M C Carminati1, C Piazzese2, M Pepi3, G Tamborini3, P Gripari3, G Pontone3, R Krause4, A Auricchio4, R M Lang5, E G Caiani6. 1. Laboratory for Neutron Scattering and Imaging, Paul Scherrer Institut, CH5232 Villigen-PSI, Switzerland. Electronic address: chiara.carminati@psi.ch. 2. School of Engineering, Cardiff University, Cardiff, United Kingdom. 3. Centro Cardiologico Monzino, IRCCS Milano, Italy. 4. Centre for Computational Medicine in Cardiology, Institute of Computational Sciences, Università della Svizzera Italiana, Lugano, Switzerland. 5. Noninvasive Cardiac Imaging Laboratories, Department of Cardiology, University of Chicago, Chicago, IL, USA. 6. Department of Electronics, Information and Bioengineering, Politecnico di Milano, Milano, Italy.
Abstract
OBJECT: We present in this paper the application of a statistical shape model of the left ventricle (LV) built from transthoracic real time 3D echocardiography (3DE) to segment the LV endocardium and epicardium in cardiac magnetic resonance (CMR) images. MATERIAL AND METHODS: The LV model was built from a training database constituted by over 9000 surfaces obtained from retrospectively selected 3DE examination of 435 patients with various pathologies. Three-dimensional segmentation of the endocardium and the epicardium was obtained by processing CMR images acquired in 30 patients with a dedicated active shape modelling (ASM) algorithm using the proposed LV model. RESULTS: The segmentation results obtained with the proposed method were compared with those obtained by the manual reference technique; similarity was proven by computing: i) point to surface distance (<2 mm), ii) Dice similarity coefficient (>89%), iii) Hausdorff distance (∼5 mm). This was furthermore confirmed by equivalence testing, linear regression and Bland Altman analysis applied on derived clinical parameters, such as LV volumes and mass. CONCLUSIONS: This study showed the potential usefulness of the proposed inter-modal ASM approach featuring a 3DE-based LV model for the 3D segmentation of the LV myocardium in CMR images.
OBJECT: We present in this paper the application of a statistical shape model of the left ventricle (LV) built from transthoracic real time 3D echocardiography (3DE) to segment the LV endocardium and epicardium in cardiac magnetic resonance (CMR) images. MATERIAL AND METHODS: The LV model was built from a training database constituted by over 9000 surfaces obtained from retrospectively selected 3DE examination of 435 patients with various pathologies. Three-dimensional segmentation of the endocardium and the epicardium was obtained by processing CMR images acquired in 30 patients with a dedicated active shape modelling (ASM) algorithm using the proposed LV model. RESULTS: The segmentation results obtained with the proposed method were compared with those obtained by the manual reference technique; similarity was proven by computing: i) point to surface distance (<2 mm), ii) Dice similarity coefficient (>89%), iii) Hausdorff distance (∼5 mm). This was furthermore confirmed by equivalence testing, linear regression and Bland Altman analysis applied on derived clinical parameters, such as LV volumes and mass. CONCLUSIONS: This study showed the potential usefulness of the proposed inter-modal ASM approach featuring a 3DE-based LV model for the 3D segmentation of the LV myocardium in CMR images.
Authors: Leonid Goubergrits; Katharina Vellguth; Lukas Obermeier; Adriano Schlief; Lennart Tautz; Jan Bruening; Hans Lamecker; Angelika Szengel; Olena Nemchyna; Christoph Knosalla; Titus Kuehne; Natalia Solowjowa Journal: Front Cardiovasc Med Date: 2022-07-05
Authors: Muhammad Ali Shoaib; Khin Wee Lai; Joon Huang Chuah; Yan Chai Hum; Raza Ali; Samiappan Dhanalakshmi; Huanhuan Wang; Xiang Wu Journal: Front Public Health Date: 2022-08-25