Image Quality Assessment for Rigid Motion Compensation

TL;DR

This paper presents a neural network-guided autofocus method for estimating rigid patient motion in CBCT scans, improving image quality by reducing motion artifacts during stroke imaging.

Contribution

The novel approach uses a neural network trained to regress reprojection error for accurate motion estimation, outperforming traditional entropy-based methods.

Findings

Neural network method achieves superior motion estimation accuracy.

Method adapts well to unseen motion amplitudes.

Improves image quality by reducing artifacts in CBCT scans.

Abstract

Diagnostic stroke imaging with C-arm cone-beam computed tomography (CBCT) enables reduction of time-to-therapy for endovascular procedures. However, the prolonged acquisition time compared to helical CT increases the likelihood of rigid patient motion. Rigid motion corrupts the geometry alignment assumed during reconstruction, resulting in image blurring or streaking artifacts. To reestablish the geometry, we estimate the motion trajectory by an autofocus method guided by a neural network, which was trained to regress the reprojection error, based on the image information of a reconstructed slice. The network was trained with CBCT scans from 19 patients and evaluated using an additional test patient. It adapts well to unseen motion amplitudes and achieves superior results in a motion estimation benchmark compared to the commonly used entropy-based method.