A dual-prompt framework combining spatial-mask priors and clinical-text conditioning for CT-only GTV delineation in esophageal cancer: A multicenter study.

BACKGROUND

Accurate gross tumor volume (GTV) delineation is essential for esophageal cancer radiotherapy, but CT-only automatic delineation remains difficult because of indistinct tumor boundaries.

PURPOSE: This study aimed to develop and validate a two-stage dual-prompt framework combining a spatial-mask prior with LLaMA3-encoded clinical-text conditioning for primary esophageal GTV delineation.

METHODS

This multicenter study included 857 patients: 500 for development, 125 for internal validation, 50 for ablation analysis, and 182 for external validation. The proposed framework consists of two stages: (1) a CT-based automatic segmentation network generating an initial GTV as a spatial mask prompt, and (2) a refinement network that jointly incorporates spatial mask prompt and LLaMA3-encoded clinical text prompt derived from structured clinical information. Performance was evaluated using overlap, surface distance, and volumetric metrics, and compared with multiple state-of-the-art deep learning models. Ablation and radiomics analyses assessed component contributions and downstream consistency.

RESULTS

In internal validation, the framework achieved a DSC of 80.32 ± 6.65%, an HD95 of 11.42 ± 8.90 mm, and an absolute volume difference of 9.99 ± 10.49 mL; all Holm-adjusted p values were <0.001 versus the comparison models. Mean DSCs were 78.60 ± 13.39% and 78.36 ± 15.54% in the external cohorts. Mean DSCs were 78.60 ± 13.39% and 78.36 ± 15.54% in the two external cohorts, respectively. In external cohort A, ContextUNETR showed a lower mean HD95 than the proposed model (10.93 ± 8.03 vs. 13.44 ± 18.90 mm), although the paired difference was not statistically significant after Holm correction (adjusted p = 0.906). Compared with the direct Stage-1 output, the complete framework consistently improved overlap, boundary-distance, and volumetric-agreement metrics across the internal and both external validation cohorts (all adjusted p < 0.001). LLaMA3 encoding improved DSC versus an MLP using the same variables (adjusted p = 0.009), whereas ASSD did not differ significantly. Automatic and manual GTVs showed high radiomic concordance and comparable prognostic performance.

CONCLUSION

The framework improved overlap and volumetric agreement for CT-only primary esophageal GTV delineation across multicenter validation cohorts, although boundary-distance performance varied across external cohorts.