DocumentCode :
1440691
Title :
Automatic Parameter Selection for Multimodal Image Registration
Author :
Hahn, Dieter A. ; Daum, Volker ; Hornegger, Joachim
Author_Institution :
Dept. of Comput. Sci., Friedrich-Alexander-Univ. of Erlangen-Nuremberg (FAU), Erlangen, Germany
Volume :
29
Issue :
5
fYear :
2010
fDate :
5/1/2010 12:00:00 AM
Firstpage :
1140
Lastpage :
1155
Abstract :
Over the past ten years similarity measures based on intensity distributions have become state-of-the-art in automatic multimodal image registration. An implementation for clinical usage has to support a plurality of images. However, a generally applicable parameter configuration for the number and sizes of histogram bins, optimal Parzen-window kernel widths or background thresholds cannot be found. This explains why various research groups present partly contradictory empirical proposals for these parameters. This paper proposes a set of data-driven estimation schemes for a parameter-free implementation that eliminates major caveats of heuristic trial and error. We present the following novel approaches: a new coincidence weighting scheme to reduce the influence of background noise on the similarity measure in combination with Max-Lloyd requantization, and a tradeoff for the automatic estimation of the number of histogram bins. These methods have been integrated into a state-of-the-art rigid registration that is based on normalized mutual information and applied to CT-MR, PET-MR, and MR-MR image pairs of the RIRE 2.0 database. We compare combinations of the proposed techniques to a standard implementation using default parameters, which can be found in the literature, and to a manual registration by a medical expert. Additionally, we analyze the effects of various histogram sizes, sampling rates, and error thresholds for the number of histogram bins. The comparison of the parameter selection techniques yields 25 approaches in total, with 114 registrations each. The number of bins has no significant influence on the proposed implementation that performs better than both the manual and the standard method in terms of acceptance rates and target registration error (TRE). The overall mean TRE is 2.34 mm compared to 2.54 mm for the manual registration and 6.48 mm for a standard implementation. Our results show a significant TRE reduction for distortion-corrected magnet- c resonance images.
Keywords :
biomedical MRI; computerised tomography; image registration; medical image processing; parameter estimation; positron emission tomography; CT-MR image pairs; MR-MR image pairs; Max-Lloyd requantization; PET-MR image pairs; RIRE 2.0 database; automatic parameter selection; coincidence weighting scheme; data-driven estimation schemes; distortion-corrected magnetic resonance images; intensity distributions; multimodal image registration; normalized mutual information; parameter configuration; parameter-free implementation; similarity measures; target registration error; Background noise; Biomedical imaging; Histograms; Image databases; Image registration; Kernel; Manuals; Mutual information; Noise measurement; Proposals; Adaptive binning; Parzen-window estimation; automatic parameter estimation; coincidence weighting; normalized mutual information; Algorithms; Animals; Artificial Intelligence; Diagnostic Imaging; Image Enhancement; Image Interpretation, Computer-Assisted; Imaging, Three-Dimensional; Pattern Recognition, Automated; Subtraction Technique; Tomography, X-Ray Computed;
fLanguage :
English
Journal_Title :
Medical Imaging, IEEE Transactions on
Publisher :
ieee
ISSN :
0278-0062
Type :
jour
DOI :
10.1109/TMI.2010.2041358
Filename :
5430984
Link To Document :
بازگشت