Direct optimization of the probability of lesion origin in proton treatment planning for low-grade glioma patients

TL;DR

This paper introduces an automated treatment planning method for low-grade glioma patients that directly incorporates a predictive model for lesion origin into the optimization process, improving plan quality.

Contribution

It extends the POLO model with a volumetric correction and integrates it into an open-source planning toolkit for automated, outcome-driven proton therapy planning.

Findings

Clinically acceptable plans can be generated with minimized POLO predictions.

The framework maintains target coverage despite shifts in dose and LET$_{ ext{d}}$ distributions.

Outcome predictions remain robust under various optimization scenarios.

Abstract

In proton therapy of low-grade glioma (LGG) patients, contrast-enhancing brain lesions (CEBLs) on magnetic resonance imaging are considered predictive of late radiation-induced lesions. From the observation that CEBLs tend to concentrate in regions of increased dose-averaged linear energy transfer (LET$_{\text{d}}$) and proximal to the ventricular system, the probability of lesion origin (POLO) model has been established as a multivariate logistic regression model for the voxel-wise probability prediction of the CEBL origin. To date, leveraging the predictive power of the POLO model for treatment planning relies on hand tuning the dose and LET$_{\text{d}}$ distribution to minimize the resulting probability predictions. In this paper, we therefore propose automated POLO model-based treatment planning by directly integrating POLO calculation and optimization into plan optimization for LGG patients. We introduce an extension of the original POLO model including a volumetric correction factor, and a model-based optimization scheme featuring a linear reformulation of the model together with feasible optimization functions based on the predicted POLO values. The developed framework is implemented in the open-source treatment planning toolkit matRad. Our framework can generate clinically acceptable treatment plans while automatically taking into account outcome predictions from the POLO model. It also supports the definition of customized POLO model-based objective and constraint functions. Optimization results from a sample LGG patient show that the POLO model-based outcome predictions can be minimized under expectable shifts in dose, LET$_{\text{d}}$, and POLO distributions, while sustaining target coverage ($\Delta_{\text{PTV}} \text{D95}_{RBE,fx}\approx{0.00}$, $\Delta_{\text{GTV}} \text{D95}_{RBE,fx}\approx{0.03}$), even when NTCP is strongly down-regulated.