Automating liver biopsy segmentation with a robust, open-source tool for pathology research: the HOTSPoT model
Authors:
Open Access
- 18 July 2025
- journal article
- Published by Springer Nature in npj Digital Medicine
- Vol. 8 (1) , 455
Abstract
Artificial intelligence applications in liver pathology remain limited, with existing tools either narrowly focused or lacking external validation. This study introduces HOTSPoT, an open-source, validated transformer-based model for automated segmentation of portal tracts in H&E-stained liver biopsy whole slide images. A multi-institutional dataset of 223 cases was used, with annotations by expert hepatopathologists. HOTSPoT achieved high performance with mean Dice scores of 0.92 (train/val) and 0.91 (test), and mean IoUs of 0.86, 0.85, and 0.84, respectively, showing minimal domain shift. Automated portal tract quantification showed strong concordance with manual assessments (κ up to 0.90), and portal area correlated with fibrosis stage (r = 0.87, p < 0.001). The model is available as a TorchScript file with a modified WSInfer library, enabling efficient WSI-level inference and integration with QuPath for advanced pathology analysis.Keywords
Funding Information
- German Research Foundation (PRACTIS – Clinician Scientist Program of Hannover Medical School DFG, ME 3696/3)
- Ministero dell'Università e della Ricerca (PNRR PE06 “HEAL ITALIA – Health Extended ALliance for Innovative Therapies, Advanced Lab-research and Integrated Approaches of Precision Medicine” - Spoke 4 - Precision Diagnostics, Dipartimenti di Eccellenza 2023-2027 (l. 232/2016, art. 1, commi 314 - 337), PNRR PE06 “HEAL ITALIA – Health Extended ALliance for Innovative Therapies, Advanced Lab-research and Integrated Approaches of Precision Medicine” - Spoke 4 - Precision Diagnostics, PNRR PE06 “HEAL ITALIA – Health Extended ALliance for Innovative Therapies, Advanced Lab-research and Integrated Approaches of Precision Medicine” - Spoke 4 - Precision Diagnostics)
- Fondazione Regionale per la Ricerca Biomedica (Bando Giovani “Early Career Award” FRRB - CUP H53C24000630002 “AIVAR - Artificial Intelligence-Enhanced Diagnosis of PBC-AIH Variant Syndrome., Bando Giovani “Early Career Award” FRRB - CUP H53C24000630002 “AIVAR - Artificial Intelligence-Enhanced Diagnosis of PBC-AIH Variant Syndrome., Bando Giovani “Early Career Award” FRRB - CUP H53C24000630002 “AIVAR - Artificial Intelligence-Enhanced Diagnosis of PBC-AIH Variant Syndrome.)
This publication has 35 references indexed in Scilit:
- Next-Generation Morphometry for pathomics-data mining in histopathologyNature Communications, 2023
- Survey of liver pathologists to assess attitudes towards digital pathology and artificial intelligenceJournal of Clinical Pathology, 2023
- Data-driven color augmentation for H&E stained images in computational pathologyJournal of Pathology Informatics, 2023
- Artificial intelligence based liver portal tract region identification and quantification with transplant biopsy whole-slide imagesComputers in Biology and Medicine, 2022
- Consensus recommendations for histological criteria of autoimmune hepatitis from the International AIH Pathology GroupLiver International, 2022
- Automated Detection of Portal Fields and Central Veins in Whole-Slide Images of Liver TissueJournal of Pathology Informatics, 2022
- Measuring Domain Shift for Deep Learning in HistopathologyIEEE Journal of Biomedical and Health Informatics, 2020
- Pathology Image Analysis Using Segmentation Deep Learning AlgorithmsThe American Journal of Pathology, 2019
- QuPath: Open source software for digital pathology image analysisScientific Reports, 2017
- The normal adult human liver biopsy: A quantitative reference standardHepatology, 1998