Semi-automated Processing of Real-Time CMR Scans for Left Ventricle Segmentation

None, None; None, None; None, None; None, None; None, None

Semi-automated Processing of Real-Time CMR Scans for Left Ventricle Segmentation

Conference Paper (2018)

Author(s)

Rahil Shahzad (Leiden University Medical Center)

Martin Fasshauer (University of Göttingen)

Boudewijn P.F. Lelieveldt (Leiden University Medical Center, TU Delft - Pattern Recognition and Bioinformatics)

Joachim Lotz (University of Göttingen)

Rob J. van der Geest (Leiden University Medical Center)

Research Group

Pattern Recognition and Bioinformatics

Segmentation Registration Left ventricle Realtime-MR Semi-automatic

DOI related publication

https://doi.org/10.1007/978-3-319-92258-4_6 Final published version

To reference this document use

https://resolver.tudelft.nl/uuid:394cbd42-ed58-4e7e-829c-9cfb36ff0004

More Info

expand_more

Publication Year

2018

Language

English

Research Group

Pattern Recognition and Bioinformatics

Pages (from-to)

57-66

Publisher

Springer

ISBN (print)

978-3-319-92257-7

ISBN (electronic)

978-3-319-92258-4

Event

WBIR 2018 (2018-06-28 - 2018-06-29), Leiden, Netherlands

Downloads counter

172

Abstract

We present a workflow for processing real-time cardiac MR (RT-CMR) scans for segmenting the left ventricle (LV) on short-axis slices (SAX). Our method is based on image registration, where the LV endocardium and epicardium are segmented by propagating a reference contour over all the frames of the RT-CMR SAX scans. Our method was evaluated on 19 subjects, the accuracy of the automatic LV endocardium and epicardium segmentation was compared to those defined manually. The proposed method obtained a dice similarity coefficient (DSC) of 0.94 and a mean surface-to-surface distance (MSD) measure of 0.89 ± 0.53 mm. Additionally, a number of automatically obtained clinical measures were compared to ground truth values. On average we obtained a Pearson’s correlation coefficient (R) of 0.94 (0.99–0.74).