Histogram- and Diffusion-Based Medical Out-of-Distribution Detection
This work addresses safety in medical AI by improving anomaly detection, but it is incremental as it builds on existing methods for a specific challenge.
The paper tackled out-of-distribution detection in medical images by combining histogram- and diffusion-based methods, finding that the diffusion method was sensitive to blur and bias field samples but struggled with anatomical deformations and other anomalies.
Out-of-distribution (OOD) detection is crucial for the safety and reliability of artificial intelligence algorithms, especially in the medical domain. In the context of the Medical OOD (MOOD) detection challenge 2023, we propose a pipeline that combines a histogram-based method and a diffusion-based method. The histogram-based method is designed to accurately detect homogeneous anomalies in the toy examples of the challenge, such as blobs with constant intensity values. The diffusion-based method is based on one of the latest methods for unsupervised anomaly detection, called DDPM-OOD. We explore this method and propose extensive post-processing steps for pixel-level and sample-level anomaly detection on brain MRI and abdominal CT data provided by the challenge. Our results show that the proposed DDPM method is sensitive to blur and bias field samples, but faces challenges with anatomical deformation, black slice, and swapped patches. These findings suggest that further research is needed to improve the performance of DDPM for OOD detection in medical images.