Pretreatment Histopathology-Based Tumor Microenvironment Modeling Predicts Treatment-Specific Objective Responses in Non-small Cell Lung Cancer
Accurate prediction of treatment response remains challenging in cancer. To facilitate response prediction in non-small cell lung cancer (NSCLC), we developed PRISM, an interpretable multiscale graph-learning framework for estimating treatment-specific objective response from pretreatment H&E whole-slide images. PRISM integrated multiresolution tissue representations with a cell-level tumor microenvironment (TME) hypergraph, thereby treating higher-order microenvironmental organization as a learnable component of treatment-response prediction. Samples from 7,082 patients from four Chinese centers were screened. PRISM was evaluated across treatment specific cohorts receiving targeted therapy (T), EGFR-targeted therapy (T_EGFR), immune checkpoint inhibitor–based therapy (ICI), chemoimmunotherapy (CI), and chemotherapy (C) using patient-level internal cross-validation, independent multicenter external validation, and prospective silent validation. PRISM predicted early objective responses across prespecified systemic therapies in NSCLC. In comparison to 18 established multiple-instance learning and computational pathology baseline models, PRISM remained competitive, with numerical advantages in selected tasks. Multiscale attribution and exploratory H&E-derived TME analyses provided spatial context for model predictions. Overall, PRISM offers a morphology-based framework for estimating early response to prespecified systemic therapies and warrants further prospective multicenter evaluation.
Authors
- 聂德林
- Qiya Song (ORCID: https://orcid.org/0000-0002-3115-0672)
- Liangrui Pan (ORCID: https://orcid.org/0000-0003-0565-4217)
- Desheng Xiao (ORCID: https://orcid.org/0000-0003-2204-5042)
- Yang Liu (ORCID: https://orcid.org/0000-0001-7300-9215)
- Xiang Wang (ORCID: https://orcid.org/0000-0002-5211-7206)
- Zhihong Chen (ORCID: https://orcid.org/0000-0002-1030-3289)
- Ling Xiao (ORCID: https://orcid.org/0000-0003-0893-1777)
- Xiong Peng (ORCID: https://orcid.org/0000-0002-4606-4312)
- Qiankun Li (ORCID: https://orcid.org/0000-0001-5121-1682)
- Yaning Yang (ORCID: https://orcid.org/0009-0002-5819-7005)
- Chenchen Nie (ORCID: https://orcid.org/0009-0002-8800-2651)
- Qide Liang (ORCID: https://orcid.org/0009-0004-2036-5792)
- Jiayu Qian (ORCID: https://orcid.org/0009-0007-7148-2843)
- Bin Xie (ORCID: https://orcid.org/0009-0003-9402-2920)
- Fanghua Hu (ORCID: https://orcid.org/0009-0000-6052-7283)
Institutions
- Central South University (CN)
- Nanyang Technological University (SG)
- Hunan Normal University (CN)
- Zhengzhou University (CN)
- Hunan Cancer Hospital (CN)
- Second Xiangya Hospital of Central South University (CN)
- Xiangya Hospital Central South University (CN)
- Xiangtan University (CN)
Publication Details
- Journal
- Cancer Research
- Published
- 2026-11-19
- DOI
- https://doi.org/10.1158/0008-5472.can-26-1365
- Primary Topic
- AI in cancer detection
- Type
- article
- Field-Weighted Citation Impact
- 0.00