Segmentation of optic disc, fovea and retinal vasculature using a single\n convolutional neural network

2017/02/01 by Jen Hong Tan, U. Rajendra Acharya, Tan, Jen Hong +7
Computer Science · Medicine · #Computer Vision and Pattern Recognition (cs.CV) #Digital Imaging for Blood Diseases #FOS: Computer and information sciences #Glaucoma and retinal disorders #Machine Learning (cs.LG) #Retinal Imaging and Analysis #Retinal and Optic Conditions

paper · pdf · doi:10.48550/arxiv.1702.00509

openalex publication_date 2017/02/01 · openalex created_date 2022/10/02 · openalex updated_date 2026/07/28

Abstract

We have developed and trained a convolutional neural network to automatically\nand simultaneously segment optic disc, fovea and blood vessels. Fundus images\nwere normalised before segmentation was performed to enforce consistency in\nbackground lighting and contrast. For every effective point in the fundus\nimage, our algorithm extracted three channels of input from the neighbourhood\nof the point and forward the response across the 7 layer network. In average,\nour segmentation achieved an accuracy of 92.68 percent on the testing set from\nDrive database.\n

Citations

• Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification

Related

• A Fully Convolutional Neural Network based Structured Prediction\n Approach Towards the Retinal Vessel Segmentation
• Segmentation of Retinal Blood Vessels Using Deep Learning
• Deep Dilated Convolutional Nets for the Automatic Segmentation of\n Retinal Vessels
• A Labeling-Free Approach to Supervising Deep Neural Networks for Retinal Blood Vessel Segmentation
• Contextual Information Enhanced Convolutional Neural Networks for Retinal Vessel Segmentation in Color Fundus Images