Self-supervised AI reveals a lethal discohesive phenotype in lung adenocarcinoma

作者：Kai Rakovic, Alexandrina Pancheva, Adalberto Claudio Quiros, Jose Coelho‐Lima, Zhangyi He, David A. Dorward, Marco Sereno, Claire Wilson, Craig Dick, David A. Moore, Fiona Ballantyne, Catherine Ficken, Ana Teodòsio, Silvia Martinelli, Rachel Baird, Leah Officer-Jones, Ian Powley, David K. Chang, Crispin Miller, Ke Yuan, John Le Quesne · 发表于：bioRxiv (Cold Spring Harbor Laboratory) · 年份：2025 · DOI：10.1101/2025.11.12.688049 · 研究领域：AI in cancer detection、Radiomics and Machine Learning in Medical Imaging、Lung Cancer Diagnosis and Treatment

Applications of artificial intelligence (AI) to histopathology are now common, but most require supervision which inherently limits their scope. By using self-supervised learning (SSL), we discover and quantify the full range of histopathological appearances in a disease, and associate them with clinicopathological ground truths such as prognosis. We used this approach to discover under-appreciated morphologies of lung adenocarcinoma (LUAD), using a highly characterised resected tumour cohort of over 4000 slides from over 1000 patients. By constructing an authoritative lexicon of recurrent LUAD appearances, we ab initio discovered several stromal morphologies strongly predictive of outcome. With multimodal data integration and external dataset validation, we propose that epithelial discohesion is lethal, but only in the context of immunologically cold stroma. Both these morphological features are independent of current prognostic schema. Crucially, we describe these features in the context of real-world diagnostic histopathology, giving them immediate clinical translatability.