Share Email Print

Proceedings Paper

A first step toward uncovering the truth about weight tuning in deformable image registration
Author(s): Kleopatra Pirpinia; Peter A. N. Bosman; Jan-Jakob Sonke; Marcel van Herk; Tanja Alderliesten
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Deformable image registration is currently predominantly solved by optimizing a weighted linear combination of objectives. Successfully tuning the weights associated with these objectives is not trivial, leading to trial-and-error approaches. Such an approach assumes an intuitive interplay between weights, optimization objectives, and target registration errors. However, it is not known whether this always holds for existing registration methods. To investigate the interplay between weights, optimization objectives, and registration errors, we employ multi-objective optimization. Here, objectives of interest are optimized simultaneously, causing a set of multiple optimal solutions to exist, called the optimal Pareto front. Our medical application is in breast cancer and includes the challenging prone-supine registration problem. In total, we studied the interplay in three different ways. First, we ran many random linear combinations of objectives using the well-known registration software elastix. Second, since the optimization algorithms used in registration are typically of a local-search nature, final solutions may not always form a Pareto front. We therefore employed a multi-objective evolutionary algorithm that finds weights that correspond to registration outcomes that do form a Pareto front. Third, we examined how the interplay differs if a true multi-objective (i.e., weight-free) image registration method is used. Results indicate that a trial-and-error weight-adaptation approach can be successful for the easy prone to prone breast image registration case, due to the absence of many local optima. With increasing problem difficulty the use of more advanced approaches can be of value in finding and selecting the optimal registration outcomes.

Paper Details

Date Published: 21 March 2016
PDF: 9 pages
Proc. SPIE 9784, Medical Imaging 2016: Image Processing, 978445 (21 March 2016); doi: 10.1117/12.2216370
Show Author Affiliations
Kleopatra Pirpinia, The Netherlands Cancer Institute (Netherlands)
Peter A. N. Bosman, Ctr. voor Wiskunde en Informatica (Netherlands)
Jan-Jakob Sonke, The Netherlands Cancer Institute (Netherlands)
Marcel van Herk, The Univ. of Manchester (United Kingdom)
Academisch Medisch Centrum (Netherlands)
Tanja Alderliesten, Academisch Medisch Centrum (Netherlands)

Published in SPIE Proceedings Vol. 9784:
Medical Imaging 2016: Image Processing
Martin A. Styner; Elsa D. Angelini, Editor(s)

© SPIE. Terms of Use
Back to Top