Partial supervision for the FeTA challenge 2021

Autor: Fidon, Lucas, Aertsen, Michael, Shit, Suprosanna, Demaerel, Philippe, Ourselin, S��bastien, Deprest, Jan, Vercauteren, Tom

This paper describes our method for our participation in the FeTA challenge2021 (team name: TRABIT). The performance of convolutional neural networks for medical image segmentation is thought to correlate positively with the number of training data.

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::eaa9de025ae3fe55e4516af5dfa8032f
http://arxiv.org/abs/2111.02408

Label-set Loss Functions for Partial Supervision: Application to Fetal Brain 3D MRI Parcellation

Autor: Fidon, Lucas, Aertsen, Michael, Emam, Doaa, Mufti, Nada, Guffens, Fr��d��ric, Deprest, Thomas, Demaerel, Philippe, David, Anna L., Melbourne, Andrew, Ourselin, S��bastien, Deprest, Jan, Vercauteren, Tom

Deep neural networks have increased the accuracy of automatic segmentation, however, their accuracy depends on the availability of a large number of fully segmented images. Methods to train deep neural networks using images for which some, but not al

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fc42d02bce6bc9adeb4f506d6abeb3a8
http://arxiv.org/abs/2107.03846

An MRF-UNet Product of Experts for Image Segmentation

Autor: Brudfors, Mikael, Balbastre, Ya��l, Ashburner, John, Rees, Geraint, Nachev, Parashkev, Ourselin, S��bastien, Cardoso, M. Jorge

While convolutional neural networks (CNNs) trained by back-propagation have seen unprecedented success at semantic segmentation tasks, they are known to struggle on out-of-distribution data. Markov random fields (MRFs) on the other hand, encode simpl

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1e4c199080feaaa2dfd0fe5de17ef294
http://arxiv.org/abs/2104.05495

Simulation of Brain Resection for Cavity Segmentation Using Self-Supervised and Semi-Supervised Learning

Autor: P��rez-Garc��a, Fernando, Rodionov, Roman, Alim-Marvasti, Ali, Sparks, Rachel, Duncan, John S., Ourselin, S��bastien

Resective surgery may be curative for drug-resistant focal epilepsy, but only 40% to 70% of patients achieve seizure freedom after surgery. Retrospective quantitative analysis could elucidate patterns in resected structures and patient outcomes to im

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ef066c403b56aa8067d4f5674848e5cf
http://arxiv.org/abs/2006.15693

A Heteroscedastic Uncertainty Model for Decoupling Sources of MRI Image Quality

Autor: Shaw, Richard, Sudre, Carole H., Ourselin, S. bastien, Cardoso, M. Jorge

Publikováno v: Shaw, R, Sudre, C H, Ourselin, S B & Cardoso, M J 2020, A Heteroscedastic Uncertainty Model for Decoupling Sources of MRI Image Quality . in T Arbel, I B Ayed, M de Bruijne, M Descoteaux, H Lombaert & C Pal (eds), Proceedings of the 3rd Conference on Medical Imaging with Deep Learning, MIDL 2020 . vol. 121, Proceedings of Machine Learning Research, ML Research Press, pp. 733-742, 3rd Conference on Medical Imaging with Deep Learning, MIDL 2020, Virtual, Online, Canada, 06/07/2020 .

Quality control (QC) of medical images is essential to ensure that downstream analyses such as segmentation can be performed successfully. Currently, QC is predominantly performed visually at significant time and operator cost. We aim to automate the

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=od_____10172::6288ed5e80d2cfea9d86b9b6b24e3bdc
https://research.vumc.nl/en/publications/a819bac3-f653-4fa4-8e31-63f63fc63f1e