# Measurement-guided therapeutic-dose prediction using multi-level gated modality-fusion model for volumetric-modulated arc radiotherapy

## TL;DR

This paper introduces a new AI model to predict radiation doses in cancer radiotherapy, improving accuracy and efficiency for patient safety.

## Contribution

A novel deep learning model is proposed that fuses multi-level features from different modalities to enhance therapeutic-dose prediction accuracy.

## Key findings

- The model achieved the lowest mean absolute and root mean square errors in dose prediction.
- It outperformed existing models in dosimetric congruence metrics like DVHs and GPR.
- Predicted dose differences were mostly within 6 Gy, except near skin or mask boundaries.

## Abstract

Radiotherapy is a fundamental cancer treatment method, and pre-treatment patient-specific quality assurance (prePSQA) plays a crucial role in ensuring dose accuracy and patient safety. Artificial intelligence model for measurement-free prePSQA have been investigated over the last few years. While these models stack successive pooling layers to carry out sequential learning, directly splice together different modalities along channel dimensions and feed them into shared encoder-decoder network, which greatly reduces the anatomical features specific to different modalities. Furthermore, the existing models simply take advantage of low-dimensional dosimetry information, meaning that the spatial features about the complex dose distribution may be lost and limiting the predictive power of the models. The purpose of this study is to develop a novel deep learning model for measurement-guided therapeutic-dose (MDose) prediction from head and neck cancer radiotherapy data.

The enrolled 310 patients underwent volumetric-modulated arc radiotherapy (VMAT) were randomly divided into the training set (186 cases, 60%), validation set (62 cases, 20%), and test set (62 cases, 20%). The effective prediction model explicitly integrates the multi-scale features that are specific to CT and dose images, takes into account the useful spatial dose information and fully exploits the mutual promotion within the different modalities. It enables medical physicists to analyze the detailed locations of spatial dose differences and to simultaneously generate clinically applicable dose-volume histograms (DVHs) metrics and gamma passing rate (GPR) outcomes.

The proposed model achieved better performance of MDose prediction, and dosimetric congruence of DVHs, GPR with the ground truth compared with several state-of-the-art models. Quantitative experimental predictions show that the proposed model achieved the lowest values for the mean absolute error (37.99) and root mean square error (4.916), and the highest values for the peak signal-to-noise ratio (52.622), structural similarity (0.986) and universal quality index (0.932). The predicted dose values of all voxels were within 6 Gy in the dose difference maps, except for the areas near the skin or thermoplastic mask indentation boundaries.

We have developed a feasible MDose prediction model that could potentially improve the efficiency and accuracy of prePSQA for head and neck cancer radiotherapy, providing a boost for clinical adaptive radiotherapy.