PuSH - Publication Server of Helmholtz Zentrum München

Export: TXT Text RIS Endnote (RIS) BIB BibTeX
Bercea, C.-I. ; Wiestler, B.* ; Rueckert, D.* ; Schnabel, J.A.

Reversing the Abnormal: Pseudo-Healthy Generative Networks for Anomaly Detection.

In: (Medical Image Computing and Computer Assisted Intervention – MICCAI 2023). Berlin [u.a.]: Springer, 2023. 293-303 (Lect. Notes Comput. Sc. ; 14224 LNCS)
DOI
Early and accurate disease detection is crucial for patient management and successful treatment outcomes. However, the automatic identification of anomalies in medical images can be challenging. Conventional methods rely on large labeled datasets which are difficult to obtain. To overcome these limitations, we introduce a novel unsupervised approach, called PHANES (Pseudo Healthy generative networks for ANomaly Segmentation). Our method has the capability of reversing anomalies, i.e., preserving healthy tissue and replacing anomalous regions with pseudo-healthy (PH) reconstructions. Unlike recent diffusion models, our method does not rely on a learned noise distribution nor does it introduce random alterations to the entire image. Instead, we use latent generative networks to create masks around possible anomalies, which are refined using inpainting generative networks. We demonstrate the effectiveness of PHANES in detecting stroke lesions in T1w brain MRI datasets and show significant improvements over state-of-the-art (SOTA) methods. We believe that our proposed framework will open new avenues for interpretable, fast, and accurate anomaly segmentation with the potential to support various clinical-oriented downstream tasks. Code: https://github.com/ci-ber/PHANES
Altmetric
Tags
Annotations
Special Publikation
Hide on homepage

Edit extra information
Edit own tags
Private
Edit own annotation
Private
Hide on publication lists
on hompage
Mark as special
publikation
Publication type Article: Conference contribution
Keywords Generative Networks ; Unsupervised Anomaly Detection
Language english
Publication Year 2023
HGF-reported in Year 2023
ISSN (print) / ISBN 0302-9743
e-ISSN 1611-3349
Conference Title Medical Image Computing and Computer Assisted Intervention – MICCAI 2023
Journal Lecture Notes in Computer Science
Quellenangaben Volume: 14224 LNCS, Issue: , Pages: 293-303 Article Number: , Supplement: ,
Publisher Springer
Publishing Place Berlin [u.a.]
Institute(s) Institute for Machine Learning in Biomed Imaging (IML)
Helmholtz Artifical Intelligence Cooperation Unit (HAICU)
POF-Topic(s) 30205 - Bioengineering and Digital Health
Research field(s) Enabling and Novel Technologies
PSP Element(s) G-507100-001
G-530005-001
Grants Helmholtz Association under the joint research school "Munich School for Data Science -MUDS"
DOI 10.1007/978-3-031-43904-9_29
WOS ID 001109633700029
Scopus ID 85174691721
Erfassungsdatum 2023-11-28
[➜Report correction]