Learning Deep Similarity Metric for 3D MR-TRUS Registration

Purpose The fusion of transrectal ultrasound (TRUS) and magnetic resonance (MR) images for guiding targeted prostate biopsy has significantly improved the biopsy yield of aggressive cancers. A key component of MRTRUS fusion is image registration. However, it is very challenging to obtain a robust automatic MR-TRUS registration due to the large appearance difference between the two imaging modalities. The work presented in this paper aims to tackle this problem by addressing two challenges: (i) the definition of a suitable similarity metric and (ii) the determination of a suitable optimization strategy. Methods This work proposes the use of a deep convolutional neural network to learn a similarity metric for MR-TRUS registration. We also use a composite optimization strategy that explores the solution space in order to search for a suitable initialization for the second-order optimization of the learned This work was supported by the Intramural Research Program of the National Institutes of Health, the National Institutes of Health Center for Interventional Oncology, and NIH grants 1ZIDBC011242 and 1ZIDCL040015. G. Haskins, U. Kruger, P. Yan* Department of Biomedical Engineering, Rensselaer Polytechnic Institute, Troy, NY 12180, USA Asterisk indicates corresponding author Tel.: +1-518-276-4476 E-mail: yanp2@rpi.edu J. Kruecker Philips Research North America, Cambridge, MA 02141, USA S. Xu, P.A. Pinto, B.J. Wood National Institutes of Health, Center for Interventional Oncology, Radiology & Imaging Sciences, Bethesda, MD 20892, USA ar X iv :1 80 6. 04 54 8v 2 [ cs .C V ] 1 5 O ct 2 01 8