Deep learning-based histomorphological subtyping and risk stratification of small cell lung cancer from hematoxylin and eosin-stained whole slide images

作者：Yibo Zhang, Shilong Liu, Jun Chen, Ruanqi Chen, Zijian Yang, Ruyu Sheng, Xin Li, T Wang, Hong Yu Liu, Fan Yang, Jianming Ying, Lin Yang, Jie Sun, Meng Zhou · 发表于：Genome Medicine · 年份：2025 · DOI：10.1186/s13073-025-01526-5 · 被引用次数：12 · 研究领域：Lung Cancer Research Studies、Radiomics and Machine Learning in Medical Imaging、Ferroptosis and cancer prognosis

BACKGROUND: Accurate subtyping and risk stratification are imperative for prognostication and clinical decision-making in small cell lung cancer (SCLC). However, traditional molecular subtyping is resource-intensive and challenging to translate into clinical practice. METHODS: A total of 517 SCLC patients and their corresponding hematoxylin and eosin (H&E)-stained whole slide images (WSIs) from three independent medical institutions were analyzed. A hybrid clustering-based unsupervised deep representation learning model was developed to identify histomorphological phenotypes (HIPO) and characterize tumor ecosystem diversity. Consensus clustering and a deep learning-based stratification system were used to define histomorphological subtypes (HIPOS) based on patient-level HIPO features. Survival analysis and Cox proportional hazards regression models were used to assess the clinical significance of HIPOS. An integrated analysis of pathomics, proteomics, and immunohistochemistry was conducted to explore the biological and microenvironmental correlates of HIPOS. RESULTS: We performed histomorphological phenotyping of SCLC using unsupervised deep representation learning from WSIs and identified 15 HIPOs. Unsupervised clustering of HIPO profiles stratified SCLCs into two reproducible image-based subtypes: HIPOS-I and HIPOS-II. Patients in the HIPOS-I group had better overall survival and disease-free survival compared to those in HIPOS-II, independent of clinical features and molec...