arXiv 2604.237992026-04-26cs.CV

VitaminP: 跨模态学习实现常规组织学图像的全细胞分割

VitaminP: cross-modal learning enables whole-cell segmentation from routine histology

Department of Translational Molecular Pathology, Division of Pathology and Laboratory Medicine, The University of Texas MD Anderson Cancer Center（转化分子病理学部门，病理与实验室医学分会，德克萨斯大学MD安德森癌症中心）；Institute for Data Science in Oncology, The University of Texas MD Anderson Cancer Center（肿瘤数据科学研究所，德克萨斯大学MD安德森癌症中心）；The University of Texas MD Anderson Cancer Center（德克萨斯大学MD安德森癌症中心）

Yasin Shokrollahi, Karina B. Pinao Gonzales, Elizve N. Barrientos Toro, Paul Acosta, Patient Mosaic Team, Pingjun Chen, Yinyin Yuan, Xiaoxi Pan

备注：: 44 pages, 10 figures. Code and models available

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

VitaminP通过跨模态学习从常规H&E图像实现全细胞分割，利用配对的H&E-mIF数据迁移分子边界信息以克服H&E的细胞质对比度限制，构建了跨模态监督策略，并在14个公开数据集上训练，超越了四种最新方法并在未见数据集上泛化。

摘要：

准确的全细胞和核分割对于精准病理学和空间组学至关重要，但常规的苏木素-伊红染色（H&E）提供了有限的细胞质对比度，限制了分析仅限于核。多色免疫荧光（mIF）有助于精确的全细胞界定，但受限于成本和可及性。我们介绍了VitaminP，一种跨模态学习框架，能够从H&E图像实现全细胞分割。通过学习配对的H&E-mIF数据，VitaminP将mIF中的分子边界信息转移到H&E中以克服细胞质对比度限制，确立了跨模态监督作为一种通用策略，以恢复缺失的生物结构。我们训练VitaminP于14个公开数据集，涵盖34种癌症类型和超过700万实例，整合公开可用的标签与本文生成的大量注释，形成一个最大的分割资源。VitaminP超越了四种最新方法，并泛化到未见数据集，包括一个涵盖24种罕见癌症类型的内部数据集。我们进一步开发了VitaminPScope，一个开源平台，提供可扩展推理的界面，并促进广泛应用。

英文摘要：

Accurate whole-cell and nuclear segmentation is essential for precision pathology and spatial omics, yet routine hematoxylin and eosin (H&E) staining provides limited cytoplasmic contrast, restricting analyses to nuclei. Multiplex immunofluorescence (mIF) facilitates precise whole-cell delineation but remains constrained by cost and accessibility. We introduce VitaminP, a cross-modal learning framework enabling whole cell segmentation from H&E images. By learning from paired H&E-mIF data, VitaminP transfers molecular boundary information from mIF to overcome cytoplasmic contrast in H&E, establishing cross-modal supervision as a general strategy for recovering missing biological structure. We train VitaminP on 14 public datasets covering 34 cancer types and over 7 million instances, integrating publicly available labels with extensive annotations generated in this study, forming one of the largest resources for segmentation. VitaminP outperforms four state-of-the-art methods and generalizes to unseen datasets, including an in-house dataset spanning 24 rare cancer types. We further developed VitaminPScope, an open-source platform providing an interface for scalable inference and enabling broad adoption.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。