Table of Contents
Algorithms, Volume 12, Issue 5 (May 2019)
- Issues are regarded as officially published after their release is announced to the table of contents alert mailing list.
- You may sign up for e-mail alerts to receive table of contents of newly released issues.
- PDF is the official format for papers published in both, html and pdf forms. To view the papers in pdf format, click on the "PDF Full-text" link, and use the free Adobe Reader to open them.
Cover Story (view full-size image) Current medical deformable image registration (DIR) methods optimize the weighted sums of key [...] Read more. Current medical deformable image registration (DIR) methods optimize the weighted sums of key objectives of interest (e.g., dissimilarity, deformation magnitude, and guidance error). Having one weight combination that yields high-quality results for any instance of a specific DIR problem (i.e., a class solution) would facilitate the clinical application of DIR. A multi-objective optimization approach for DIR removes the need for manual tuning of the weight combination, providing a set of high-quality trade-off solutions. Here, we employed an evolutionary machine-learning approach to compute a multi-objective class solution for DIR—a set of weight combinations that, when used on any instance of a DIR problem, yields multiple high-quality DIR outcomes. We applied this approach to DIR of breast MRIs. From this set, a preferred DIR outcome can be intuitively selected, potentially facilitating the use of DIR in clinical practice. View this pa