# Unsupervised 3D out-of-distribution detection with latent diffusion models Source: [Unsupervised 3D out-of-distribution detection with latent diffusion models]() Collection index: [llms.txt]() Data updated: 2025-10-26T01:30:17.231Z Authors: Mark S. Graham, Walter Hugo Lopez Pinaya, Paul Wright, Petru-Daniel Tudosiu, Yee H. Mah, James T. Teo, H. Rolf J\\"ager, David Werring, Parashkev Nachev, Sebastien Ourselin, M. Jorge Cardoso Published: 2023-07-07T18:00:38.000Z ## Abstract Methods for out-of-distribution (OOD) detection that scale to 3D data are crucial components of any real-world clinical deep learning system. Classic denoising diffusion probabilistic models (DDPMs) have been recently proposed as a robust way to perform reconstruction-based OOD detection on 2D datasets, but do not trivially scale to 3D data. In this work, we propose to use Latent Diffusion Models (LDMs), which enable the scaling of DDPMs to high-resolution 3D medical data. We validate the proposed approach on near- and far-OOD datasets and compare it to a recently proposed, 3D-enabled approach using Latent Transformer Models (LTMs). Not only does the proposed LDM-based approach achieve statistically significant better performance, it also shows less sensitivity to the underlying latent representation, more favourable memory scaling, and produces better spatial anomaly maps. Code is available at https://github.com/marksgraham/ddpm-ood ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Anomaly Detection on ADNI (test)](): Anomaly Detection; ADNI (test); Dice Score: 0.23. - [Anomaly Detection on HCP (test)](): Anomaly Detection; HCP (test); Dice Score: 21. - [Anomaly Detection on ADHD200 (test)](): Anomaly Detection; ADHD200 (test); Dice Score: 23. - [Anomaly Detection on ADNI 3 (test)](): Anomaly Detection; ADNI 3 (test); Dice Score: 24. - [Anomaly Detection on AIBL (test)](): Anomaly Detection; AIBL (test); Dice Score: 20. - [Anomaly Detection on ATLAS (test)](): Anomaly Detection; ATLAS (test); Dice Score: 0.22. ## Original sources and implementation [Original paper]() [PDF]()