We evaluate the integration of 3D preoperative computed tomography angiography of the coronary arteries with intraoperative 2D X-ray angiographies by a recently proposed novel registration-by-regression method. The method relates image features of 2D projection images to the transformation parameters of the 3D image. We compared different sets of features and studied the influence of preprocessing the training set. For the registration evaluation, a gold standard was developed from eight X-ray angiography sequences from six different patients. The alignment quality was measured using the 3D mean target registration error (mTRE). The registration-by-regression method achieved moderate accuracy (median mTRE of 15 mm) on real images. It does therefore not provide yet a complete solution to the 3D–2D registration problem but it could be used as an initialisation method to eliminate the need for manual initialisation.

Additional Metadata
Keywords 3D/2D image registration, coronary arteries, image guided interventions, neural networks, regression
Persistent URL dx.doi.org/10.1080/21681163.2015.1054520, hdl.handle.net/1765/98847
Journal Computer Methods in Biomechanics and Biomedical Engineering: Imaging and Visualization
Note No subscription'no full text available yet
Gouveia, A.R, Metz, C.T, Freire, R, Almeida, P. (Pedro), & Klein, S. (2017). Registration-by-regression of coronary CTA and X-ray angiography. Computer Methods in Biomechanics and Biomedical Engineering: Imaging and Visualization, 5(3), 208–220. doi:10.1080/21681163.2015.1054520