Advancing Deformable Medical Image Registration with Multi-axis Cross-covariance Attention

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Meng, Mingyuan, Fulham, Michael, Bi, Lei, Kim, Jinman
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912169287745536
author Meng, Mingyuan
Fulham, Michael
Bi, Lei
Kim, Jinman
author_facet Meng, Mingyuan
Fulham, Michael
Bi, Lei
Kim, Jinman
contents Deformable image registration is a fundamental requirement for medical image analysis. Recently, transformers have been widely used in deep learning-based registration methods for their ability to capture long-range dependency via self-attention (SA). However, the high computation and memory loads of SA (growing quadratically with the spatial resolution) hinder transformers from processing subtle textural information in high-resolution image features, e.g., at the full and half image resolutions. This limits deformable registration as the high-resolution textural information is crucial for finding precise pixel-wise correspondence between subtle anatomical structures. Cross-covariance Attention (XCA), as a "transposed" version of SA that operates across feature channels, has complexity growing linearly with the spatial resolution, providing the feasibility of capturing long-range dependency among high-resolution image features. However, existing XCA-based transformers merely capture coarse global long-range dependency, which are unsuitable for deformable image registration relying primarily on fine-grained local correspondence. In this study, we propose to improve existing deep learning-based registration methods by embedding a new XCA mechanism. To this end, we design an XCA-based transformer block optimized for deformable medical image registration, named Multi-Axis XCA (MAXCA). Our MAXCA serves as a general network block that can be embedded into various registration network architectures. It can capture both global and local long-range dependency among high-resolution image features by applying regional and dilated XCA in parallel via a multi-axis design. Extensive experiments on two well-benchmarked inter-/intra-patient registration tasks with seven public medical datasets demonstrate that our MAXCA block enables state-of-the-art registration performance.
format Preprint
id arxiv_https___arxiv_org_abs_2412_18545
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Advancing Deformable Medical Image Registration with Multi-axis Cross-covariance Attention
Meng, Mingyuan
Fulham, Michael
Bi, Lei
Kim, Jinman
Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
Deformable image registration is a fundamental requirement for medical image analysis. Recently, transformers have been widely used in deep learning-based registration methods for their ability to capture long-range dependency via self-attention (SA). However, the high computation and memory loads of SA (growing quadratically with the spatial resolution) hinder transformers from processing subtle textural information in high-resolution image features, e.g., at the full and half image resolutions. This limits deformable registration as the high-resolution textural information is crucial for finding precise pixel-wise correspondence between subtle anatomical structures. Cross-covariance Attention (XCA), as a "transposed" version of SA that operates across feature channels, has complexity growing linearly with the spatial resolution, providing the feasibility of capturing long-range dependency among high-resolution image features. However, existing XCA-based transformers merely capture coarse global long-range dependency, which are unsuitable for deformable image registration relying primarily on fine-grained local correspondence. In this study, we propose to improve existing deep learning-based registration methods by embedding a new XCA mechanism. To this end, we design an XCA-based transformer block optimized for deformable medical image registration, named Multi-Axis XCA (MAXCA). Our MAXCA serves as a general network block that can be embedded into various registration network architectures. It can capture both global and local long-range dependency among high-resolution image features by applying regional and dilated XCA in parallel via a multi-axis design. Extensive experiments on two well-benchmarked inter-/intra-patient registration tasks with seven public medical datasets demonstrate that our MAXCA block enables state-of-the-art registration performance.
title Advancing Deformable Medical Image Registration with Multi-axis Cross-covariance Attention
topic Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.18545