Automated cell annotation and classification on histopathology for spatial biomarker discovery

Abstract Histopathology with hematoxylin and eosin (H&E) staining is routinely employed for clinical diagnoses. Single-cell analysis of histopathology provides a powerful tool for understanding the intricate cellular interactions underlying disease progression and therapeutic response. However,...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhe Li, Seyed Hossein Mirjahanmardi, Rasoul Sali, Feyisope Eweje, Matthew Gopaulchan, Leon Kloker, Xiaoming Zhang, Guoxin Li, Yuming Jiang, Ruijiang Li
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Nature Communications
Online Access:https://doi.org/10.1038/s41467-025-61349-1
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849332151848271872
author Zhe Li
Seyed Hossein Mirjahanmardi
Rasoul Sali
Feyisope Eweje
Matthew Gopaulchan
Leon Kloker
Xiaoming Zhang
Guoxin Li
Yuming Jiang
Ruijiang Li
author_facet Zhe Li
Seyed Hossein Mirjahanmardi
Rasoul Sali
Feyisope Eweje
Matthew Gopaulchan
Leon Kloker
Xiaoming Zhang
Guoxin Li
Yuming Jiang
Ruijiang Li
author_sort Zhe Li
collection DOAJ
description Abstract Histopathology with hematoxylin and eosin (H&E) staining is routinely employed for clinical diagnoses. Single-cell analysis of histopathology provides a powerful tool for understanding the intricate cellular interactions underlying disease progression and therapeutic response. However, existing efforts are hampered by inefficient and error-prone human annotations. Here, we present an experimental and computational approach for automated cell annotation and classification on H&E-stained images. Instead of human annotations, we use multiplexed immunofluorescence (mIF) to define cell types based on cell lineage protein markers. By co-registering H&E images with mIF of the same tissue section at the single-cell level, we create a dataset of 1,127,252 cells with high-quality annotations on tissue microarray cores. A deep learning model combining self-supervised learning with domain adaptation is trained to classify four cell types on H&E images with an overall accuracy of 86%-89%, and the cell classification model is applicable to whole slide images. Further, we show that spatial interactions among specific immune cells in the tumor microenvironment are linked to patient survival and response to immune checkpoint inhibitors. Our work provides a scalable approach for single-cell analysis of standard histopathology and may enable discovery of novel spatial biomarkers for precision oncology.
format Article
id doaj-art-06c6632e20dc42d5b3ef99b153f29604
institution Kabale University
issn 2041-1723
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Nature Communications
spelling doaj-art-06c6632e20dc42d5b3ef99b153f296042025-08-20T03:46:17ZengNature PortfolioNature Communications2041-17232025-07-0116111510.1038/s41467-025-61349-1Automated cell annotation and classification on histopathology for spatial biomarker discoveryZhe Li0Seyed Hossein Mirjahanmardi1Rasoul Sali2Feyisope Eweje3Matthew Gopaulchan4Leon Kloker5Xiaoming Zhang6Guoxin Li7Yuming Jiang8Ruijiang Li9Department of Radiation Oncology, Stanford University School of MedicineDepartment of Radiation Oncology, Stanford University School of MedicineDepartment of Radiation Oncology, Stanford University School of MedicineDepartment of Radiation Oncology, Stanford University School of MedicineDepartment of Radiation Oncology, Stanford University School of MedicineInstitute for Computational & Mathematical EngineeringDepartment of Pathology, Stanford University School of MedicineDepartment of General Surgery, Nanfang Hospital, Southern Medical UniversityDepartment of Radiation Oncology, Stanford University School of MedicineDepartment of Radiation Oncology, Stanford University School of MedicineAbstract Histopathology with hematoxylin and eosin (H&E) staining is routinely employed for clinical diagnoses. Single-cell analysis of histopathology provides a powerful tool for understanding the intricate cellular interactions underlying disease progression and therapeutic response. However, existing efforts are hampered by inefficient and error-prone human annotations. Here, we present an experimental and computational approach for automated cell annotation and classification on H&E-stained images. Instead of human annotations, we use multiplexed immunofluorescence (mIF) to define cell types based on cell lineage protein markers. By co-registering H&E images with mIF of the same tissue section at the single-cell level, we create a dataset of 1,127,252 cells with high-quality annotations on tissue microarray cores. A deep learning model combining self-supervised learning with domain adaptation is trained to classify four cell types on H&E images with an overall accuracy of 86%-89%, and the cell classification model is applicable to whole slide images. Further, we show that spatial interactions among specific immune cells in the tumor microenvironment are linked to patient survival and response to immune checkpoint inhibitors. Our work provides a scalable approach for single-cell analysis of standard histopathology and may enable discovery of novel spatial biomarkers for precision oncology.https://doi.org/10.1038/s41467-025-61349-1
spellingShingle Zhe Li
Seyed Hossein Mirjahanmardi
Rasoul Sali
Feyisope Eweje
Matthew Gopaulchan
Leon Kloker
Xiaoming Zhang
Guoxin Li
Yuming Jiang
Ruijiang Li
Automated cell annotation and classification on histopathology for spatial biomarker discovery
Nature Communications
title Automated cell annotation and classification on histopathology for spatial biomarker discovery
title_full Automated cell annotation and classification on histopathology for spatial biomarker discovery
title_fullStr Automated cell annotation and classification on histopathology for spatial biomarker discovery
title_full_unstemmed Automated cell annotation and classification on histopathology for spatial biomarker discovery
title_short Automated cell annotation and classification on histopathology for spatial biomarker discovery
title_sort automated cell annotation and classification on histopathology for spatial biomarker discovery
url https://doi.org/10.1038/s41467-025-61349-1
work_keys_str_mv AT zheli automatedcellannotationandclassificationonhistopathologyforspatialbiomarkerdiscovery
AT seyedhosseinmirjahanmardi automatedcellannotationandclassificationonhistopathologyforspatialbiomarkerdiscovery
AT rasoulsali automatedcellannotationandclassificationonhistopathologyforspatialbiomarkerdiscovery
AT feyisopeeweje automatedcellannotationandclassificationonhistopathologyforspatialbiomarkerdiscovery
AT matthewgopaulchan automatedcellannotationandclassificationonhistopathologyforspatialbiomarkerdiscovery
AT leonkloker automatedcellannotationandclassificationonhistopathologyforspatialbiomarkerdiscovery
AT xiaomingzhang automatedcellannotationandclassificationonhistopathologyforspatialbiomarkerdiscovery
AT guoxinli automatedcellannotationandclassificationonhistopathologyforspatialbiomarkerdiscovery
AT yumingjiang automatedcellannotationandclassificationonhistopathologyforspatialbiomarkerdiscovery
AT ruijiangli automatedcellannotationandclassificationonhistopathologyforspatialbiomarkerdiscovery