Goh Jocelyn Hui Lin, Lei Xiaofeng, Chee Miao-Li, Qian Yiming, Yu Marco, Rim Tyler Hyungtaek, Nusinovici Simon, Chen David Ziyou, Koh Kai Hui, Yew Samantha Min Er, Chen Yibing, Koh Victor Teck Chang, Sabanayagam Charumathi, Wong Tien Yin, Xu Xinxing, Goh Rick Siow Mong, Liu Yong, Cheng Ching-Yu, Tham Yih-Chung
Singapore Eye Research Institute, Singapore National Eye Centre, Singapore.
Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A∗STAR), Singapore.
Ophthalmol Sci. 2025 Jun 3;5(6):100837. doi: 10.1016/j.xops.2025.100837. eCollection 2025 Nov-Dec.
Age-related cataract is the leading cause of vision impairment. Researchers have utilized various imaging modalities, including slit beam, diffuse anterior segment, and retinal imaging, to develop deep learning (DL) algorithms for automated cataract analysis. However, the comparative performance of these algorithms across different ocular imaging modalities remains unevaluated, mainly due to the absence of standardized test sets across studies.
Retrospective study.
Across all the models, the Singapore Malay Eye Study data set was used for training (N = 7093 eyes) and internal testing (N = 1649 eyes). The Singapore Indian Eye Study (SINDI; N = 5579 eyes) and the Singapore Chinese Eye Study (SCES; N = 5658 eyes) were used for external testing. A community study data set of nonmydriatic retinal photos (N = 310 eyes) was used for external testing of the retinal model.
We developed 3 single-modality DL models (retinal, slit beam, and diffuse anterior segment photos) and 4 ensemble models (4 different combinations of the 3 single-modality models) to detect visually significant cataract (VSC). We defined eyes with VSC as having significant cataract (based on the modified Wisconsin cataract grading system) with a best-corrected visual acuity of <20/60.
Area under receiver operating characteristic curve (AUC).
In the internal test, the retinal model had the highest AUC value (97.0%; 95% confidence interval [CI], 95.9-98.2), compared with the slit beam model (AUC, 93.4%; 95% CI, 90.1-96.7; = .029) and diffuse anterior segment model (AUC, 94.4; 95% CI, 92.3-96.4; = .002). There was no significant difference in AUC when comparing the retinal model with the ensemble models (all ≥ .07). These trends were consistently observed in the external test sets. In nonmydriatic eyes, the retinal model showed reasonable performance (AUC, 89.8%; 95% CI, 89.6-89.9).
Our findings highlight the retinal model as a promising tool for detecting VSC, outperforming slit beam and diffuse anterior segment models. Because retinal photography is routine in diabetic retinopathy screening, this approach could enable opportunistic cataract screening with minimal add-on cost.
Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.
年龄相关性白内障是视力损害的主要原因。研究人员利用了各种成像方式，包括裂隙光束、眼前段弥散成像和视网膜成像，来开发用于自动白内障分析的深度学习（DL）算法。然而，这些算法在不同眼部成像方式下的比较性能仍未得到评估，主要是因为各研究中缺乏标准化测试集。
回顾性研究。
在所有模型中，新加坡马来人眼研究数据集用于训练（N = 7093只眼）和内部测试（N = 1649只眼）。新加坡印度人眼研究（SINDI；N = 5579只眼）和新加坡华人眼研究（SCES；N = 5658只眼）用于外部测试。一个非散瞳视网膜照片的社区研究数据集（N = 310只眼）用于视网膜模型的外部测试。
我们开发了3个单模态DL模型（视网膜、裂隙光束和眼前段弥散照片）和4个集成模型（3个单模态模型的4种不同组合）来检测具有视觉意义的白内障（VSC）。我们将患有VSC的眼睛定义为患有显著白内障（基于改良的威斯康星白内障分级系统）且最佳矫正视力<20/60的眼睛。
受试者操作特征曲线下面积（AUC）。
在内部测试中，视网膜模型的AUC值最高（97.0%；95%置信区间[CI]，95.9 - 98.2），相比之下，裂隙光束模型（AUC，93.4%；95% CI，90.1 - 96.7；P = 0.029）和眼前段弥散模型（AUC，94.4；95% CI，92.3 - 96.4；P = 0.002）。将视网膜模型与集成模型进行比较时，AUC无显著差异（所有P≥0.07）。这些趋势在外部测试集中也一致观察到。在非散瞳眼中，视网膜模型表现出合理的性能（AUC，89.8%；95% CI，89.6 - 89.9）。
我们的研究结果突出了视网膜模型作为检测VSC的一种有前景的工具，其性能优于裂隙光束模型和眼前段弥散模型。由于视网膜摄影在糖尿病视网膜病变筛查中是常规操作，这种方法可以在几乎不增加额外成本的情况下实现机会性白内障筛查。
在本文末尾的脚注和披露中可能会发现专有或商业披露信息。
Zotero 插件
