A 3D Cross-modal Keypoint Descriptor for MR-US Matching and Registration

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Morozov, Daniil, Dorent, Reuben, Haouchine, Nazim
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908929087242240
author Morozov, Daniil
Dorent, Reuben
Haouchine, Nazim
author_facet Morozov, Daniil
Dorent, Reuben
Haouchine, Nazim
contents Intraoperative registration of real-time ultrasound (iUS) to preoperative Magnetic Resonance Imaging (MRI) remains an unsolved problem due to severe modality-specific differences in appearance, resolution, and field-of-view. To address this, we propose a novel 3D cross-modal keypoint descriptor for MRI-iUS matching and registration. Our approach employs a patient-specific matching-by-synthesis approach, generating synthetic iUS volumes from preoperative MRI. This enables supervised contrastive training to learn a shared descriptor space. A probabilistic keypoint detection strategy is then employed to identify anatomically salient and modality-consistent locations. During training, a curriculum-based triplet loss with dynamic hard negative mining is used to learn descriptors that are i) robust to iUS artifacts such as speckle noise and limited coverage, and ii) rotation-invariant. At inference, the method detects keypoints in MR and real iUS images and identifies sparse matches, which are then used to perform rigid registration. Our approach is evaluated using 3D MRI-iUS pairs from the ReMIND dataset. Experiments show that our approach outperforms state-of-the-art keypoint matching methods across 11 patients, with an average precision of 69.8%. For image registration, our method achieves a competitive mean Target Registration Error of 2.39 mm on the ReMIND2Reg benchmark. Compared to existing iUS-MR registration approaches, our framework is interpretable, requires no manual initialization, and shows robustness to iUS field-of-view variation. Code, data and model weights are available at https://github.com/morozovdd/CrossKEY.
format Preprint
id arxiv_https___arxiv_org_abs_2507_18551
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A 3D Cross-modal Keypoint Descriptor for MR-US Matching and Registration
Morozov, Daniil
Dorent, Reuben
Haouchine, Nazim
Computer Vision and Pattern Recognition
Intraoperative registration of real-time ultrasound (iUS) to preoperative Magnetic Resonance Imaging (MRI) remains an unsolved problem due to severe modality-specific differences in appearance, resolution, and field-of-view. To address this, we propose a novel 3D cross-modal keypoint descriptor for MRI-iUS matching and registration. Our approach employs a patient-specific matching-by-synthesis approach, generating synthetic iUS volumes from preoperative MRI. This enables supervised contrastive training to learn a shared descriptor space. A probabilistic keypoint detection strategy is then employed to identify anatomically salient and modality-consistent locations. During training, a curriculum-based triplet loss with dynamic hard negative mining is used to learn descriptors that are i) robust to iUS artifacts such as speckle noise and limited coverage, and ii) rotation-invariant. At inference, the method detects keypoints in MR and real iUS images and identifies sparse matches, which are then used to perform rigid registration. Our approach is evaluated using 3D MRI-iUS pairs from the ReMIND dataset. Experiments show that our approach outperforms state-of-the-art keypoint matching methods across 11 patients, with an average precision of 69.8%. For image registration, our method achieves a competitive mean Target Registration Error of 2.39 mm on the ReMIND2Reg benchmark. Compared to existing iUS-MR registration approaches, our framework is interpretable, requires no manual initialization, and shows robustness to iUS field-of-view variation. Code, data and model weights are available at https://github.com/morozovdd/CrossKEY.
title A 3D Cross-modal Keypoint Descriptor for MR-US Matching and Registration
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.18551