Conditional Segmentation in Lieu of Image Registration
Yipeng Hu, Eli Gibson, Dean C. Barratt, Mark Emberton, J. Alison, Noble, Tom Vercauteren

TL;DR
This paper introduces a novel approach to image registration by learning to locate corresponding regions of interest directly through conditional segmentation, simplifying the process and improving accuracy in medical imaging applications.
Contribution
It proposes replacing traditional registration with a conditional segmentation method focused on ROI localization, demonstrating improved accuracy in prostate MRI and ultrasound registration.
Findings
Median TRE of 2.1 mm for prostate ROI registration
Over 34% reduction in TRE compared to previous methods
Quantitative bias-variance analysis explains accuracy improvements
Abstract
Classical pairwise image registration methods search for a spatial transformation that optimises a numerical measure that indicates how well a pair of moving and fixed images are aligned. Current learning-based registration methods have adopted the same paradigm and typically predict, for any new input image pair, dense correspondences in the form of a dense displacement field or parameters of a spatial transformation model. However, in many applications of registration, the spatial transformation itself is only required to propagate points or regions of interest (ROIs). In such cases, detailed pixel- or voxel-level correspondence within or outside of these ROIs often have little clinical value. In this paper, we propose an alternative paradigm in which the location of corresponding image-specific ROIs, defined in one image, within another image is learnt. This results in replacing…
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.
