Unsupervised Anomaly Detection of Diseases in the Female Pelvis for Real-Time MR Imaging

2026-02-05

AI Summary

This study addresses the challenge of real-time anomaly detection in female pelvic MRI, where high anatomical variability and diverse pathologies limit the applicability of existing AI methods that rely on pathology-specific annotations. The authors propose an unsupervised anomaly detection framework that trains a residual variational autoencoder exclusively on healthy pelvic MRI scans and localizes pathological regions via reconstruction error heatmaps, eliminating the need for abnormality labels. This approach achieves, for the first time, a pathology- and protocol-agnostic screening capability by integrating synthetic data augmentation through diffusion models and cross-protocol training, enabling real-time detection of multiple conditions—including uterine fibroids, endometrial cancer, and endometriosis. Evaluated on public datasets, the method attains an AUC of 0.736, sensitivity of 0.828, specificity of 0.692, and an inference speed of 92.6 frames per second.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning
• Data Mining & Knowledge Management: Anomaly/Outlier Detection

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Pelvic diseases in women of reproductive age represent a major global health burden, with diagnosis frequently delayed due to high anatomical variability, complicating MRI interpretation. Existing AI approaches are largely disease-specific and lack real-time compatibility, limiting generalizability and clinical integration. To address these challenges, we establish a benchmark framework for disease- and parameter-agnostic, real-time-compatible unsupervised anomaly detection in pelvic MRI. The method uses a residual variational autoencoder trained exclusively on healthy sagittal T2-weighted scans acquired across diverse imaging protocols to model normal pelvic anatomy. During inference, reconstruction error heatmaps indicate deviations from learned healthy structure, enabling detection of pathological regions without labeled abnormal data. The model is trained on 294 healthy scans and augmented with diffusion-generated synthetic data to improve robustness. Quantitative evaluation on the publicly available Uterine Myoma MRI Dataset yields an average area-under-the-curve (AUC) value of 0.736, with 0.828 sensitivity and 0.692 specificity. Additional inter-observer clinical evaluation extends analysis to endometrial cancer, endometriosis, and adenomyosis, revealing the influence of anatomical heterogeneity and inter-observer variability on performance interpretation. With a reconstruction time of approximately 92.6 frames per second, the proposed framework establishes a baseline for unsupervised anomaly detection in the female pelvis and supports future integration into real-time MRI. Code is available upon request (https://github.com/AniKnu/UADPelvis), prospective data sets are available for academic collaboration.

Problem

• unsupervised anomaly detection
• pelvic MRI
• real-time imaging
• disease diagnosis
• anatomical variability

Innovation

• unsupervised anomaly detection
• real-time MRI
• variational autoencoder
• diffusion-generated synthetic data
• disease-agnostic