Lung cancer dose distribution prediction based on a dual-branch feature extraction network

IF 3.2 2区医学 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING

Medical physics Pub Date : 2025-03-24 DOI:10.1002/mp.17775

Haifeng Zhang, Yongxin Liu, Yanjun Yu, Fuli Zhang

{"title":"Lung cancer dose distribution prediction based on a dual-branch feature extraction network","authors":"Haifeng Zhang, Yongxin Liu, Yanjun Yu, Fuli Zhang","doi":"10.1002/mp.17775","DOIUrl":null,"url":null,"abstract":"<div>\n \n \n <section>\n \n <h3> Background</h3>\n \n <p>Currently, predicting dose distributions through neural networks can improve the automation level of radiotherapy planning. However, a single neural network often has limitations in its ability to extract features and obtain clinical information.</p>\n </section>\n \n <section>\n \n <h3> Purpose</h3>\n \n <p>To assist in the development of volumetric modulated arc therapy (VMAT) plans for non-small cell lung cancer (NSCLC) patients, a dual-branch feature extraction neural network is proposed to predict dose distributions.</p>\n </section>\n \n <section>\n \n <h3> Methods</h3>\n \n <p>This study proposes a dual-branch feature extraction network named CTNet, which consists of a convolutional network and a transformer network in parallel to extract local and global features that are meaningful for dose prediction tasks. A feature fusion module has been developed to reduce the heterogeneity of the two extracted features. To promote the learning of two types of features in the network, weighted mean square error and multiscale structural loss were used. The network was trained on 144 VMAT plans of NSCLC patients. The performance of this network was compared with that of several commonly used networks, and the network performance was evaluated on the basis of the voxel-level mean absolute error (MAE) within the planning target volume (PTV) and organs at risk (OARs), as well as the error in clinical dose‒volume metrics.</p>\n </section>\n \n <section>\n \n <h3> Results</h3>\n \n <p>The MAE between the predicted dose distribution and the manually planned dose distribution within the PTV was 1.14 Gy, and the D95 error was less than 1 Gy. Compared with the other four commonly used networks, the dose error of the CTNet was the smallest in the PTV and OARs.</p>\n </section>\n \n <section>\n \n <h3> Conclusions</h3>\n \n <p>The proposed CTNet uses the transformer and convolutional networks to extract global information, such as the relative position of the PTV and OARs, as well as local information, such as shape and size, enabling accurate prediction of the dose distribution for NSCLC patients undergoing VMAT radiotherapy.</p>\n </section>\n </div>","PeriodicalId":18384,"journal":{"name":"Medical physics","volume":"52 6","pages":"4454-4463"},"PeriodicalIF":3.2000,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Medical physics","FirstCategoryId":"3","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/mp.17775","RegionNum":2,"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

Background

Currently, predicting dose distributions through neural networks can improve the automation level of radiotherapy planning. However, a single neural network often has limitations in its ability to extract features and obtain clinical information.

Purpose

To assist in the development of volumetric modulated arc therapy (VMAT) plans for non-small cell lung cancer (NSCLC) patients, a dual-branch feature extraction neural network is proposed to predict dose distributions.

Methods

This study proposes a dual-branch feature extraction network named CTNet, which consists of a convolutional network and a transformer network in parallel to extract local and global features that are meaningful for dose prediction tasks. A feature fusion module has been developed to reduce the heterogeneity of the two extracted features. To promote the learning of two types of features in the network, weighted mean square error and multiscale structural loss were used. The network was trained on 144 VMAT plans of NSCLC patients. The performance of this network was compared with that of several commonly used networks, and the network performance was evaluated on the basis of the voxel-level mean absolute error (MAE) within the planning target volume (PTV) and organs at risk (OARs), as well as the error in clinical dose‒volume metrics.

Results

The MAE between the predicted dose distribution and the manually planned dose distribution within the PTV was 1.14 Gy, and the D95 error was less than 1 Gy. Compared with the other four commonly used networks, the dose error of the CTNet was the smallest in the PTV and OARs.

Conclusions

The proposed CTNet uses the transformer and convolutional networks to extract global information, such as the relative position of the PTV and OARs, as well as local information, such as shape and size, enabling accurate prediction of the dose distribution for NSCLC patients undergoing VMAT radiotherapy.

查看原文本刊更多论文

基于双分支特征提取网络的肺癌剂量分布预测。

背景：目前，利用神经网络预测剂量分布可以提高放疗计划的自动化水平。然而，单个神经网络在提取特征和获取临床信息方面往往存在局限性。目的：为了帮助制定非小细胞肺癌（NSCLC）患者的体积调制电弧治疗（VMAT）计划，提出了一种双分支特征提取神经网络来预测剂量分布。方法：本研究提出了一种双分支特征提取网络CTNet，该网络由卷积网络和变压器网络并行组成，用于提取对剂量预测任务有意义的局部和全局特征。为了减少提取的两个特征的异构性，开发了特征融合模块。为了促进网络中两类特征的学习，使用了加权均方误差和多尺度结构损失。该网络对144例NSCLC患者的VMAT计划进行了训练。将该网络的性能与几种常用网络的性能进行比较，并根据规划目标体积（PTV）和危险器官（OARs）内的体素级平均绝对误差（MAE）以及临床剂量-体积指标的误差对网络性能进行评估。结果：PTV内预测剂量分布与人工计划剂量分布的MAE为1.14 Gy， D95误差小于1 Gy。与其他四种常用网络相比，CTNet在PTV和OARs中的剂量误差最小。结论：本文提出的CTNet利用变压器和卷积网络提取PTV和OARs的相对位置等全局信息和形状、大小等局部信息，能够准确预测VMAT放疗NSCLC患者的剂量分布。

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

Medical physics 医学-核医学

CiteScore

6.80

自引率

15.80%

发文量

660

审稿时长

1.7 months

期刊介绍： Medical Physics publishes original, high impact physics, imaging science, and engineering research that advances patient diagnosis and therapy through contributions in 1) Basic science developments with high potential for clinical translation 2) Clinical applications of cutting edge engineering and physics innovations 3) Broadly applicable and innovative clinical physics developments Medical Physics is a journal of global scope and reach. By publishing in Medical Physics your research will reach an international, multidisciplinary audience including practicing medical physicists as well as physics- and engineering based translational scientists. We work closely with authors of promising articles to improve their quality.