Cross-technique transfer learning for autoplanning in magnetic resonance imaging–guided adaptive radiotherapy for rectal cancer

IF 3.3 3区医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Physica Medica-European Journal of Medical Physics Pub Date : 2025-01-01 DOI:10.1016/j.ejmp.2024.104873

Xiaonan Liu , Deqi Chen , Yuxiang Liu , Kuo Men , Jianrong Dai , Hong Quan , Xinyuan Chen

{"title":"Cross-technique transfer learning for autoplanning in magnetic resonance imaging–guided adaptive radiotherapy for rectal cancer","authors":"Xiaonan Liu , Deqi Chen , Yuxiang Liu , Kuo Men , Jianrong Dai , Hong Quan , Xinyuan Chen","doi":"10.1016/j.ejmp.2024.104873","DOIUrl":null,"url":null,"abstract":"<div><h3>Purpose</h3><div>Automated treatment plan generation is essential for magnetic resonance imaging (MRI)-guided adaptive radiotherapy (MRIgART) to ensure standardized treatment-plan quality. We proposed a novel cross-technique transfer learning (CTTL)-based strategy for online MRIgART autoplanning.</div></div><div><h3>Method</h3><div>We retrospectively analyzed the data from 210 rectal cancer patients. A source dose prediction model was initially trained using a large volume of volumetric-modulated arc therapy data. Subsequently, a single patient’s pretreatment data was employed to construct a CTTL-based dose prediction model (CTTL_M) for each new patient undergoing MRIgART. The CTTL_M predicted dose distributions for subsequent treatment fractions. We optimized an auto plan using the parameters based on dose prediction. Performance of our CTTL_M was assessed using dose–volume histogram and mean absolute error (MAE). Our auto plans were compared with clinical plans regarding plan quality, efficiency, and complexity.</div></div><div><h3>Results</h3><div>CTTL_M significantly improved the dose prediction accuracy, particularly in planning target volumes (median MAE: 1.27 % vs. 7.06 %). The auto plans reduced high-dose exposure to the bladder (D<sub>0.1cc</sub>: 2,601.93 vs. 2,635.43 cGy, <em>P</em> < 0.001) and colon (D<sub>0.1cc</sub>: 2,593.22 vs. 2,624.89 cGy, <em>P</em> < 0.001). The mean colon dose decreased from 1,865.08 to 1,808.16 cGy (<em>P</em> = 0.035). The auto plans maintained similar planning time, monitor units, and plan complexity as clinical plans.</div></div><div><h3>Conclusions</h3><div>We proposed an online ART autoplanning method for generating high-quality plans with improved organ sparing. Its high degree of automation can standardize planning quality across varying expertise levels, mitigating subjective assessment and errors.</div></div>","PeriodicalId":56092,"journal":{"name":"Physica Medica-European Journal of Medical Physics","volume":"129 ","pages":"Article 104873"},"PeriodicalIF":3.3000,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Physica Medica-European Journal of Medical Physics","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1120179724013413","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING","Score":null,"Total":0}

引用次数: 0

Abstract

Purpose

Automated treatment plan generation is essential for magnetic resonance imaging (MRI)-guided adaptive radiotherapy (MRIgART) to ensure standardized treatment-plan quality. We proposed a novel cross-technique transfer learning (CTTL)-based strategy for online MRIgART autoplanning.

Method

We retrospectively analyzed the data from 210 rectal cancer patients. A source dose prediction model was initially trained using a large volume of volumetric-modulated arc therapy data. Subsequently, a single patient’s pretreatment data was employed to construct a CTTL-based dose prediction model (CTTL_M) for each new patient undergoing MRIgART. The CTTL_M predicted dose distributions for subsequent treatment fractions. We optimized an auto plan using the parameters based on dose prediction. Performance of our CTTL_M was assessed using dose–volume histogram and mean absolute error (MAE). Our auto plans were compared with clinical plans regarding plan quality, efficiency, and complexity.

Results

CTTL_M significantly improved the dose prediction accuracy, particularly in planning target volumes (median MAE: 1.27 % vs. 7.06 %). The auto plans reduced high-dose exposure to the bladder (D_0.1cc: 2,601.93 vs. 2,635.43 cGy, P < 0.001) and colon (D_0.1cc: 2,593.22 vs. 2,624.89 cGy, P < 0.001). The mean colon dose decreased from 1,865.08 to 1,808.16 cGy (P = 0.035). The auto plans maintained similar planning time, monitor units, and plan complexity as clinical plans.

Conclusions

We proposed an online ART autoplanning method for generating high-quality plans with improved organ sparing. Its high degree of automation can standardize planning quality across varying expertise levels, mitigating subjective assessment and errors.

查看原文本刊更多论文

跨技术迁移学习在磁共振成像引导下直肠癌自适应放疗中的应用。

目的：自动生成治疗计划是磁共振成像（MRI）引导的自适应放疗（MRIgART）确保标准化治疗计划质量的必要条件。提出了一种基于跨技术迁移学习（CTTL）的MRIgART在线自动规划策略。方法：回顾性分析210例直肠癌患者的临床资料。源剂量预测模型最初使用大量的体积调制电弧治疗数据进行训练。随后，利用单个患者的预处理数据，为每个新接受MRIgART的患者构建基于cttl的剂量预测模型（CTTL_M）。CTTL_M预测了后续治疗组分的剂量分布。我们利用基于剂量预测的参数优化了一个自动计划。使用剂量-体积直方图和平均绝对误差（MAE）评估CTTL_M的性能。将我们的自动计划与临床计划在计划质量、效率和复杂性方面进行比较。结果：CTTL_M显著提高了剂量预测精度，特别是在计划靶体积方面（MAE中位数：1.27% vs. 7.06%）。自动计划减少了膀胱高剂量暴露（D0.1cc: 2,601.93 vs. 2,635.43 cGy, p0.1 cc: 2,593.22 vs. 2,624.89 cGy， P）。结论：我们提出了一种在线ART自动计划方法，用于生成高质量的计划，改善了器官保留。它的高度自动化可以标准化不同专业水平的规划质量，减少主观评估和错误。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Physica Medica-European Journal of Medical Physics 生物-生物物理

CiteScore

6.80

自引率

14.70%

发文量

493

审稿时长

78 days

期刊介绍： Physica Medica, European Journal of Medical Physics, publishing with Elsevier from 2007, provides an international forum for research and reviews on the following main topics: Medical Imaging Radiation Therapy Radiation Protection Measuring Systems and Signal Processing Education and training in Medical Physics Professional issues in Medical Physics.