A subspecialty diagnostic system powered by self-supervised learning for cervical histopathology

Cervical cancer remains a major malignancy in women, with large-scale human papillomavirus-based screening generating a large volume of biopsies and, for advanced cases, surgical specimens, imposing an overwhelming diagnostic burden that necessitates precise histopathological evaluation. Although deep learning shows promise, general foundation models offer a broader reach but remain limited in capturing subspecialty-specific features and task adaptability. We introduce the Cervical Subspecialty Pathology (CerS-Path) diagnostic system, built upon the subspecialized dataset and developed through two synergistic pretraining stages: self-supervised learning on approximately 190 million tissue patches to build a cervical-specific feature extractor, and multimodal enhancement with 2.5 million image-text pairs, followed by diagnostic functions integration and downstream task enhancement. CerS-Path integrates eight functions—across morphological diagnosis, predictive analytics, and multimodal tasks—to cover the diagnostic workflow from biopsies to resection specimens. Comprehensive evaluations demonstrate improved performance in cervical pathology in female patients, where CerS-Path outperforms state-of-the-art foundation models across 26 of 30 diagnostic tasks. Furthermore, in multicenter retrospective and prospective validation across six independent cohorts of women, CerS-Path achieves up to 99% sensitivity for clinically relevant lesion detection with acceptable specificity across sites, highlighting its potential for screening-derived histopathology and suitability for integration into high-volume diagnostic pathways. Foundation models could be promising for cervical cancer screening, but have important limitations for their clinical deployment. Here, the authors introduce the Cervical Subspecialty Pathology (CerS-Path) diagnostic system, a self-supervised learning framework for cervical cancer pathology that outperforms state-of-the-art foundation models across multiple diagnostic tasks.

Authors

Institutions

Publication Details

Journal
Nature Communications
Published
2026-11-14
DOI
https://doi.org/10.1038/s41467-026-79121-4
Citations
2
Primary Topic
AI in cancer detection
Type
article
Field-Weighted Citation Impact
2.79

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

A subspecialty diagnostic system powered by self-supervised learning for cervical histopathology

Chao He, Xinrui Chen, Qiang Huang, Yonghong He et al.
2 citations
Nature Communications
AI in cancer detection
2.79
article

A subspecialty diagnostic system powered by self-supervised learning for cervical histopathology

Chao He, Xinrui Chen, Qiang Huang, Yonghong He, Qiming He, Mingwen Zhao, Zhiyuan Shen, Bin Hu, Xi Deng, Hanzhong Liu, Yizhi Wang, Jiawen Li, Tian Guan
article en
2 citations

Abstract

Cervical cancer remains a major malignancy in women, with large-scale human papillomavirus-based screening generating a large volume of biopsies and, for advanced cases, surgical specimens, imposing an overwhelming diagnostic burden that necessitates precise histopathological evaluation. Although deep learning shows promise, general foundation models offer a broader reach but remain limited in capturing subspecialty-specific features and task adaptability. We introduce the Cervical Subspecialty Pathology (CerS-Path) diagnostic system, built upon the subspecialized dataset and developed through two synergistic pretraining stages: self-supervised learning on approximately 190 million tissue patches to build a cervical-specific feature extractor, and multimodal enhancement with 2.5 million image-text pairs, followed by diagnostic functions integration and downstream task enhancement. CerS-Path integrates eight functions—across morphological diagnosis, predictive analytics, and multimodal tasks—to cover the diagnostic workflow from biopsies to resection specimens. Comprehensive evaluations demonstrate improved performance in cervical pathology in female patients, where CerS-Path outperforms state-of-the-art foundation models across 26 of 30 diagnostic tasks. Furthermore, in multicenter retrospective and prospective validation across six independent cohorts of women, CerS-Path achieves up to 99% sensitivity for clinically relevant lesion detection with acceptable specificity across sites, highlighting its potential for screening-derived histopathology and suitability for integration into high-volume diagnostic pathways. Foundation models could be promising for cervical cancer screening, but have important limitations for their clinical deployment. Here, the authors introduce the Cervical Subspecialty Pathology (CerS-Path) diagnostic system, a self-supervised learning framework for cervical cancer pathology that outperforms state-of-the-art foundation models across multiple diagnostic tasks.

Nature Communications
University of Oxford (GB), The Central Hospital of Xiao gan (CN), Hubei Provincial Women and Children's Hospital (CN), Peng Cheng Laboratory (CN), Guangdong Province Women and Children Hospital (CN), First Affiliated Hospital of Soochow University (CN), Chinese People's Liberation Army (CN), Wuhan University of Science and Technology (CN), Jinfeng Laboratory (CN), Research Institute of Tsinghua University in Shenzhen (CN), Tsinghua Shenzhen International Graduate School (CN), Zhejiang University (CN), Fuzhou University (CN), Tsinghua University (CN)
National Natural Science Foundation of China, Zhejiang University, Wuhan University of Science and Technology, Tsinghua Shenzhen International Graduate School
Good health and well-being
Openalex Percentile: Top 10%
AI in cancer detection
2.79
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon