Improved Segmentation of Infant Retinal Images and Quantitative Vascular Analysis

Retinopathy of Prematurity is a leading cause of visual impairment in preterm infants and is characterized by dilation and tortuosity of the retinal blood vessels in the plus disease stage. However, the diagnosis of plus disease is subjective and qualitative; hence, quantitative methods and computer...

Full description

Saved in:
Bibliographic Details
Main Authors: Ying Wang, Xiaoyu Zheng, Chunlei He, Jianfeng Zhang, Shoujun Huang
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10772091/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850107444471005184
author Ying Wang
Xiaoyu Zheng
Chunlei He
Jianfeng Zhang
Shoujun Huang
author_facet Ying Wang
Xiaoyu Zheng
Chunlei He
Jianfeng Zhang
Shoujun Huang
author_sort Ying Wang
collection DOAJ
description Retinopathy of Prematurity is a leading cause of visual impairment in preterm infants and is characterized by dilation and tortuosity of the retinal blood vessels in the plus disease stage. However, the diagnosis of plus disease is subjective and qualitative; hence, quantitative methods and computer-based image analysis are required to improve the objectivity of the diagnosis. In this study, we proposed a computer-based image analysis method aimed at segmenting blood vessels and the optic disc in retinal images and providing quantitative features of the vessels to assist doctors in diagnosing plus disease. This method comprises two main stages. In the first stage, we used fundus images of a preterm infant with manually annotated vessel segmentation labels to train U-Net3 network, which is a U-Net network with the dual attention modules. Simultaneously, we used images with optic disc segmentation labels to train U-Net1 network, which is a U-Net network with half of the channels. The F1 score of the vessel segmentation network was 0.8116, and the sensitivity was 0.8273. The F1 score of the optic disc segmentation network was 0.9346, with a sensitivity of 0.9395. In the second stage, we calculated the vessel tortuosity in different retinal regions of the vessel segmentation images using least-squares linear regression. In addition, we computed the vessel density and width within the optimal region of interest, which is defined as a radius four times the diameter of the optic disc. The quantitative results revealed that the vessel tortuosity, density, and width obtained in this study can be used as diagnostic features.
format Article
id doaj-art-3fcddd1c08c34f73b15f1036e1fe96d3
institution OA Journals
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-3fcddd1c08c34f73b15f1036e1fe96d32025-08-20T02:38:35ZengIEEEIEEE Access2169-35362024-01-011218184618185710.1109/ACCESS.2024.350944110772091Improved Segmentation of Infant Retinal Images and Quantitative Vascular AnalysisYing Wang0Xiaoyu Zheng1Chunlei He2Jianfeng Zhang3https://orcid.org/0000-0001-8883-3450Shoujun Huang4https://orcid.org/0000-0002-4385-6023School of Mathematical Sciences, Zhejiang Normal University, Jinhua, ChinaDepartment of Ophthalmology, Children’s Hospital, National Clinical Research Center for Child Health, Zhejiang University School of Medicine, Hangzhou, ChinaCollege of Mathematical Medicine, Zhejiang Normal University, Jinhua, ChinaCollege of Mathematical Medicine, Zhejiang Normal University, Jinhua, ChinaCollege of Mathematical Medicine, Zhejiang Normal University, Jinhua, ChinaRetinopathy of Prematurity is a leading cause of visual impairment in preterm infants and is characterized by dilation and tortuosity of the retinal blood vessels in the plus disease stage. However, the diagnosis of plus disease is subjective and qualitative; hence, quantitative methods and computer-based image analysis are required to improve the objectivity of the diagnosis. In this study, we proposed a computer-based image analysis method aimed at segmenting blood vessels and the optic disc in retinal images and providing quantitative features of the vessels to assist doctors in diagnosing plus disease. This method comprises two main stages. In the first stage, we used fundus images of a preterm infant with manually annotated vessel segmentation labels to train U-Net3 network, which is a U-Net network with the dual attention modules. Simultaneously, we used images with optic disc segmentation labels to train U-Net1 network, which is a U-Net network with half of the channels. The F1 score of the vessel segmentation network was 0.8116, and the sensitivity was 0.8273. The F1 score of the optic disc segmentation network was 0.9346, with a sensitivity of 0.9395. In the second stage, we calculated the vessel tortuosity in different retinal regions of the vessel segmentation images using least-squares linear regression. In addition, we computed the vessel density and width within the optimal region of interest, which is defined as a radius four times the diameter of the optic disc. The quantitative results revealed that the vessel tortuosity, density, and width obtained in this study can be used as diagnostic features.https://ieeexplore.ieee.org/document/10772091/Deep convolutional neural networksplus diseaseretinopathy of prematuritysegmentation
spellingShingle Ying Wang
Xiaoyu Zheng
Chunlei He
Jianfeng Zhang
Shoujun Huang
Improved Segmentation of Infant Retinal Images and Quantitative Vascular Analysis
IEEE Access
Deep convolutional neural networks
plus disease
retinopathy of prematurity
segmentation
title Improved Segmentation of Infant Retinal Images and Quantitative Vascular Analysis
title_full Improved Segmentation of Infant Retinal Images and Quantitative Vascular Analysis
title_fullStr Improved Segmentation of Infant Retinal Images and Quantitative Vascular Analysis
title_full_unstemmed Improved Segmentation of Infant Retinal Images and Quantitative Vascular Analysis
title_short Improved Segmentation of Infant Retinal Images and Quantitative Vascular Analysis
title_sort improved segmentation of infant retinal images and quantitative vascular analysis
topic Deep convolutional neural networks
plus disease
retinopathy of prematurity
segmentation
url https://ieeexplore.ieee.org/document/10772091/
work_keys_str_mv AT yingwang improvedsegmentationofinfantretinalimagesandquantitativevascularanalysis
AT xiaoyuzheng improvedsegmentationofinfantretinalimagesandquantitativevascularanalysis
AT chunleihe improvedsegmentationofinfantretinalimagesandquantitativevascularanalysis
AT jianfengzhang improvedsegmentationofinfantretinalimagesandquantitativevascularanalysis
AT shoujunhuang improvedsegmentationofinfantretinalimagesandquantitativevascularanalysis