Confidence Estimation for Medical Image Registration Based On Stereo Confidences

• Published in: IEEE transactions on medical imaging Vol. 35; no. 2; pp. 539 - 549
• Main Authors: Saygili, Gorkem, Staring, Marius, Hendriks, Emile A.
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.02.2016; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Accuracy; Algorithms; Biomedical imaging; Brain - diagnostic imaging; Confidence; Confidence estimation; Confidence intervals; Diagnostic Imaging - methods; Error analysis; Errors; Estimates; Estimation; Feature extraction; Ground truth; Humans; Image Processing, Computer-Assisted - methods; Image registration; Lung - diagnostic imaging; Measurement uncertainty; medical image registration; Searching; Shape; stereo confidence
• ISSN: 0278-0062; 1558-254X; 1558-254X
• DOI: 10.1109/TMI.2015.2481609

In this paper, we propose a novel method to estimate the confidence of a registration that does not require any ground truth, is independent from the registration algorithm and the resulting confidence is correlated with the amount of registration error. We first apply a local search to match patterns between the registered image pairs. Local search induces a cost space per voxel which we explore further to estimate the confidence of the registration similar to confidence estimation algorithms for stereo matching. We test our method on both synthetically generated registration errors and on real registrations with ground truth. The experimental results show that our confidence measure can estimate registration errors and it is correlated with local errors.