PuSH - Publikationsserver des Helmholtz Zentrums München

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)
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.
Altmetric
Weitere Metriken?
[➜Einloggen]
Zusatzinfos bearbeiten [➜Einloggen]
Publikationstyp Artikel: Konferenzbeitrag
Korrespondenzautor
Schlagwörter Instance Imbalance Awareness ; Lightsheet Microscopy ; Multiple Sclerosis ; Semantic Segmentation Loss Function
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.]
Nichtpatentliteratur Publikationen
Institut(e) Helmholtz Artifical Intelligence Cooperation Unit (HAICU)
Institute for Tissue Engineering and Regenerative Medicine (ITERM)
Institute of Radiation Medicine (IRM)