Scholarlink

Purpose <p>Deep learning-based 3D dose prediction boosts radiotherapy planning efficiency and consistency, yet most models rely solely on anatomical data and assume homogeneous beam configurations, impairing their robustness in esophageal cancer intensity-modulated radiotherapy (IMRT) with heterogeneous beam arrangements. This study explored whether explicit beam geometry modeling enhances voxel-level dose prediction accuracy, robustness in rare beam configurations, and clinical workflow efficiency.</p> Methods <p>A retrospective analysis was performed on 751 esophageal cancer IMRT patients. Two models with the identical AS-NeSt backbone were constructed: an anatomy-only dose prediction model (ADP) and an anatomy-and-angle-based model (AADP) integrating ray-tracing-derived beam geometry representations (normalized beam coverage and overlap maps) accessible in pre-planning. Model performance was assessed on an independent test set (<i>n</i> = 100), a rare-beam configuration cohort (<i>n</i> = 33) and a clinical validation cohort (<i>n</i> = 42), against clinical plans as the reference baseline. Evaluation was based on dosimetric metrics and isodose spatial similarity, along with an analysis of its robustness on unseen beam configurations and impact in a crossover clinical workflow study.</p> Results <p>Compared with ADP, AADP significantly reduced prediction errors for most targets and organs at risk, cutting average dosimetric error from 2.88% to 2.02%, with prominent improvements in low-to-intermediate dose regions (lung and heart). The mean Dice similarity coefficient of isodose volumes rose from 0.90 to 0.93. For rare beam configurations, AADP exhibited superior robustness (average error: 3.08% vs. 4.52%). Notably, AADP-assisted planning shortened total planning time by up to 65% (from 111.4 to 38.5&#xa0;min for junior physicists), reduced iterations, and improved intra- and inter-physicist dose consistency.</p> Conclusions <p>This study confirms explicit ray-tracing-based beam geometry modeling enhances the accuracy, robustness, and clinical utility of 3D dose prediction for esophageal cancer IMRT, supporting beam geometry as a critical component of clinically deployable, physics-informed dose prediction models.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Explicit modeling of beam geometry improves three-dimensional dose prediction for esophageal cancer radiotherapy under heterogeneous beam configurations

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月22日

查看全文
  • Yanhua Duan,
  • Hua Chen,
  • Hao Wang,
  • Hongbin Cao,
  • Hengle Gu,
  • Yan Shao,
  • Aihui Feng,
  • Ying Huang,
  • Zhenjiong Shen,
  • Qing Kong,
  • Zhiyong Xu

摘要

Purpose

Deep learning-based 3D dose prediction boosts radiotherapy planning efficiency and consistency, yet most models rely solely on anatomical data and assume homogeneous beam configurations, impairing their robustness in esophageal cancer intensity-modulated radiotherapy (IMRT) with heterogeneous beam arrangements. This study explored whether explicit beam geometry modeling enhances voxel-level dose prediction accuracy, robustness in rare beam configurations, and clinical workflow efficiency.

Methods

A retrospective analysis was performed on 751 esophageal cancer IMRT patients. Two models with the identical AS-NeSt backbone were constructed: an anatomy-only dose prediction model (ADP) and an anatomy-and-angle-based model (AADP) integrating ray-tracing-derived beam geometry representations (normalized beam coverage and overlap maps) accessible in pre-planning. Model performance was assessed on an independent test set (n = 100), a rare-beam configuration cohort (n = 33) and a clinical validation cohort (n = 42), against clinical plans as the reference baseline. Evaluation was based on dosimetric metrics and isodose spatial similarity, along with an analysis of its robustness on unseen beam configurations and impact in a crossover clinical workflow study.

Results

Compared with ADP, AADP significantly reduced prediction errors for most targets and organs at risk, cutting average dosimetric error from 2.88% to 2.02%, with prominent improvements in low-to-intermediate dose regions (lung and heart). The mean Dice similarity coefficient of isodose volumes rose from 0.90 to 0.93. For rare beam configurations, AADP exhibited superior robustness (average error: 3.08% vs. 4.52%). Notably, AADP-assisted planning shortened total planning time by up to 65% (from 111.4 to 38.5 min for junior physicists), reduced iterations, and improved intra- and inter-physicist dose consistency.

Conclusions

This study confirms explicit ray-tracing-based beam geometry modeling enhances the accuracy, robustness, and clinical utility of 3D dose prediction for esophageal cancer IMRT, supporting beam geometry as a critical component of clinically deployable, physics-informed dose prediction models.