Habitat-aware radiomics and adaptive 2.5D deep learning predict treatment response and long-term survival in ESCC patients undergoing neoadjuvant chemoimmunotherapy.
Authors
Affiliations (13)
Affiliations (13)
- 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.
- School of Nuclear Science and Technology, University of South China, Hengyang, Hunan, China.
- Department of Ultrasound, The Second Affiliated Hospital, Xi'an Jiaotong University, Xi'an, China.
- Department of PET-CT, The Second Affiliated Hospital of Harbin Medical University, Harbin, 150001, China. [email protected].
- Department of PET-CT, The First Affiliated Hospital of Xi'an Jiaotong University, Xi'an, 710000, China. [email protected].
- Department of Ultrasound, The Second Affiliated Hospital of Harbin Medical University, Harbin, China. [email protected].
- Ultrasound molecular imaging Joint laboratory of Heilongjiang province (International Cooperation), Harbin, China. [email protected].
- State Key Laboratory of Frigid Zone cardiovascular diseases, ministry of science and technology, Harbin, China. [email protected].
Abstract
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. 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). Habitat radiomics achieved superior validation AUC (0.865, 95% CI: 0.778-0.953), outperforming conventional radiomics (ΔAUC + 3.6%, P < 0.01) and clinical models (ΔAUC + 6.4%, P < 0.001). SHAP identified the invasive front (H2) as dominant predictor (40% of top features), with wavelet_LHH_firstorder_Entropy showing highest impact (SHAP = + 0.42). The 2.5D MIL model demonstrated strong generalizability (validation AUC: 0.861). The combined model achieved state-of-the-art test performance (AUC = 0.824, sensitivity = 0.875) with superior calibration (Hosmer-Lemeshow P > 0.800), effective survival stratification (test C-index: 0.809), and 23-41% net benefit improvement in DCA. Integrating habitat radiomics and 2.5D deep learning enables interpretable dual diagnostic-prognostic stratification in ESCC, advancing precision oncology by decoding spatial heterogeneity.