Learning to Avoid Poor Images: Towards Task-aware C-arm Cone-beam CT Trajectories

TL;DR

This paper proposes a task-aware, patient-specific approach to optimize C-arm CBCT trajectories by autonomously adjusting out-of-plane angulation using deep learning, reducing metal artifacts and improving image quality during surgery.

Contribution

It introduces an autonomous method to adapt CBCT trajectories in real-time, minimizing poor images caused by artifacts, which is a novel step towards task-aware intra-operative imaging.

Findings

Reduced metal artifacts in synthetic and real data

Demonstrated effectiveness of scene-specific trajectory adjustments

First step towards task-aware CBCT protocols

Abstract

Metal artifacts in computed tomography (CT) arise from a mismatch between physics of image formation and idealized assumptions during tomographic reconstruction. These artifacts are particularly strong around metal implants, inhibiting widespread adoption of 3D cone-beam CT (CBCT) despite clear opportunity for intra-operative verification of implant positioning, e.g. in spinal fusion surgery. On synthetic and real data, we demonstrate that much of the artifact can be avoided by acquiring better data for reconstruction in a task-aware and patient-specific manner, and describe the first step towards the envisioned task-aware CBCT protocol. The traditional short-scan CBCT trajectory is planar, with little room for scene-specific adjustment. We extend this trajectory by autonomously adjusting out-of-plane angulation. This enables C-arm source trajectories that are scene-specific in that they avoid acquiring "poor images", characterized by beam hardening, photon starvation, and noise. The recommendation of ideal out-of-plane angulation is performed on-the-fly using a deep convolutional neural network that regresses a detectability-rank derived from imaging physics.