Weakly Supervised Deep Learning-based Intracranial Hemorrhage Localization

Simple item page
dc.contributor.authorNemček, Jakubcs
dc.contributor.authorVičar, Tomášcs
dc.contributor.authorJakubíček, Romancs
dc.date.issued2022-03-01cs
dc.description.abstractIntracranial hemorrhage is a life-threatening disease, which requires fast medical intervention. Owing to the duration of data annotation, head CT images are usually available only with slice-level labeling. However, information about the exact position could be beneficial for a radiologist. This paper presents a fully automated weakly supervised method of precise hemorrhage localization in axial CT slices using only position-free labels. An algorithm based on multiple instance learning is introduced that generates hemorrhage likelihood maps for a given CT slice and even finds the coordinates of bleeding. Two different publicly available datasets are used to train and test the proposed method. The Dice coefficient, sensitivity and positive predictive value of 58.08 %, 54.72 % and 61.88 %. respectively, are achieved on data from the test dataset.en
dc.formattextcs
dc.format.extent111-116cs
dc.format.mimetypeapplication/pdfcs
dc.identifier.citationProceedings of the 15th International Joint Conference on Biomedical Engineering Systems and Technologies - (Volume 2) . 2022, p. 111-116.en
dc.identifier.doi10.5220/0010825000003123cs
dc.identifier.isbn978-989-758-552-4cs
dc.identifier.orcid0000-0003-4748-5802cs
dc.identifier.orcid0000-0002-9136-7873cs
dc.identifier.orcid0000-0003-4293-260Xcs
dc.identifier.other178071cs
dc.identifier.researcheridC-6006-2018cs
dc.identifier.researcheridD-3622-2018cs
dc.identifier.scopus57202426072cs
dc.identifier.urihttp://hdl.handle.net/11012/208176
dc.language.isoencs
dc.publisherSciTePresscs
dc.relation.ispartofProceedings of the 15th International Joint Conference on Biomedical Engineering Systems and Technologies - (Volume 2)cs
dc.relation.urihttps://www.scitepress.org/Link.aspx?doi=10.5220/0010825000003123cs
dc.rightsCreative Commons Attribution-NonCommercial-NoDerivatives 4.0 Internationalcs
dc.rights.accessopenAccesscs
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/cs
dc.subjectIntracranial Hemorrhageen
dc.subjectComputed Tomographyen
dc.subjectDeep Learningen
dc.subjectConvolutional Neural Networken
dc.subjectWeakly Supervised Learningen
dc.subjectLocalizationen
dc.subjectAttentionen
dc.subjectMultiple Instance Learningen
dc.titleWeakly Supervised Deep Learning-based Intracranial Hemorrhage Localizationen
dc.type.driverconferenceObjecten
dc.type.statusPeer-revieweden
dc.type.versionpublishedVersionen
sync.item.dbidVAV-178071en
sync.item.dbtypeVAVen
sync.item.insts2025.02.03 15:39:55en
sync.item.modts2025.01.17 15:13:46en
thesis.grantorVysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií. Ústav biomedicínského inženýrstvícs
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
108250.pdf
Size:
1.27 MB
Format:
Adobe Portable Document Format
Description:
108250.pdf
Download
Collections
Ústav biomedicínského inženýrství