CADD: Context aware disease deviations via restoration of brain images using normative conditional diffusion models

TL;DR

CADD introduces a novel conditional diffusion model for normative brain image modeling, improving anomaly detection in heterogeneous clinical datasets by balancing healthy restoration with subject-specific feature retention.

Contribution

The paper presents the first conditional diffusion model for normative 3D brain imaging, incorporating clinical context and a new inpainting strategy for enhanced disease deviation detection.

Findings

State-of-the-art abnormality detection performance

Effective handling of heterogeneous clinical datasets

Robustness to lower contrast and motion artifacts

Abstract

Applying machine learning to real-world medical data, e.g. from hospital archives, has the potential to revolutionize disease detection in brain images. However, detecting pathology in such heterogeneous cohorts is a difficult challenge. Normative modeling, a form of unsupervised anomaly detection, offers a promising approach to studying such cohorts where the ``normal'' behavior is modeled and can be used at subject level to detect deviations relating to disease pathology. Diffusion models have emerged as powerful tools for anomaly detection due to their ability to capture complex data distributions and generate high-quality images. Their performance relies on image restoration; differences between the original and restored images highlight potential abnormalities. However, unlike normative models, these diffusion model approaches do not incorporate clinical information which provides important context to guide the disease detection process. Furthermore, standard approaches often poorly restore healthy regions, resulting in poor reconstructions and suboptimal detection performance. We present CADD, the first conditional diffusion model for normative modeling in 3D images. To guide the healthy restoration process, we propose a novel inference inpainting strategy which balances anomaly removal with retention of subject-specific features. Evaluated on three challenging datasets, including clinical scans, which may have lower contrast, thicker slices, and motion artifacts, CADD achieves state-of-the-art performance in detecting neurological abnormalities in heterogeneous cohorts.