IVAICVAug 7, 2025

Coarse-to-Fine Joint Registration of MR and Ultrasound Images via Imaging Style Transfer

arXiv:2508.05240v11 citationsh-index: 2
Originality Synthesis-oriented
AI Analysis

This addresses a domain-specific medical imaging problem for surgical planning, but it is incremental as it builds on existing methods like CycleGAN and standard registration techniques.

The paper tackled the problem of registering pre-surgery MR and post-resection US images by using a coarse-to-fine pipeline with style transfer, resulting in improved consistency between image pairs in most cases.

We developed a pipeline for registering pre-surgery Magnetic Resonance (MR) images and post-resection Ultrasound (US) images. Our approach leverages unpaired style transfer using 3D CycleGAN to generate synthetic T1 images, thereby enhancing registration performance. Additionally, our registration process employs both affine and local deformable transformations for a coarse-to-fine registration. The results demonstrate that our approach improves the consistency between MR and US image pairs in most cases.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes