利用域适应进行高效分割以用于MRI引导和CBCT引导的在线自适应放疗。

Efficient segmentation using domain adaptation for MRI-guided and CBCT-guided online adaptive radiotherapy.

作者信息

Liu Yuxiang, Yang Bining, Chen Xinyuan, Zhu Ji, Ji Guangqian, Liu Yueping, Chen Bo, Lu Ningning, Yi Junlin, Wang Shulian, Li Yexiong, Dai Jianrong, Men Kuo

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.

出版信息

Radiother Oncol. 2023 Nov;188:109871. doi: 10.1016/j.radonc.2023.109871. Epub 2023 Aug 25.

DOI:10.1016/j.radonc.2023.109871

PMID:37634767

Abstract

BACKGROUND

Delineation of regions of interest (ROIs) is important for adaptive radiotherapy (ART) but it is also time consuming and labor intensive.

AIM

This study aims to develop efficient segmentation methods for magnetic resonance imaging-guided ART (MRIgART) and cone-beam computed tomography-guided ART (CBCTgART).

MATERIALS AND METHODS

MRIgART and CBCTgART studies enrolled 242 prostate cancer patients and 530 nasopharyngeal carcinoma patients, respectively. A public dataset of CBCT from 35 pancreatic cancer patients was adopted to test the framework. We designed two domain adaption methods to learn and adapt the features from planning computed tomography (pCT) to MRI or CBCT modalities. The pCT was transformed to synthetic MRI (sMRI) for MRIgART, while CBCT was transformed to synthetic CT (sCT) for CBCTgART. Generalized segmentation models were trained with large popular data in which the inputs were sMRI for MRIgART and pCT for CBCTgART. Finally, the personalized models for each patient were established by fine-tuning the generalized model with the contours on pCT of that patient. The proposed method was compared with deformable image registration (DIR), a regular deep learning (DL) model trained on the same modality (DL-regular), and a generalized model in our framework (DL-generalized).

RESULTS

The proposed method achieved better or comparable performance. For MRIgART of the prostate cancer patients, the mean dice similarity coefficient (DSC) of four ROIs was 87.2%, 83.75%, 85.36%, and 92.20% for the DIR, DL-regular, DL-generalized, and proposed method, respectively. For CBCTgART of the nasopharyngeal carcinoma patients, the mean DSC of two target volumes were 90.81% and 91.18%, 75.17% and 58.30%, for the DIR, DL-regular, DL-generalized, and the proposed method, respectively. For CBCTgART of the pancreatic cancer patients, the mean DSC of two ROIs were 61.94% and 61.44%, 63.94% and 81.56%, for the DIR, DL-regular, DL-generalized, and the proposed method, respectively.

CONCLUSION

The proposed method utilizing personalized modeling improved the segmentation accuracy of ART.

摘要

背景

感兴趣区域（ROI）的勾画对于自适应放疗（ART）很重要，但它也耗时且费力。

目的

本研究旨在开发用于磁共振成像引导的ART（MRIgART）和锥束计算机断层扫描引导的ART（CBCTgART）的高效分割方法。

材料与方法

MRIgART和CBCTgART研究分别纳入了242例前列腺癌患者和530例鼻咽癌患者。采用来自35例胰腺癌患者的CBCT公共数据集来测试该框架。我们设计了两种域适应方法，以学习并将来自计划计算机断层扫描（pCT）的特征适应于MRI或CBCT模态。对于MRIgART，将pCT转换为合成MRI（sMRI），而对于CBCTgART，将CBCT转换为合成CT（sCT）。使用大量流行数据训练广义分割模型，其中对于MRIgART，输入为sMRI，对于CBCTgART，输入为pCT。最后，通过使用该患者pCT上的轮廓对广义模型进行微调，为每个患者建立个性化模型。将所提出的方法与可变形图像配准（DIR）、在相同模态上训练的常规深度学习（DL）模型（DL-regular）以及我们框架中的广义模型（DL-generalized）进行比较。

结果

所提出的方法取得了更好或相当的性能。对于前列腺癌患者的MRIgART，DIR、DL-regular、DL-generalized和所提出的方法，四个ROI的平均骰子相似系数（DSC）分别为87.2%、83.75%、85.36%和92.20%。对于鼻咽癌患者的CBCTgART，DIR、DL-regular、DL-generalized和所提出的方法，两个靶区体积的平均DSC分别为90.81%和91.18%、75.17%和58.30%。对于胰腺癌患者的CBCTgART，DIR、DL-regular、DL-generalized和所提出的方法，两个ROI的平均DSC分别为61.94%和61.44%、63.94%和81.56%。