Skip to content

Read-only version: For security reasons, the Research Information System (FIS) has been temporarily replaced by this read-only version. All public content and full texts remain available; login, editing, submission and statistics are not available. Questions: fis@uni-bamberg.de

Home › Publications › unORANIC : Unsupervised Orthogonalization of Anatomy and Image-Characteristic Features

Publication

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.

Details

Faculty/Chair
Faculty/Professorship
Author
Publisher Information
Otto-Friedrich-Universität : Bamberg
Year of publication
2025
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
Licence
URN
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
004 Computer science
RVK Classification
ST 330
Peer Reviewed
yes
International Distribution
yes
Open Access Journal
no
Type
Conferenceobject
URI
Activation date
2025-06-02

Permalink: https://fis.uni-bamberg.de/handle/uniba/106934 · Data as JSON · Cite: BibTeX · RIS

Data as of: 2026-11-16

Restricted read-only access: login, editing and submission are temporarily disabled.