English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

During spinal fusion surgery, screws are placed close to critical nervessuggesting the need for highly accurate screw placement. Verifying screwplacement on high-quality tomographic imaging is essential. C-arm Cone-beam CT(CBCT) provides intraoperative 3D tomographic imaging which would allow forimmediate verification and, if needed, revision. However, the reconstructionquality attainable with commercial CBCT devices is insufficient, predominantlydue to severe metal artifacts in the presence of pedicle screws. Theseartifacts arise from a mismatch between the true physics of image formation andan idealized model thereof assumed during reconstruction. Prospectivelyacquiring views onto anatomy that are least affected by this mismatch can,therefore, improve reconstruction quality. We propose to adjust the C-arm CBCTsource trajectory during the scan to optimize reconstruction quality withrespect to a certain task, i.e. verification of screw placement. Adjustmentsare performed on-the-fly using a convolutional neural network that regresses aquality index for possible next views given the current x-ray image. Adjustingthe CBCT trajectory to acquire the recommended views results in non-circularsource orbits that avoid poor images, and thus, data inconsistencies. Wedemonstrate that convolutional neural networks trained on realisticallysimulated data are capable of predicting quality metrics that enablescene-specific adjustments of the CBCT source trajectory. Using bothrealistically simulated data and real CBCT acquisitions of asemi-anthropomorphic phantom, we show that tomographic reconstructions of theresulting scene-specific CBCT acquisitions exhibit improved image qualityparticularly in terms of metal artifacts. Since the optimization objective isimplicitly encoded in a neural network, the proposed approach overcomes theneed for 3D information at run-time.

A Learning-based Method for Online Adjustment of C-arm Cone-Beam CT Source Trajectories for Artifact Avoidance