Detection of Diabetic Retinopathy Using Longitudinal Self-supervised Learning - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Detection of Diabetic Retinopathy Using Longitudinal Self-supervised Learning

Résumé

Longitudinal imaging is able to capture both static anatomical structures and dynamic changes in disease progression towards earlier and better patient-specific pathology management. However, conventional approaches for detecting diabetic retinopathy (DR) rarely take advantage of longitudinal information to improve DR analysis. In this work, we investigate the benefit of exploiting self-supervised learning with a longitudinal nature for DR diagnosis purposes. We compare different longitudinal self-supervised learning (LSSL) methods to model the disease progression from longitudinal retinal color fundus photographs (CFP) to detect early DR severity changes using a pair of consecutive exams. The experiments were conducted on a longitudinal DR screening dataset with or without those trained encoders (LSSL) acting as a longitudinal pretext task. Results achieve an AUC of 0.875 for the baseline (model trained from scratch) and an AUC of 0.96 (95% CI: 0.9593-0.9655 DeLong test) with a p-value <2.2e–16 on early fusion using a simple ResNet alike architecture with frozen LSSL weights, suggesting that the LSSL latent space enables to encode the dynamic of DR progression.

Dates et versions

hal-04504392 , version 1 (14-03-2024)

Identifiants

Citer

Rachid Zeghlache, Pierre-Henri Conze, Mostafa El Habib Daho, Ramin Tadayoni, Pascal Massin, et al.. Detection of Diabetic Retinopathy Using Longitudinal Self-supervised Learning. OMIA 2022: 9th International Workshop on Ophthalmic Medical Image Analysis Held in Conjunction with MICCAI 2022, Sep 2022, Singapore, Singapore. pp.43-52, ⟨10.1007/978-3-031-16525-2_5⟩. ⟨hal-04504392⟩
0 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More