Research

Paper

AI LLM March 03, 2026

GloPath: An Entity-Centric Foundation Model for Glomerular Lesion Assessment and Clinicopathological Insights

Authors

Qiming He, Jing Li, Tian Guan, Yifei Ma, Zimo Zhao, Yanxia Wang, Hongjing Chen, Yingming Xu, Shuang Ge, Yexing Zhang, Yizhi Wang, Xinrui Chen, Lianghui Zhu, Yiqing Liu, Qingxia Hou, Shuyan Zhao, Xiaoqin Wang, Lili Ma, Peizhen Hu, Qiang Huang, Zihan Wang, Zhiyuan Shen, Junru Cheng, Siqi Zeng, Jiurun Chen, Zhen Song, Chao He, Zhe Wang, Yonghong He

Abstract

Glomerular pathology is central to the diagnosis and prognosis of renal diseases, yet the heterogeneity of glomerular morphology and fine-grained lesion patterns remain challenging for current AI approaches. We present GloPath, an entity-centric foundation model trained on over one million glomeruli extracted from 14,049 renal biopsy specimens using multi-scale and multi-view self-supervised learning. GloPath addresses two major challenges in nephropathology: glomerular lesion assessment and clinicopathological insights discovery. For lesion assessment, GloPath was benchmarked across three independent cohorts on 52 tasks, including lesion recognition, grading, few-shot classification, and cross-modality diagnosis-outperforming state-of-the-art methods in 42 tasks (80.8%). In the large-scale real-world study, it achieved an ROC-AUC of 91.51% for lesion recognition, demonstrating strong robustness in routine clinical settings. For clinicopathological insights, GloPath systematically revealed statistically significant associations between glomerular morphological parameters and clinical indicators across 224 morphology-clinical variable pairs, demonstrating its capacity to connect tissue-level pathology with patient-level outcomes. Together, these results position GloPath as a scalable and interpretable platform for glomerular lesion assessment and clinicopathological discovery, representing a step toward clinically translatable AI in renal pathology.

Metadata

arXiv ID: 2603.02926
Provider: ARXIV
Primary Category: cs.CV
Published: 2026-03-03
Fetched: 2026-03-04 03:41

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.02926v1</id>\n    <title>GloPath: An Entity-Centric Foundation Model for Glomerular Lesion Assessment and Clinicopathological Insights</title>\n    <updated>2026-03-03T12:32:12Z</updated>\n    <link href='https://arxiv.org/abs/2603.02926v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.02926v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Glomerular pathology is central to the diagnosis and prognosis of renal diseases, yet the heterogeneity of glomerular morphology and fine-grained lesion patterns remain challenging for current AI approaches. We present GloPath, an entity-centric foundation model trained on over one million glomeruli extracted from 14,049 renal biopsy specimens using multi-scale and multi-view self-supervised learning. GloPath addresses two major challenges in nephropathology: glomerular lesion assessment and clinicopathological insights discovery. For lesion assessment, GloPath was benchmarked across three independent cohorts on 52 tasks, including lesion recognition, grading, few-shot classification, and cross-modality diagnosis-outperforming state-of-the-art methods in 42 tasks (80.8%). In the large-scale real-world study, it achieved an ROC-AUC of 91.51% for lesion recognition, demonstrating strong robustness in routine clinical settings. For clinicopathological insights, GloPath systematically revealed statistically significant associations between glomerular morphological parameters and clinical indicators across 224 morphology-clinical variable pairs, demonstrating its capacity to connect tissue-level pathology with patient-level outcomes. Together, these results position GloPath as a scalable and interpretable platform for glomerular lesion assessment and clinicopathological discovery, representing a step toward clinically translatable AI in renal pathology.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CV'/>\n    <published>2026-03-03T12:32:12Z</published>\n    <arxiv:primary_category term='cs.CV'/>\n    <author>\n      <name>Qiming He</name>\n    </author>\n    <author>\n      <name>Jing Li</name>\n    </author>\n    <author>\n      <name>Tian Guan</name>\n    </author>\n    <author>\n      <name>Yifei Ma</name>\n    </author>\n    <author>\n      <name>Zimo Zhao</name>\n    </author>\n    <author>\n      <name>Yanxia Wang</name>\n    </author>\n    <author>\n      <name>Hongjing Chen</name>\n    </author>\n    <author>\n      <name>Yingming Xu</name>\n    </author>\n    <author>\n      <name>Shuang Ge</name>\n    </author>\n    <author>\n      <name>Yexing Zhang</name>\n    </author>\n    <author>\n      <name>Yizhi Wang</name>\n    </author>\n    <author>\n      <name>Xinrui Chen</name>\n    </author>\n    <author>\n      <name>Lianghui Zhu</name>\n    </author>\n    <author>\n      <name>Yiqing Liu</name>\n    </author>\n    <author>\n      <name>Qingxia Hou</name>\n    </author>\n    <author>\n      <name>Shuyan Zhao</name>\n    </author>\n    <author>\n      <name>Xiaoqin Wang</name>\n    </author>\n    <author>\n      <name>Lili Ma</name>\n    </author>\n    <author>\n      <name>Peizhen Hu</name>\n    </author>\n    <author>\n      <name>Qiang Huang</name>\n    </author>\n    <author>\n      <name>Zihan Wang</name>\n    </author>\n    <author>\n      <name>Zhiyuan Shen</name>\n    </author>\n    <author>\n      <name>Junru Cheng</name>\n    </author>\n    <author>\n      <name>Siqi Zeng</name>\n    </author>\n    <author>\n      <name>Jiurun Chen</name>\n    </author>\n    <author>\n      <name>Zhen Song</name>\n    </author>\n    <author>\n      <name>Chao He</name>\n    </author>\n    <author>\n      <name>Zhe Wang</name>\n    </author>\n    <author>\n      <name>Yonghong He</name>\n    </author>\n  </entry>"
}