A more effective CT synthesizer using transformers for cone-beam CT-guided adaptive radiotherapy

Xinyuan Chen; Yuxiang Liu; Bining Yang; Ji Zhu; Siqi Yuan; Xuejie Xie; Yueping Liu; Jianrong Dai; Kuo Men

doi:10.3389/fonc.2022.988800

A more effective CT synthesizer using transformers for cone-beam CT-guided adaptive radiotherapy

Front Oncol. 2022 Aug 25:12:988800. doi: 10.3389/fonc.2022.988800. eCollection 2022.

Authors

Xinyuan Chen^{1

2}, Yuxiang Liu^{1

3}, Bining Yang¹, Ji Zhu¹, Siqi Yuan¹, Xuejie Xie¹, Yueping Liu¹, Jianrong Dai¹, Kuo Men¹

Affiliations

¹ National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China.
² National Cancer Center/National Clinical Research Center for Cancer/Hebei Cancer Hospital, Chinese Academy of Medical Sciences, Langfang, China.
³ School of Physics and Technology, Wuhan University, Wuhan, China.

Abstract

Purpose: The challenge of cone-beam computed tomography (CBCT) is its low image quality, which limits its application for adaptive radiotherapy (ART). Despite recent substantial improvement in CBCT imaging using the deep learning method, the image quality still needs to be improved for effective ART application. Spurred by the advantages of transformers, which employs multi-head attention mechanisms to capture long-range contextual relations between image pixels, we proposed a novel transformer-based network (called TransCBCT) to generate synthetic CT (sCT) from CBCT. This study aimed to further improve the accuracy and efficiency of ART.

Materials and methods: In this study, 91 patients diagnosed with prostate cancer were enrolled. We constructed a transformer-based hierarchical encoder-decoder structure with skip connection, called TransCBCT. The network also employed several convolutional layers to capture local context. The proposed TransCBCT was trained and validated on 6,144 paired CBCT/deformed CT images from 76 patients and tested on 1,026 paired images from 15 patients. The performance of the proposed TransCBCT was compared with a widely recognized style transferring deep learning method, the cycle-consistent adversarial network (CycleGAN). We evaluated the image quality and clinical value (application in auto-segmentation and dose calculation) for ART need.

Results: TransCBCT had superior performance in generating sCT from CBCT. The mean absolute error of TransCBCT was 28.8 ± 16.7 HU, compared to 66.5 ± 13.2 for raw CBCT, and 34.3 ± 17.3 for CycleGAN. It can preserve the structure of raw CBCT and reduce artifacts. When applied in auto-segmentation, the Dice similarity coefficients of bladder and rectum between auto-segmentation and oncologist manual contours were 0.92 and 0.84 for TransCBCT, respectively, compared to 0.90 and 0.83 for CycleGAN. When applied in dose calculation, the gamma passing rate (1%/1 mm criterion) was 97.5% ± 1.1% for TransCBCT, compared to 96.9% ± 1.8% for CycleGAN.

Conclusions: The proposed TransCBCT can effectively generate sCT for CBCT. It has the potential to improve radiotherapy accuracy.

Keywords: CBCT; adaptive radiotherapy; deep learning; image quality; transformer.