cs.CVNov 16, 2026

Pathology Randomization for Synthetic Priors and Zero-Shot Detection

Authors: Alexandra G. Roberts, Tonmoy Hossain, Mark Olchanyi, Stefan Brandstätter, Jonathan Williams Ramirez, Ana Lawry Aguila, Matthew Rosen, Annabel Sorby-Adams, 

Organizations: Harvard Medical School and Massachusetts General Hospital · Massachusetts Institute of Technology · Medical University of Vienna · Microsoft

Abstract

Hospital brain imaging archives hold a diverse array of pathology at sample sizes beyond prospective studies, particularly for underrepresented populations and diseases. To unlock uncurated clinical data and scale analysis, methods are needed to detect abnormalities across contrasts and resolutions. Synthetic data has provided robust, contrast-agnostic models for a variety of human neuroimaging tasks in healthy anatomy, but pathology detection and other tasks in clinical settings still require real patient data, contrast-specific models, or disease-specific generators. We propose PathoDraw, a generative model of brain MRI with pathology. A conditional distribution of lesions given the healthy anatomy is drawn into the label map before contrast-agnostic rendering, and a single network estimates healthy anatomy with exact signed intensity deviation of any input scan. The contrast-agnostic 3D UNet learns the healthy labels under the lesion and the signed deviation directly and identifies pathology via robust tissue statistics and learned features, despite no training on real pathology. We show zero-shot detection on public stroke, tumor, and white matter hyperintensity datasets as well as archived clinical data, spanning T1T_1w, FLAIR and T2T_2w at various resolutions under a recent unsupervised anomaly detection benchmark protocol. Our single model exceeds or performs comparably to contrast-specific anomaly detectors trained on real scans and keeps healthy anatomy intact. The same generator trains networks for super-resolution and for registration in the presence of pathology. Our model, robust across acquisition and disease, enables the use of uncurated, archived data for clinical analysis. Our code is available at https://github.com/agr78/Pathology-Randomizer.

Figures & tables

Explore similar work

CardsList
  1. Zero-Shot Brain MRI Inpainting with 2.5D Unconditional Flow Priors

    Oct 6, 2026Arnela Hadzic, Franz Thaler, Simon Johannes Joham +1Image InpaintingMedical Image Synthesis

  2. VariaFlow: Uncertainty-Aware Flow Matching for Unsupervised Anomaly Detection

    Oct 30, 2026Arnela Hadzic, Martin Urschler, Cosmin I. BerceaMedical Image Anomaly DetectionUnsupervised Anomaly Detection

  3. A4-MR: Abnormality Aware Anatomical Alignment for MR

    Oct 9, 2026Noel D'souza, Zhijian Yang, Nishank Singla +15Medical Imaging Foundation ModelsRadiology VLMs