kth.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Calibrating ensembles for scalable uncertainty quantification in deep learning-based medical image segmentation
Department of Applied Mathematics and Theoretical Physics, University of Cambridge, Cambridge, United Kingdom; Department of Radiology, University of Cambridge, Cambridge, United Kingdom; Department for Diagnostic and Interventional Radiology and Nuclear Medicine, University Hospital Hamburg-Eppendorf, Hamburg, Germany; Jung diagnostics GmbH, Hamburg, Germany.ORCID iD: 0000-0003-4872-4246
Department of Radiology, University of Cambridge, Cambridge, United Kingdom; Cancer Research UK Cambridge Centre, University of Cambridge, Cambridge, United Kingdom.ORCID iD: 0000-0003-3464-9206
Cancer Research UK Cambridge Centre, University of Cambridge, Cambridge, United Kingdom; Cancer Research UK Cambridge Institute, University of Cambridge, Cambridge, United Kingdom; Department of Oncology, University of Cambridge, Cambridge, United Kingdom.
Department of Radiology, University of Cambridge, Cambridge, United Kingdom; Cancer Research UK Cambridge Centre, University of Cambridge, Cambridge, United Kingdom; Medical Image Analysis & Artificial Intelligence (MIAAI), Department of Medicine, Danube Private University, Krems, Austria.
Show others and affiliations
2023 (English)In: Computers in Biology and Medicine, ISSN 0010-4825, E-ISSN 1879-0534, Vol. 163, article id 107096Article in journal (Refereed) Published
Abstract [en]

Uncertainty quantification in automated image analysis is highly desired in many applications. Typically, machine learning models in classification or segmentation are only developed to provide binary answers; however, quantifying the uncertainty of the models can play a critical role for example in active learning or machine human interaction. Uncertainty quantification is especially difficult when using deep learning-based models, which are the state-of-the-art in many imaging applications. The current uncertainty quantification approaches do not scale well in high-dimensional real-world problems. Scalable solutions often rely on classical techniques, such as dropout, during inference or training ensembles of identical models with different random seeds to obtain a posterior distribution. In this paper, we present the following contributions. First, we show that the classical approaches fail to approximate the classification probability. Second, we propose a scalable and intuitive framework for uncertainty quantification in medical image segmentation that yields measurements that approximate the classification probability. Third, we suggest the usage of k-fold cross-validation to overcome the need for held out calibration data. Lastly, we motivate the adoption of our method in active learning, creating pseudo-labels to learn from unlabeled images and human–machine collaboration.

Place, publisher, year, edition, pages
Elsevier Ltd , 2023. Vol. 163, article id 107096
Keywords [en]
Deep learning, Segmentation, Uncertainty quantification
National Category
Computer Vision and Robotics (Autonomous Systems) Radiology, Nuclear Medicine and Medical Imaging
Identifiers
URN: urn:nbn:se:kth:diva-331437DOI: 10.1016/j.compbiomed.2023.107096ISI: 001028875900001PubMedID: 37302375Scopus ID: 2-s2.0-85161555981OAI: oai:DiVA.org:kth-331437DiVA, id: diva2:1781597
Note

QC 20230710

Available from: 2023-07-10 Created: 2023-07-10 Last updated: 2023-08-10Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textPubMedScopus

Authority records

Öktem, Ozan

Search in DiVA

By author/editor
Buddenkotte, ThomasEscudero Sanchez, LorenaÖktem, OzanSala, EvisRundo, Leonardo
By organisation
Numerical Analysis, NA
In the same journal
Computers in Biology and Medicine
Computer Vision and Robotics (Autonomous Systems)Radiology, Nuclear Medicine and Medical Imaging

Search outside of DiVA

GoogleGoogle Scholar

doi
pubmed
urn-nbn

Altmetric score

doi
pubmed
urn-nbn
Total: 75 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf