Eldad Haber1, Jan Modersitzki. 1. Department of Mathematics and Computer Science, Emory University, Atlanta, GA 30233, USA. haber@mathcs.emory.edu
Abstract
OBJECTIVES: A particular problem in image registration arises for multi-modal images taken from different imaging devices and/or modalities. Starting in 1995, mutual information has shown to be a very successful distance measure for multi-modal image registration. Therefore, mutual information is considered to be the state-of-the-art approach to multi-modal image registration. However, mutual information has also a number of well-known drawbacks. Its main disadvantage is that it is known to be highly non-convex and has typically many local maxima. METHODS: This observation motivates us to seek a different image similarity measure which is better suited for optimization but as well capable to handle multi-modal images. RESULTS: In this work, we investigate an alternative distance measure which is based on normalized gradients. CONCLUSIONS: As we show, the alternative approach is deterministic, much simpler, easier to interpret, fast and straightforward to implement, faster to compute, and also much more suitable to numerical optimization.
OBJECTIVES: A particular problem in image registration arises for multi-modal images taken from different imaging devices and/or modalities. Starting in 1995, mutual information has shown to be a very successful distance measure for multi-modal image registration. Therefore, mutual information is considered to be the state-of-the-art approach to multi-modal image registration. However, mutual information has also a number of well-known drawbacks. Its main disadvantage is that it is known to be highly non-convex and has typically many local maxima. METHODS: This observation motivates us to seek a different image similarity measure which is better suited for optimization but as well capable to handle multi-modal images. RESULTS: In this work, we investigate an alternative distance measure which is based on normalized gradients. CONCLUSIONS: As we show, the alternative approach is deterministic, much simpler, easier to interpret, fast and straightforward to implement, faster to compute, and also much more suitable to numerical optimization.
Authors: Peter Kohlmann; Jan Strehlow; Betram Jobst; Stefan Krass; Jan-Martin Kuhnigk; Angela Anjorin; Oliver Sedlaczek; Sebastian Ley; Hans-Ulrich Kauczor; Mark Oliver Wielpütz Journal: Int J Comput Assist Radiol Surg Date: 2014-07-03 Impact factor: 2.924
Authors: Thomas Lange; Nils Papenberg; Stefan Heldmann; Jan Modersitzki; Bernd Fischer; Hans Lamecker; Peter M Schlag Journal: Int J Comput Assist Radiol Surg Date: 2008-10-19 Impact factor: 2.924
Authors: Benjamin C Lee; Jonathan B Moody; Alexis Poitrasson-Rivière; Amanda C Melvin; Richard L Weinberg; James R Corbett; Venkatesh L Murthy; Edward P Ficaro Journal: J Nucl Cardiol Date: 2018-11-07 Impact factor: 5.952
Authors: Benjamin Irving; James M Franklin; Bartłomiej W Papież; Ewan M Anderson; Ricky A Sharma; Fergus V Gleeson; Sir Michael Brady; Julia A Schnabel Journal: Med Image Anal Date: 2016-03-21 Impact factor: 8.545