Lightweight Optic Disc and Optic Cup Segmentation Based on MobileNetv3 Convolutional Neural Network.

IF 3.4 3区 医学 Q1 ENGINEERING, MULTIDISCIPLINARY
Yuanqiong Chen, Zhijie Liu, Yujia Meng, Jianfeng Li
{"title":"Lightweight Optic Disc and Optic Cup Segmentation Based on MobileNetv3 Convolutional Neural Network.","authors":"Yuanqiong Chen, Zhijie Liu, Yujia Meng, Jianfeng Li","doi":"10.3390/biomimetics9100637","DOIUrl":null,"url":null,"abstract":"<p><p>Glaucoma represents a significant global contributor to blindness. Accurately segmenting the optic disc (OD) and optic cup (OC) to obtain precise CDR is essential for effective screening. However, existing convolutional neural network (CNN)-based segmentation techniques are often limited by high computational demands and long inference times. This paper proposes an efficient end-to-end method for OD and OC segmentation, utilizing the lightweight MobileNetv3 network as the core feature-extraction module. Our approach combines boundary branches with adversarial learning, to achieve multi-label segmentation of the OD and OC. We validated our proposed approach across three public available datasets: Drishti-GS, RIM-ONE-r3, and REFUGE. The outcomes reveal that the Dice coefficients for the segmentation of OD and OC within these datasets are 0.974/0.900, 0.966/0.875, and 0.962/0.880, respectively. Additionally, our method substantially lowers computational complexity and inference time, thereby enabling efficient and precise segmentation of the optic disc and optic cup.</p>","PeriodicalId":8907,"journal":{"name":"Biomimetics","volume":null,"pages":null},"PeriodicalIF":3.4000,"publicationDate":"2024-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11506706/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Biomimetics","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.3390/biomimetics9100637","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0

Abstract

Glaucoma represents a significant global contributor to blindness. Accurately segmenting the optic disc (OD) and optic cup (OC) to obtain precise CDR is essential for effective screening. However, existing convolutional neural network (CNN)-based segmentation techniques are often limited by high computational demands and long inference times. This paper proposes an efficient end-to-end method for OD and OC segmentation, utilizing the lightweight MobileNetv3 network as the core feature-extraction module. Our approach combines boundary branches with adversarial learning, to achieve multi-label segmentation of the OD and OC. We validated our proposed approach across three public available datasets: Drishti-GS, RIM-ONE-r3, and REFUGE. The outcomes reveal that the Dice coefficients for the segmentation of OD and OC within these datasets are 0.974/0.900, 0.966/0.875, and 0.962/0.880, respectively. Additionally, our method substantially lowers computational complexity and inference time, thereby enabling efficient and precise segmentation of the optic disc and optic cup.

基于 MobileNetv3 卷积神经网络的轻量级视盘和视杯分割。
青光眼是导致全球失明的重要原因。准确分割视盘(OD)和视杯(OC)以获得精确的 CDR 对有效筛查至关重要。然而,现有的基于卷积神经网络(CNN)的分割技术往往受到计算要求高和推理时间长的限制。本文利用轻量级 MobileNetv3 网络作为核心特征提取模块,提出了一种高效的端到端 OD 和 OC 分割方法。我们的方法将边界分支与对抗学习相结合,实现了 OD 和 OC 的多标签分割。我们在三个公开数据集上验证了我们提出的方法:Drishti-GS、RIM-ONE-r3 和 REFUGE。结果显示,在这些数据集中,OD 和 OC 分割的 Dice 系数分别为 0.974/0.900、0.966/0.875 和 0.962/0.880。此外,我们的方法大大降低了计算复杂度和推理时间,从而实现了对视盘和视杯的高效、精确分割。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Biomimetics
Biomimetics Biochemistry, Genetics and Molecular Biology-Biotechnology
CiteScore
3.50
自引率
11.10%
发文量
189
审稿时长
11 weeks
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信