Out-of-Distribution Detection in Medical Imaging via Diffusion Trajectories

TL;DR

This paper introduces a novel, efficient out-of-distribution detection method for medical imaging that uses diffusion trajectories from a pre-trained denoising diffusion model, achieving state-of-the-art results with reduced computational cost.

Contribution

The paper presents a reconstruction-free OOD detection approach leveraging diffusion trajectories, which generalizes across datasets and improves detection accuracy while reducing inference complexity.

Findings

Achieves state-of-the-art OOD detection performance on multiple benchmarks.

Reduces inference computational cost by using only five diffusion steps.

Improves detection accuracy by up to 10.43% for Near-OOD and 18.10% for Far-OOD.

Abstract

In medical imaging, unsupervised out-of-distribution (OOD) detection offers an attractive approach for identifying pathological cases with extremely low incidence rates. In contrast to supervised methods, OOD-based approaches function without labels and are inherently robust to data imbalances. Current generative approaches often rely on likelihood estimation or reconstruction error, but these methods can be computationally expensive, unreliable, and require retraining if the inlier data changes. These limitations hinder their ability to distinguish nominal from anomalous inputs efficiently, consistently, and robustly. We propose a reconstruction-free OOD detection method that leverages the forward diffusion trajectories of a Stein score-based denoising diffusion model (SBDDM). By capturing trajectory curvature via the estimated Stein score, our approach enables accurate anomaly scoring with only five diffusion steps. A single SBDDM pre-trained on a large, semantically aligned medical dataset generalizes effectively across multiple Near-OOD and Far-OOD benchmarks, achieving state-of-the-art performance while drastically reducing computational cost during inference. Compared to existing methods, SBDDM achieves a relative improvement of up to 10.43% and 18.10% for Near-OOD and Far-OOD detection, making it a practical building block for real-time, reliable computer-aided diagnosis.