ub.xmlui.mirage2.page-structure.muninLogoub.xmlui.mirage2.page-structure.openResearchArchiveLogo
    • EnglishEnglish
    • norsknorsk
  • Velg spraaknorsk 
    • EnglishEnglish
    • norsknorsk
  • Administrasjon/UB
Vis innførsel 
  •   Hjem
  • Fakultet for naturvitenskap og teknologi
  • Institutt for fysikk og teknologi
  • Artikler, rapporter og annet (fysikk og teknologi)
  • Vis innførsel
  •   Hjem
  • Fakultet for naturvitenskap og teknologi
  • Institutt for fysikk og teknologi
  • Artikler, rapporter og annet (fysikk og teknologi)
  • Vis innførsel
JavaScript is disabled for your browser. Some features of this site may not work without it.

Anomaly detection-inspired few-shot medical image segmentation through self-supervision with supervoxels

Permanent lenke
https://hdl.handle.net/10037/26143
DOI
https://doi.org/10.1016/j.media.2022.102385
Thumbnail
Åpne
article.pdf (2.928Mb)
Publisert versjon (PDF)
Dato
2022-02-11
Type
Journal article
Tidsskriftartikkel
Peer reviewed

Forfatter
Hansen, Stine; Gautam, Srishti; Jenssen, Robert; Kampffmeyer, Michael
Sammendrag
Recent work has shown that label-efficient few-shot learning through self-supervision can achieve promising medical image segmentation results. However, few-shot segmentation models typically rely on prototype representations of the semantic classes, resulting in a loss of local information that can degrade performance. This is particularly problematic for the typically large and highly heterogeneous background class in medical image segmentation problems. Previous works have attempted to address this issue by learning additional prototypes for each class, but since the prototypes are based on a limited number of slices, we argue that this ad-hoc solution is insufficient to capture the background properties. Motivated by this, and the observation that the foreground class (e.g., one organ) is relatively homogeneous, we propose a novel anomaly detection-inspired approach to few-shot medical image segmentation in which we refrain from modeling the background explicitly. Instead, we rely solely on a single foreground prototype to compute anomaly scores for all query pixels. The segmentation is then performed by thresholding these anomaly scores using a learned threshold. Assisted by a novel self-supervision task that exploits the 3D structure of medical images through supervoxels, our proposed anomaly detection-inspired few-shot medical image segmentation model outperforms previous state-of-the-art approaches on two representative MRI datasets for the tasks of abdominal organ segmentation and cardiac segmentation
Er en del av
Hansen, S. (2022). Leveraging Supervoxels for Medical Image Volume Segmentation With Limited Supervision. (Doctoral thesis). https://hdl.handle.net/10037/27613.
Forlag
Elsevier
Sitering
Hansen, Gautam, Jenssen, Kampffmeyer. Anomaly detection-inspired few-shot medical image segmentation through self-supervision with supervoxels. Medical Image Analysis. 2022;78:1-12
Metadata
Vis full innførsel
Samlinger
  • Artikler, rapporter og annet (fysikk og teknologi) [1057]
Copyright 2022 The Author(s)

Bla

Bla i hele MuninEnheter og samlingerForfatterlisteTittelDatoBla i denne samlingenForfatterlisteTittelDato
Logg inn

Statistikk

Antall visninger
UiT

Munin bygger på DSpace

UiT Norges Arktiske Universitet
Universitetsbiblioteket
uit.no/ub - munin@ub.uit.no

Tilgjengelighetserklæring