Sensitivity analysis of biological washout and depth selection for a machine learning based dose verification framework in proton therapy

TL;DR

This study evaluates how biological washout and depth selection affect a machine learning-based dose verification method in proton therapy, demonstrating robustness and potential for clinical application.

Contribution

It introduces a sensitivity analysis framework for key factors impacting AI-based dose verification in proton therapy, using a bi-directional RNN model with simulated data.

Findings

AI framework shows robustness to biological washout and depth selection variations

Good accuracy in range uncertainty, MAE, and MRE metrics

Potential for online patient-specific verification in clinical settings

Abstract

Dose verification based on proton-induced positron emitters is a promising quality assurance tool and may leverage the strength of artificial intelligence. To move a step closer towards practical application, the sensitivity analysis of two factors needs to be performed: biological washout and depth selection. selection. A bi-directional recurrent neural network (RNN) model was developed. The training dataset was generated based upon a CT image-based phantom (abdomen region) and multiple beam energies/pathways, using Monte-Carlo simulation (1 mm spatial resolution, no biological washout). For the modeling of biological washout, a simplified analytical model was applied to change raw activity profiles over a period of 5 minutes, incorporating both physical decay and biological washout. For the study of depth selection (a challenge linked to multi field/angle irradiation), truncations were applied at different window lengths (100, 125, 150 mm) to raw activity profiles. Finally, the performance of a worst-case scenario was examined by combining both factors (depth selection: 125 mm, biological washout: 5 mins). The accuracy was quantitatively evaluated in terms of range uncertainty, mean absolute error (MAE) and mean relative errors (MRE). Our proposed AI framework shows good immunity to the perturbation associated with two factors. The detection of proton-induced positron emitters, combined with machine learning, has great potential to implement online patient-specific verification in proton therapy.