npj Artificial Intelligence Computer Science Applications

UPMA: unspecified pretraining and modular adaptation for context-aware target delineation in adaptive esophageal radiotherapy

Yihua Sun, Sijuan Huang, Hee Guan Khor, Haojie Han, Yongsheng Zhang, Lu Bai, Qi Chen, Shaobin Wang, Qinghe Peng, Guochen Ning, Haojiang Li, Fang Chen, Xin Yang, Hongen Liao
Springer Nature · 2026-09-02 · DOI 10.1038/s44387-026-00143-w

Abstract

Abstract Esophageal cancer, a serious malignancy, is primarily treated with radiotherapy (RT). Accurate delineation of gross tumor volume (GTV) and clinical target volume (CTV) is essential, yet manual contouring is time-consuming and automatic methods remain challenging. Adaptive radiotherapy enables personalized target adjustments, but tumor changes following initial RT complicate delineation, and automatic second-phase replanning is underexplored. We propose the Unspecified Pretraining and Modular Adaptation (UPMA) framework for context-aware second-phase esophageal target delineation. UPMA pretrains its network on diverse datasets to comprehend tumor and anatomical features, then modularly adapts it for second-phase tasks with minimal parameters. The method improves Dice scores by over 23% for GTV and over 5% for CTV, while reducing learnable parameters by over 73% during adaptation. In clinical evaluations, 73.7% and 52.6% of the predicted GTVs and CTVs required only minor edits. UPMA generalizes across diverse patient characteristics and imaging factors, supporting automated adaptive radiotherapy for precise, personalized treatment.

Read at publisher →