Salvato in:
Dettagli Bibliografici
Autori principali: Brandstätter, Stefan, Seeböck, Philipp, Fürböck, Christoph, Pochepnia, Svitlana, Prosch, Helmut, Langs, Georg
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2410.18683
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909362824413184
author Brandstätter, Stefan
Seeböck, Philipp
Fürböck, Christoph
Pochepnia, Svitlana
Prosch, Helmut
Langs, Georg
author_facet Brandstätter, Stefan
Seeböck, Philipp
Fürböck, Christoph
Pochepnia, Svitlana
Prosch, Helmut
Langs, Georg
contents 2D to 3D registration is essential in tasks such as diagnosis, surgical navigation, environmental understanding, navigation in robotics, autonomous systems, or augmented reality. In medical imaging, the aim is often to place a 2D image in a 3D volumetric observation to w. Current approaches for rigid single slice in volume registration are limited by requirements such as pose initialization, stacks of adjacent slices, or reliable anatomical landmarks. Here, we propose a self-supervised 2D/3D registration approach to match a single 2D slice to the corresponding 3D volume. The method works in data without anatomical priors such as images of tumors. It addresses the dimensionality disparity and establishes correspondences between 2D in-plane and 3D out-of-plane rotation-equivariant features by using group equivariant CNNs. These rotation-equivariant features are extracted from the 2D query slice and aligned with their 3D counterparts. Results demonstrate the robustness of the proposed slice-in-volume registration on the NSCLC-Radiomics CT and KIRBY21 MRI datasets, attaining an absolute median angle error of less than 2 degrees and a mean-matching feature accuracy of 89% at a tolerance of 3 pixels.
format Preprint
id arxiv_https___arxiv_org_abs_2410_18683
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Rigid Single-Slice-in-Volume registration via rotation-equivariant 2D/3D feature matching
Brandstätter, Stefan
Seeböck, Philipp
Fürböck, Christoph
Pochepnia, Svitlana
Prosch, Helmut
Langs, Georg
Computer Vision and Pattern Recognition
Machine Learning
2D to 3D registration is essential in tasks such as diagnosis, surgical navigation, environmental understanding, navigation in robotics, autonomous systems, or augmented reality. In medical imaging, the aim is often to place a 2D image in a 3D volumetric observation to w. Current approaches for rigid single slice in volume registration are limited by requirements such as pose initialization, stacks of adjacent slices, or reliable anatomical landmarks. Here, we propose a self-supervised 2D/3D registration approach to match a single 2D slice to the corresponding 3D volume. The method works in data without anatomical priors such as images of tumors. It addresses the dimensionality disparity and establishes correspondences between 2D in-plane and 3D out-of-plane rotation-equivariant features by using group equivariant CNNs. These rotation-equivariant features are extracted from the 2D query slice and aligned with their 3D counterparts. Results demonstrate the robustness of the proposed slice-in-volume registration on the NSCLC-Radiomics CT and KIRBY21 MRI datasets, attaining an absolute median angle error of less than 2 degrees and a mean-matching feature accuracy of 89% at a tolerance of 3 pixels.
title Rigid Single-Slice-in-Volume registration via rotation-equivariant 2D/3D feature matching
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2410.18683