Fatemeh Zabihollahy1, James A White2, Eranga Ukwatta1. 1. Department of Systems and Computer Engineering, Carleton University, Ottawa, ON, Canada. 2. Stephenson Cardiac Imaging Centre, Libin Cardiovascular Institute of Alberta, University of Calgary, Calgary, AB, USA.
Abstract
PURPOSE: Accurate three-dimensional (3D) segmentation of myocardial replacement fibrosis (i.e., scar) is emerging as a potentially valuable tool for risk stratification and procedural planning in patients with ischemic cardiomyopathy. The main purpose of this study was to develop a semiautomated method using a 3D convolutional neural network (CNN)-based for the segmentation of left ventricle (LV) myocardial scar from 3D late gadolinium enhancement magnetic resonance (LGE-MR) images. METHODS: Our proposed CNN is built upon several convolutional and pooling layers aimed at choosing appropriate features from LGE-MR images to distinguish between myocardial scar and healthy tissues of the left ventricle. In contrast to previous methods that consider image intensity as the sole feature, CNN-based algorithms have the potential to improve the accuracy of scar segmentation through the creation of unconventional features that separate scar from normal myocardium in the feature space. The first step of our pipeline was to manually delineate the left ventricular myocardium, which was used as the region of interest for scar segmentation. Our developed algorithm was trained using 265,220 volume patches extracted from ten 3D LGE-MR images, then was validated on 450,454 patches from a testing dataset of 24 3D LGE-MR images, all obtained from patients with chronic myocardial infarction. We evaluated our method in the context of several alternative methods by comparing algorithm-generated segmentations to manual delineations performed by experts. RESULTS: Our CNN-based method reported an average Dice similarity coefficient (DSC) and Jaccard Index (JI) of 93.63% ± 2.6% and 88.13% ± 4.70%. In comparison to several previous methods, including K-nearest neighbor (KNN), hierarchical max flow (HMF), full width at half maximum (FWHM), and signal threshold to reference mean (STRM), the developed algorithm reported significantly higher accuracy for DSC with a P-value less than 0.0001. CONCLUSIONS: Our experimental results demonstrated that our CNN-based proposed method yielded the highest accuracy of all contemporary LV myocardial scar segmentation methodologies, inclusive of the most widely used signal intensity-based methods, such as FWHM and STRM. To our knowledge, this is the first description of LV myocardial scar tissue segmentation from 3D LGE-MR images using a CNN-based method.
PURPOSE: Accurate three-dimensional (3D) segmentation of myocardial replacement fibrosis (i.e., scar) is emerging as a potentially valuable tool for risk stratification and procedural planning in patients with ischemic cardiomyopathy. The main purpose of this study was to develop a semiautomated method using a 3D convolutional neural network (CNN)-based for the segmentation of left ventricle (LV) myocardial scar from 3D late gadolinium enhancement magnetic resonance (LGE-MR) images. METHODS: Our proposed CNN is built upon several convolutional and pooling layers aimed at choosing appropriate features from LGE-MR images to distinguish between myocardial scar and healthy tissues of the left ventricle. In contrast to previous methods that consider image intensity as the sole feature, CNN-based algorithms have the potential to improve the accuracy of scar segmentation through the creation of unconventional features that separate scar from normal myocardium in the feature space. The first step of our pipeline was to manually delineate the left ventricular myocardium, which was used as the region of interest for scar segmentation. Our developed algorithm was trained using 265,220 volume patches extracted from ten 3D LGE-MR images, then was validated on 450,454 patches from a testing dataset of 24 3D LGE-MR images, all obtained from patients with chronic myocardial infarction. We evaluated our method in the context of several alternative methods by comparing algorithm-generated segmentations to manual delineations performed by experts. RESULTS: Our CNN-based method reported an average Dice similarity coefficient (DSC) and Jaccard Index (JI) of 93.63% ± 2.6% and 88.13% ± 4.70%. In comparison to several previous methods, including K-nearest neighbor (KNN), hierarchical max flow (HMF), full width at half maximum (FWHM), and signal threshold to reference mean (STRM), the developed algorithm reported significantly higher accuracy for DSC with a P-value less than 0.0001. CONCLUSIONS: Our experimental results demonstrated that our CNN-based proposed method yielded the highest accuracy of all contemporary LV myocardial scar segmentation methodologies, inclusive of the most widely used signal intensity-based methods, such as FWHM and STRM. To our knowledge, this is the first description of LV myocardial scar tissue segmentation from 3D LGE-MR images using a CNN-based method.
Authors: Adriana Argentiero; Giuseppe Muscogiuri; Mark G Rabbat; Chiara Martini; Nicolò Soldato; Paolo Basile; Andrea Baggiano; Saima Mushtaq; Laura Fusini; Maria Elisabetta Mancini; Nicola Gaibazzi; Vincenzo Ezio Santobuono; Sandro Sironi; Gianluca Pontone; Andrea Igoren Guaricci Journal: J Clin Med Date: 2022-05-19 Impact factor: 4.964
Authors: Tonghe Wang; Yang Lei; Sibo Tian; Xiaojun Jiang; Jun Zhou; Tian Liu; Sean Dresser; Walter J Curran; Hui-Kuo Shu; Xiaofeng Yang Journal: Med Phys Date: 2019-05-21 Impact factor: 4.071
Authors: Giuseppe Muscogiuri; Valentina Volpato; Riccardo Cau; Mattia Chiesa; Luca Saba; Marco Guglielmo; Alberto Senatieri; Gregorio Chierchia; Gianluca Pontone; Serena Dell'Aversana; U Joseph Schoepf; Mason G Andrews; Paolo Basile; Andrea Igoren Guaricci; Paolo Marra; Denisa Muraru; Luigi P Badano; Sandro Sironi Journal: Heliyon Date: 2022-10-05
Authors: Andrew Lin; Márton Kolossváry; Ivana Išgum; Pál Maurovich-Horvat; Piotr J Slomka; Damini Dey Journal: Expert Rev Med Devices Date: 2020-06-16 Impact factor: 3.166