Cross-Sim-NGF: FFT-Based Global Rigid Multimodal Alignment of Image Volumes using Normalized Gradient Fields

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Öfverstedt, Johan, Lindblad, Joakim, Sladoje, Nataša
Natura: Preprint
Pubblicazione: 2021
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909365430124544
author Öfverstedt, Johan
Lindblad, Joakim
Sladoje, Nataša
author_facet Öfverstedt, Johan
Lindblad, Joakim
Sladoje, Nataša
contents Multimodal image alignment involves finding spatial correspondences between volumes varying in appearance and structure. Automated alignment methods are often based on local optimization that can be highly sensitive to their initialization. We propose a global optimization method for rigid multimodal 3D image alignment, based on a novel efficient algorithm for computing similarity of normalized gradient fields (NGF) in the frequency domain. We validate the method experimentally on a dataset comprised of 20 brain volumes acquired in four modalities (T1w, Flair, CT, [18F] FDG PET), synthetically displaced with known transformations. The proposed method exhibits excellent performance on all six possible modality combinations, and outperforms all four reference methods by a large margin. The method is fast; a 3.4Mvoxel global rigid alignment requires approximately 40 seconds of computation, and the proposed algorithm outperforms a direct algorithm for the same task by more than three orders of magnitude. Open-source implementation is provided.
format Preprint
id arxiv_https___arxiv_org_abs_2110_10156
institution arXiv
publishDate 2021
record_format arxiv
spellingShingle Cross-Sim-NGF: FFT-Based Global Rigid Multimodal Alignment of Image Volumes using Normalized Gradient Fields
Öfverstedt, Johan
Lindblad, Joakim
Sladoje, Nataša
Image and Video Processing
Computer Vision and Pattern Recognition
Multimodal image alignment involves finding spatial correspondences between volumes varying in appearance and structure. Automated alignment methods are often based on local optimization that can be highly sensitive to their initialization. We propose a global optimization method for rigid multimodal 3D image alignment, based on a novel efficient algorithm for computing similarity of normalized gradient fields (NGF) in the frequency domain. We validate the method experimentally on a dataset comprised of 20 brain volumes acquired in four modalities (T1w, Flair, CT, [18F] FDG PET), synthetically displaced with known transformations. The proposed method exhibits excellent performance on all six possible modality combinations, and outperforms all four reference methods by a large margin. The method is fast; a 3.4Mvoxel global rigid alignment requires approximately 40 seconds of computation, and the proposed algorithm outperforms a direct algorithm for the same task by more than three orders of magnitude. Open-source implementation is provided.
title Cross-Sim-NGF: FFT-Based Global Rigid Multimodal Alignment of Image Volumes using Normalized Gradient Fields
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2110.10156