Misdirected Registration Uncertainty
Jie Luo, Karteek Popuri, Dana Cobzas, Hongyi Ding, William M. Wells, III, Masashi Sugiyama

TL;DR
This paper critically examines the common practice of using transformation uncertainty to quantify registration uncertainty in medical image registration, revealing potential inaccuracies and proposing a nuanced perspective.
Contribution
It demonstrates that transformation uncertainty may be misleading for registration confidence and questions the reliance on the mode of transformation distribution for voxel correspondence.
Findings
Transformation uncertainty can be misleading for registration confidence.
Using the mode of transformation distribution may not always be appropriate.
The paper highlights the need for more accurate uncertainty quantification methods.
Abstract
Being a task of establishing spatial correspondences, medical image registration is often formalized as finding the optimal transformation that best aligns two images. Since the transformation is such an essential component of registration, most existing researches conventionally quantify the registration uncertainty, which is the confidence in the estimated spatial correspondences, by the transformation uncertainty. In this paper, we give concrete examples and reveal that using the transformation uncertainty to quantify the registration uncertainty is inappropriate and sometimes misleading. Based on this finding, we also raise attention to an important yet subtle aspect of probabilistic image registration, that is whether it is reasonable to determine the correspondence of a registered voxel solely by the mode of its transformation distribution.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMedical Image Segmentation Techniques · Medical Imaging Techniques and Applications · Image Retrieval and Classification Techniques
