CorticalFlow: A Diffeomorphic Mesh Transformer Network for Cortical Surface Reconstruction
Dec 6, 2021
Speakers
Leo Lebrat
Speaker · 0 followers
Rodrigo Santa Cruz
Speaker · 0 followers
Frederic De Gournay
Speaker · 0 followers
Pierrick Bourgeat
Speaker · 0 followers
Jurgen Fripp
Speaker · 0 followers
Clinton Fookes
Speaker · 0 followers
Olivier Salvado
Speaker · 0 followers
About
In this paper, we introduce CorticalFlow, a new geometric deep-learning model that, given a 3-dimensional image, learns to deform a reference template towards a targeted object. To conserve the template mesh’s topological properties, we train our model over a set of diffeomorphic transformations. This new implementation of a flow Ordinary Differential Equation (ODE) framework benefits from a small GPU memory footprint, allowing the generation of surfaces with several hundred thousand vertices. To reduce topological errors introduced by its discrete resolution, we derive numeric conditions which improve the manifoldness of the predicted triangle mesh. To exhibit the utility of CorticalFlow, we demonstrate its performance for the challenging task of brain cortical surface reconstruction. In contrast to the current state-of-the-art, CorticalFlow produces superior surfaces while reducing the computation time from nine and a half minutes to one second. More significantly, CorticalFlow enforces the generation of anatomically plausible surfaces; the absence of which has been a major impediment restricting the clinical relevance of such surface reconstruction methods.In this paper, we introduce CorticalFlow, a new geometric deep-learning model that, given a 3-dimensional image, learns to deform a reference template towards a targeted object. To conserve the template mesh’s topological properties, we train our model over a set of diffeomorphic transformations. This new implementation of a flow Ordinary Differential Equation (ODE) framework benefits from a small GPU memory footprint, allowing the generation of surfaces with several hundred thousand vertices. T…
Organizer
NeurIPS 2021
Account · 1.9k followers
About NeurIPS 2021
Neural Information Processing Systems (NeurIPS) is a multi-track machine learning and computational neuroscience conference that includes invited talks, demonstrations, symposia and oral and poster presentations of refereed papers. Following the conference, there are workshops which provide a less formal setting.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
On Episodes, Prototypical Networks, and Few-Shot Learning
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Deep Self-Dissimilarities as Powerful Visual Fingerprints
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Opacus: User-Friendly Differential Privacy in PyTorch
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
VoiceMixer: Adversarial Voice Style Mixup
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Balancing Fairness and Robustness via Partial Invariance
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Compression and Acceleration of Pre-trained Language Models
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%