# Interpretable Unsupervised Deformable Image Registration via Confidence-bound Multi-Hop Visual Reasoning

arXiv: https://arxiv.org/abs/2602.00211 · HTML: https://mlsanity.com/paper/2602.00211/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 36 references that are in the map.
- First posted on arXiv 30 Jan 2026.

## Builds on (most cited first, 10 of 10)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Deep Learning in Medical Image Registration: A Survey](https://mlsanity.com/paper/1903.02026/) (2019)
- [ViT-V-Net: Vision Transformer for Unsupervised Volumetric Medical Image Registration](https://mlsanity.com/paper/2104.06468/) (2021)
- [CycleMorph: Cycle Consistent Unsupervised Deformable Image Registration](https://mlsanity.com/paper/2008.05772/) (2020)
- [A survey on deep learning in medical image registration: new technologies, uncertainty, evaluation metrics, and beyond](https://mlsanity.com/paper/2307.15615/) (2023)
- [Diffusion-empowered AutoPrompt MedSAM](https://mlsanity.com/paper/2502.06817/) (2025)
- [AutoFuse: Automatic Fusion Networks for Deformable Medical Image Registration](https://mlsanity.com/paper/2309.05271/) (2023)
- [Improving Generalization of Medical Image Registration Foundation Model](https://mlsanity.com/paper/2505.06527/) (2025)
- [A Resolution Enhancement Plug-in for Deformable Registration of Medical Images](https://mlsanity.com/paper/2112.15180/) (2021)
- [Tumor aware recurrent inter-patient deformable image registration of computed tomography scans with lung cancer](https://mlsanity.com/paper/2409.11910/) (2024)

## Abstract (arXiv)

Unsupervised deformable image registration requires aligning complex anatomical structures without reference labels, making interpretability and reliability critical. Existing deep learning methods achieve considerable accuracy but often lack transparency, leading to error drift and reduced clinical trust. We propose a novel Multi-Hop Visual Chain of Reasoning (VCoR) framework that reformulates registration as a progressive reasoning process. Inspired by the iterative nature of clinical decision-making, each visual reasoning hop integrates a Localized Spatial Refinement (LSR) module to enrich feature representations and a Cross-Reference Attention (CRA) mechanism that leads the iterative refinement process, preserving anatomical consistency. This multi-hop strategy enables robust handling of large deformations and produces a transparent sequence of intermediate predictions with a theoretical bound. Beyond accuracy, our framework offers built-in interpretability by estimating uncertainty via the stability and convergence of deformation fields across hops. Extensive evaluations on two challenging public datasets, DIR-Lab 4D CT (lung) and IXI T1-weighted MRI (brain), demonstrate that VCoR achieves competitive registration accuracy while offering rich intermediate visualizations and confidence measures. By embedding an implicit visual reasoning paradigm, we present an interpretable, reliable, and clinically viable unsupervised medical image registration.