Learning Non-rigid Deformations for Robust, Constrained Point-based Registration in Image-Guided MR-TRUS Prostate Intervention

Accurate and robust non-rigid image registration is critical for image-guided interventions. Non-rigid registration is a challenging task that is further complicated if the fusion involves images of different modalities. Intensity-based registration algorithms must deal with complex intensity relationships, which makes finding the optimal solution difficult. As an alternative to maximizing an intensity-based similarity metric, such as mutual information, anatomical structures of interest may first be segmented from the images, and then be registered to each other to perform the image fusion.

Source: Medical Image Analysis - April 13, 2017 Category: Radiology Authors: John A. Onofrey, Lawrence H. Staib, Saradwata Sarkar, Rajesh Venkataraman, Cayce B. Nawaf, Preston C. Sprenkle, Xenophon Papademetris Source Type: research