scispace - formally typeset
O

Olivier Bernard

Researcher at French Institute for Research in Computer Science and Automation

Publications -  830
Citations -  42407

Olivier Bernard is an academic researcher from French Institute for Research in Computer Science and Automation. The author has contributed to research in topics: Liver transplantation & Segmentation. The author has an hindex of 96, co-authored 790 publications receiving 37878 citations. Previous affiliations of Olivier Bernard include Intelligence and National Security Alliance & Institut national des sciences appliquées.

Papers
More filters
Journal ArticleDOI

3D harmonic phase tracking with anatomical regularization

TL;DR: A novel algorithm that extends HARP to handle 3D tagged MRI images and shows low bias and strain errors under 5% for longitudinal and circumferential strains, while the second and third quartiles of the radial strain errors are in the (-5%,5%) range.
Journal ArticleDOI

Analysis of motion tracking in echocardiographic image sequences: influence of system geometry and point-spread function.

TL;DR: The tracking accuracy study shows that tracking errors are larger for the usual cartesian data, whatever the estimation algorithm, indicating that speckle tracking is more reliable when based on the unconverted polar data, and accuracy is improved by using the bilinear deformable block matching (BDBM) algorithm.
Proceedings ArticleDOI

Fast and fully automatic 3D echocardiographic segmentation using B-spline explicit active surfaces

TL;DR: It is shown that fully automatic segmentation of the left ventricle using the proposed method provides an efficient, fast and accurate solution for quantification of the main cardiac indices used in routine clinical practice.
Journal ArticleDOI

Modelling the effect of temperature on phytoplankton growth across the global ocean

TL;DR: It is shown that temperature actually drives evolution and that the optimum temperature for phytoplankton growth is strongly linked to thermal amplitude variations.
Proceedings ArticleDOI

Fully Automatic Real-Time Ejection Fraction and MAPSE Measurements in 2D Echocardiography Using Deep Neural Networks

TL;DR: It is concluded that deep learning can be used to fully automate cardiac ultrasound measurements in real-time while scanning, however more work remains to improve the accuracy.