A Hybrid Transformers-based Convolutional Neural Network Model for Keratoconus Detection in Scheimpflug-based Dynamic Corneal Deformation Videos.

IF 1.6 Q3 OPHTHALMOLOGY

Journal of Ophthalmic & Vision Research Pub Date : 2025-06-18 eCollection Date: 2025-01-01 DOI:10.18502/jovr.v20.17716

Hazem Abdelmotaal, Rossen Mihaylov Hazarbasanov, Ramin Salouti, M Hossein Nowroozzadeh, Suphi Taneri, Ali H Al-Timemy, Alexandru Lavric, Hidenori Takahashi, Siamak Yousefi

{"title":"A Hybrid Transformers-based Convolutional Neural Network Model for Keratoconus Detection in Scheimpflug-based Dynamic Corneal Deformation Videos.","authors":"Hazem Abdelmotaal, Rossen Mihaylov Hazarbasanov, Ramin Salouti, M Hossein Nowroozzadeh, Suphi Taneri, Ali H Al-Timemy, Alexandru Lavric, Hidenori Takahashi, Siamak Yousefi","doi":"10.18502/jovr.v20.17716","DOIUrl":null,"url":null,"abstract":"Purpose: To assess the performance of a hybrid Transformer-based convolutional neural network (CNN) model for automated detection of keratoconus in stand-alone Scheimpflug-based dynamic corneal deformation videos (DCDVs).Methods: We used transfer learning for feature extraction from DCDVs. These feature maps were augmented by self-attention to model long-range dependencies before classification to identify keratoconus directly. Model performance was evaluated by objective accuracy metrics based on DCDVs from two independent cohorts with 275 and 546 subjects.Results: The model's sensitivity and specificity in detecting keratoconus were 93% and 84%, respectively. The AUC of the keratoconus probability score based on the external validation database was 0.97.Conclusion: The hybrid Transformer-based model was highly sensitive and specific in discriminating normal from keratoconic eyes using DCDV(s) at levels that may prove useful in clinical practice.","PeriodicalId":16586,"journal":{"name":"Journal of Ophthalmic & Vision Research","volume":"20 ","pages":""},"PeriodicalIF":1.6000,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12260730/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Ophthalmic & Vision Research","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.18502/jovr.v20.17716","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/1/1 0:00:00","PubModel":"eCollection","JCR":"Q3","JCRName":"OPHTHALMOLOGY","Score":null,"Total":0}

引用次数: 0

Abstract

Purpose: To assess the performance of a hybrid Transformer-based convolutional neural network (CNN) model for automated detection of keratoconus in stand-alone Scheimpflug-based dynamic corneal deformation videos (DCDVs).

Methods: We used transfer learning for feature extraction from DCDVs. These feature maps were augmented by self-attention to model long-range dependencies before classification to identify keratoconus directly. Model performance was evaluated by objective accuracy metrics based on DCDVs from two independent cohorts with 275 and 546 subjects.

Results: The model's sensitivity and specificity in detecting keratoconus were 93% and 84%, respectively. The AUC of the keratoconus probability score based on the external validation database was 0.97.

Conclusion: The hybrid Transformer-based model was highly sensitive and specific in discriminating normal from keratoconic eyes using DCDV(s) at levels that may prove useful in clinical practice.

查看原文本刊更多论文

基于混合变压器的卷积神经网络模型在基于scheimpflug的动态角膜变形视频中检测圆锥角膜。

目的：评估基于混合变压器的卷积神经网络（CNN）模型在独立的基于scheimpflug的动态角膜变形视频（DCDVs）中自动检测圆锥角膜的性能。方法：采用迁移学习方法对dcdv进行特征提取。在分类之前，这些特征映射通过自我关注来增强模型的远程依赖关系，从而直接识别圆锥角膜。通过基于两个独立队列（分别有275和546名受试者）的dcv的客观准确性指标来评估模型的性能。结果：该模型检测圆锥角膜的敏感性为93%，特异性为84%。基于外部验证数据库的圆锥角膜概率评分的AUC为0.97。结论：基于混合transformer的模型在使用DCDV(s)水平区分正常眼和角膜斜视眼方面具有高度的敏感性和特异性，可用于临床实践。

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