Labeling Vertebrae with Two-dimensional Reformations of Multidetector CT Images: An Adversarial Approach for Incorporating Prior Knowledge of Spine Anatomy.

To use and test a labeling algorithm that operates on two-dimensional reformations, rather than three-dimensional data to locate and identify vertebrae. The authors improved the Btrfly Net, a fully convolutional network architecture described by Sekuboyina et al, which works on sagittal and coronal maximum intensity projections (MIPs) and augmented it with two additional components: spine localization and adversarial a priori learning. Furthermore, two variants of adversarial training schemes that incorporated the anatomic a priori knowledge into the Btrfly Net were explored. The superiority of the proposed approach for labeling vertebrae on three datasets was investigated: a public benchmarking dataset of 302 CT scans and two in-house datasets with a total of 238 CT scans. The Wilcoxon signed rank test was employed to compute the statistical significance of the improvement in performance observed with various architectural components in the authors' approach. On the public dataset, the authors' approach using the described Btrfly Net with energy-based prior encoding (Btrfly An identification performance comparable to existing three-dimensional approaches was achieved when labeling vertebrae on two-dimensional MIPs. The performance was further improved using the proposed adversarial training regimen that effectively enforced local spine a priori knowledge during training. Spine localization increased the generalizability of our approach by homogenizing the content in the MIPs.

Informations de copyright

2020 by the Radiological Society of North America, Inc.

Déclaration de conflit d'intérêts

Disclosures of Conflicts of Interest: A.S. Activities related to the present article: grant/grants pending and travel support from the European Research Council relationships. Activities not related to the present article: disclosed no relevant relationships. Other relationships: disclosed no relevant relationships. M.R. Activities related to the present article: German Excellence Initiative (and the European Union Seventh Framework Program under grant agreement n291763. Activities not related to the present article: currently employed by the Friedrich Miescher Institute for Biomedical Research. Other relationships: disclosed no relevant relationships. A.V. disclosed no relevant relationships. B.H.M. disclosed no relevant relationships. J.S.K. Activities related to the present article: grant from European Research Council StG iback and Nvidia. Activities not related to the present article: payment for lectures from Philips Healthcare. Other relationships: disclosed no relevant relationships.