LU-Net: a multi-task network to improve the robustness of segmentation of left ventriclular structures by deep learning in 2D echocardiography

no code implementations • 4 Apr 2020 • Sarah Leclerc, Erik Smistad, Andreas Østvik, Frederic Cervenansky, Florian Espinosa, Torvald Espeland, Erik Andreas Rye Berg, Thomas Grenier, Carole Lartizien, Pierre-Marc Jodoin, Lasse Lovstakken, Olivier Bernard

Results obtained on a large open access dataset show that our method outperforms the current best performing deep learning solution and achieved an overall segmentation accuracy lower than the intra-observer variability for the epicardial border (i. e. on average a mean absolute error of 1. 5mm and a Hausdorff distance of 5. 1mm) with 11% of outliers.

Cardiac Segmentation Segmentation

Morphological Signature for Improvement of Weakly Supervised Segmentation of Quadriceps Muscles on Magnetic Resonance Imaging Data

no code implementations • MIDL 2019 • Hoai-Thu Nguyen, Sylvain Grange, Magalie Viallon, Rémi Grange, Pierre Croisille, Olivier Bernard, Thomas Grenier

Our results show that using few atlases (3 in lieu of 6) based on our morphological measurement improves segmentation quality and decrease computational time for multi-atlas segmentation with CL.

Data Augmentation Medical Diagnosis +2

Deep Learning for Segmentation using an Open Large-Scale Dataset in 2D Echocardiography

no code implementations • 16 Aug 2019 • Sarah Leclerc, Erik Smistad, João Pedrosa, Andreas Østvik, Frederic Cervenansky, Florian Espinosa, Torvald Espeland, Erik Andreas Rye Berg, Pierre-Marc Jodoin, Thomas Grenier, Carole Lartizien, Jan D'hooge, Lasse Lovstakken, Olivier Bernard

Delineation of the cardiac structures from 2D echocardiographic images is a common clinical task to establish a diagnosis.