Habitat-aware radiomics and adaptive 2.5D deep learning predict treatment response and long-term survival in ESCC patients undergoing neoadjuvant chemoimmunotherapy
European Journal of Nuclear Medicine and Molecular Imaging · 2026-02 · 53 (3) · 1651-1670
DOI: 10.1007/s00259-025-07522-6 ↗Kurz gefasst
Fachartikel in der Zeitschrift European Journal of Nuclear Medicine and Molecular Imaging, online erschienen am 17.09.2025. Verfasst von Xing Gao und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of Ultrasound, The Second Affiliated Hospital of Harbin Medical University, Harbin, China. Hauptthemen laut MEDLINE: Esophageal Neoplasms, Deep Learning, Neoadjuvant Therapy, Esophageal Squamous Cell Carcinoma. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 43 Literaturangaben. Gefördert von: Natural Science Foundation of China, Longjiang science and Technology Talent Wild ChunYan Support Project.
Abstract (Originalsprache)
PURPOSE: Current radiomic approaches inadequately resolve spatial intratumoral heterogeneity (ITH) in esophageal squamous cell carcinoma (ESCC), limiting neoadjuvant chemoimmunotherapy (NACI) response prediction. We propose an interpretable multimodal framework to: (1) quantitatively map intra-/peritumoral heterogeneity via voxel-wise habitat radiomics; (2) model cross-sectional tumor biology using 2.5D deep learning; and (3) establish mechanism-driven biomarkers via SHAP interpretability to identify resistance-linked subregions. METHODS: This dual-center retrospective study analyzed 269 treatment-naïve ESCC patients with baseline PET/CT (training: n = 144; validation: n = 62; test: n = 63). Habitat radiomics delineated tumor subregions via K-means clustering (Calinski-Harabasz-optimized) on PET/CT, extracting 1,834 radiomic features per modality. A multi-stage pipeline (univariate filtering, mRMR, LASSO regression) selected 32 discriminative features. The 2.5D model aggregated ± 4 peri-tumoral slices, fusing PET/CT via MixUp channels using a fine-tuned ResNet50 (ImageNet-pretrained), with multi-instance learning (MIL) translating slice-level features to patient-level predictions. Habitat features, MIL signatures, and clinical variables were integrated via five-classifier ensemble (ExtraTrees/SVM/RandomForest) and Crossformer architecture (SMOTE-balanced). Validation included AUC, sensitivity, specificity, calibration curves, decision curve analysis (DCA), survival metrics (C-index, Kaplan-Meier), and interpretability (SHAP, Grad-CAM). RESULTS: Habitat radiomics achieved superior validation AUC (0.865, 95% CI: 0.778-0.953), outperforming conventional radiomics (ΔAUC + 3.6%, P 0.800), effective survival stratification (test C-index: 0.809), and 23-41% net benefit improvement in DCA. CONCLUSION: Integrating habitat radiomics and 2.5D deep learning enables interpretable dual diagnostic-prognostic stratification in ESCC, advancing precision oncology by decoding spatial heterogeneity.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Ultrasound, The Second Affiliated Hospital of Harbin Medical University, Harbin, China.
- Department of PET-CT, The First Affiliated Hospital of Xi'an Jiaotong University, Xi'an, 710000, China.
- Department of Ultrasound, Xi'an Electric Power Central Hospital, Xi'an, China.
- Department of Ultrasound, The First Affiliated Hospital of Xi'an Jiaotong University, Xi'an, China.
- Department of Magnetic Resonance Imaging, The First Affiliated Hospital of Harbin Medical University, Harbin, China.
- Department of Pathology, Heilongjiang Provincial Hospital, Harbin, China.
Förderung
- Natural Science Foundation of China
- Longjiang science and Technology Talent Wild ChunYan Support Project
Zitieren
APA
Gao, X., Yang, L., She, T., Wang, F., Ding, H., Lu, Y., Xu, Y., Wang, Y., Li, P., Duan, X., & Leng, X. (2026). Habitat-aware radiomics and adaptive 2.5D deep learning predict treatment response and long-term survival in ESCC patients undergoing neoadjuvant chemoimmunotherapy. European Journal of Nuclear Medicine and Molecular Imaging, 53(3), 1651-1670. https://doi.org/10.1007/s00259-025-07522-6
Vancouver
Gao X, Yang L, She T, Wang F, Ding H, Lu Y, et al. Habitat-aware radiomics and adaptive 2.5D deep learning predict treatment response and long-term survival in ESCC patients undergoing neoadjuvant chemoimmunotherapy. European Journal of Nuclear Medicine and Molecular Imaging. 2026;53(3):1651-1670. doi:10.1007/s00259-025-07522-6
BibTeX
@article{Gao2026,
author = {Gao, Xing and Yang, Liping and She, Tianyu and Wang, Fei and Ding, Hongchao and Lu, Yanhong and Xu, Yuchao and Wang, Yuan and Li, Ping and Duan, Xiaoyi and Leng, Xiaoping},
title = {Habitat-aware radiomics and adaptive 2.5D deep learning predict treatment response and long-term survival in ESCC patients undergoing neoadjuvant chemoimmunotherapy},
journal = {European Journal of Nuclear Medicine and Molecular Imaging},
year = {2026},
volume = {53},
number = {3},
pages = {1651--1670},
doi = {10.1007/s00259-025-07522-6}
}
EUVIMED