Kalman filter in quality assurance in radiotherapy: A practical application for daily dose quality control

Abstract

This study introduces a Kalman filter (KF)-based approach to enhance the daily dose quality control of radiotherapy equipment. The radiation production system is modeled as a dynamic system governed by state equations. The KF is applied to 30 months of daily dose quality control (DDQC) data from Varian® Halcyon systems delivering 6 MV flattening filter-free beams. Input measurements for the KF derive from quality control data collected with the Sun Nuclear® DailyQA 3 detector. Monitor units, rather than time, serve as the independent variable, with two iteration frequencies evaluated. The evolution model includes terms for monitor chamber aging and sensitivity corrections based on atmospheric pressure, with a second model further accounting for room temperature.

The KF extracts additional insights from the quality control measurements. Outliers are detected using a two-standard-deviation window, and drift prediction enables proactive scheduling of dose recalibrations. A significant correlation is observed between KF outputs and machine interventions, such as maintenance, recalibration, and component replacement.

Further refinements in the evolution model and the inclusion of additional input measurements could improve precision. The systematic collection and automated analysis of machine event logs could also enhance early issue detection and provide a more robust framework for decision-making. The lightweight and computationally efficient nature of KF models, combined with their scalability, suggests they could become a valuable tool for establishing a proactive, data-driven paradigm in radiotherapy quality assurance.