Unsupervised 3D out-of-distribution detection with latent diffusion models
This addresses a crucial need for robust OOD detection in clinical deep learning systems, though it appears incremental as it adapts existing diffusion models to 3D data.
The paper tackled the problem of scaling out-of-distribution detection to 3D data, proposing a method using Latent Diffusion Models that achieved statistically significant better performance compared to a 3D-enabled baseline.
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