Multi-Path Recurrent U-Net Segmentation of Retinal Fundus Image
Diabetes can induce diseases including diabetic retinopathy, cataracts, glaucoma, etc. The blindness caused by these diseases is irreversible. Early analysis of retinal fundus images, including optic disc and optic cup detection and retinal blood vessel segmentation, can effectively identify these d...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-05-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/10/11/3777 |
id |
doaj-8bb5956af72941b3a9b3ea3a104bfe4d |
---|---|
record_format |
Article |
spelling |
doaj-8bb5956af72941b3a9b3ea3a104bfe4d2020-11-25T02:33:29ZengMDPI AGApplied Sciences2076-34172020-05-01103777377710.3390/app10113777Multi-Path Recurrent U-Net Segmentation of Retinal Fundus ImageYun Jiang0Falin Wang1Jing Gao2Simin Cao3College of Computer Science and Engineering, Northwest Normal University, Lanzhou 730070, ChinaCollege of Computer Science and Engineering, Northwest Normal University, Lanzhou 730070, ChinaCollege of Computer Science and Engineering, Northwest Normal University, Lanzhou 730070, ChinaCollege of Computer Science and Engineering, Northwest Normal University, Lanzhou 730070, ChinaDiabetes can induce diseases including diabetic retinopathy, cataracts, glaucoma, etc. The blindness caused by these diseases is irreversible. Early analysis of retinal fundus images, including optic disc and optic cup detection and retinal blood vessel segmentation, can effectively identify these diseases. The existing methods lack sufficient discrimination power for the fundus image and are easily affected by pathological regions. This paper proposes a novel multi-path recurrent U-Net architecture to achieve the segmentation of retinal fundus images. The effectiveness of the proposed network structure was proved by two segmentation tasks: optic disc and optic cup segmentation and retinal vessel segmentation. Our method achieved state-of-the-art results in the segmentation of the Drishti-GS1 dataset. Regarding optic disc segmentation, the accuracy and Dice values reached 0.9967 and 0.9817, respectively; as regards optic cup segmentation, the accuracy and Dice values reached 0.9950 and 0.8921, respectively. Our proposed method was also verified on the retinal blood vessel segmentation dataset DRIVE and achieved a good accuracy rate.https://www.mdpi.com/2076-3417/10/11/3777retinal image segmentationconvolutional neural networkdeep learning |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Yun Jiang Falin Wang Jing Gao Simin Cao |
spellingShingle |
Yun Jiang Falin Wang Jing Gao Simin Cao Multi-Path Recurrent U-Net Segmentation of Retinal Fundus Image Applied Sciences retinal image segmentation convolutional neural network deep learning |
author_facet |
Yun Jiang Falin Wang Jing Gao Simin Cao |
author_sort |
Yun Jiang |
title |
Multi-Path Recurrent U-Net Segmentation of Retinal Fundus Image |
title_short |
Multi-Path Recurrent U-Net Segmentation of Retinal Fundus Image |
title_full |
Multi-Path Recurrent U-Net Segmentation of Retinal Fundus Image |
title_fullStr |
Multi-Path Recurrent U-Net Segmentation of Retinal Fundus Image |
title_full_unstemmed |
Multi-Path Recurrent U-Net Segmentation of Retinal Fundus Image |
title_sort |
multi-path recurrent u-net segmentation of retinal fundus image |
publisher |
MDPI AG |
series |
Applied Sciences |
issn |
2076-3417 |
publishDate |
2020-05-01 |
description |
Diabetes can induce diseases including diabetic retinopathy, cataracts, glaucoma, etc. The blindness caused by these diseases is irreversible. Early analysis of retinal fundus images, including optic disc and optic cup detection and retinal blood vessel segmentation, can effectively identify these diseases. The existing methods lack sufficient discrimination power for the fundus image and are easily affected by pathological regions. This paper proposes a novel multi-path recurrent U-Net architecture to achieve the segmentation of retinal fundus images. The effectiveness of the proposed network structure was proved by two segmentation tasks: optic disc and optic cup segmentation and retinal vessel segmentation. Our method achieved state-of-the-art results in the segmentation of the Drishti-GS1 dataset. Regarding optic disc segmentation, the accuracy and Dice values reached 0.9967 and 0.9817, respectively; as regards optic cup segmentation, the accuracy and Dice values reached 0.9950 and 0.8921, respectively. Our proposed method was also verified on the retinal blood vessel segmentation dataset DRIVE and achieved a good accuracy rate. |
topic |
retinal image segmentation convolutional neural network deep learning |
url |
https://www.mdpi.com/2076-3417/10/11/3777 |
work_keys_str_mv |
AT yunjiang multipathrecurrentunetsegmentationofretinalfundusimage AT falinwang multipathrecurrentunetsegmentationofretinalfundusimage AT jinggao multipathrecurrentunetsegmentationofretinalfundusimage AT simincao multipathrecurrentunetsegmentationofretinalfundusimage |
_version_ |
1724813865206677504 |