Convolutional Neural Networks for Robust and Real-Time 2-D/3-D Registration
Shun Miao⁎; Jane Z. Wang†; Rui Liao⁎ ⁎Siemens Medical Solutions USA, Inc., Princeton, NJ, United States†University of British Columbia, Vancouver, BC, Canada
Abstract
Existing intensity-based methods formulate 2-D/3-D registration as optimization problems, where the transformation parameters are iteratively optimized over a scalar-valued image similarity measure. This is an ineffective formulation because the information from the images cannot be fully utilized using a scalar-valued representation, and it leads to two major limitations: (i) slow computation, and (ii) small capture range. In this chapter, we present a more effective Convolutional ...
Get Deep Learning for Medical Image Analysis now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
