跳到正文
arXiv cs.AI· Alexandra G. Roberts, Tonmoy Hossain, Mark Olchanyi, Stefan Brandst\"atter, Jonathan Williams Ramirez, Ana Lawry Aguila, Matthew Rosen, Annabel Sorby-Adams, W. Taylor Kimberly, Juan Eugenio Iglesias·· 4 小时前AI 评分34

PathoDraw:面向合成先验与零样本检测的病理随机化生成模型

Pathology Randomization for Synthetic Priors and Zero-Shot Detection

AI 导读

PathoDraw 是一种带病理的脑 MRI 生成模型,将病灶条件分布绘入标签图后再做对比度无关渲染,并用单个 3D UNet 直接学习健康解剖与带符号强度偏差,在未用真实病理数据训练的情况下实现零样本检测。

正文 · 原文

View PDF HTML (experimental)

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 $T_1$w, FLAIR and $T_2$w 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 this https URL.
Comments: 25 pages, 9 figures, 13 tables (8-page main text with appendices). Code: this https URL
Subjects: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Image and Video Processing (eess.IV)
MSC classes: 68T45, 68T07, 92C55
ACM classes: I.4.6; I.4.3; I.2.6; J.3
Cite as: arXiv:2611.21975 [cs.CV]
  (or arXiv:2611.21975v1 [cs.CV] for this version)
  https://doi.org/10.48550/arXiv.2611.21975

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Alexandra Roberts [view email]
[v1] Mon, 16 Nov 2026 22:58:56 UTC (10,384 KB)

来源:arXiv cs.AI · arxiv.org