Master Project — Medical AI

MR Anomaly Detection

📅 Jun 2025 – Dec 2025 🎓 Universität Zürich & USZ 👥 Team of 5

Overview

Developed deep learning-based anomaly detection methods as a patient-specific quality assurance step for MR-only radiotherapy, focusing on detecting metal-induced artifacts in pelvic MR images before synthetic CT generation.

🎯 Goal: Enable automatic pre-screening for MR-only radiotherapy workflows by detecting out-of-distribution patterns (metallic implants, artifacts) in MR images that could compromise synthetic CT quality.

Key Contributions

Technical Approach

Anomaly Detection Methods Evaluated

Input Representations

Post-Processing Pipeline

Results

🏆 Single-Center Performance

0.90 Patient-Level Dice achieved with PatchCore after post-processing optimization

🌐 Multi-Center Generalization

0.77 Dice Score maintained across different scanner types and imaging protocols

Key Finding: Memory-bank method PatchCore achieves the most favorable trade-off between localization accuracy and patient-level detection, remaining comparatively robust under multi-center domain shifts.

Clinical Impact

Tech Stack

Python PyTorch Anomalib PatchCore NIfTI Medical Imaging SimpleITK scikit-image