基于彩色眼底图像的无代码深度学习青光眼检测

Code-Free Deep Learning Glaucoma Detection on Color Fundus Images.

作者信息

Milad Daniel, Antaki Fares, Mikhail David, Farah Andrew, El-Khoury Jonathan, Touma Samir, Durr Georges M, Nayman Taylor, Playout Clément, Keane Pearse A, Duval Renaud

机构信息

Department of Ophthalmology, Université de Montréal, Montreal, Québec, Canada.

Centre Universitaire d'Ophtalmologie (CUO), Hôpital Maisonneuve-Rosemont, CIUSSS de l'Est-de-l'Île-de-Montréal, Montreal, Quebec, Canada.

出版信息

Ophthalmol Sci. 2025 Jan 30;5(4):100721. doi: 10.1016/j.xops.2025.100721. eCollection 2025 Jul-Aug.

DOI:10.1016/j.xops.2025.100721

PMID:40182983

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11964632/

Abstract

OBJECTIVE

Code-free deep learning (CFDL) allows clinicians with no coding experience to build their own artificial intelligence models. This study assesses the performance of CFDL in glaucoma detection from fundus images in comparison to expert-designed models.

DESIGN

Deep learning model development, testing, and validation.

SUBJECTS

A total of 101 442 labeled fundus images from the Rotterdam EyePACS Artificial Intelligence for Robust Glaucoma Screening (AIROGS) dataset were included.

METHODS

Ophthalmology trainees without coding experience designed a CFDL binary model using the Rotterdam EyePACS AIROGS dataset of fundus images (101 442 labeled images) to differentiate glaucoma from normal optic nerves. We compared our results with bespoke models from the literature. We then proceeded to externally validate our model using 2 datasets, the Retinal Fundus Glaucoma Challenge (REFUGE) and the Glaucoma grading from Multi-Modality imAges (GAMMA) at 0.1, 0.3, and 0.5 confidence thresholds.

MAIN OUTCOME MEASURES

Area under the precision-recall curve (AuPRC), sensitivity at 95% specificity (SE@95SP), accuracy, area under the receiver operating curve (AUC), and positive predictive value (PPV).

RESULTS

The CFDL model showed high performance metrics that were comparable to the bespoke deep learning models. Our single-label classification model had an AuPRC of 0.988, an SE@95SP of 95%, and an accuracy of 91% (compared with 85% SE@95SP for the top bespoke models). Using the REFUGE dataset for external validation, our model had an SE@95SP, AUC, PPV, and accuracy of 83%, 0.960%, 73% to 94%, and 95% to 98%, respectively, at the 0.1, 0.3, and 0.5 confidence threshold cutoffs. Using the GAMMA dataset for external validation at the same confidence threshold cutoffs, our model had an SE@95SP, AUC, PPV, and accuracy of 98%, 0.994%, 94% to 96%, and 94% to 97%, respectively.

CONCLUSION

The capacity of CFDL models to perform glaucoma screening using fundus images presents a compelling proof of concept, empowering clinicians to explore innovative model designs for broad glaucoma screening in the near future.

FINANCIAL DISCLOSURES

Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

摘要

目的

无代码深度学习（CFDL）使没有编码经验的临床医生能够构建自己的人工智能模型。本研究评估了CFDL在从眼底图像中检测青光眼方面的性能，并与专家设计的模型进行比较。

设计

深度学习模型的开发、测试和验证。

研究对象

纳入了来自鹿特丹EyePACS人工智能用于稳健青光眼筛查（AIROGS）数据集的总共101442张标记眼底图像。

方法

没有编码经验的眼科实习生使用鹿特丹EyePACS眼底图像AIROGS数据集（101442张标记图像）设计了一个CFDL二元模型，以区分青光眼和正常视神经。我们将我们的结果与文献中的定制模型进行了比较。然后，我们使用视网膜眼底青光眼挑战（REFUGE）和多模态图像青光眼分级（GAMMA）这两个数据集，在0.1、0.3和0.5的置信阈值下对我们的模型进行外部验证。

主要观察指标

精确召回率曲线下面积（AuPRC）、95%特异性时的灵敏度（SE@95SP）、准确率、受试者工作特征曲线下面积（AUC）和阳性预测值（PPV）。

结果

CFDL模型显示出与定制深度学习模型相当的高性能指标。我们的单标签分类模型的AuPRC为0.988，SE@95SP为95%，准确率为91%（相比之下，顶级定制模型的SE@95SP为85%）。使用REFUGE数据集进行外部验证时，在0.1、0.3和0.5的置信阈值临界值下，我们的模型的SE@95SP、AUC、PPV和准确率分别为83%、0.960%、73%至94%和95%至98%。在相同的置信阈值临界值下，使用GAMMA数据集进行外部验证时，我们的模型的SE@95SP、AUC、PPV和准确率分别为98%、0.994%、94%至96%和94%至97%。