Learning to Avoid Poor Images: Towards Task-aware C-arm Cone-beam CT Trajectories
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.
KeywordsRobotic imaging Deep reinforcement learning
We gratefully acknowledge support of the NVIDIA Corporation for donating GPUs, and Gerhard Kleinzig and Sebastian Vogt from SIEMENS for making an ARCADIS Orbic 3D available. JNZ was supported by a DAAD FITweltweit fellowship.
Supplementary material 1 (mp4 7730 KB)
- 7.Milletari, F., Birodkar, V., Sofka, M.: Straight to the point: reinforcement learning for user guidance in ultrasound. arXiv preprint arXiv:1903.00586 (2019)
- 8.Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556 [cs] (2014)
- 9.Stayman, J.W., Siewerdsen, J.H.: Task-based trajectories in iteratively reconstructed interventional cone-beam CT. In: Proceedings 12th International Meeting Fully 3D Image Reconstruction Radiology Nuclear Medcine, pp. 257–260 (2013)Google Scholar
- 11.Unberath, M., et al.: DeepDRR – a catalyst for machine learning in fluoroscopy-guided procedures. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-López, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11073, pp. 98–106. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00937-3_12CrossRefGoogle Scholar
- 12.United States Bone and Joint Initiative: The Burden of Musculoskeletal Diseases in the United States (BMUS). Third Edition edn. (2014)Google Scholar