1 code implementation • 12 Apr 2022 • Pierre-Louis Antonsanti, Thomas Benseghir, Vincent Jugnon, Mario Ghosn, Perrine Chassat, Irène Kaltenmark, Joan Glaunès
The generated deformations extend consistently to the liver volume, and are evaluated on points of interest for the physicians, with an average distance of 5. 8mm (+/- 2. 7) for vessels bifurcations and 5. 13mm (+/- 2. 5) for tumors landmarks.
no code implementations • 1 Feb 2022 • Matthis Maillard, Anton François, Joan Glaunès, Isabelle Bloch, Pietro Gori
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).
1 code implementation • 16 Jun 2021 • Anton François, Pietro Gori, Joan Glaunès
In this paper, we propose an implementation of both Large Deformation Diffeomorphic Metric Mapping (LDDMM) and Metamorphosis image registration using a semi-Lagrangian scheme for geodesic shooting.
1 code implementation • 23 Mar 2021 • Pierre-Louis Antonsanti, Joan Glaunès, Thomas Benseghir, Vincent Jugnon, Irène Kaltenmark
In computer vision and medical imaging, the problem of matching structures finds numerous applications from automatic annotation to data reconstruction.
no code implementations • NeurIPS 2020 • Jean Feydy, Joan Glaunès, Benjamin Charlier, Michael Bronstein
Geometric methods rely on tensors that can be encoded using a symbolic formula and data arrays, such as kernel and distance matrices.
no code implementations • 25 Sep 2020 • Pierre-Louis Antonsanti, Thomas Benseghir, Vincent Jugnon, Joan Glaunès
Automatic annotation of anatomical structures can help simplify workflow during interventions in numerous clinical applications but usually involves a large amount of annotated data.