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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Purpose: To use and test a labelling algorithm that operates ontwo-dimensional (2D) reformations, rather than three-dimensional (3D) data tolocate and identify vertebrae.  Methods: We improved the Btrfly Net (described by Sekuboyina et al) thatworks on sagittal and coronal maximum intensity projections (MIP) and augmentedit with two additional components: spine-localization and adversarial apriori-learning. Furthermore, we explored two variants of adversarial trainingschemes that incorporated the anatomical a priori knowledge into the BtrflyNet. We investigated the superiority of the proposed approach for labellingvertebrae on three datasets: a public benchmarking dataset of 302 CT scans andtwo in-house datasets with a total of 238 CT scans. We employed Wilcoxonsigned-rank test to compute the statistical significance of the improvement inperformance observed due to various architectural components in our approach.  Results: On the public dataset, our approach using the describedBtrfly(pe-eb) network performed on par with current state-of-the-art methodsachieving a statistically significant (p < .001) vertebrae identification rateof 88.5+/-0.2 % and localization distances of less than 7-mm. On the in-housedatasets that had a higher inter-scan data variability, we obtained anidentification rate of 85.1+/-1.2%.  Conclusion: An identification performance comparable to existing 3Dapproaches was achieved when labelling vertebrae on 2D MIPs. The performancewas further improved using the proposed adversarial training regime thateffectively enforced local spine a priori knowledge during training. Lastly,spine-localization increased the generalizability of our approach byhomogenizing the content in the MIPs.

Labelling Vertebrae with 2D Reformations of Multidetector CT Images: An Adversarial Approach for Incorporating Prior Knowledge of Spine Anatomy