Neural Graphics Primitives-based Deformable Image Registration for On-the-fly Motion Extraction

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Li, Xia, Zhang, Fabian, Li, Muheng, Weber, Damien, Lomax, Antony, Buhmann, Joachim, Zhang, Ye
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913227609210880
author Li, Xia
Zhang, Fabian
Li, Muheng
Weber, Damien
Lomax, Antony
Buhmann, Joachim
Zhang, Ye
author_facet Li, Xia
Zhang, Fabian
Li, Muheng
Weber, Damien
Lomax, Antony
Buhmann, Joachim
Zhang, Ye
contents Intra-fraction motion in radiotherapy is commonly modeled using deformable image registration (DIR). However, existing methods often struggle to balance speed and accuracy, limiting their applicability in clinical scenarios. This study introduces a novel approach that harnesses Neural Graphics Primitives (NGP) to optimize the displacement vector field (DVF). Our method leverages learned primitives, processed as splats, and interpolates within space using a shallow neural network. Uniquely, it enables self-supervised optimization at an ultra-fast speed, negating the need for pre-training on extensive datasets and allowing seamless adaptation to new cases. We validated this approach on the 4D-CT lung dataset DIR-lab, achieving a target registration error (TRE) of 1.15\pm1.15 mm within a remarkable time of 1.77 seconds. Notably, our method also addresses the sliding boundary problem, a common challenge in conventional DIR methods.
format Preprint
id arxiv_https___arxiv_org_abs_2402_05568
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Neural Graphics Primitives-based Deformable Image Registration for On-the-fly Motion Extraction
Li, Xia
Zhang, Fabian
Li, Muheng
Weber, Damien
Lomax, Antony
Buhmann, Joachim
Zhang, Ye
Medical Physics
Computer Vision and Pattern Recognition
Intra-fraction motion in radiotherapy is commonly modeled using deformable image registration (DIR). However, existing methods often struggle to balance speed and accuracy, limiting their applicability in clinical scenarios. This study introduces a novel approach that harnesses Neural Graphics Primitives (NGP) to optimize the displacement vector field (DVF). Our method leverages learned primitives, processed as splats, and interpolates within space using a shallow neural network. Uniquely, it enables self-supervised optimization at an ultra-fast speed, negating the need for pre-training on extensive datasets and allowing seamless adaptation to new cases. We validated this approach on the 4D-CT lung dataset DIR-lab, achieving a target registration error (TRE) of 1.15\pm1.15 mm within a remarkable time of 1.77 seconds. Notably, our method also addresses the sliding boundary problem, a common challenge in conventional DIR methods.
title Neural Graphics Primitives-based Deformable Image Registration for On-the-fly Motion Extraction
topic Medical Physics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2402.05568