Improved Anomaly Detection in Medical Images via Mean Shift Density Enhancement

TL;DR

This paper introduces a novel hybrid anomaly detection framework for medical images that combines self-supervised learning with manifold-based density estimation, achieving state-of-the-art results.

Contribution

The proposed framework uniquely integrates Mean Shift Density Enhancement with representation learning, improving anomaly detection in medical imaging with limited abnormal samples.

Findings

Achieves highest AUC on four datasets

Attains highest Average Precision on five datasets

Near-perfect performance on brain tumor detection (0.981 AUC/AP)

Abstract

Anomaly detection in medical imaging is essential for identifying rare pathological conditions, particularly when annotated abnormal samples are limited. We propose a hybrid anomaly detection framework that integrates self-supervised representation learning with manifold-based density estimation, a combination that remains largely unexplored in this domain. Medical images are first embedded into a latent feature space using pretrained, potentially domain-specific, backbones. These representations are then refined via Mean Shift Density Enhancement (MSDE), an iterative manifold-shifting procedure that moves samples toward regions of higher likelihood. Anomaly scores are subsequently computed using Gaussian density estimation in a PCA-reduced latent space, where Mahalanobis distance measures deviation from the learned normal distribution. The framework follows a one-class learning paradigm and requires only normal samples for training. Extensive experiments on seven medical imaging datasets demonstrate state-of-the-art performance. MSDE achieves the highest AUC on four datasets and the highest Average Precision on five datasets, including near-perfect performance on brain tumor detection (0.981 AUC/AP). These results underscore the potential of the proposed framework as a scalable clinical decision-support tool for early disease detection, screening in low-label settings, and robust deployment across diverse imaging modalities.