Integrated 3D Anatomical Model for Automatic Myocardial Segmentation in Cardiac CT Imagery.

IF 1.3 Q4 ENGINEERING, BIOMEDICAL

Computer Methods in Biomechanics and Biomedical Engineering-Imaging and Visualization Pub Date : 2019-01-01 Epub Date: 2019-03-07 DOI:10.1080/21681163.2019.1583607

N Dahiya, A Yezzi, M Piccinelli, E Garcia

{"title":"Integrated 3D Anatomical Model for Automatic Myocardial Segmentation in Cardiac CT Imagery.","authors":"N Dahiya, A Yezzi, M Piccinelli, E Garcia","doi":"10.1080/21681163.2019.1583607","DOIUrl":null,"url":null,"abstract":"<p><p>Segmentation of epicardial and endocardial boundaries is a critical step in diagnosing cardiovascular function in heart patients. The manual tracing of organ contours in Computed Tomography Angiography (CTA) slices is subjective, time-consuming and impractical in clinical setting. We propose a novel multi-dimensional automatic edge detection algorithm based on shape priors and principal component analysis (PCA). We have developed a highly customized parametric model for implicit representations of segmenting curves (3D) for Left Ventricle (LV), Right Ventricle (RV), and Epicardium (Epi) used simultaneously to achieve myocardial segmentation. We have combined these representations in a region-based image modeling framework with high level constraints enabling the modeling of complex cardiac anatomical structures to automatically guide the segmentation of endo/epicardial boundaries. Test results on 30 short-axis CTA datasets show robust segmentation with error (mean ± std mm) of (1.46 ± 0.41), (2.06 ± 0.65), (2.88 ± 0.59) for LV, RV and Epi respectively.</p>","PeriodicalId":51800,"journal":{"name":"Computer Methods in Biomechanics and Biomedical Engineering-Imaging and Visualization","volume":null,"pages":null},"PeriodicalIF":1.3000,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/21681163.2019.1583607","citationCount":"13","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computer Methods in Biomechanics and Biomedical Engineering-Imaging and Visualization","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1080/21681163.2019.1583607","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2019/3/7 0:00:00","PubModel":"Epub","JCR":"Q4","JCRName":"ENGINEERING, BIOMEDICAL","Score":null,"Total":0}

引用次数: 13

Abstract

Segmentation of epicardial and endocardial boundaries is a critical step in diagnosing cardiovascular function in heart patients. The manual tracing of organ contours in Computed Tomography Angiography (CTA) slices is subjective, time-consuming and impractical in clinical setting. We propose a novel multi-dimensional automatic edge detection algorithm based on shape priors and principal component analysis (PCA). We have developed a highly customized parametric model for implicit representations of segmenting curves (3D) for Left Ventricle (LV), Right Ventricle (RV), and Epicardium (Epi) used simultaneously to achieve myocardial segmentation. We have combined these representations in a region-based image modeling framework with high level constraints enabling the modeling of complex cardiac anatomical structures to automatically guide the segmentation of endo/epicardial boundaries. Test results on 30 short-axis CTA datasets show robust segmentation with error (mean ± std mm) of (1.46 ± 0.41), (2.06 ± 0.65), (2.88 ± 0.59) for LV, RV and Epi respectively.

Abstract Image

查看原文本刊更多论文

心脏CT图像自动分割的集成三维解剖模型。

心外膜和心内膜边界的分割是诊断心脏病患者心血管功能的关键步骤。计算机断层扫描血管造影(CTA)切片中器官轮廓的手工追踪是主观的，耗时的，在临床环境中不切实际的。提出了一种基于形状先验和主成分分析的多维自动边缘检测算法。我们开发了一个高度定制的参数化模型，用于同时实现左心室(LV)、右心室(RV)和心外膜(Epi)的隐式分割曲线(3D)表示。我们将这些表征结合在一个基于区域的图像建模框架中，该框架具有高水平的约束，能够对复杂的心脏解剖结构进行建模，从而自动指导心脏内/心外膜边界的分割。在30个短轴CTA数据集上的测试结果显示，LV、RV和Epi的分割误差(平均±标准差mm)分别为(1.46±0.41)、(2.06±0.65)、(2.88±0.59)。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Computer Methods in Biomechanics and Biomedical Engineering-Imaging and Visualization ENGINEERING, BIOMEDICAL-

CiteScore

2.80

自引率

6.20%

发文量

102

期刊介绍： Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization is an international journal whose main goals are to promote solutions of excellence for both imaging and visualization of biomedical data, and establish links among researchers, clinicians, the medical technology sector and end-users. The journal provides a comprehensive forum for discussion of the current state-of-the-art in the scientific fields related to imaging and visualization, including, but not limited to: Applications of Imaging and Visualization Computational Bio- imaging and Visualization Computer Aided Diagnosis, Surgery, Therapy and Treatment Data Processing and Analysis Devices for Imaging and Visualization Grid and High Performance Computing for Imaging and Visualization Human Perception in Imaging and Visualization Image Processing and Analysis Image-based Geometric Modelling Imaging and Visualization in Biomechanics Imaging and Visualization in Biomedical Engineering Medical Clinics Medical Imaging and Visualization Multi-modal Imaging and Visualization Multiscale Imaging and Visualization Scientific Visualization Software Development for Imaging and Visualization Telemedicine Systems and Applications Virtual Reality Visual Data Mining and Knowledge Discovery.