Recursive Deformable Image Registration Network with Mutual Attention

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zheng, Jian-Qing, Wang, Ziyang, Huang, Baoru, Lim, Ngee Han, Vincent, Tonia, Papiez, Bartlomiej W.
Natura: Preprint
Pubblicazione: 2022
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914877937811456
author Zheng, Jian-Qing
Wang, Ziyang
Huang, Baoru
Lim, Ngee Han
Vincent, Tonia
Papiez, Bartlomiej W.
author_facet Zheng, Jian-Qing
Wang, Ziyang
Huang, Baoru
Lim, Ngee Han
Vincent, Tonia
Papiez, Bartlomiej W.
contents Deformable image registration, estimating the spatial transformation between different images, is an important task in medical imaging. Many previous studies have used learning-based methods for multi-stage registration to perform 3D image registration to improve performance. The performance of the multi-stage approach, however, is limited by the size of the receptive field where complex motion does not occur at a single spatial scale. We propose a new registration network combining recursive network architecture and mutual attention mechanism to overcome these limitations. Compared with the state-of-the-art deep learning methods, our network based on the recursive structure achieves the highest accuracy in lung Computed Tomography (CT) data set (Dice score of 92\% and average surface distance of 3.8mm for lungs) and one of the most accurate results in abdominal CT data set with 9 organs of various sizes (Dice score of 55\% and average surface distance of 7.8mm). We also showed that adding 3 recursive networks is sufficient to achieve the state-of-the-art results without a significant increase in the inference time.
format Preprint
id arxiv_https___arxiv_org_abs_2206_01863
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Recursive Deformable Image Registration Network with Mutual Attention
Zheng, Jian-Qing
Wang, Ziyang
Huang, Baoru
Lim, Ngee Han
Vincent, Tonia
Papiez, Bartlomiej W.
Computer Vision and Pattern Recognition
Deformable image registration, estimating the spatial transformation between different images, is an important task in medical imaging. Many previous studies have used learning-based methods for multi-stage registration to perform 3D image registration to improve performance. The performance of the multi-stage approach, however, is limited by the size of the receptive field where complex motion does not occur at a single spatial scale. We propose a new registration network combining recursive network architecture and mutual attention mechanism to overcome these limitations. Compared with the state-of-the-art deep learning methods, our network based on the recursive structure achieves the highest accuracy in lung Computed Tomography (CT) data set (Dice score of 92\% and average surface distance of 3.8mm for lungs) and one of the most accurate results in abdominal CT data set with 9 organs of various sizes (Dice score of 55\% and average surface distance of 7.8mm). We also showed that adding 3 recursive networks is sufficient to achieve the state-of-the-art results without a significant increase in the inference time.
title Recursive Deformable Image Registration Network with Mutual Attention
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2206.01863