A Multimodal Deep Learning Framework Integrating Tumor Microenvironment Niches for Overall Survival Prediction in Esophageal Squamous Cell Carcinoma
ABSTRACT Accurate prediction of overall survival (OS) in esophageal squamous cell carcinoma (ESCC) is hindered by the limited prognostic resolution of conventional staging. Here, we developed MENISA, a multimodal deep learning framework integrating clinical data, CT imaging, whole‐slide pathology images, and annotated tumor microenvironment (TME) niches, specifically perineural and lymphovascular invasion to predict OS. In two multicenter cohorts totaling 450 patients, the model achieved robust predictive performance (internal validation C‐index: 0.778; external validation C‐index: 0.675) and significantly stratified patients into distinct risk groups ( p ≤ 0.001). Interpretability analysis identified TME niches as important prognostic drivers, bridging the gap between macroscopic radiomics and mesoscopic histology by introducing intermediate‐scale TME niches as a complementary prognostic dimension. This study demonstrates the clinical utility of integrating intermediate‐scale microenvironmental features, offering a precision oncology tool for personalized risk stratification in ESCC.
Authors
- Shunsuke Koga (ORCID: https://orcid.org/0000-0001-8868-9700)
- Xin Hong (ORCID: https://orcid.org/0000-0002-9671-0116)
- Hui Yang (ORCID: https://orcid.org/0000-0002-6800-6308)
- Xiaomin Ni (ORCID: https://orcid.org/0000-0002-7769-8297)
- Hao Li (ORCID: https://orcid.org/0000-0002-2225-3119)
- Xiaokun Liang (ORCID: https://orcid.org/0000-0002-1207-5726)
- Chulong Zhang (ORCID: https://orcid.org/0009-0007-1149-1860)
- Wei Teng (ORCID: https://orcid.org/0000-0001-5663-1440)
- Yaoqin Xie (ORCID: https://orcid.org/0000-0002-1412-2354)
- Ping Zhou (ORCID: https://orcid.org/0000-0001-8365-1754)
- Jingdong Zhang (ORCID: https://orcid.org/0000-0002-0711-2764)
- Hao Yu (ORCID: https://orcid.org/0000-0003-2793-7912)
- Yan Min (ORCID: https://orcid.org/0000-0003-0521-5732)
- Xuefei Lin
- Zhihao Xie (ORCID: https://orcid.org/0009-0004-9994-1915)
- Yang Zhang (ORCID: https://orcid.org/0000-0003-4855-5163)
- Md Tauhidul Islam
- Yuanyue Zhang
- Jianbo Wang
- Henan Zhang
- Xiaoyan Li
- Guang Yang (ORCID: https://orcid.org/0009-0000-6847-7006)
Institutions
- Shandong University (CN)
- Hospital of the University of Pennsylvania (US)
- Southern University of Science and Technology (CN)
- Shenzhen Bay Laboratory (CN)
- Chinese University of Hong Kong, Shenzhen (CN)
- Shenzhen Institutes of Advanced Technology (CN)
- Shenzhen Technology University (CN)
- Liaoning Cancer Hospital & Institute (CN)
- Qilu Hospital of Shandong University (CN)
- Hainan Medical University (CN)
- China Medical University (CN)
- Northeastern University (CN)
- Stanford University (US)
Publication Details
- Journal
- iMetaMed
- Published
- 2026-11-03
- DOI
- https://doi.org/10.1002/imm3.70066
- Primary Topic
- Radiomics and Machine Learning in Medical Imaging
- Type
- article
- Field-Weighted Citation Impact
- 0.00