arXiv cs.AI· Pengyu Kan (Johns Hopkins University), Craig Jones (Johns Hopkins University, University of Alberta), Kenichi Oishi (Johns Hopkins University School of Medicine)·· 13 小时前AI 评分22
OpenMAP-HIE：病理先验引导的扩散模型实现无监督新生儿缺氧缺血性脑病病灶分割
OpenMAP-HIE: Pathology Informed Score-based Diffusion Model for Unsupervised Neonatal Hypoxic-Ischemic Encephalopathy Lesion Segmentation
AI 导读
Johns Hopkins 团队提出 OpenMAP-HIE，一种病理先验引导的 score-based 扩散模型，无需体素级病灶标注即可在 ADC 图像上定位新生儿缺氧缺血性脑病（HIE）病灶。
正文 · 原文
Authors:Pengyu Kan (Johns Hopkins University), Craig Jones (Johns Hopkins University, University of Alberta), Kenichi Oishi (Johns Hopkins University School of Medicine)
Abstract:Accurate localization of neonatal hypoxic--ischemic encephalopathy (HIE) lesions on apparent diffusion coefficient (ADC) images is clinically important but is limited by scarce expert annotations and substantial variation in lesion appearance. We propose OpenMAP-HIE, a pathology-informed score-based diffusion model for unsupervised HIE lesion localization without voxel-wise lesion supervision. A denoising diffusion model learns the healthy neonatal ADC distribution, while a ControlNet-based conditional branch preserves patient-specific anatomy. At inference, anomaly evidence is derived directly from differences between conditional and unconditioned noise predictions at independently evaluated diffusion noise levels, avoiding dependence on a final pseudo-healthy reconstruction or sequential reverse-diffusion chain. Based on the characteristic ADC reduction associated with acute HIE, only discrepancies consistent with the expected pathological direction are retained and aggregated across noise levels using a geometric mean. Spatial mean filtering further suppresses isolated responses. The framework was evaluated on the BONBID-HIE dataset. The ADC-only method achieved a Dice score of $0.283\pm0.244$, average precision of $0.505$, Hausdorff distance of $25.45\pm15.63$ mm, mean average surface distance of $9.40\pm8.49$ mm, and normalized surface distance of $0.355\pm0.236$, providing the best overlap and surface-distance performance among the evaluated unsupervised methods and Dice performance comparable to supervised ADC-only models. Optional population-derived ADC $Z$-map refinement further increased Dice to $0.602\pm0.269$. These findings support pathology-informed score discrepancies as a useful signal for neonatal HIE lesion localization, while highlighting remaining challenges in detecting small and low-contrast lesions.
| Comments: | 22 pages, 4 figures, 9 tables |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.29322 [cs.CV] |
| (or arXiv:2610.29322v2 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.29322 arXiv-issued DOI via DataCite |
Submission history
From: Pengyu Kan [view email]
[v1]
Wed, 21 Oct 2026 07:22:50 UTC (3,110 KB)
[v2]
Thu, 22 Oct 2026 03:44:19 UTC (3,110 KB)
来源：arXiv cs.AI · arxiv.org