Incorporating the synthetic CT image for improving the performance of deformable image registration between planning CT and cone-beam CT

Frontiers in Oncology

Oncology

Shupeng Chen¹  Na Li²  Jingjing Dai³  Tangsheng Wang³  Chulong Zhang³  Yaoqin Xie³  Xiaokun Liang³  Wenfeng He³  Xuanru Zhou⁴ 

[1] Department of Radiation Oncology, Beaumont Health, Royal Oak, MI, United States;School of Biomedical Engineering, Guangdong Medical University, Dongguan, Guangdong, China;Dongguan Key Laboratory of Medical Electronics and Medical Imaging Equipment, Dongguan, Guangdong, China;Songshan Lake Innovation Center of Medicine & Engineering, Guangdong Medical University, Dongguan, Guangdong, China;Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong, China;Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong, China;Department of Biomedical Engineering, Southern Medical University, Guangzhou, China;

关键词: synthetic image;    deformable image registration (DIR);    breast cancer;    deep learning;    radiation therapy;   

DOI  :  10.3389/fonc.2023.1127866

 received in 2022-12-20, accepted in 2023-01-25,  发布年份 2023

来源: Frontiers

【 摘 要 】

ObjectiveTo develop a contrast learning-based generative (CLG) model for the generation of high-quality synthetic computed tomography (sCT) from low-quality cone-beam CT (CBCT). The CLG model improves the performance of deformable image registration (DIR).MethodsThis study included 100 post-breast-conserving patients with the pCT images, CBCT images, and the target contours, which the physicians delineated. The CT images were generated from CBCT images via the proposed CLG model. We used the Sct images as the fixed images instead of the CBCT images to achieve the multi-modality image registration accurately. The deformation vector field is applied to propagate the target contour from the pCT to CBCT to realize the automatic target segmentation on CBCT images. We calculate the Dice similarity coefficient (DSC), 95 % Hausdorff distance (HD95), and average surface distance (ASD) between the prediction and reference segmentation to evaluate the proposed method.ResultsThe DSC, HD95, and ASD of the target contours with the proposed method were 0.87 ± 0.04, 4.55 ± 2.18, and 1.41 ± 0.56, respectively. Compared with the traditional method without the synthetic CT assisted (0.86 ± 0.05, 5.17 ± 2.60, and 1.55 ± 0.72), the proposed method was outperformed, especially in the soft tissue target, such as the tumor bed region.ConclusionThe CLG model proposed in this study can create the high-quality sCT from low-quality CBCT and improve the performance of DIR between the CBCT and the pCT. The target segmentation accuracy is better than using the traditional DIR.

【 授权许可】

Unknown   
Copyright © 2023 Li, Zhou, Chen, Dai, Wang, Zhang, He, Xie and Liang