Multi-Comparison of Different Ocular Imaging Modality-based Deep Learning Models for Visually Significant Cataract Detection

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...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Ophthalmology science (Online) Ročník 5; číslo 6; s. 100837
Hlavní autori: 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
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Netherlands Elsevier Inc 01.11.2025
Elsevier
Predmet:
Artificial intelligence
Cataract detection
Deep learning
Ocular imaging
Ophthalmology
Original
Retinal imaging
PSC
Ocular imaging
CI
VSC
DL
Cataract detection
DR
SINDI
AUC
Deep learning
SIMES
SCES
Artificial intelligence
Retinal imaging
Singapore Indian Eye Study
visually significant cataract
diabetic retinopathy
Singapore Malay Eye Study
posterior subcapsular
area under receiver operating characteristic curve
confidence interval
Singapore Chinese Eye Study
ISSN:2666-9145, 2666-9145
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí: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; Pdiff = .029) and diffuse anterior segment model (AUC, 94.4; 95% CI, 92.3–96.4; Pdiff = .002). There was no significant difference in AUC when comparing the retinal model with the ensemble models (all Pdiff ≥ .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.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
J.H.L.G. and X.L. contributed equally to this work.
C.-Y.C. and Y.-C.T. contributed equally to this work.
ISSN:2666-9145
2666-9145
DOI:10.1016/j.xops.2025.100837