Classification of healthy and pathological human corneas by the analysis of clinical SD-OCT images using machine learning

Maëlle Vilbert, Corentin Soubeiran, Benjamin Memmi, C. Georgeon, V. Borderie, A. Chessel, K. Plamann
{"title":"Classification of healthy and pathological human corneas by the analysis of clinical SD-OCT images using machine learning","authors":"Maëlle Vilbert, Corentin Soubeiran, Benjamin Memmi, C. Georgeon, V. Borderie, A. Chessel, K. Plamann","doi":"10.1117/12.2670703","DOIUrl":null,"url":null,"abstract":"Photorefractive Keratectomy (PRK) is a widely used laser-assisted refractive surgical technique. While generally safe, in some cases it leads to subepithelial inflammation or fibrosis. We here present a robust, machine learning based algorithm for the detection of fibrosis based on Spectral Domain Optical Coherence Tomography (SD-OCT) images recorded in vivo on standard clinical devices. The images first undergo a treatment by a previously developed algorithm for standardisation. The analysis of the pre-treated images allow the extraction of quantitative parameters characterizing the transparency of human corneas. We here propose an extension of this work. Our model is based on 9 morphological quantifiers of the corneal epithelium and in particular of Bowman's layer. In a first step it is trained on SD-OCT images of corneas presenting Fuchs dystrophy, which causes similar symptoms of fibrosis. We trained a Random Forest model for the classification of corneas into \"healthy\" and \"pathological\" classes resulting in a classification accuracy (or success rate) of 97%. The transfer of this same model to images from patients who have undergone Photorefractive Keratectomy (PRK) surgery shows that the model output for probability of healthy classification provides a quantified indicator of corneal healing in the post-operative follow-up. The sensitivity of this probability was studied using repeatability data. We could therefore demonstrate the ability of artificial intelligence to detect sub-epithelial scars identified by clinicians as the origin of post-operative visual haze.","PeriodicalId":278089,"journal":{"name":"European Conference on Biomedical Optics","volume":"64 4 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"European Conference on Biomedical Optics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1117/12.2670703","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Photorefractive Keratectomy (PRK) is a widely used laser-assisted refractive surgical technique. While generally safe, in some cases it leads to subepithelial inflammation or fibrosis. We here present a robust, machine learning based algorithm for the detection of fibrosis based on Spectral Domain Optical Coherence Tomography (SD-OCT) images recorded in vivo on standard clinical devices. The images first undergo a treatment by a previously developed algorithm for standardisation. The analysis of the pre-treated images allow the extraction of quantitative parameters characterizing the transparency of human corneas. We here propose an extension of this work. Our model is based on 9 morphological quantifiers of the corneal epithelium and in particular of Bowman's layer. In a first step it is trained on SD-OCT images of corneas presenting Fuchs dystrophy, which causes similar symptoms of fibrosis. We trained a Random Forest model for the classification of corneas into "healthy" and "pathological" classes resulting in a classification accuracy (or success rate) of 97%. The transfer of this same model to images from patients who have undergone Photorefractive Keratectomy (PRK) surgery shows that the model output for probability of healthy classification provides a quantified indicator of corneal healing in the post-operative follow-up. The sensitivity of this probability was studied using repeatability data. We could therefore demonstrate the ability of artificial intelligence to detect sub-epithelial scars identified by clinicians as the origin of post-operative visual haze.
利用机器学习分析临床SD-OCT图像,对健康和病理人角膜进行分类
光屈光性角膜切除术(PRK)是一种广泛应用的激光辅助屈光手术技术。虽然通常是安全的,但在某些情况下,它会导致上皮下炎症或纤维化。我们在此提出了一种基于谱域光学相干断层扫描(SD-OCT)在标准临床设备上记录的体内图像的鲁棒的、基于机器学习的纤维化检测算法。这些图像首先要经过先前开发的标准化算法的处理。预处理图像的分析允许提取定量参数表征人类角膜的透明度。我们在此提议扩展这项工作。我们的模型是基于角膜上皮特别是鲍曼层的9个形态学量词。第一步是对呈现富氏营养不良的角膜的SD-OCT图像进行训练,富氏营养不良会导致类似的纤维化症状。我们训练了一个随机森林模型,将角膜分为“健康”和“病理”两类,分类准确率(或成功率)达到97%。将相同的模型移植到接受光屈光性角膜切除术(PRK)患者的图像中,结果表明,健康分类概率的模型输出为术后随访中角膜愈合提供了量化指标。利用可重复性数据研究了该概率的敏感性。因此,我们可以证明人工智能能够检测被临床医生确定为术后视觉模糊来源的亚上皮疤痕。
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
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:604180095
Book学术官方微信