Cargando…

Guideline-based learning for standard plane extraction in 3-D echocardiography

The extraction of six standard planes in 3-D cardiac ultrasound plays an important role in clinical examination to analyze cardiac function. A guideline-based learning method for efficient and accurate standard plane extraction is proposed. A cardiac ultrasound guideline determines appropriate opera...

Descripción completa

Detalles Bibliográficos
Autores principales: Zhu, Peifei, Li, Zisheng
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Society of Photo-Optical Instrumentation Engineers 2018
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6245496/
https://www.ncbi.nlm.nih.gov/pubmed/30840749
http://dx.doi.org/10.1117/1.JMI.5.4.044503
_version_ 1783372254186307584
author Zhu, Peifei
Li, Zisheng
author_facet Zhu, Peifei
Li, Zisheng
author_sort Zhu, Peifei
collection PubMed
description The extraction of six standard planes in 3-D cardiac ultrasound plays an important role in clinical examination to analyze cardiac function. A guideline-based learning method for efficient and accurate standard plane extraction is proposed. A cardiac ultrasound guideline determines appropriate operation steps for clinical examinations. The idea of guideline-based learning is incorporating machine learning approaches into each stage of the guideline. First, Hough forest with hierarchical search is applied for 3-D feature point detection. Second, initial planes are determined using anatomical regularities according to the guideline. Finally, a regression forest integrated with constraints of plane regularities is applied for refining each plane. The proposed method was evaluated on a 3-D cardiac ultrasound dataset and a synthetic dataset. Compared with other plane extraction methods, it demonstrated an improved accuracy with a significantly faster running time of [Formula: see text]. Furthermore, it showed the proposed method was robust for a range abnormalities and image qualities, which would be seen in clinical practice.
format Online
Article
Text
id pubmed-6245496
institution National Center for Biotechnology Information
language English
publishDate 2018
publisher Society of Photo-Optical Instrumentation Engineers
record_format MEDLINE/PubMed
spelling pubmed-62454962019-11-20 Guideline-based learning for standard plane extraction in 3-D echocardiography Zhu, Peifei Li, Zisheng J Med Imaging (Bellingham) Computer-Aided Diagnosis The extraction of six standard planes in 3-D cardiac ultrasound plays an important role in clinical examination to analyze cardiac function. A guideline-based learning method for efficient and accurate standard plane extraction is proposed. A cardiac ultrasound guideline determines appropriate operation steps for clinical examinations. The idea of guideline-based learning is incorporating machine learning approaches into each stage of the guideline. First, Hough forest with hierarchical search is applied for 3-D feature point detection. Second, initial planes are determined using anatomical regularities according to the guideline. Finally, a regression forest integrated with constraints of plane regularities is applied for refining each plane. The proposed method was evaluated on a 3-D cardiac ultrasound dataset and a synthetic dataset. Compared with other plane extraction methods, it demonstrated an improved accuracy with a significantly faster running time of [Formula: see text]. Furthermore, it showed the proposed method was robust for a range abnormalities and image qualities, which would be seen in clinical practice. Society of Photo-Optical Instrumentation Engineers 2018-11-20 2018-10 /pmc/articles/PMC6245496/ /pubmed/30840749 http://dx.doi.org/10.1117/1.JMI.5.4.044503 Text en © The Authors. https://creativecommons.org/licenses/by/3.0/ Published by SPIE under a Creative Commons Attribution 3.0 Unported License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI.
spellingShingle Computer-Aided Diagnosis
Zhu, Peifei
Li, Zisheng
Guideline-based learning for standard plane extraction in 3-D echocardiography
title Guideline-based learning for standard plane extraction in 3-D echocardiography
title_full Guideline-based learning for standard plane extraction in 3-D echocardiography
title_fullStr Guideline-based learning for standard plane extraction in 3-D echocardiography
title_full_unstemmed Guideline-based learning for standard plane extraction in 3-D echocardiography
title_short Guideline-based learning for standard plane extraction in 3-D echocardiography
title_sort guideline-based learning for standard plane extraction in 3-d echocardiography
topic Computer-Aided Diagnosis
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6245496/
https://www.ncbi.nlm.nih.gov/pubmed/30840749
http://dx.doi.org/10.1117/1.JMI.5.4.044503
work_keys_str_mv AT zhupeifei guidelinebasedlearningforstandardplaneextractionin3dechocardiography
AT lizisheng guidelinebasedlearningforstandardplaneextractionin3dechocardiography