Transfer Learning and Multi-Feature Fusion-Based Deep Learning Model for Idiopathic Macular Hole Diagnosis and Grading from Optical Coherence Tomography Images.

Clinical ophthalmology (Auckland, N.Z.) Pub Date : 2025-05-16 eCollection Date: 2025-01-01 DOI:10.2147/OPTH.S521558
Ye-Ting Lin, Xu Xiong, Ying-Ping Zheng, Qiong Zhou
{"title":"Transfer Learning and Multi-Feature Fusion-Based Deep Learning Model for Idiopathic Macular Hole Diagnosis and Grading from Optical Coherence Tomography Images.","authors":"Ye-Ting Lin, Xu Xiong, Ying-Ping Zheng, Qiong Zhou","doi":"10.2147/OPTH.S521558","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Idiopathic macular hole is an ophthalmic disease that seriously affects vision, and its early diagnosis and treatment have important clinical significance to reduce the occurrence of blindness. At present, OCT is the gold standard for diagnosing this disease, but its application is limited due to the need for professional ophthalmologist to diagnose it. The introduction of artificial intelligence will break this situation and make its diagnosis efficient, and how to build an effective predictive model is the key to the problem, and more clinical trials are still needed to verify it.</p><p><strong>Objective: </strong>This study aims to evaluate the role of deep learning systems in Idiopathic Macular Hole diagnosis, grading, and prediction.</p><p><strong>Methods: </strong>A single-center, retrospective study used binocular OCT images from IMH patients at the First Affiliated Hospital of Nanchang University (November 2019 - January 2023). A deep learning algorithm, including traditional omics, Resnet101, and fusion models incorporating multi-feature fusion and transfer learning, was developed. Model performance was evaluated using accuracy and AUC. Logistic regression analyzed clinical factors, and a nomogram predicted surgical risk. Analysis was conducted with SPSS 22.0 and R 3.6.3. <i>P</i> < 0.05 was statistically significant.</p><p><strong>Results: </strong>Among 229 OCT images, the traditional omics, Resnet101, and fusion models achieved accuracies of 93%, 94%, and 95%, respectively, in the training set. In the test set, the fusion model and Resnet101 correctly identified 39 images, while the traditional omics model identified 35. The nomogram had a C-index of 0.996, with macular hole diameter most strongly associated with surgical risk.</p><p><strong>Conclusion: </strong>The deep learning system with transfer learning and multi-feature fusion effectively diagnoses and grades IMH from OCT images.</p>","PeriodicalId":93945,"journal":{"name":"Clinical ophthalmology (Auckland, N.Z.)","volume":"19 ","pages":"1593-1607"},"PeriodicalIF":0.0000,"publicationDate":"2025-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12091069/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Clinical ophthalmology (Auckland, N.Z.)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.2147/OPTH.S521558","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/1/1 0:00:00","PubModel":"eCollection","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Background: Idiopathic macular hole is an ophthalmic disease that seriously affects vision, and its early diagnosis and treatment have important clinical significance to reduce the occurrence of blindness. At present, OCT is the gold standard for diagnosing this disease, but its application is limited due to the need for professional ophthalmologist to diagnose it. The introduction of artificial intelligence will break this situation and make its diagnosis efficient, and how to build an effective predictive model is the key to the problem, and more clinical trials are still needed to verify it.

Objective: This study aims to evaluate the role of deep learning systems in Idiopathic Macular Hole diagnosis, grading, and prediction.

Methods: A single-center, retrospective study used binocular OCT images from IMH patients at the First Affiliated Hospital of Nanchang University (November 2019 - January 2023). A deep learning algorithm, including traditional omics, Resnet101, and fusion models incorporating multi-feature fusion and transfer learning, was developed. Model performance was evaluated using accuracy and AUC. Logistic regression analyzed clinical factors, and a nomogram predicted surgical risk. Analysis was conducted with SPSS 22.0 and R 3.6.3. P < 0.05 was statistically significant.

Results: Among 229 OCT images, the traditional omics, Resnet101, and fusion models achieved accuracies of 93%, 94%, and 95%, respectively, in the training set. In the test set, the fusion model and Resnet101 correctly identified 39 images, while the traditional omics model identified 35. The nomogram had a C-index of 0.996, with macular hole diameter most strongly associated with surgical risk.

Conclusion: The deep learning system with transfer learning and multi-feature fusion effectively diagnoses and grades IMH from OCT images.

基于迁移学习和多特征融合的深度学习模型用于光学相干断层成像的特发性黄斑孔诊断和分级。
背景:特发性黄斑孔是一种严重影响视力的眼部疾病,早期诊断和治疗对减少失明的发生具有重要的临床意义。目前,OCT是诊断本病的金标准,但由于需要专业眼科医生诊断,其应用受到限制。人工智能的引入将打破这一局面,使其诊断更加高效,而如何构建有效的预测模型是问题的关键,还需要更多的临床试验来验证。目的:本研究旨在评估深度学习系统在特发性黄斑裂孔诊断、分级和预测中的作用。方法:采用单中心回顾性研究,使用2019年11月至2023年1月南昌大学第一附属医院IMH患者的双目OCT图像。开发了一种深度学习算法,包括传统的组学、Resnet101和融合多特征融合和迁移学习的融合模型。使用精度和AUC来评估模型性能。Logistic回归分析临床因素,用nomogram预测手术风险。采用SPSS 22.0和R 3.6.3进行分析。P < 0.05差异有统计学意义。结果:在229张OCT图像中,传统组学、Resnet101和融合模型在训练集中的准确率分别达到93%、94%和95%。在测试集中,融合模型和Resnet101正确识别了39张图像,而传统组学模型正确识别了35张。图c指数为0.996,黄斑孔直径与手术风险相关性最强。结论:基于迁移学习和多特征融合的深度学习系统能有效地对OCT图像进行IMH诊断和分级。
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
CiteScore
4.10
自引率
0.00%
发文量
0
×
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