Decoupling Respiratory and Angular Variation in Rotational X-ray Scans Using a Prior Bilinear Model

TL;DR

This paper introduces a bilinear model leveraging prior 4D scans to effectively separate respiratory and angular variations in rotational X-ray scans, simplifying respiratory feature extraction for radiation therapy.

Contribution

It proposes a novel bilinear modeling approach based on the linearity of the X-ray transform and prior knowledge, enabling separation of respiratory and angular effects in rotational scans.

Findings

Achieved a mean estimation error of 3.01% in gray values for unseen angles.

Demonstrated the model's effectiveness on 5 patient 4D CTs.

Validated the approach for driving respiratory motion models in radiation therapy.

Abstract

Data-driven respiratory signal extraction from rotational X-ray scans is a challenge as angular effects overlap with respiration-induced change in the scene. In this paper, we use the linearity of the X-ray transform to propose a bilinear model based on a prior 4D scan to separate angular and respiratory variation. The bilinear estimation process is supported by a B-spline interpolation using prior knowledge about the trajectory angle. Consequently, extraction of respiratory features simplifies to a linear problem. Though the need for a prior 4D CT seems steep, our proposed use-case of driving a respiratory motion model in radiation therapy usually meets this requirement. We evaluate on DRRs of 5 patient 4D CTs in a leave-one-phase-out manner and achieve a mean estimation error of 3.01 % in the gray values for unseen viewing angles. We further demonstrate suitability of the extracted weights to drive a motion model for treatments with a continuously rotating gantry.