Multi-center Dose Prediction Using Attention-aware Deep learning Algorithm Based on Transformers for Cervical Cancer Radiotherapy

Z Wu; X Jia; L Lu; C Xu; Y Pang; S Peng; M Liu; Y Wu

doi:10.1016/j.clon.2024.03.022

Multi-center Dose Prediction Using Attention-aware Deep learning Algorithm Based on Transformers for Cervical Cancer Radiotherapy

Clin Oncol (R Coll Radiol). 2024 Mar 26:S0936-6555(24)00119-5. doi: 10.1016/j.clon.2024.03.022. Online ahead of print.

Authors

Z Wu¹, X Jia², L Lu³, C Xu⁴, Y Pang⁵, S Peng⁵, M Liu⁶, Y Wu⁷

Affiliations

¹ Department of Digital Medicine, School of Biomedical Engineering and Medical Imaging, Army Medical University, Chongqing, PR China; Department of Radiotherapy, Zigong First People's Hospital, Sichuan, PR China; Yu-Yue Pathology Research Center, Jinfeng Laboratory, Chongqing, PR China.
² Department of Radiotherapy, The Ninth People's Hospital Affiliated to Shanghai Jiaotong University School of Medicine, Shanghai, PR China.
³ Department of Radiotherapy, Tongling People's Hospital, Anhui, PR China.
⁴ Department of Radiotherapy, Beijing Luhe Hospital Affiliated to Capital Medical University, Beijing, PR China.
⁵ Department of Radiotherapy, Zigong First People's Hospital, Sichuan, PR China.
⁶ Department of Digital Medicine, School of Biomedical Engineering and Medical Imaging, Army Medical University, Chongqing, PR China. Electronic address: 2249717501@qq.com.
⁷ Department of Digital Medicine, School of Biomedical Engineering and Medical Imaging, Army Medical University, Chongqing, PR China; Yu-Yue Pathology Research Center, Jinfeng Laboratory, Chongqing, PR China. Electronic address: wuy1979@tmmu.edu.cn.

PMID: 38631974
DOI: 10.1016/j.clon.2024.03.022

Abstract

Aims: Accurate dose delivery is crucial for cervical cancer volumetric modulated arc therapy (VMAT). We aimed to develop a robust deep-learning (DL) algorithm for fast and accurate dose prediction of cervical cancer VMAT in multicenter datasets and then explore the feasibility of the DL algorithm to endometrial cancer VMAT with different prescriptions.

Materials and methods: We proposed the AtTranNet algorithm for three-dimensional dose prediction. A total of 367 cervical patients were enrolled in this study. Three hundred twenty-two cervical patients from 3 centers were randomly divided into 70%, 10%, and 20% as training, validation, and testing sets, respectively. Forty-five cervical patients from another center were selected for external testing. Moreover, 70 patients of endometrial cancer with different prescriptions were further selected to test the model. Prediction precision was evaluated by dosimetric difference, dose map, and dose-volume histogram metrics.

Results: The prediction results were all clinically acceptable. The mean absolute error within the body in internal testing was 0.66 ± 0.63%. The maximum |δD| for planning target volume was observed in D98, which is 1.24 ± 2.73 Gy. The maximum |δD| for organs at risk was observed in Dmean of bladder, which is 4.79 ± 3.14 Gy. The maximum |δV| were observed in V40 of pelvic bones, which is 4.77 ± 4.48%.

Conclusion: AtTranNet showed the feasibility and reasonable accuracy in the dose prediction for cervical cancer in multiple centers. The model can also be generalized for endometrial cancer with different prescriptions without any transfer learning.

Keywords: Cervical cancer; deep learning; dose prediction; multi-center; volumetric modulated arc therapy.