3D transformer-based dose prediction in HDR brachytherapy for cervical cancer

Abstract

Background: The clinical process of high-dose-rate brachytherapy (HDRBT) is time-consuming and relies on user expertise and preference. Deep learning-based dose prediction can act as a quality assurance (QA) tool to identify suboptimal needle placement and enhance treatment planning efficiency in HDR interstitial brachytherapy. This study aims to introduce a 3D transformer-based deep learning method to automatically predict the dose distribution in HDR brachytherapy for cervical cancer. Methods: We retrospectively analyzed 96 CT-based treatment plans from 24 patients with cervical cancer who underwent interstitial HDRBT with needle insertion. The transformer mechanism was integrated into a convolutional neural network (CNN) to capture long-distance characteristics and global information. The prediction performance was evaluated by the mean error of dose‒volume histogram metrics between clinical and predicted dose maps, gamma analysis, and the Dice similarity coefficient (DSC) of the 1–30 Gy isodose volumes. Results: The mean D90 and D95 errors for HRCTV were less than 0.1 Gy, and the mean D2cc for organs at risk (bladder, rectum, and bowel) was less than 0.6 Gy. The mean DSC of the 1–30 Gy isodose volume was 0.87. The 3D transformer-based CNN model can predict dose maps that are highly consistent with the clinical treatment plans. Conclusions: A novel 3D transformer-based deep learning model was successfully developed for dose prediction in HDR interstitial brachytherapy. This method can automatically generate accurate 3D dose distributions, exhibiting great clinical potential for improving treatment efficiency and standardizing brachytherapy treatment planning. Trial registration: No. ZF2020-084.2; Oct 16, 2020.