深度学习辅助肺癌自动放射治疗计划的临床实施和评估。

Clinical implementation and evaluation of deep learning-assisted automatic radiotherapy treatment planning for lung cancer.

机构信息

National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 100021, China.

Department of Radiation Oncology, Fudan University Shanghai Cancer Center, Shanghai 200032, China; Department of Oncology, Shanghai Medical College, Fudan University, Shanghai 200032, China; Shanghai Clinical Research Center for Radiation Oncology, China; Shanghai Key Laboratory of Radiation Oncology, Shanghai 200032, China.

出版信息

Phys Med. 2024 Aug;124:104492. doi: 10.1016/j.ejmp.2024.104492. Epub 2024 Aug 2.

DOI:10.1016/j.ejmp.2024.104492

PMID:39094213

Abstract

PURPOSE

The purpose of the study is to investigate the clinical application of deep learning (DL)-assisted automatic radiotherapy planning for lung cancer.

METHODS

A DL model was developed for predicting patient-specific doses, trained and validated on a dataset of 235 patients with diverse target volumes and prescriptions. The model was integrated into clinical workflow with DL-predicted objective functions. The automatic plans were retrospectively designed for additional 50 treated manual volumetric modulated arc therapy (VMAT) plans. A comparison was made between automatic and manual plans in terms of dosimetric indexes, monitor units (MUs) and planning time. Plan quality metric (PQM) encompassing these indexes was evaluated, with higher PQM values indicating superior plan quality. Qualitative evaluations of two plans were conducted by four reviewers.

RESULTS

The PQM score was 40.7 ± 13.1 for manual plans and 40.8 ± 13.5 for automatic plans (P = 0.75). Compared to manual plans, the targets coverage and homogeneity of automatic plans demonstrated no significant difference. Manual plans exhibited better sparing for lung in V5 (difference: 1.8 ± 4.2 %, P = 0.02), whereas automatic plans showed enhanced sparing for heart in V30 (difference: 1.4 ± 4.7 %, P = 0.02) and for spinal cord in Dmax (difference: 0.7 ± 4.7 Gy, P = 0.04). The planning time and MUs of automatic plans were significantly reduced by 70.5 ± 20.0 min and 97.4 ± 82.1. Automatic plans were deemed acceptable in 88 % of the reviews (176/200).

CONCLUSIONS

The DL-assisted approach for lung cancer notably decreased planning time and MUs, while demonstrating comparable or superior quality relative to manual plans. It has the potential to provide benefit to lung cancer patients.

摘要

目的

本研究旨在探讨深度学习（DL）辅助自动放疗计划在肺癌中的临床应用。

方法

针对具有不同靶区和处方的 235 例患者数据集，开发了一个用于预测患者特定剂量的 DL 模型，对其进行训练和验证。该模型与 DL 预测的目标函数相结合，集成到临床工作流程中。对 50 例已接受手动容积旋转调强放疗（VMAT）治疗的计划进行回顾性自动设计。比较了自动计划和手动计划在剂量学指标、监测器单位（MU）和计划时间方面的差异。评估了包含这些指标的计划质量度量（PQM），PQM 值越高表示计划质量越高。由四位评审员对两个计划进行了定性评估。

结果

手动计划的 PQM 评分为 40.7±13.1，自动计划的 PQM 评分为 40.8±13.5（P=0.75）。与手动计划相比，自动计划在靶区覆盖率和均匀性方面没有显著差异。手动计划在 V5 中对肺的保护更好（差异：1.8±4.2%，P=0.02），而自动计划在 V30 中对心脏的保护更好（差异：1.4±4.7%，P=0.02），在脊髓的 Dmax 中保护更好（差异：0.7±4.7 Gy，P=0.04）。自动计划的计划时间和 MU 分别显著减少了 70.5±20.0 min 和 97.4±82.1。88%（176/200）的评价认为自动计划是可以接受的。