Options
unORANIC : Unsupervised Orthogonalization of Anatomy and Image-Characteristic Features
Dörrich, Sebastian; Di Salvo, Francesco; Ledig, Christian (2025): unORANIC : Unsupervised Orthogonalization of Anatomy and Image-Characteristic Features, in: Bamberg: Otto-Friedrich-Universität, S. 1–11.
Faculty/Chair:
Publisher Information:
Year of publication:
2025
Pages:
Source/Other editions:
Xiaohuan Cao, Xuanang Xu, Islem Rekik, u. a. (Hrsg.), Machine Learning in Medical Imaging : 14th International Workshop, MLMI 2023, Held in Conjunction with MICCAI 2023, Vancouver, BC, Canada, October 8, 2023 ; Proceedings, Part I, Cham: Springer Nature Switzerland, 2023, S. 62–71, ISBN: 978-3-031-45672-5, 978-3-031-45673-2
Year of first publication:
2023
Language:
English
Abstract:
We introduce unORANIC, an unsupervised approach that uses an adapted loss function to drive the orthogonalization of anatomy and image-characteristic features. The method is versatile for diverse modalities and tasks, as it does not require domain knowledge, paired data samples, or labels. During test time unORANIC is applied to potentially corrupted images, orthogonalizing their anatomy and characteristic components, to subsequently reconstruct corruption-free images, showing their domain-invariant anatomy only. This feature orthogonalization further improves generalization and robustness against corruptions. We confirm this qualitatively and quantitatively on 5 distinct datasets by assessing unORANIC’s classification accuracy, corruption detection and revision capabilities. Our approach shows promise for enhancing the generalizability and robustness of practical applications in medical image analysis. The source code is available at github.com/sdoerrich97/unORANIC.
GND Keywords: ; ; ; ; ; ; ;
Deep Learning
Bildanalyse
Mensch
Anatomie
Orthogonalisierung
Robustheit
Generalisierung
Informatik
Keywords: ; ; ; ;
feature orthogonalization
robustness
corruption revision
unsupervised learning
generalization
DDC Classification:
RVK Classification:
Peer Reviewed:
Yes:
International Distribution:
Yes:
Type:
Conferenceobject
Activation date:
June 2, 2025
Permalink
https://fis.uni-bamberg.de/handle/uniba/106934