A histomorphological atlas of resected mesothelioma discovered by self-supervised learning from 3446 whole-slide images

Farzaneh Seyedshahi, Kai Rakovic, Nicolas Poulain, Adalberto Claudio Quiros, Ian R. Powley, Cathy Richards, Hussein Uraiby, Sonja Klebe, David A. Moore, Apostolos Nakas, Claire R. Wilson, Marco Sereno, Leah Officer-Jones, Catherine Ficken, Ana Teodosio, Fiona Ballantyne, Daniel Murphy, Ke Yuan, John Le Quesne

Abstract: Mesothelioma is a highly lethal and poorly biologically understood disease which presents diagnostic challenges due to its morphological complexity. This study uses self-supervised AI (Artificial Intelligence) to map the histomorphological landscape of the disease. The resulting atlas consists of recurrent patterns identified from 3446 Hematoxylin and Eosin (H&E) stained images scanned from resected tumour slides. These patterns generate highly interpretable predictions, achieving state-of-the-art performance with 0.65 concordance index (c-index) for outcomes and 88% AUC in subtyping. Their clinical relevance is endorsed by comprehensive human pathological assessment. Furthermore, we characterise the molecular underpinnings of these diverse, meaningful, predictive patterns. Our approach both improves diagnosis and deepens our understanding of mesothelioma biology, highlighting the power of this self-learning method in clinical applications and scientific discovery. Mesothelioma is a highly lethal cancer that remains challenging to diagnose. Here, the authors curate a histomorphological atlas of resected mesothelioma and map it using self-supervised AI endorsed by human pathological assessment, revealing patterns that generate highly interpretable predictions.

External IDs:doi:10.1038/s41467-025-63846-9