Developing diverse ensemble architectures for automatic brain tumor classification

A tétel rövid nézete
dc.contributor.authorBogacsovics, Gergo
dc.contributor.authorHarangi, Balazs
dc.contributor.authorHajdu, Andras
dc.contributor.authorBogacsovics Gergo (2024-) (xxx)
dc.contributor.authorHarangi Balazs (2024-) (xxx)
dc.contributor.authorHajdu András (1973-) (matematikus, informatikus)
dc.contributor.submitterdepAdattudomány és Vizualizáció Tanszék -- 905
dc.contributor.submitterdepIK
dc.contributor.submitterdepDebreceni Egyetem
dc.date.accessioned2024-09-09T12:07:09Z
dc.date.available2024-09-09T12:07:09Z
dc.date.oa2025-03-26
dc.date.updated2024-09-09T12:07:09Z
dc.description.abstractBrain tumors pose a serious threat in our modern society, with a clear increase in global cases each year. Therefore, developing robust solutions that could automatically and reliably detect brain tumors in their early stages is of utmost importance. In our paper, we revisit the problem of building performant ensembles for clinical usage by maximizing the diversity of the member models during the training procedure. We present an improved, more robust, extended version of our framework and propose solutions that could be integrated into a Computer-Aided Diagnosis system to accurately classify some of the most common types of brain tumors: meningioma, glioma, and pituitary tumors. We show that the new framework based on the histogram loss can be seen as a natural extension of the former approach, as it also calculates the inner products of the latent vectors produced by each member to measure similarity, but at the same time, it also makes it possible to capture more complex patterns. We also present several variants of our framework to incorporate member models with varying dimensional feature vectors and to cope with imbalanced datasets. We evaluate our solutions on a clinically tested dataset of 3,064 T1-weighted contrast-enhanced magnetic resonance images and show that they greatly outperform other state-of-the-art approaches and the base architectures as well, achieving over 92% accuracy, 92% macro and weighted precision, 91% macro and 92% weighted F1 score, and over 90% macro and 92% weighted sensitivity. © The Author(s) 2024.
dc.description.correctorLB
dc.identifier.citationMultimedia Tools and Applications. -2024 (2024), p. 1-44. -Multimed Tools Appl. -1573-7721
dc.identifier.doi10.1007/s11042-024-19657-z
dc.identifier.issn1573-7721
dc.identifier.opachttps://ebib.lib.unideb.hu/ebib/CorvinaWeb?action=cclfind&resultview=long&ccltext=idno+BIBFORM123882
dc.identifier.urihttps://hdl.handle.net/2437/379959
dc.identifier.urlhttps://link.springer.com/10.1007/s11042-024-19657-z
dc.languageger
dc.languageeng
dc.rights.accessopen access article
dc.rights.ownerszerzők
dc.subject.otheridegen nyelvű folyóiratközlemény külföldi lapban
dc.subject.otherBrain tumor
dc.subject.otherDeep learning
dc.subject.otherDiversity
dc.subject.otherEnsemble learning
dc.subject.otherScreening systems
dc.titleDeveloping diverse ensemble architectures for automatic brain tumor classification
Fájlok
Eredeti köteg (ORIGINAL bundle)
Megjelenítve 1 - 1 (Összesen 1)
Nincs kép
Név:
FILE_UP_0_s11042-024-19657-z.pdf
Méret:
3.65 MB
Formátum:
Adobe Portable Document Format
Leírás:
Kiadói változat
Letöltés
Gyűjtemények
Publikációs Adatbázis