# Conditional Segmentation in Lieu of Image Registration

arXiv: https://arxiv.org/abs/1907.00438 · HTML: https://mlsanity.com/paper/1907.00438/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Jun 2019.

## Built on by (most cited first, 7 of 7)

- [Enhancing Medical Image Registration via Appearance Adjustment Networks](https://mlsanity.com/paper/2103.05213/) (2021)
- [Semantic similarity metrics for learned image registration](https://mlsanity.com/paper/2104.10051/) (2021)
- [One registration is worth two segmentations](https://mlsanity.com/paper/2405.10879/) (2024)
- [A Narrative Review of Image Processing Techniques Related to Prostate Ultrasound](https://mlsanity.com/paper/2407.00678/) (2024)
- [Deep Compatible Learning for Partially-Supervised Medical Image Segmentation](https://mlsanity.com/paper/2206.09148/) (2022)
- [SAMReg: SAM-enabled Image Registration with ROI-based Correspondence](https://mlsanity.com/paper/2410.14083/) (2024)
- [Register Anything: Estimating "Corresponding Prompts" for Segment Anything Model](https://mlsanity.com/paper/2508.01697/) (2025)

## Abstract (arXiv)

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 image registration by a conditional segmentation algorithm, which can build on typical image segmentation networks and their widely-adopted training strategies. Using the registration of 3D MRI and ultrasound images of the prostate as an example to demonstrate this new approach, we report a median target registration error (TRE) of 2.1 mm between the ground-truth ROIs defined on intraoperative ultrasound images and those propagated from the preoperative MR images. Significantly lower (>34%) TREs were obtained using the proposed conditional segmentation compared with those obtained from a previously-proposed spatial-transformation-predicting registration network trained with the same multiple ROI labels for individual image pairs. We conclude this work by using a quantitative bias-variance analysis to provide one explanation of the observed improvement in registration accuracy.