Show simple item record

AuthorDegerli, Aysen
AuthorSohrab, Fahad
AuthorKiranyaz, Serkan
AuthorGabbouj, Moncef
Available date2023-09-24T08:57:19Z
Publication Date2022
Publication NameComputing in Cardiology
ResourceScopus
ISSN2325-8861
URIhttp://dx.doi.org/10.22489/CinC.2022.242
URIhttp://hdl.handle.net/10576/47896
AbstractMyocardial infarction (MI) is the leading cause of mortaZity and morbidity in the world. Early therapeutics of MI can ensure the prevention of further myocardial necrosis. Echocardiography is the fundamental imaging technique that can reveal the earliest sign of MI. However, the scarcity of echocardiographic datasets for the MI detection is the major issue for training data-driven classification algorithms. In this study, we propose a frame-work for early detection of MI over multi-view echocardio-graphy that leverages one-class classification (OCC) techniques. The OCC techniques are used to train a model for detecting a specific target class using instances from that particular category only. We investigated the usage of uni-modal and multi-modal one-class classification techniques in the proposed framework using the HMC-QU dataset that includes apical 4-chamber (A4C) and apical 2-chamber (A2C) views in a total of 260 echocardiography recordings. Experimental results show that the multi-modal approach achieves a sensitivity level of 85.23% and F1-Score of 80.21%.
SponsorThis study was supported in part by the NSF-Business Finland Center for Visual and Decision Informatics (CVDI) Advanced Machine Learning for Industrial Applications (AMaLIA) under Grant 4183/31/2021, and in part by the Haltian Stroke-Data projects.
Languageen
PublisherIEEE Computer Society
SubjectImage and Video Processing (eess.IV)
Computer Vision and Pattern Recognition (cs.CV)
TitleEarly Myocardial Infarction Detection with One-Class Classification over Multi-view Echocardiography
TypeConference Paper
Pagination-
Volume Number2022-September
dc.accessType Abstract Only


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record