Literature DB >> 33247342

Reliable segmentation of 2D cardiac magnetic resonance perfusion image sequences using time as the 3rd dimension.

Veit Sandfort1,2, Matthew Jacobs3,4, Andrew E Arai3, Li-Yueh Hsu3,5.   

Abstract

OBJECTIVES: Cardiac magnetic resonance (CMR) first-pass perfusion is an established noninvasive diagnostic imaging modality for detecting myocardial ischemia. A CMR perfusion sequence provides a time series of 2D images for dynamic contrast enhancement of the heart. Accurate myocardial segmentation of the perfusion images is essential for quantitative analysis and it can facilitate automated pixel-wise myocardial perfusion quantification.
METHODS: In this study, we compared different deep learning methodologies for CMR perfusion image segmentation. We evaluated the performance of several image segmentation methods using convolutional neural networks, such as the U-Net in 2D and 3D (2D plus time) implementations, with and without additional motion correction image processing step. We also present a modified U-Net architecture with a novel type of temporal pooling layer which results in improved performance.
RESULTS: The best DICE scores were 0.86 and 0.90 for LV myocardium and LV cavity, while the best Hausdorff distances were 2.3 and 2.1 pixels for LV myocardium and LV cavity using 5-fold cross-validation. The methods were corroborated in a second independent test set of 20 patients with similar performance (best DICE scores 0.84 for LV myocardium).
CONCLUSIONS: Our results showed that the LV myocardial segmentation of CMR perfusion images is best performed using a combination of motion correction and 3D convolutional networks which significantly outperformed all tested 2D approaches. Reliable frame-by-frame segmentation will facilitate new and improved quantification methods for CMR perfusion imaging. KEY POINTS: • Reliable segmentation of the myocardium offers the potential to perform pixel level perfusion assessment. • A deep learning approach in combination with motion correction, 3D (2D + time) methods, and a deep temporal connection module produced reliable segmentation results.

Entities:  

Keywords:  Cardiac magnetic resonance imaging; Deep learning; Image segmentation; Myocardial perfusion

Mesh:

Year:  2020        PMID: 33247342     DOI: 10.1007/s00330-020-07474-5

Source DB:  PubMed          Journal:  Eur Radiol        ISSN: 0938-7994            Impact factor:   5.315


  7 in total

Review 1.  Cardiac MR perfusion image processing techniques: a survey.

Authors:  Vikas Gupta; Hortense A Kirişli; Emile A Hendriks; Rob J van der Geest; Martijn van de Giessen; Wiro Niessen; Johan H C Reiber; Boudewijn P F Lelieveldt
Journal:  Med Image Anal       Date:  2012-01-10       Impact factor: 8.545

Review 2.  Imaging sequences for first pass perfusion --a review.

Authors:  Peter Kellman; Andrew E Arai
Journal:  J Cardiovasc Magn Reson       Date:  2007       Impact factor: 5.364

3.  elastix: a toolbox for intensity-based medical image registration.

Authors:  Stefan Klein; Marius Staring; Keelin Murphy; Max A Viergever; Josien P W Pluim
Journal:  IEEE Trans Med Imaging       Date:  2009-11-17       Impact factor: 10.048

4.  Automatic regional analysis of myocardial native T1 values: left ventricle segmentation and AHA parcellations.

Authors:  Hsiao-Hui Huang; Chun-Yu Huang; Chiao-Ning Chen; Yun-Wen Wang; Teng-Yi Huang
Journal:  Int J Cardiovasc Imaging       Date:  2017-07-21       Impact factor: 2.357

5.  Robust universal nonrigid motion correction framework for first-pass cardiac MR perfusion imaging.

Authors:  Mitchel Benovoy; Matthew Jacobs; Farida Cheriet; Nagib Dahdah; Andrew E Arai; Li-Yueh Hsu
Journal:  J Magn Reson Imaging       Date:  2017-02-15       Impact factor: 4.813

6.  Right ventricle segmentation from cardiac MRI: a collation study.

Authors:  Caroline Petitjean; Maria A Zuluaga; Wenjia Bai; Jean-Nicolas Dacher; Damien Grosgeorge; Jérôme Caudron; Su Ruan; Ismail Ben Ayed; M Jorge Cardoso; Hsiang-Chou Chen; Daniel Jimenez-Carretero; Maria J Ledesma-Carbayo; Christos Davatzikos; Jimit Doshi; Guray Erus; Oskar M O Maier; Cyrus M S Nambakhsh; Yangming Ou; Sébastien Ourselin; Chun-Wei Peng; Nicholas S Peters; Terry M Peters; Martin Rajchl; Daniel Rueckert; Andres Santos; Wenzhe Shi; Ching-Wei Wang; Haiyan Wang; Jing Yuan
Journal:  Med Image Anal       Date:  2014-10-28       Impact factor: 8.545

7.  Diagnostic Performance of Fully Automated Pixel-Wise Quantitative Myocardial Perfusion Imaging by Cardiovascular Magnetic Resonance.

Authors:  Li-Yueh Hsu; Matthew Jacobs; Mitchel Benovoy; Allison D Ta; Hannah M Conn; Susanne Winkler; Anders M Greve; Marcus Y Chen; Sujata M Shanbhag; W Patricia Bandettini; Andrew E Arai
Journal:  JACC Cardiovasc Imaging       Date:  2018-02-14
  7 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.