxiv.2009.01548

Abstract

Age related macular degeneration (AMD) is one of the major causes for\nblindness in the elderly population. In this report, we propose deep learning\nbased methods for retinal analysis using color fundus images for computer aided\ndiagnosis of AMD. We leverage the recent state of the art deep networks for\nbuilding a single fundus image based AMD classification pipeline. We also\npropose methods for the other directly relevant and auxiliary tasks such as\nlesions detection and segmentation, fovea detection and optic disc\nsegmentation. We propose the use of generative adversarial networks (GANs) for\nthe tasks of segmentation and detection. We also propose a novel method of\nfovea detection using GANs.\n

Related

• AMDNet23: A combined deep Contour-based Convolutional Neural Network and Long Short Term Memory system to diagnose Age-related Macular Degeneration
• Surpassing state of the art on AMD area estimation from RGB fundus images through careful selection of U-Net architectures and loss functions for class imbalance
• Unsupervised deep learning for grading of age-related macular degeneration using retinal fundus images
• A multi-task deep learning model for the classification of Age-related Macular Degeneration
• Multi-Scale Convolutional Neural Network for Automated AMD Classification using Retinal OCT Images