N
Nicholas Ayache
Researcher at French Institute for Research in Computer Science and Automation
Publications - 639
Citations - 47063
Nicholas Ayache is an academic researcher from French Institute for Research in Computer Science and Automation. The author has contributed to research in topics: Segmentation & Image registration. The author has an hindex of 97, co-authored 624 publications receiving 43140 citations. Previous affiliations of Nicholas Ayache include University of Las Palmas de Gran Canaria & Mauna Kea Technologies.
Papers
More filters
Journal ArticleDOI
Deep Learning for the Detection, Localization, and Characterization of Focal Liver Lesions on Abdominal US Images.
Hind Dadoun,Anne-Laure Rousseau,Eric de Kerviler,Jean Michel Correas,A.-M. Tissier,Fanny Joujou,Sylvain Bodard,Kemel Khezzane,Constance de Margerie-Mellon,Hervé Delingette,Nicholas Ayache +10 more
TL;DR: DETR demonstrated high specificity for detection, localization, and characterization of FLLs on abdominal US images and met or exceeded that of two experts and Faster R-CNN for these tasks.
A Grid Service for the Interactive Use of a Parallel Non-Rigid Registration Algorithm
TL;DR: In this article, a registration grid service is proposed to improve the usability of a non-rigid registration software running in parallel on a cluster of workstations, which is composed of a graphical user interface on the user side that interacts in a complex and fluid manner with the registration system running on a remote parallel computer.
Journal ArticleDOI
Detection, Localization, and Characterization of Focal Liver Lesions in Abdominal US with Deep Learning
Hind Dadoun,Anne-Laure Rousseau,Eric de Kerviler,Jean Michel Correas,A.-M. Tissier,Fanny Joujou,Sylvain Bodard,Kemel Khezzane,Constance de Margerie-Mellon,Hervé Delingette,Nicholas Ayache +10 more
TL;DR: In this article , two object detectors, Faster R-CNN and Detection Transformer (DETR), were fine-tuned on a dataset of 1026 patients (n = 2551 B-mode abdominal US images obtained between 2014 and 2018).
Proceedings ArticleDOI
Reconstruction of buildings from multiple high resolution images
TL;DR: An algorithm to reconstruct buildings in an urban scene from a large number of aerial images using a digital elevation model obtained with multiple baseline stereomatching method that is very efficient in removing matching ambiguities and improving the precision of the elevation estimates.
Book ChapterDOI
Myocardial Infarct Localization Using Neighbourhood Approximation Forests
TL;DR: A machine-learning algorithm for the automatic localization of myocardial infarct in the left ventricle is presented, which constructs neighbourhood approximation forests, which are trained with previously diagnosed 4D cardiac sequences.