Longitudinal self-supervised learning using neural ordinary differential equation - IMT Atlantique Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Longitudinal self-supervised learning using neural ordinary differential equation

Ramin Tadayoni
  • Fonction : Auteur
  • PersonId : 1117815

Résumé

Longitudinal analysis in medical imaging is crucial to investigate the progressive changes in anatomical structures or disease progression over time. In recent years, a novel class of algorithms has emerged with the goal of learning disease progression in a self-supervised manner, using either pairs of consecutive images or time series of images. By capturing temporal patterns without any external labels or supervision, longitudinal self-supervised learning (LSSL) has become a promising avenue. To better understand this core method, we explore in this paper the LSSL algorithm under different scenarios. The original LSSL is embedded in an auto-encoder (AE) structure. However, conventional self-supervised strategies are usually implemented in a Siamese-like manner. Therefore, (as a first novelty) in this study, we explore the use of Siamese-like LSSL. Another new core framework named neural ordinary differential equation (NODE). NODE is a neural network architecture that learns the dynamics of ordinary differential equations (ODE) through the use of neural networks. Many temporal systems can be described by ODE, including disease progression modeling. We believe that there is an interesting connection to make between LSSL and NODE. This paper aims at providing a better understanding of those core algorithms for learning the disease progression with the mentioned change. In our different experiments, we employ a longitudinal dataset, named OPHDIAT, targeting diabetic retinopathy (DR) follow-up. Our results demonstrate the application of LSSL without including a reconstruction term, as well as the potential of incorporating NODE in conjunction with LSSL.
Fichier non déposé

Dates et versions

hal-04171357 , version 1 (26-07-2023)

Identifiants

  • HAL Id : hal-04171357 , version 1

Citer

Rachid Zeghlache, Pierre-Henri Conze, Mostafa El Habib Daho, Yihao Li, Hugo Le Boité, et al.. Longitudinal self-supervised learning using neural ordinary differential equation. International Workshop on Predictive Intelligence in Medicine, Oct 2023, Vancouver (Canada), Canada. ⟨hal-04171357⟩
80 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More