Retinal Vessels Detection Using Convolutional Neural Networks in Fundus Images

Md. Mohaimenul Islam, Tahmina Nasrin Poly, Yu-Chuan (Jack) Li

Research output: Contribution to journalArticle

Abstract

Computer-aided detection (CAD) system is a realistic option for physicians to screen fundus images. Automated segmentation of retinal vessel is in fundus important step to identify the retinal disease region. However, identification of the retinal disease region accurately is still challenging due to the varied distribution of blood vessel on noisy and low contrast fundus images. Healthcare system has been changing significantly with the emergence of machine learning (ML), deep learning (DL) and artificial intelligence (AI) in recent year. Retinal vessel detection is one such area of application of deep learning, for improving the accuracy of detection and segmentation and the quality of patient care. Recently, the convolutional neural networks (CNN) have been applied to the detection of the retinal vessel from fundus images and have demonstrated promising results. The range of accuracy of the CNN model was 0.91-0.95 and the area under the receiver operating curve was 0.09-0.98. Therefore, CNN may play a crucial role in determining the therapeutic methods and detecting the retinal vessel accurately in an individual manner. In this survey, we described the use of CNN in fundus imaging, especially focused on CNN technique, clinical application for retinal vessel detection and future prospective.
Original languageTraditional Chinese
JournalbioRxiv
DOIs
Publication statusPublished - Jan 1 2019

Cite this

Retinal Vessels Detection Using Convolutional Neural Networks in Fundus Images. / Islam, Md. Mohaimenul; Poly, Tahmina Nasrin; Li, Yu-Chuan (Jack).

In: bioRxiv, 01.01.2019.

Research output: Contribution to journalArticle

@article{d28346bc024d48b8b1786815cc70d804,
title = "Retinal Vessels Detection Using Convolutional Neural Networks in Fundus Images",
abstract = "Computer-aided detection (CAD) system is a realistic option for physicians to screen fundus images. Automated segmentation of retinal vessel is in fundus important step to identify the retinal disease region. However, identification of the retinal disease region accurately is still challenging due to the varied distribution of blood vessel on noisy and low contrast fundus images. Healthcare system has been changing significantly with the emergence of machine learning (ML), deep learning (DL) and artificial intelligence (AI) in recent year. Retinal vessel detection is one such area of application of deep learning, for improving the accuracy of detection and segmentation and the quality of patient care. Recently, the convolutional neural networks (CNN) have been applied to the detection of the retinal vessel from fundus images and have demonstrated promising results. The range of accuracy of the CNN model was 0.91-0.95 and the area under the receiver operating curve was 0.09-0.98. Therefore, CNN may play a crucial role in determining the therapeutic methods and detecting the retinal vessel accurately in an individual manner. In this survey, we described the use of CNN in fundus imaging, especially focused on CNN technique, clinical application for retinal vessel detection and future prospective.",
author = "Islam, {Md. Mohaimenul} and Poly, {Tahmina Nasrin} and Li, {Yu-Chuan (Jack)}",
year = "2019",
month = "1",
day = "1",
doi = "10.1101/737668",
language = "繁體中文",
journal = "bioRxiv",

}

TY - JOUR

T1 - Retinal Vessels Detection Using Convolutional Neural Networks in Fundus Images

AU - Islam, Md. Mohaimenul

AU - Poly, Tahmina Nasrin

AU - Li, Yu-Chuan (Jack)

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Computer-aided detection (CAD) system is a realistic option for physicians to screen fundus images. Automated segmentation of retinal vessel is in fundus important step to identify the retinal disease region. However, identification of the retinal disease region accurately is still challenging due to the varied distribution of blood vessel on noisy and low contrast fundus images. Healthcare system has been changing significantly with the emergence of machine learning (ML), deep learning (DL) and artificial intelligence (AI) in recent year. Retinal vessel detection is one such area of application of deep learning, for improving the accuracy of detection and segmentation and the quality of patient care. Recently, the convolutional neural networks (CNN) have been applied to the detection of the retinal vessel from fundus images and have demonstrated promising results. The range of accuracy of the CNN model was 0.91-0.95 and the area under the receiver operating curve was 0.09-0.98. Therefore, CNN may play a crucial role in determining the therapeutic methods and detecting the retinal vessel accurately in an individual manner. In this survey, we described the use of CNN in fundus imaging, especially focused on CNN technique, clinical application for retinal vessel detection and future prospective.

AB - Computer-aided detection (CAD) system is a realistic option for physicians to screen fundus images. Automated segmentation of retinal vessel is in fundus important step to identify the retinal disease region. However, identification of the retinal disease region accurately is still challenging due to the varied distribution of blood vessel on noisy and low contrast fundus images. Healthcare system has been changing significantly with the emergence of machine learning (ML), deep learning (DL) and artificial intelligence (AI) in recent year. Retinal vessel detection is one such area of application of deep learning, for improving the accuracy of detection and segmentation and the quality of patient care. Recently, the convolutional neural networks (CNN) have been applied to the detection of the retinal vessel from fundus images and have demonstrated promising results. The range of accuracy of the CNN model was 0.91-0.95 and the area under the receiver operating curve was 0.09-0.98. Therefore, CNN may play a crucial role in determining the therapeutic methods and detecting the retinal vessel accurately in an individual manner. In this survey, we described the use of CNN in fundus imaging, especially focused on CNN technique, clinical application for retinal vessel detection and future prospective.

U2 - 10.1101/737668

DO - 10.1101/737668

M3 - 文章

JO - bioRxiv

JF - bioRxiv

ER -