POLAFFINI: Efficient feature-based polyaffine initialization for improved non-linear image registration

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Legouhy, Antoine, Callaghan, Ross, Azadbakht, Hojjat, Zhang, Hui
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929414875381760
author Legouhy, Antoine
Callaghan, Ross
Azadbakht, Hojjat
Zhang, Hui
author_facet Legouhy, Antoine
Callaghan, Ross
Azadbakht, Hojjat
Zhang, Hui
contents This paper presents an efficient feature-based approach to initialize non-linear image registration. Today, nonlinear image registration is dominated by methods relying on intensity-based similarity measures. A good estimate of the initial transformation is essential, both for traditional iterative algorithms and for recent one-shot deep learning (DL)-based alternatives. The established approach to estimate this starting point is to perform affine registration, but this may be insufficient due to its parsimonious, global, and non-bending nature. We propose an improved initialization method that takes advantage of recent advances in DL-based segmentation techniques able to instantly estimate fine-grained regional delineations with state-of-the-art accuracies. Those segmentations are used to produce local, anatomically grounded, feature-based affine matchings using iteration-free closed-form expressions. Estimated local affine transformations are then fused, with the log-Euclidean polyaffine framework, into an overall dense diffeomorphic transformation. We show that, compared to its affine counterpart, the proposed initialization leads to significantly better alignment for both traditional and DL-based non-linear registration algorithms. The proposed approach is also more robust and significantly faster than commonly used affine registration algorithms such as FSL FLIRT.
format Preprint
id arxiv_https___arxiv_org_abs_2407_03922
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle POLAFFINI: Efficient feature-based polyaffine initialization for improved non-linear image registration
Legouhy, Antoine
Callaghan, Ross
Azadbakht, Hojjat
Zhang, Hui
Computer Vision and Pattern Recognition
This paper presents an efficient feature-based approach to initialize non-linear image registration. Today, nonlinear image registration is dominated by methods relying on intensity-based similarity measures. A good estimate of the initial transformation is essential, both for traditional iterative algorithms and for recent one-shot deep learning (DL)-based alternatives. The established approach to estimate this starting point is to perform affine registration, but this may be insufficient due to its parsimonious, global, and non-bending nature. We propose an improved initialization method that takes advantage of recent advances in DL-based segmentation techniques able to instantly estimate fine-grained regional delineations with state-of-the-art accuracies. Those segmentations are used to produce local, anatomically grounded, feature-based affine matchings using iteration-free closed-form expressions. Estimated local affine transformations are then fused, with the log-Euclidean polyaffine framework, into an overall dense diffeomorphic transformation. We show that, compared to its affine counterpart, the proposed initialization leads to significantly better alignment for both traditional and DL-based non-linear registration algorithms. The proposed approach is also more robust and significantly faster than commonly used affine registration algorithms such as FSL FLIRT.
title POLAFFINI: Efficient feature-based polyaffine initialization for improved non-linear image registration
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.03922