T
Tom Vercauteren
Researcher at King's College London
Publications - 443
Citations - 19699
Tom Vercauteren is an academic researcher from King's College London. The author has contributed to research in topics: Segmentation & Computer science. The author has an hindex of 47, co-authored 381 publications receiving 14216 citations. Previous affiliations of Tom Vercauteren include Mauna Kea Technologies & Wellcome Trust.
Papers
More filters
Proceedings ArticleDOI
A Log-Euclidean and Total Variation based Variational Framework for Computational Sonography
Jyotirmoy Banerjee,Premal A. Patel,F. Ushakov,Donald Peebles,Jan Deprest,Jan Deprest,Sebastien Ourselin,David J. Hawkes,Tom Vercauteren,Tom Vercauteren +9 more
TL;DR: A log-Euclidean framework is introduced to ensure that the tensors are positive-definite, eventually ensuring non-negative images and regularise the underpinning ill-posed variational problem while preserving edge information by relying on a total variation penalisation of the tensor field in the log domain.
Book ChapterDOI
Permutohedral Attention Module for Efficient Non-Local Neural Networks
TL;DR: This paper proposes a new attention module, that they call Permutohedral Attention Module (PAM), to efficiently capture non-local characteristics of the image and demonstrates the efficiency and scalability of this module with the challenging task of vertebrae segmentation and labeling.
Segmentation propagation from deformable atlases for brain mapping and analysis
Marius George Linguraru,Tom Vercauteren,Mauricio Reyes,Miguel Ángel González-Ballester,Nicholas Ayache +4 more
TL;DR: In this article, a deformable atlas is used for the detection and segmentation of brain nuclei, to allow analysis of brain structures, which is based on a combination of rigid, affine and nonlinear registration, a priori information on key anatomical landmarks and propagation of the information of the atlas.
Diffeomorphic demons and the EMPIRE10 challenge
TL;DR: The registration of thoracic images is a common but still challenging problem with critical clinical applications (e.g. radiotherapy and diagnosis) and the proposed method appears to be a very e fficient registration method.
Journal ArticleDOI
Deep Quality Estimation: Creating Surrogate Models for Human Quality Ratings
Florian Kofler,Ivan Ezhov,Lucas Fidon,Izabela Horvath,E. D. L. Rosa,John LaMaster,Hongwei Li,Tom Finck,Suprosanna Shit,Johannes C. Paetzold,Spyridon Bakas,Marie Piraud,Jan S. Kirschke,Tom Vercauteren,Claus Zimmer,Benedikt Wiestler,Bjoern H. Menze +16 more
TL;DR: This work evaluates on a complex multi-class segmentation problem, specifically glioma segmentation following the BraTS annotation protocol, using surrogate quality estimation models to approximate human quality ratings on scarce expert data.