Unsupervised Deep Generative Models for Anomaly Detection in Neuroimaging: A Systematic Scoping Review

2025-10-16

AI Summary

To address the scarcity of annotated data in neuroimaging anomaly detection, this paper systematically reviews unsupervised deep generative models—including autoencoders, variational autoencoders (VAEs), generative adversarial networks (GANs), and diffusion models—for modeling normative brain anatomy from healthy neuroimaging data. The core methodological innovation lies in constructing a normalized representation of brain structure and generating interpretable pseudo-normal reference images to enable pixel-level anomaly localization. The framework further supports semi-supervised fine-tuning and cross-disease bias mapping, facilitating the discovery of novel imaging biomarkers. Comprehensive evaluation across 49 studies demonstrates robust performance in detecting focal lesions such as tumors and strokes; certain approaches exhibit high sensitivity to subtle abnormalities. Notably, the paradigm shows significant clinical translational potential in rare and heterogeneous neurological disorders.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Data Mining & Knowledge Management: Anomaly/Outlier Detection

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics

Abstract

Unsupervised deep generative models are emerging as a promising alternative to supervised methods for detecting and segmenting anomalies in brain imaging. Unlike fully supervised approaches, which require large voxel-level annotated datasets and are limited to well-characterised pathologies, these models can be trained exclusively on healthy data and identify anomalies as deviations from learned normative brain structures. This PRISMA-guided scoping review synthesises recent work on unsupervised deep generative models for anomaly detection in neuroimaging, including autoencoders, variational autoencoders, generative adversarial networks, and denoising diffusion models. A total of 49 studies published between 2018 - 2025 were identified, covering applications to brain MRI and, less frequently, CT across diverse pathologies such as tumours, stroke, multiple sclerosis, and small vessel disease. Reported performance metrics are compared alongside architectural design choices. Across the included studies, generative models achieved encouraging performance for large focal lesions and demonstrated progress in addressing more subtle abnormalities. A key strength of generative models is their ability to produce interpretable pseudo-healthy (also referred to as counterfactual) reconstructions, which is particularly valuable when annotated data are scarce, as in rare or heterogeneous diseases. Looking ahead, these models offer a compelling direction for anomaly detection, enabling semi-supervised learning, supporting the discovery of novel imaging biomarkers, and facilitating within- and cross-disease deviation mapping in unified end-to-end frameworks. To realise clinical impact, future work should prioritise anatomy-aware modelling, development of foundation models, task-appropriate evaluation metrics, and rigorous clinical validation.

Problem

• Detecting brain anomalies without annotated data using generative models
• Segmenting diverse pathologies from tumors to vascular diseases
• Creating interpretable reconstructions for rare and heterogeneous diseases

Innovation

• Unsupervised deep generative models trained on healthy data
• Models identify anomalies as deviations from normative structures
• Generate interpretable pseudo-healthy reconstructions for clinical insights