Unsupervised and weakly supervised approaches for answer selection tasks with scarce annotations

Autor: Vallee Emmanuel, Charlet Delphine, Galassi Francesca, Marzinotto Gabriel, Clérot Fabrice, Meyer Frank

Publikováno v: Open Computer Science, Vol 9, Iss 1, Pp 136-144 (2019)

Addressing Answer Selection (AS) tasks with complex neural networks typically requires a large amount of annotated data to increase the accuracy of the models. In this work, we are interested in simple models that can potentially give good performanc

Externí odkaz: https://doaj.org/article/41d341f503bd4cbe8da95b1adc3f2635

Quantification of Lipid-Rich Core in Carotid Atherosclerosis Using Magnetic Resonance T2 Mapping: Relation to Clinical Presentation

Autor: Chai, Joshua T., Biasiolli, Luca, Li, Linqing, Alkhalil, Mohammad, Galassi, Francesca, Darby, Chris, Halliday, Alison W., Hands, Linda, Magee, Timothy, Perkins, Jeremy, Sideso, Ed, Handa, Ashok, Jezzard, Peter, Robson, Matthew D., Choudhury, Robin P.

Publikováno v: In JACC: Cardiovascular Imaging July 2017 10(7):747-756

Expert Variability and Deep Learning Performance in Spinal Cord Lesion Segmentation for Multiple Sclerosis Patients

Autor: Walsh, Ricky, Meurée, Cédric, Kerbrat, Anne, Masson, Arthur, Hussein, Burhan Rashid, Gaubert, Malo, Galassi, Francesca, Combès, Benoit

Publikováno v: 2023 IEEE 36th International Symposium on Computer-Based Medical Systems (CBMS)
CBMS 2023-36th IEEE International Symposium on Computer-Based Medical Systems (CBMS)
CBMS 2023-36th IEEE International Symposium on Computer-Based Medical Systems (CBMS), Jun 2023, L'Aquila, Italy. pp.1-8

Accepted at 2023 IEEE 36th International Symposium on Computer-Based Medical Systems (CBMS).© 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::759ce5dd9e8144cc3fb726a6689a841f
https://inria.hal.science/hal-04090598/document

A study on loss functions and decision thresholds for the segmentation of multiple sclerosis lesions on spinal cord MRI

Autor: Hussein, Burhan Rashid, Meurée, Cédric, Gaubert, Malo, Masson, Arthur, Kerbrat, Anne, Combès, Benoît, Galassi, Francesca

Publikováno v: IABM 2023-Colloque Français d'Intelligence Artificielle en Imagerie Biomédicale
IABM 2023-Colloque Français d'Intelligence Artificielle en Imagerie Biomédicale, Mar 2023, Paris, France
2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI)
20th IEEE International Symposium on Biomedical Imaging (ISBI 2023)
20th IEEE International Symposium on Biomedical Imaging (ISBI 2023), Apr 2023, Cartagena (Colombia), Colombia

International audience; Multiple sclerosis (MS) patients often present hyper-intense T2-w lesions in the spinal cord. The severe imbalance between background and lesion classes poses a major challenge to Deep Learning segmentation approaches, requiri

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::80af369475e893ae10c5164ff9d098f5
https://hal.science/hal-03865212v2/document

A Clinically-Compatible Workflow for Computer-Aided Assessment of Brain Disease Activity in Multiple Sclerosis Patients

Autor: Combès, Benoît, Kerbrat, Anne, Pasquier, Guillaume, Commowick, Olivier, Le Bon, Brandon, Galassi, Francesca, L'Hostis, Philippe, El Graoui, Nora, Chouteau, Raphael, Cordonnier, Emmanuel, Edan, Gilles, Ferré, Jean-Christophe

Publikováno v: Frontiers in Medicine
Frontiers in Medicine, 2021, 8, pp.1-14. ⟨10.3389/fmed.2021.740248⟩
Frontiers in Medicine, Frontiers media, 2021, 8, pp.1-14. ⟨10.3389/fmed.2021.740248⟩

International audience; Over the last 10 years, the number of approved disease modifying drugs acting on the focal inflammatory process in Multiple Sclerosis (MS) has increased from 3 to 10. This wide choice offers the opportunity of a personalized m

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::c004ac0b7a030a42846508127c70a303
https://inria.hal.science/hal-03466664