Machine-learning-based integration of temporal and spectral prompt gamma-ray information for proton range verification

TL;DR

This study shows that using only the timing of gamma rays, not their energy, is enough for accurate proton therapy monitoring.

Contribution

The study is the first to evaluate the integration of temporal and spectral prompt gamma-ray data for proton range verification using machine learning.

Findings

Temporal-only features achieved RMSE of 3-4 mm, matching previous models.

Spectral-only and image features resulted in RMSE over 5 mm, showing worse performance.

Combining time and energy data did not improve accuracy over time-only data.

Abstract

Prompt gamma-ray timing (PGT) and prompt gamma-ray spectroscopy (PGS) are non-invasive techniques for dose delivery monitoring in proton radiotherapy. Integrating PGT and PGS into a unified data analysis framework may improve proton range verification by incorporating both temporal and spectral information from prompt gamma-ray events. This study evaluates the effectiveness of this integration for enhancing the accuracy of proton range verification using machine-learning.

A homogeneous phantom was irradiated with 162 and 225 MeV static and scanned proton beams. Air cavities of 5, 10 and 20 mm were introduced to simulate anatomical variations. The energy and time of arrival of prompt gamma rays were measured using a PGT detector. 2-dimensional time-energy spectra were extracted for 1,440 proton spots. Different feature sets (energy-only, time-only, energy-restricted time, image) were computed. These feature sets were used by four different machine-learning models to predict range shifts. Model performance was assessed using the root mean square error (RMSE).

Time-only and combined time-energy feature sets exhibited good performance with RMSE values of 3 to 4 mm, consistent with previously developed models. Energy-only and image features led to poorer performance with RMSE values exceeding 5 mm. The integration of energy-only features did not improve prediction accuracy compared to exclusively using time-only features.

While spectral information did not contribute additional value for determining proton beam range shifts in the investigated setup, the findings show that temporal information alone is sufficient to perform accurate proton range verification.

•Spectral data from uncollimated prompt gammas for proton range is not yet explored.•A homogeneous PMMA phantom with air cavities of different thicknesses was irradiated.•Machine-learning models using temporal and spectral data were developed and compared.•No added value for proton range shift prediction using spectral data was observed.•Temporal data was sufficient for accurate proton range verification.

Spectral data from uncollimated prompt gammas for proton range is not yet explored.

A homogeneous PMMA phantom with air cavities of different thicknesses was irradiated.

Machine-learning models using temporal and spectral data were developed and compared.

No added value for proton range shift prediction using spectral data was observed.

Temporal data was sufficient for accurate proton range verification.

Figures