Cargando…

An Unsupervised Learning-Based Multi-Organ Registration Method for 3D Abdominal CT Images

Medical image registration is an essential technique to achieve spatial consistency geometric positions of different medical images obtained from single- or multi-sensor, such as computed tomography (CT), magnetic resonance (MR), and ultrasound (US) images. In this paper, an improved unsupervised le...

Descripción completa

Detalles Bibliográficos
Autores principales: Yang, Shaodi, Zhao, Yuqian, Liao, Miao, Zhang, Fan
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8472627/
https://www.ncbi.nlm.nih.gov/pubmed/34577461
http://dx.doi.org/10.3390/s21186254
_version_ 1784574781272621056
author Yang, Shaodi
Zhao, Yuqian
Liao, Miao
Zhang, Fan
author_facet Yang, Shaodi
Zhao, Yuqian
Liao, Miao
Zhang, Fan
author_sort Yang, Shaodi
collection PubMed
description Medical image registration is an essential technique to achieve spatial consistency geometric positions of different medical images obtained from single- or multi-sensor, such as computed tomography (CT), magnetic resonance (MR), and ultrasound (US) images. In this paper, an improved unsupervised learning-based framework is proposed for multi-organ registration on 3D abdominal CT images. First, the explored coarse-to-fine recursive cascaded network (RCN) modules are embedded into a basic U-net framework to achieve more accurate multi-organ registration results from 3D abdominal CT images. Then, a topology-preserving loss is added in the total loss function to avoid a distortion of the predicted transformation field. Four public databases are selected to validate the registration performances of the proposed method. The experimental results show that the proposed method is superior to some existing traditional and deep learning-based methods and is promising to meet the real-time and high-precision clinical registration requirements of 3D abdominal CT images.
format Online
Article
Text
id pubmed-8472627
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-84726272021-09-28 An Unsupervised Learning-Based Multi-Organ Registration Method for 3D Abdominal CT Images Yang, Shaodi Zhao, Yuqian Liao, Miao Zhang, Fan Sensors (Basel) Article Medical image registration is an essential technique to achieve spatial consistency geometric positions of different medical images obtained from single- or multi-sensor, such as computed tomography (CT), magnetic resonance (MR), and ultrasound (US) images. In this paper, an improved unsupervised learning-based framework is proposed for multi-organ registration on 3D abdominal CT images. First, the explored coarse-to-fine recursive cascaded network (RCN) modules are embedded into a basic U-net framework to achieve more accurate multi-organ registration results from 3D abdominal CT images. Then, a topology-preserving loss is added in the total loss function to avoid a distortion of the predicted transformation field. Four public databases are selected to validate the registration performances of the proposed method. The experimental results show that the proposed method is superior to some existing traditional and deep learning-based methods and is promising to meet the real-time and high-precision clinical registration requirements of 3D abdominal CT images. MDPI 2021-09-18 /pmc/articles/PMC8472627/ /pubmed/34577461 http://dx.doi.org/10.3390/s21186254 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Yang, Shaodi
Zhao, Yuqian
Liao, Miao
Zhang, Fan
An Unsupervised Learning-Based Multi-Organ Registration Method for 3D Abdominal CT Images
title An Unsupervised Learning-Based Multi-Organ Registration Method for 3D Abdominal CT Images
title_full An Unsupervised Learning-Based Multi-Organ Registration Method for 3D Abdominal CT Images
title_fullStr An Unsupervised Learning-Based Multi-Organ Registration Method for 3D Abdominal CT Images
title_full_unstemmed An Unsupervised Learning-Based Multi-Organ Registration Method for 3D Abdominal CT Images
title_short An Unsupervised Learning-Based Multi-Organ Registration Method for 3D Abdominal CT Images
title_sort unsupervised learning-based multi-organ registration method for 3d abdominal ct images
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8472627/
https://www.ncbi.nlm.nih.gov/pubmed/34577461
http://dx.doi.org/10.3390/s21186254
work_keys_str_mv AT yangshaodi anunsupervisedlearningbasedmultiorganregistrationmethodfor3dabdominalctimages
AT zhaoyuqian anunsupervisedlearningbasedmultiorganregistrationmethodfor3dabdominalctimages
AT liaomiao anunsupervisedlearningbasedmultiorganregistrationmethodfor3dabdominalctimages
AT zhangfan anunsupervisedlearningbasedmultiorganregistrationmethodfor3dabdominalctimages
AT yangshaodi unsupervisedlearningbasedmultiorganregistrationmethodfor3dabdominalctimages
AT zhaoyuqian unsupervisedlearningbasedmultiorganregistrationmethodfor3dabdominalctimages
AT liaomiao unsupervisedlearningbasedmultiorganregistrationmethodfor3dabdominalctimages
AT zhangfan unsupervisedlearningbasedmultiorganregistrationmethodfor3dabdominalctimages