A Deep Residual Learning Implementation of Metamorphosis - Equipe Image, Modélisation, Analyse, GEométrie, Synthèse Access content directly
Conference Papers Year : 2022

A Deep Residual Learning Implementation of Metamorphosis


In medical imaging, most of the image registration methods implicitly assume a one-to-one correspondence between the source and target images (i.e., diffeomorphism). However, this is not necessarily the case when dealing with pathological medical images (e.g., presence of a tumor, lesion, etc.). To cope with this issue, the Metamorphosis model has been proposed. It modifies both the shape and the appearance of an image to deal with the geometrical and topological differences. However, the high computational time and load have hampered its applications so far. Here, we propose a deep residual learning implementation of Metamorphosis that drastically reduces the computational time at inference. Furthermore, we also show that the proposed framework can easily integrate prior knowledge of the localization of topological changes (e.g., segmentation masks) that can act as spatial regularization to correctly disentangle appearance and shape changes. We test our method on the BraTS 2021 dataset, showing that it outperforms current state-of-the-art methods in the alignment of images with brain tumors.
Fichier principal
Vignette du fichier
Metamorphoses_ISBI.pdf (993.21 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03552709 , version 1 (02-02-2022)


  • HAL Id : hal-03552709 , version 1


Matthis Maillard, Anton François, Joan Glaunès, Isabelle Bloch, Pietro Gori. A Deep Residual Learning Implementation of Metamorphosis. IEEE ISBI 2022, Mar 2022, Kolkata, India. ⟨hal-03552709⟩
236 View
100 Download


Gmail Facebook X LinkedIn More