Early prediction of proton therapy dose distributions and DVHs for hepatocellular carcinoma using contour-based CNN models from diagnostic CT and MRI

Abstract

Background: Proton therapy is commonly used for treating hepatocellular carcinoma (HCC); however, its feasibility can be challenging to assess in large tumors or those adjacent to critical organs at risk (OARs), which are typically assessed only after planning computed tomography (CT) acquisition. This study aimed to predict proton dose distributions using diagnostic CT (dCT) and diagnostic MRI (dMRI) with a convolutional neural network (CNN), enabling early treatment feasibility assessments.

Methods: Dose distributions and dose-volume histograms (DVHs) were calculated for 118 patients with HCC using intensity-modulated proton therapy (IMPT) and passive proton therapy. A CPU-based CNN model was used to predict DVHs and 3D dose distributions from diagnostic images. Prediction accuracy was evaluated using mean absolute error (MAE), mean squared error (MSE), peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and gamma passing rate with a 3 mm/3% criterion.

Results: The predicted DVHs and dose distributions showed high agreement with actual values. MAE remained below 3.0%, with passive techniques achieving 1.2-1.8%. MSE was below 0.004 in all cases. PSNR ranged from 24 to 28 dB, and SSIM exceeded 0.94 in most conditions. Gamma passing rates averaged 82-83% for IMPT and 92-93% for passive techniques. The model achieved comparable accuracy when using dMRI and dCT.

Conclusions: This study demonstrates that early dose distribution prediction from diagnostic imaging is feasible and accurate using a lightweight CNN model. Despite anatomical variability between diagnostic and planning images, this approach provides timely insights into treatment feasibility, potentially supporting insurance pre-authorization, reducing unnecessary imaging, and optimizing clinical workflows for HCC proton therapy.

Keywords: Convolutional neural network; Diagnostic imaging; Dose distribution; Dose volume histogram; Hepatocellular carcinoma; Intensity-modulated proton therapy; Passive methods; Proton therapy.

Fig. 1

A Workflow of CNN1 Models for Predicting DVH (Inference Phase) The model predicts DVHs from geometric parameters derived from diagnostic images during the inference phase. B Workflow of CNN2 for 3D Dose Distribution Prediction (Inference Phase). CNN2 predicts 3D dose distributions from geometric and predicted DVH data during the inference phase

Fig. 2

Average DVHs for the normal liver, duodenum, and bile duct across all test patients, predicted from both dCT and dMRI using IMPT and passive proton techniques. The solid lines represent the actual DVHs, and the dashed lines represent the predicted DVHs. The DVHs show good agreement, confirming that the predicted values visually match the true values closely

Fig. 3

Predicted dose distribution maps for two test patients. These three-dimensional dose distributions were predicted using IMPT and passive irradiation techniques on dCT and dMRI. The CDPs were calculated by integrating dose distributions across the axial, sagittal, and coronal planes. The true and predicted values are compared on the X and Y axes at the marked lines in the images

Fig. 4

Gamma passing rates (3 mm/3%) for predicted dose distributions across all test patients. The mean ± standard deviation were 82.39 ± 5.63% for IMPT_dCT, 83.04 ± 5.92% for IMPT_dMRI, 92.96 ± 3.10% for Passive_dCT, and 92.02 ± 3.60% for Passive_dMRI