Constrative Learning for Kidney Transplant Analysis using MRI data and Deep Convolutional Networks - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Constrative Learning for Kidney Transplant Analysis using MRI data and Deep Convolutional Networks

Résumé

In this work, we propose contrastive learning schemes based on a 3D Convolutional Neural Network (CNN) to generate meaningful representations for kidney transplants associated with different relevant clinical information. To deal with the problem of a limited amount of data, we investigate various two-stream schemes pre-trained in a contrastive manner, where we use the cosine embedding loss to learn to discriminate pairs of inputs. Our universal 3D CNN models identify low dimensional manifolds for representing Dynamic ContrastEnhanced Magnetic Resonance Imaging series from four different follow-up exams after the transplant surgery. Feature visualization analysis highlights the relevance of our proposed contrastive pre-trainings and therefore their significance in the study of chronic dysfunction mechanisms in renal transplantation, setting the path for future research in this area. The code is available at https://github.com/leomlck/renal_transplant_imaging.
Fichier principal
Vignette du fichier
89_constrative_learning_for_kidne.pdf (4.18 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04528420 , version 1 (01-04-2024)

Identifiants

  • HAL Id : hal-04528420 , version 1

Citer

Leo Milecki, Vicky Kalogeiton, Sylvain Bodard, Jean-Michel Correas, Marc-Olivier Timsit, et al.. Constrative Learning for Kidney Transplant Analysis using MRI data and Deep Convolutional Networks. Medical Imaging with Deep Learning 2022, Jul 2022, Zürich, Switzerland. ⟨hal-04528420⟩
0 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More