Saved in:
Bibliographic Details
Main Authors: Shokrollahi, Yasin, Gonzales, Karina B. Pinao, Toro, Elizve N. Barrientos, Acosta, Paul, Team, Patient Mosaic, Chen, Pingjun, Yuan, Yinyin, Pan, Xiaoxi
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.23799
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915959522983936
author Shokrollahi, Yasin
Gonzales, Karina B. Pinao
Toro, Elizve N. Barrientos
Acosta, Paul
Team, Patient Mosaic
Chen, Pingjun
Yuan, Yinyin
Pan, Xiaoxi
author_facet Shokrollahi, Yasin
Gonzales, Karina B. Pinao
Toro, Elizve N. Barrientos
Acosta, Paul
Team, Patient Mosaic
Chen, Pingjun
Yuan, Yinyin
Pan, Xiaoxi
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_23799
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle VitaminP: cross-modal learning enables whole-cell segmentation from routine histology
Shokrollahi, Yasin
Gonzales, Karina B. Pinao
Toro, Elizve N. Barrientos
Acosta, Paul
Team, Patient Mosaic
Chen, Pingjun
Yuan, Yinyin
Pan, Xiaoxi
Computer Vision and Pattern Recognition
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.
title VitaminP: cross-modal learning enables whole-cell segmentation from routine histology
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.23799