Validation of a deep learning-based material estimation model for Monte Carlo dose calculation in proton therapy

Abstract

Objective: Computed tomography (CT) to material property conversion dominates proton range uncertainty, impacting the quality of proton treatment planning. Physics-based and machine learning-based methods have been investigated to leverage dual-energy CT (DECT) to predict proton ranges. Recent development includes physics-informed deep learning (DL) for material property inference. This paper aims to develop a framework to validate Monte Carlo dose calculation (MCDC) using CT-based material characterization models. Approach: The proposed framework includes two experiments to validate in vivo dose and water equivalent thickness (WET) distributions using anthropomorphic and porcine phantoms. Phantoms were irradiated using anteroposterior proton beams, and the exit doses and residual ranges were measured by MatriXX PT and multi-layer strip ionization chamber. Two pre-trained conventional and physics-informed residual networks (RN/PRN) were used for mass density inference from DECT. Additional two heuristic material conversion models using single-energy CT (SECT) and DECT were implemented for comparisons. The gamma index was used for dose comparisons with criteria of 3%/3mm (10% dose threshold). Main results: The phantom study showed that MCDC with PRN achieved mean gamma passing rates of 95.9% and 97.8% for the anthropomorphic and porcine phantoms. The rates were 86.0% and 79.7% for MCDC with the empirical DECT model. WET analyses indicated that the mean WET variations between measurement and simulation were -1.66 mm, -2.48 mm, and -0.06 mm for MCDC using a Hounsfield look-up table with SECT and empirical and PRN models with DECT. Validation experiments indicated that MCDC with PRN achieved consistent dose and WET distributions with measurement. Significance: The proposed framework can be used to identify the optimal CT-based material characterization model for MCDC to improve proton range uncertainty. The framework can systematically verify the accuracy of proton treatment planning, and it can potentially be implemented in the treatment room to be instrumental in online adaptive treatment planning.

Characterization of 250 MeV Protons from the Varian ProBeam PBS System for FLASH Radiation Therapy

“…The IDD measurement includes the range uncertainty of ± 1 mm. Because the R80 value minimizes the dependency on initial energy spread [ 30 ], the measured R80 is compared with the continuous slowing down approximation range from the National Institute of Standards and Technology. The R80 differences are within 1 and 3 mm when compared with National Institute of Standards and Technology data for 249- and 250-MeV proton ranges, respectively.…”

A vision-GNN framework for retinopathy classification using optical coherence tomography

“…Rapid improvements in artificial intelligence (AI) have enabled broad application of AI-assisted medical image analysis (classification, segmentation, registration, synthesis) pipelines [4][5][6][7][8][9][10][11][12][13], including semi-automated retinopathy detection systems using machine learning (ML) classifiers [14] based on human-designed features as well as fully-automated deep learning (DL) systems [15,16]. Currently, mainstream DL frameworks include Multilayer Perceptrons (MLP), Transformers [17], and Convolutional Neural Networks (CNN) [18], which can only take in grid or sequence data.…”

Ultrasound breast tumor detection based on vision graph neural network

“…They can automatically extract the image features for precise predictions in various computer vision (CV) tasks [7]. In medical imaging, DL-powered systems have significantly changed the landscape with unprecedented processing speed and accuracy [8][9][10][11][12][13][14]. Currently, convolutional neural networks (CNNs) [15] and Vision Transformers [16] are the most widely used backbone for these frameworks.…”