arXiv Open Access 2025

Are Traditional Deep Learning Model Approaches as Effective as a Retinal-Specific Foundation Model for Ocular and Systemic Disease Detection?

Samantha Min Er Yew Xiaofeng Lei Jocelyn Hui Lin Goh Yibing Chen Sahana Srinivasan +24 lainnya
Lihat Sumber

Abstrak

Background: RETFound, a self-supervised, retina-specific foundation model (FM), showed potential in downstream applications. However, its comparative performance with traditional deep learning (DL) models remains incompletely understood. This study aimed to evaluate RETFound against three ImageNet-pretrained supervised DL models (ResNet50, ViT-base, SwinV2) in detecting ocular and systemic diseases. Methods: We fine-tuned/trained RETFound and three DL models on full datasets, 50%, 20%, and fixed sample sizes (400, 200, 100 images, with half comprising disease cases; for each DR severity class, 100 and 50 cases were used. Fine-tuned models were tested internally using the SEED (53,090 images) and APTOS-2019 (3,672 images) datasets and externally validated on population-based (BES, CIEMS, SP2, UKBB) and open-source datasets (ODIR-5k, PAPILA, GAMMA, IDRiD, MESSIDOR-2). Model performance was compared using area under the receiver operating characteristic curve (AUC) and Z-tests with Bonferroni correction (P<0.05/3). Interpretation: Traditional DL models are mostly comparable to RETFound for ocular disease detection with large datasets. However, RETFound is superior in systemic disease detection with smaller datasets. These findings offer valuable insights into the respective merits and limitation of traditional models and FMs.

Topik & Kata Kunci

Penulis (29)

S

Samantha Min Er Yew

X

Xiaofeng Lei

J

Jocelyn Hui Lin Goh

Y

Yibing Chen

S

Sahana Srinivasan

M

Miao-li Chee

K

Krithi Pushpanathan

K

Ke Zou

Q

Qingshan Hou

Z

Zhi Da Soh

C

Cancan Xue

M

Marco Chak Yan Yu

C

Charumathi Sabanayagam

E

E Shyong Tai

X

Xueling Sim

Y

Yaxing Wang

J

Jost B. Jonas

V

Vinay Nangia

G

Gabriel Dawei Yang

E

Emma Anran Ran

C

Carol Yim-Lui Cheung

Y

Yangqin Feng

J

Jun Zhou

R

Rick Siow Mong Goh

Y

Yukun Zhou

P

Pearse A. Keane

Y

Yong Liu

C

Ching-Yu Cheng

Y

Yih-Chung Tham

Format Sitasi

Yew, S.M.E., Lei, X., Goh, J.H.L., Chen, Y., Srinivasan, S., Chee, M. et al. (2025). Are Traditional Deep Learning Model Approaches as Effective as a Retinal-Specific Foundation Model for Ocular and Systemic Disease Detection?. https://arxiv.org/abs/2501.12016

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2025
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓