PuSH - Publikationsserver des Helmholtz Zentrums München

Export: TXT Text RIS Endnote (RIS) BIB BibTeX
Kofler, F. ; Shit, S.* ; Ezhov, I.* ; Fidon, L.* ; Horvath, I. ; Al-Maskari, R. ; Li, H.B.* ; Bhatia, H.S. ; Loehr, T.* ; Piraud, M. ; Ertürk, A. ; Kirschke, J.* ; Peeken, J.C. ; Vercauteren, T.* ; Zimmer, C.* ; Wiestler, B.* ; Menze, B.*

blob loss: Instance Imbalance Aware Loss Functions for Semantic Segmentation.

In: (Information Processing in Medical Imaging). Berlin [u.a.]: Springer, 2023. 755-767 (Lect. Notes Comput. Sc. ; 13939 LNCS)
Verlagsversion DOI
Deep convolutional neural networks (CNN) have proven to be remarkably effective in semantic segmentation tasks. Most popular loss functions were introduced targeting improved volumetric scores, such as the Dice coefficient (DSC). By design, DSC can tackle class imbalance, however, it does not recognize instance imbalance within a class. As a result, a large foreground instance can dominate minor instances and still produce a satisfactory DSC. Nevertheless, detecting tiny instances is crucial for many applications, such as disease monitoring. For example, it is imperative to locate and surveil small-scale lesions in the follow-up of multiple sclerosis patients. We propose a novel family of loss functions, blob loss, primarily aimed at maximizing instance-level detection metrics, such as F1 score and sensitivity. Blob loss is designed for semantic segmentation problems where detecting multiple instances matters. We extensively evaluate a DSC-based blob loss in five complex 3D semantic segmentation tasks featuring pronounced instance heterogeneity in terms of texture and morphology. Compared to soft Dice loss, we achieve 5% improvement for MS lesions, 3% improvement for liver tumor, and an average 2% improvement for microscopy segmentation tasks considering F1 score.
Web of Science
Times Cited
Altmetric
1
Tags
Anmerkungen
Besondere Publikation
Auf Hompepage verbergern

Zusatzinfos bearbeiten
Eigene Tags bearbeiten
Privat
Eigene Anmerkung bearbeiten
Privat
Auf Publikationslisten für
Homepage nicht anzeigen
Als besondere Publikation
markieren
Publikationstyp Artikel: Konferenzbeitrag
Schlagwörter Instance Imbalance Awareness ; Lightsheet Microscopy ; Multiple Sclerosis ; Semantic Segmentation Loss Function
Sprache englisch
Veröffentlichungsjahr 2023
HGF-Berichtsjahr 2023
ISSN (print) / ISBN 0302-9743
e-ISSN 1611-3349
Konferenztitel Information Processing in Medical Imaging
Zeitschrift Lecture Notes in Computer Science
Quellenangaben Band: 13939 LNCS, Heft: , Seiten: 755-767 Artikelnummer: , Supplement: ,
Verlag Springer
Verlagsort Berlin [u.a.]
Institut(e) Helmholtz Artifical Intelligence Cooperation Unit (HAICU)
Institute for Tissue Engineering and Regenerative Medicine (ITERM)
Institute of Radiation Medicine (IRM)
POF Topic(s) 30205 - Bioengineering and Digital Health
30203 - Molecular Targets and Therapies
Forschungsfeld(er) Enabling and Novel Technologies
Radiation Sciences
PSP-Element(e) G-530001-001
G-505800-001
G-501300-001
DOI 10.1007/978-3-031-34048-2_58
WOS ID 001116102900058
Scopus ID 85163977420
Erfassungsdatum 2023-10-18
[➜Korrektur melden]