Self-Supervised AI Discovery of Histomorphological Phenotypes from Routine Mesothelioma Biopsies
Preprint
Abstract
Accurate subtype diagnosis is essential for guiding therapy and predicting patient outcome in malignant mesothelioma. Most computational pathology models are trained on large tissue images from resection specimens, which maximises information for training but limits model relevance in real-world diagnostic settings where small biopsies are the most usual tissue source. In this work, we assembled a large multicentre cohort of HES- and HPS-stained mesothelioma biopsy slides. We used a self-supervised learning model to evaluate the associations of biopsy-driven morphology patterns with histological subtype, molecular markers, and survival. The discovered histomorphology patterns captured a continuum of tissue phenotypes spanning epithelioid, sarcomatoid, and non-tumour morphologies. Also, patient-level HPC representations achieved excellent performance for distinguishing epithelioid from non-epithelioid mesothelioma (AUC = 0.94) and demonstrated predictive value for immunohistochemistry (IHC) markers. Additionally, HPC-derived features alone achieved performance comparable to established clinical and molecular variables (C-index = 0.65), while integration of HPCs with clinical and marker information improved performance to a C-index of 0.69. Several HPCs were significantly associated with favourable or adverse prognosis and reflected known subtype-specific biological patterns. In conclusion, self-supervised learning can discover interpretable histomorphological phenotypes directly from routine mesothelioma biopsies without further training. These AI-derived phenotypes capture clinically and biologically relevant information, linking tissue architecture to molecular characteristics, histological subtypes, and patient outcomes. The proposed framework provides a thorough evaluation of real-world biopsy data using a pre-trained model, without the need for computationally intensive retraining, and addresses the question of whether SSL-based AI can be deployed out of the box in clinical settings.Keywords
This publication has 28 references indexed in Scilit:
- Mapping the landscape of histomorphological cancer phenotypes using self-supervised learning on unannotated pathology slidesNature Communications, 2024
- MesoGraph: Automatic profiling of mesothelioma subtypes from histological imagesCell Reports Medicine, 2023
- Medical Image Analysis using Convolutional Neural Networks: A ReviewJournal of Medical Systems, 2018
- New Insights on Diagnostic Reproducibility of Biphasic Mesotheliomas: A Multi-Institutional Evaluation by the International Mesothelioma Panel From the MESOPATH Reference CenterJournal of Thoracic Oncology, 2018
- Nuclear grade and necrosis predict prognosis in malignant epithelioid pleural mesothelioma: a multi-institutional studyLaboratory Investigation, 2018
- BRCA1-Associated Protein 1 (BAP1) Immunohistochemical Expression as a Diagnostic Tool in Malignant Pleural Mesothelioma Classification: A Large Retrospective StudyJournal of Thoracic Oncology, 2016
- Comprehensive genomic analysis of malignant pleural mesothelioma identifies recurrent mutations, gene fusions and splicing alterationsNature Genetics, 2016
- BAP1 (BRCA1-associated protein 1) is a highly specific marker for differentiating mesothelioma from reactive mesothelial proliferationsLaboratory Investigation, 2015
- The diagnostic utility of D2-40 for malignant mesothelioma versus pulmonary carcinoma with pleural involvementDiagnostic Cytopathology, 2006
- Glyco- and immunohistochemical refinement of the differential diagnosis between mesothelioma and metastatic carcinoma and survival analysis of patientsThe Journal of Pathology, 2000