文献速递乳腺癌放疗放疗物理与技术

基于不确定性估计与注意力机制半监督模型用于乳腺癌CBCT图像临床靶区自动勾画

Uncertainty estimation- and attention-based semi-supervised models for automatically delineate clinical target volume in CBCT images of breast cancer.
PubMed 文献 · Radiat Oncol · 2024-05-29

本研究纳入60例保乳术后放疗患者(60幅计划CT和380幅CBCT),提出融合残差与注意力模块的RCBA-UAMT半监督模型,在少量标注数据(5%、10%、20%)下自动勾画乳腺癌CBCT图像CTV。模型平均DSC为82%、Jaccard为70%、95HD为8.93 mm、ASD为1.49 mm;与三种经典方法相比DSC和Jaccard分别提高7.89–9.33%和14.75–16.67%,95HD和ASD分别降低33.16–67.81%和36.05–75.57%。5%与10%、5%与20%标注数据间DSC、Jaccard和95HD有显著差异,10%与20%间所有指标无显著差异,故仅用10%标注数据即可达到实验目标。

要点

  • RCBA-UAMT在乳腺癌CBCT图像上勾画CTV的平均DSC为82%、Jaccard为70%、95HD为8.93 mm、ASD为1.49 mm。
  • 与三种经典方法相比,DSC和Jaccard分别提高7.89–9.33%和14.75–16.67%,95HD和ASD分别降低33.16–67.81%和36.05–75.57%。
  • 5%与10%、5%与20%标注数据间DSC、Jaccard和95HD有显著差异,10%与20%间所有指标无显著差异,仅用10%标注数据即可达到实验目标。

核心结论

  • 使用所提出的RCBA-UAMT,仅需少量标注数据即可可靠地勾画乳腺癌CBCT图像的CTV。
  • 勾画的图像可用于观察CTV变化,并为后续实施自适应放疗(ART)奠定基础。

研究设计与样本

  • 本研究纳入60例保乳术后接受放疗的患者,包括60幅计划CT和380幅CBCT。
  • 提出RCBA-UAMT半监督模型,在骨干网络3D UNet中整合残差模块与注意力模块,注意力模块可调整提取图像特征的通道与空间权重。
  • 该设计可用少量标注数据(5%、10%、20%)和大量未标注数据训练模型并分割CBCT图像。
  • 采用DSC、Jaccard、ASD和95HD四种评价指标定量评估模型分割性能。

主要发现

  • 所提方法在乳腺癌CBCT图像CTV勾画上的平均DSC、Jaccard、95HD和ASD分别为82%、70%、8.93 mm和1.49 mm。
  • 与mean teacher、uncertainty-aware mean-teacher和uncertainty rectified pyramid consistency三种经典方法相比,DSC和Jaccard分别提高7.89–9.33%和14.75–16.67%,95HD和ASD分别降低33.16–67.81%和36.05–75.57%。
  • 不同比例标注数据(5%、10%、20%)对比实验显示,5%与10%及5%与20%标注数据间DSC、Jaccard和95HD评价指标有显著差异。
  • 10%与20%标注数据间所有评价指标均无显著差异。

关键数值与推荐

  • DSC为82%、Jaccard为70%、95HD为8.93 mm、ASD为1.49 mm(乳腺癌CBCT图像CTV勾画)。
  • 与三种经典方法相比,DSC提高7.89–9.33%,Jaccard提高14.75–16.67%,95HD降低33.16–67.81%,ASD降低36.05–75.57%。
  • 5%与10%及5%与20%标注数据间DSC、Jaccard和95HD有显著差异;10%与20%间所有指标无显著差异。

临床怎么用

  • 作者认为仅使用10%标注数据即可达到实验目标。
  • 勾画的图像可用于观察CTV变化,并为后续实施ART奠定基础。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

OBJECTIVES: Accurate segmentation of the clinical target volume (CTV) of CBCT images can observe the changes of CTV during patients' radiotherapy, and lay a foundation for the subsequent implementation of adaptive radiotherapy (ART). However, segmentation is challenging due to the poor quality of CBCT images and difficulty in obtaining target volumes. An uncertainty estimation- and attention-based semi-supervised model called residual convolutional block attention-uncertainty aware mean teacher (RCBA-UAMT) was proposed to delineate the CTV in cone-beam computed tomography (CBCT) images of breast cancer automatically. METHODS: A total of 60 patients who undergone radiotherapy after breast-conserving surgery were enrolled in this study, which involved 60 planning CTs and 380 CBCTs. RCBA-UAMT was proposed by integrating residual and attention modules in the backbone network 3D UNet. The attention module can adjust channel and spatial weights of the extracted image features. The proposed design can train the model and segment CBCT images with a small amount of labeled data (5%, 10%, and 20%) and a large amount of unlabeled data. Four types of evaluation metrics, namely, dice similarity coefficient (DSC), Jaccard, average surface distance (ASD), and 95% Hausdorff distance (95HD), are used to assess the model segmentation performance quantitatively. RESULTS: The proposed method achieved average DSC, Jaccard, 95HD, and ASD of 82%, 70%, 8.93, and 1.49 mm for CTV delineation on CBCT images of breast cancer, respectively. Compared with the three classical methods of mean teacher, uncertainty-aware mean-teacher and uncertainty rectified pyramid consistency, DSC and Jaccard increased by 7.89-9.33% and 14.75-16.67%, respectively, while 95HD and ASD decreased by 33.16-67.81% and 36.05-75.57%, respectively. The comparative experiment results of the labeled data with different proportions (5%, 10% and 20%) showed significant differences in the DSC, Jaccard, and 95HD evaluation indexes in the labeled data with 5% versus 10% and 5% versus 20%. Moreover, no significant differences were observed in the labeled data with 10% versus 20% among all evaluation indexes. Therefore, we can use only 10% labeled data to achieve the experimental objective. CONCLUSIONS: Using the proposed RCBA-UAMT, the CTV of breast cancer CBCT images can be delineated reliably with a small amount of labeled data. These delineated images can be used to observe the changes in CTV and lay the foundation for the follow-up implementation of ART.

来源:Radiat Oncol,查看原文。版权归原作者所有。

引用

  1. Wang Z, Cao N, Sun J, et al. Uncertainty estimation- and attention-based semi-supervised models for automatically delineate clinical target volume in CBCT images of breast cancer. Radiat Oncol. 2024. PMID: 38811994. doi:10.1186/s13014-024-02455-0

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。