基于先验信息的宫颈癌自适应放疗中临床靶区自动勾画方法。

A prior-information-based automatic segmentation method for the clinical target volume in adaptive radiotherapy of cervical cancer.

机构信息

School of Nuclear Science and Technology, University of Science and Technology of China, Hefei, China.

Anhui Wisdom Technology Company Ltmited, Hefei, China.

出版信息

J Appl Clin Med Phys. 2024 May;25(5):e14350. doi: 10.1002/acm2.14350. Epub 2024 Mar 28.

DOI:10.1002/acm2.14350

PMID:38546277

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11087177/

Abstract

OBJECTIVE

Adaptive planning to accommodate anatomic changes during treatment often requires repeated segmentation. In this study, prior patient-specific data was integrateda into a registration-guided multi-channel multi-path (Rg-MCMP) segmentation framework to improve the accuracy of repeated clinical target volume (CTV) segmentation.

METHODS

This study was based on CT image datasets for a total of 90 cervical cancer patients who received two courses of radiotherapy. A total of 15 patients were selected randomly as the test set. In the Rg-MCMP segmentation framework, the first-course CT images (CT1) were registered to second-course CT images (CT2) to yield aligned CT images (aCT1), and the CTV in the first course (CTV1) was propagated to yield aligned CTV contours (aCTV1). Then, aCT1, aCTV1, and CT2 were combined as the inputs for 3D U-Net consisting of a channel-based multi-path feature extraction network. The performance of the Rg-MCMP segmentation framework was evaluated and compared with the single-channel single-path model (SCSP), the standalone registration methods, and the registration-guided multi-channel single-path (Rg-MCSP) model. The Dice similarity coefficient (DSC), 95% Hausdorff distance (HD95), and average surface distance (ASD) were used as the metrics.

RESULTS

The average DSC of CTV for the deformable image DIR-MCMP model was found to be 0.892, greater than that of the standalone DIR (0.856), SCSP (0.837), and DIR-MCSP (0.877), which were improvements of 4.2%, 6.6%, and 1.7%, respectively. Similarly, the rigid body DIR-MCMP model yielded an average DSC of 0.875, which exceeded standalone RB (0.787), SCSP (0.837), and registration-guided multi-channel single-path (0.848), which were improvements of 11.2%, 4.5%, and 3.2%, respectively. These improvements in DSC were statistically significant (p < 0.05).

CONCLUSION

The proposed Rg-MCMP framework achieved excellent accuracy in CTV segmentation as part of the adaptive radiotherapy workflow.

摘要

目的

在治疗过程中为适应解剖结构变化而进行的自适应计划通常需要重复进行分割。在这项研究中，将先前的患者特定数据集成到一个配准引导的多通道多路径（Rg-MCMP）分割框架中，以提高重复临床靶区（CTV）分割的准确性。

方法

本研究基于总共 90 例宫颈癌患者的 CT 图像数据集，这些患者接受了两程放疗。随机选择了 15 例患者作为测试集。在 Rg-MCMP 分割框架中，将第一疗程 CT 图像（CT1）配准到第二疗程 CT 图像（CT2），生成配准 CT 图像（aCT1），并将第一疗程的 CTV 传播，生成配准 CTV 轮廓（aCTV1）。然后，将 aCT1、aCTV1 和 CT2 组合作为由基于通道的多路径特征提取网络组成的 3D U-Net 的输入。评估 Rg-MCMP 分割框架的性能，并与单通道单路径模型（SCSP）、独立配准方法和配准引导的多通道单路径（Rg-MCSP）模型进行比较。使用 Dice 相似系数（DSC）、95%Hausdorff 距离（HD95）和平均表面距离（ASD）作为度量标准。

结果

发现变形图像 DIR-MCMP 模型的 CTV 的平均 DSC 为 0.892，大于独立 DIR（0.856）、SCSP（0.837）和 DIR-MCSP（0.877）的平均 DSC，分别提高了 4.2%、6.6%和 1.7%。同样，刚性体 DIR-MCMP 模型的平均 DSC 为 0.875，超过了独立 RB（0.787）、SCSP（0.837）和配准引导的多通道单路径（0.848），分别提高了 11.2%、4.5%和 3.2%。这些 DSC 的提高具有统计学意义（p<0.05）。