ARANet: Attention-based Residual Adversarial Network with Deep Supervision for Radiotherapy Dose Prediction of Cervical Cancer
This work addresses the problem of automating radiotherapy dose prediction for cervical cancer patients, which could reduce planning time and variability, though it appears incremental as it builds on existing deep learning approaches.
The paper tackles the time-consuming and experience-dependent manual process of radiotherapy dose planning for cervical cancer by proposing ARANet, an end-to-end network that automatically predicts 3D dose distributions, achieving superior performance compared to state-of-the-art methods on an in-house dataset of 54 patients.
Radiation therapy is the mainstay treatment for cervical cancer, and its ultimate goal is to ensure the planning target volume (PTV) reaches the prescribed dose while reducing dose deposition of organs-at-risk (OARs) as much as possible. To achieve these clinical requirements, the medical physicist needs to manually tweak the radiotherapy plan repeatedly in a trial-anderror manner until finding the optimal one in the clinic. However, such trial-and-error processes are quite time-consuming, and the quality of plans highly depends on the experience of the medical physicist. In this paper, we propose an end-to-end Attentionbased Residual Adversarial Network with deep supervision, namely ARANet, to automatically predict the 3D dose distribution of cervical cancer. Specifically, given the computer tomography (CT) images and their corresponding segmentation masks of PTV and OARs, ARANet employs a prediction network to generate the dose maps. We also utilize a multi-scale residual attention module and deep supervision mechanism to enforce the prediction network to extract more valuable dose features while suppressing irrelevant information. Our proposed method is validated on an in-house dataset including 54 cervical cancer patients, and experimental results have demonstrated its obvious superiority compared to other state-of-the-art methods.