Unsupervised detection of local errors in image registration

Image registration is used extensively in medical imaging. Visual assessment of its quality is time consuming and not necessarily accurate. Automatic estimation of registration accuracy is desired for many clinical applications. Current methods rely on learning a relationship between image features and registration error. In this paper we propose an unsupervised method for the detection of local registration errors of a user-specified magnitude. Our method analyses the consistency error of registration circuits, does not require image intensity information, and achieves an error detection accuracy of 82% for 3D liver MRI registration of breathing phases.