Repository logo
 
Publication

Deep learning methods for automatic evaluation of delayed enhancement-MRI. The results of the EMIDEC challenge

2022Journal article Restricted access
Simple item page
dc.contributor.authorLalande, Alain
dc.contributor.authorChen, Zhihao
dc.contributor.authorPommier, Thibaut
dc.contributor.authorDecourselle, Thomas
dc.contributor.authorQayyum, Abdul
dc.contributor.authorSalomon, Michel
dc.contributor.authorGinhac, Dominique
dc.contributor.authorSkandarani, Youssef
dc.contributor.authorBoucher, Arnaud
dc.contributor.authorBrahim, Khawla
dc.contributor.authorde Bruijne, Marleen
dc.contributor.authorCamarasa, Robin
dc.contributor.authorCorreia, Teresa
dc.contributor.authorFeng, Xue
dc.contributor.authorGirum, Kibrom B.
dc.contributor.authorHennemuth, Anja
dc.contributor.authorHuellebrand, Markus
dc.contributor.authorHussain, Raabid
dc.contributor.authorIvantsits, Matthias
dc.contributor.authorMa, Jun
dc.contributor.authorMeyer, Craig
dc.contributor.authorSharma, Rishabh
dc.contributor.authorShi, Jixi
dc.contributor.authorTsekos, Nikolaos V.
dc.contributor.authorVarela, Marta
dc.contributor.authorWang, Xiyue
dc.contributor.authorYang, Sen
dc.contributor.authorZhang, Hannu
dc.contributor.authorZhang, Yichi
dc.contributor.authorZhou, Yuncheng
dc.contributor.authorZhuang, Xiahai
dc.contributor.authorCouturier, Raphael
dc.contributor.authorMeriaudeau, Fabrice
dc.date.accessioned2022-11-23T09:43:58Z
dc.date.available2024-03-01T01:30:13Z
dc.date.issued2022
dc.description.abstractA key factor for assessing the state of the heart after myocardial infarction (MI) is to measure whether the myocardium segment is viable after reperfusion or revascularization therapy. Delayed enhancement-MRI or DE-MRI, which is performed 10 min after injection of the contrast agent, provides high contrast between viable and nonviable myocardium and is therefore a method of choice to evaluate the extent of MI. To automatically assess myocardial status, the results of the EMIDEC challenge that focused on this task are presented in this paper. The challenge's main objectives were twofold. First, to evaluate if deep learning methods can distinguish between non-infarct and pathological exams, i.e. exams with or without hyperenhanced area. Second, to automatically calculate the extent of myocardial infarction. The publicly available database consists of 150 exams divided into 50 cases without any hyperenhanced area after injection of a contrast agent and 100 cases with myocardial infarction (and then with a hyperenhanced area on DE-MRI), whatever their inclusion in the cardiac emergency department. Along with MRI, clinical characteristics are also provided. The obtained results issued from several works show that the automatic classification of an exam is a reachable task (the best method providing an accuracy of 0.92), and the automatic segmentation of the myocardium is possible. However, the segmentation of the diseased area needs to be improved, mainly due to the small size of these areas and the lack of contrast with the surrounding structures.pt_PT
dc.description.sponsorshipANR-17-EURE-0002; ANR-15-IDEX-0003
dc.description.versioninfo:eu-repo/semantics/publishedVersionpt_PT
dc.identifier.doi10.1016/j.media.2022.102428pt_PT
dc.identifier.issn1361-8415
dc.identifier.urihttp://hdl.handle.net/10400.1/18534
dc.language.isoengpt_PT
dc.peerreviewedyespt_PT
dc.publisherElsevierpt_PT
dc.subjectDE-MRIpt_PT
dc.subjectMyocardiumpt_PT
dc.subjectInfarctionpt_PT
dc.subjectCNNpt_PT
dc.titleDeep learning methods for automatic evaluation of delayed enhancement-MRI. The results of the EMIDEC challengept_PT
dc.typejournal article
dspace.entity.typePublication
oaire.citation.startPage102428pt_PT
oaire.citation.titleMedical Image Analysispt_PT
oaire.citation.volume79pt_PT
person.familyNameCorreia
person.givenNameTeresa
person.identifier.ciencia-idF01E-082A-5B36
person.identifier.orcid0000-0002-1606-9550
person.identifier.scopus-author-id23392190500
rcaap.rightsopenAccesspt_PT
rcaap.typearticlept_PT
relation.isAuthorOfPublication2217fb83-cb80-4f7b-b039-6476ddb910a5
relation.isAuthorOfPublication.latestForDiscovery2217fb83-cb80-4f7b-b039-6476ddb910a5

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
2108.04016.pdf
Size:
3.7 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
3.46 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

CCM2-Artigos (em revistas ou actas indexadas)