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

2025-08-05

AI Summary

Addressing the challenge of unsupervised anomaly detection in heterogeneous brain medical imaging—particularly when clinical guidance is unavailable—this paper proposes a context-aware normalizing conditional diffusion model. Methodologically, it introduces clinical variables (e.g., age, sex) into a 3D brain image conditional diffusion framework for the first time to construct a normative prior; additionally, it designs a localized inpainting strategy during inference to suppress pathological anomalies while preserving subject-specific anatomical features. Key contributions include: (1) a clinical-information-driven conditional generation mechanism that enhances model specificity; and (2) an inpainting-based inference paradigm that improves contextual sensitivity and individual anatomical fidelity. Evaluated on three challenging clinical datasets—characterized by low contrast, thick-slice acquisitions, and motion artifacts—the method achieves state-of-the-art anomaly detection performance, demonstrates strong robustness, and significantly improves identification of disease-related deviations.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Web Mining and Content Analysis: Large pretrained models with web data
• Responsible Web: Machine-in-the-loop, human agency and autonomy

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.

Problem

• Detect neurological abnormalities in heterogeneous brain image cohorts
• Improve image restoration for better anomaly detection performance
• Incorporate clinical context into normative modeling for disease detection

Innovation

• Conditional diffusion model for normative 3D imaging
• Inference inpainting balances anomaly removal and feature retention
• State-of-the-art neurological abnormality detection in heterogeneous cohorts