CT-based deep learning signatures associated with transcriptomic heterogeneity and combined with nutritional biomarkers improve prediction of 3-year overall survival in esophageal squamous cell carcinoma

A combined DLS and nutritional model enables individualized preoperative survival prediction in ESCC. DLS-based risk groups defined by the DLS exhibited transcriptomic differences in key metabolic pathways, revealing biological underpinnings of imaging-based phenotypes. Attention map visualization revealed consistent spatial focus on morphologically distinct tumor regions, enhancing the interpretability of deep learning predictions.