Application of multiple linear regression for indirect tracking of functional target for respiratory compensation in radiotherapy

Abstract

The main goal of radiotherapy is to eliminate cancerous tumors from the patient body while limiting damage to healthy tissue. Current technologies allow rather precise and effective treatment. However, respiratory motion management still remains a considerable issue. A number of different solutions, such as gating or restricted breathing, can be used for addressing this issue, but the majority of them compensate for respiratory motion only partially, while considerably extending the treatment time. In this paper we investigate multiple linear regression as a tool for predicting the position of the functional target (tumor) from an external marker. This study extends our previous work, where a standard linear regression, and a linear regression with first-order autoregressive errors were analyzed. Our computational analysis suggests that using the proposed approach for prediction of lung tumor motion is expected to improve the precision of radiotherapy. Precise compensation for respiratory motion can be achieved by controlling the position of a couch or a beam to compensate.