Multi-task learning with Multi-view Weighted Fusion Attention for artery-specific calcification analysis

Simple item page
dc.contributor.authorZhang, Weiwei
dc.contributor.authorYang, Guang
dc.contributor.authorZhang, Nan
dc.contributor.authorXu, Lei
dc.contributor.authorWang, Xiaoqing
dc.contributor.authorZhang, Yanping
dc.contributor.authorZhang, Heye
dc.contributor.authorDel Ser, Javier
dc.contributor.authorde Albuquerque, Victor Hugo C.
dc.contributor.institutionIA
dc.date.issued2021-07
dc.descriptionPublisher Copyright: © 2021 Elsevier B.V.
dc.description.abstractIn general, artery-specific calcification analysis comprises the simultaneous calcification segmentation and quantification tasks. It can help provide a thorough assessment for calcification of different coronary arteries, and further allow for an efficient and rapid diagnosis of cardiovascular diseases (CVD). However, as a high-dimensional multi-type estimation problem, artery-specific calcification analysis has not been profoundly investigated due to the intractability of obtaining discriminative feature representations. In this work, we propose a Multi-task learning network with Multi-view Weighted Fusion Attention (MMWFAnet) to solve this challenging problem. The MMWFAnet first employs a Multi-view Weighted Fusion Attention (MWFA) module to extract discriminative feature representations by enhancing the collaboration of multiple views. Specifically, MWFA weights these views to improve multi-view learning for calcification features. Based on the fusion of these multiple views, the proposed approach takes advantage of multi-task learning to obtain accurate segmentation and quantification of artery-specific calcification simultaneously. We perform experimental studies on 676 non-contrast Computed Tomography scans, achieving state-of-the-art performance in terms of multiple evaluation metrics. These compelling results evince that the proposed MMWFAnet is capable of improving the effectivity and efficiency of clinical CVD diagnosis.en
dc.description.sponsorshipJ. Del Ser receives funding support from the Consolidated Research Group MATHMODE (IT1294-19) granted by the Department of Education of the Basque Government, as well as from the ELKARTEK and EMAITEK funding programs of the Department of Economic Development and Infrastructures of the same institution. V. H. C. de Albuquerque receives support from the Brazilian National Council for Research and Development (CNPq, Grants #304315/2017-6 and #430274/2018-1 ). L. Xu receives support from a grant from the National Natural Science Foundation of China ( U1908211 ), a grant from the Capital Medical Development Research Foundation of China ( PXM2020_026272_000013 ), and a grant from the National Key Research and Development Program of China ( 2016YFC1300300 ). H. Zhang receives funding support from the National Natural Science Foundation of China (Grants U1801265 and 61771464 ), as well as a grant from the Key Program for International Cooperation Projects of Guangdong Province ( 2018A050506031 ), a grant from the Key-Area Research and Development Program of Guangdong Province ( 2019B010110001 ), the Fundamental Research Funds for 73 the Central Universities ( 19lgzd36 ), and a grant from Guangdong Natural Science Funds for Distinguished Young Scholar ( 2019B151502031 ). G. Yang receives support from the European Research Council Innovative Medicines Initiative on Development of Therapeutics and Diagnostics Combatting Coronavirus Infections Award ‘DRAGON: rapiD and secuRe AI imaging based diaGnosis, stratification, fOllow-up, and preparedness for coronavirus paNdemics’ (H2020-JTI-IMI2 101005122), and the AI for Health Imaging Award ‘CHAIMELEON: Accelerating the Lab to Market Transition of AI Tools for Cancer Management’ (H2020-SC1-FA-DTS-2019-1 952172).
dc.description.statusPeer reviewed
dc.format.extent13
dc.identifier.citationZhang , W , Yang , G , Zhang , N , Xu , L , Wang , X , Zhang , Y , Zhang , H , Del Ser , J & de Albuquerque , V H C 2021 , ' Multi-task learning with Multi-view Weighted Fusion Attention for artery-specific calcification analysis ' , Information Fusion , vol. 71 , pp. 64-76 . https://doi.org/10.1016/j.inffus.2021.01.009
dc.identifier.doi10.1016/j.inffus.2021.01.009
dc.identifier.issn1566-2535
dc.identifier.urlhttp://www.scopus.com/inward/record.url?scp=85100463819&partnerID=8YFLogxK
dc.language.isoeng
dc.relation.ispartofInformation Fusion
dc.relation.projectIDCapital Medical Development Research Foundation of China, PXM2020_026272_000013
dc.relation.projectIDDepartment of Education of the Basque Government
dc.relation.projectIDEuropean Research Council Innovative Medicines Initiative on Development of Therapeutics, H2020-JTI-IMI2 101005122-H2020-SC1-FA-DTS-2019-1 952172
dc.relation.projectIDKey Program for International Cooperation Projects of Guangdong Province, 2018A050506031
dc.relation.projectIDKey-Area Research and Development Program of Guangdong Province, 2019B010110001
dc.relation.projectIDNational Natural Science Foundation of China, NSFC, U1908211
dc.relation.projectIDConselho Nacional de Desenvolvimento Científico e Tecnológico, CNPq, 430274/2018-1-304315/2017-6
dc.relation.projectIDNational Key Research and Development Program of China, NKRDPC, 61771464-2016YFC1300300-U1801265
dc.relation.projectIDFundamental Research Funds for the Central Universities, 19lgzd36
dc.relation.projectIDNatural Science Foundation of Guangdong Province for Distinguished Young Scholars, 2019B151502031
dc.rightsinfo:eu-repo/semantics/restrictedAccess
dc.subject.keywordsArtery-specific calcification analysis
dc.subject.keywordsMulti-task learning
dc.subject.keywordsMulti-view Weighted Fusion Attention
dc.subject.keywordsMulti-view learning
dc.subject.keywordsSoftware
dc.subject.keywordsSignal Processing
dc.subject.keywordsInformation Systems
dc.subject.keywordsHardware and Architecture
dc.subject.keywordsSDG 3 - Good Health and Well-being
dc.titleMulti-task learning with Multi-view Weighted Fusion Attention for artery-specific calcification analysisen
dc.typejournal article
Files