Image-conditioned latent rectified flow models for 3D medical anomaly localisation
File(s)
Published version
Author(s)
Type
Journal Article
Abstract
Reconstruction-based methods offer a promising solution for unsupervised anomaly detection in medical imaging tasks. These methods train generative models on healthy data alone and identify anomalies as deviations between an input image and its pseudo-healthy reconstruction. The downfall of these methods is their dependence on two assumptions that often fail in practice: that models cannot reproduce unseen pathologies, yet can faithfully reconstruct healthy tissue. A recent image-conditioned diffusion approach explicitly addresses these issues by training a model to restore synthetic anomalies inserted into healthy images. However, it operates in 2D pixel space, discarding inter-slice context and incurring high computational cost. We address both limitations by performing image-conditioned restoration in a 3D latent space using a pretrained VAE and rectified flow, capturing volumetric context whilst drastically reducing computational overhead. To mitigate false positives introduced by VAE compression, we propose using the restoration change which measures the difference between the pseudo-healthy latent restoration and the VAE reconstruction of the original, rather than the standard reconstruction error. We further experiment with applying the synthetic anomaly training task directly in latent space to improve sensitivity to low-contrast anomalies, and demonstrate that ensembling models trained with pixel-space and latent-space anomalies yields the strongest overall performance. Our method establishes a new state-of-the-art for residual-based medical image anomaly detection across various benchmarks. Full code will be made available upon acceptance.
Date Issued
2026-07-24
Date Acceptance
2026-05-25
Citation
Frontiers in Radiology, 2026, 6
ISSN
2673-8740
Publisher
Frontiers Media S.A.
Journal / Book Title
Frontiers in Radiology
Volume
6
Copyright Statement
© 2026 Baugh, Müller, Cechnicka, Gu Baugh, Bonnici, Myles and Kainz. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
License URL
Identifier
10.3389/fradi.2026.1847193
Subjects
anomaly detection
anomaly localisation
medical image analysis
pseudo-healthy restoration
rectified flow models
self-supervised learning
Publication Status
Published
Article Number
1847193