research-article

Left Ventricle Segmentation and Quantification with Attention-Enhanced Segmentation and Shape Correction

Authors:

Dong NiAuthors Info & Claims

ISICDM 2019: Proceedings of the Third International Symposium on Image Computing and Digital Medicine

Pages 226 - 230

https://doi.org/10.1145/3364836.3364881

Published: 24 August 2019 Publication History

Abstract

Quantification of the left ventricle (LV) is significant for cardiac disease diagnosis and progression assessment. Methods for LV quantification include segmentation based and regression learning method. However, the regression learning method cannot provide visual inspection, while the segmentation performance is still unsatisfactory, resulting in a large quantification error.

In this paper, we present a novel neural network to segment the endocardium and epicardium from short-axis cardiac magnetic resonance sequences, and then the 11 cardiac clinical parameters were quantified. The proposed model leverages channel attention mechanism and shape correction autoencoder, to adaptively enhanced the feature maps of different receptive field and correct the prediction shape that is inconsistent with the priors, respectively.

When validated with CMR sequences of 30 patients, the proposed model got mean dice coefficients of 0.9387, 0.9585, 0.8593 and mean Hausdorff Distances of 3.3983mm, 3.7879mm, 4.7710mm for endocardium, epicardium, and myocardium, respectively, which outperforms the classical Unet, and the state-of-art ACNN [1]. When it comes to the 11 quantification cardiac parameters, the prediction errors are lower or comparable with the best methods.

References

[1]

Oktay O, Ferrante E, Kamnitsas K, et al. Anatomically constrained neural networks (ACNNs): application to cardiac image enhancement and segmentation[J]. IEEE transactions on medical imaging, 2017, 37(2): 384--395.

[2]

http://www.nccd.org.cn/

[3]

Gupta A, Kurowski L V, Singh A, et al. Cardiac MR image segmentation using deformable models[C]// Computers in Cardiology 1993, Proceedings. IEEE, 1993.

[4]

Liu H, Hu H, Xu X, et al. Automatic Left Ventricle Segmentation in Cardiac MRI Using Topological Stable- State Thresholding and Region Restricted Dynamic Programming[J]. Academic Radiology, 2012, 19(6):723--731.

[5]

Chen T, Babb J, Kellman P, et al. Semiautomated Segmentation of Myocardial Contours for Fast Strain Analysis in Cine Displacement-Encoded MRI[J]. IEEE Transactions on Medical Imaging, 2008, 27(8):1084.

[6]

Cootes T F, Taylor C J. Combining point distribution models with shape models based on finite element analysis[J]. Image and Vision Computing, 1995, 13(5): 403--409.

[7]

Davatzikos C, Tao X, Shen D. Hierarchical active shape models, using the wavelet transform[J]. IEEE transactions on medical imaging, 2003, 22(3): 414--423.

[8]

Avendi M, Kheradvar A, Jafarkhani H. A combined deeplearning and deformable-model approach to fully automatic segmentation of the left ventricle in cardiac MRI[J]. Medical Image Analysis, 2016, 30:108--119.

[9]

Xue W, Islam A, Bhaduri M, et al. Direct Multitype Cardiac Indices Estimation via Joint Representation and Regression Learning[J]. IEEE Transactions on Medical Imaging, 2017:1--1.

[10]

Petitjean C, Dacher J N. A review of segmentation methods in short axis cardiac MR images[J]. Medical Image Analysis, 2011, 15(2):169--184.

[11]

Hu J, Shen L, Sun G. Squeeze-and-excitation networks[C]// Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 7132--7141.

[12]

Li X, Wang W, Hu X, et al. Selective Kernel Networks[J]. arXiv preprint arXiv:1903.06586, 2019.

[13]

Yue Q, Luo X, Ye Q, et al. Cardiac Segmentation from LGE MRI Using Deep Neural Network Incorporating Shape and Spatial Priors[J]. arXiv preprint arXiv:1906.07347, 2019.

[14]

Li J, Yu Z, Gu Z, et al. Dilated-Inception Net: Multi-Scale Feature Aggregation for Cardiac Right Ventricle Segmentation[J]. IEEE Transactions on Biomedical Engineering, 2019.

[15]

Yu F, Koltun V. Multi-scale context aggregation by dilated convolutions[J]. arXiv preprint arXiv:1511.07122, 2015.

[16]

Peng C, Zhang X, Yu G, et al. Large Kernel Matters-Improve Semantic Segmentation by Global Convolutional Network[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 4353--4361.

[17]

Kerfoot, E., Clough, J., Oksuz, I., Lee, J., King, A.P., Schnabel,J.A., 2018. Left-ventricle quantification using residual u-net, in: Proceedings of STACOM, MICCAI 2018.

[18]

Li, J., Hu, Z., 2018. Left ventricle full quantification using deep layer aggregation based multitask relationship, in: Proceedings of STACOM, MICCAI 2018.

[19]

Liu, J., Li, X., Ren, H., Li, Q., 2018a. Multi-estimator full left ventricle quantification through ensemble learning, in:Proceedings of STACOM, MICCAI 2018.

Cited By

Du XPei ZLiu YCao XLi LLi S(2024)MultiJSQ: Direct joint segmentation and quantification of left ventricle with deep multitask‐derived regression networkCAAI Transactions on Intelligence Technology10.1049/cit2.12382Online publication date: 27-Sep-2024
https://doi.org/10.1049/cit2.12382
Zhao ZPuybareau EBoutry NGeraud T(2021)Do not Treat Boundaries and Regions Differently: An Example on Heart Left Atrial Segmentation2020 25th International Conference on Pattern Recognition (ICPR)10.1109/ICPR48806.2021.9412755(7447-7453)Online publication date: 10-Jan-2021
https://doi.org/10.1109/ICPR48806.2021.9412755
Chen CBai WDavies RBhuva AManisty CAugusto JMoon JAung NLee ASanghvi MFung KPaiva JPetersen SLukaschuk EPiechnik SNeubauer SRueckert D(2020)Improving the Generalizability of Convolutional Neural Network-Based Segmentation on CMR ImagesFrontiers in Cardiovascular Medicine10.3389/fcvm.2020.001057Online publication date: 30-Jun-2020
https://doi.org/10.3389/fcvm.2020.00105

Index Terms

Left Ventricle Segmentation and Quantification with Attention-Enhanced Segmentation and Shape Correction
1. Applied computing
  1. Life and medical sciences
    1. Bioinformatics

Recommendations

Automatic segmentation of the left ventricle cavity and myocardium in MRI data

A novel approach for the automatic segmentation has been developed to extract the epi-cardium and endo-cardium boundaries of the left ventricle (lv) of the heart. The developed segmentation scheme takes multi-slice and multi-phase magnetic resonance (MR)...
Segmentation of Left Ventricle of 2D Echocardiographic Image Using Active Contouring
CICN '11: Proceedings of the 2011 International Conference on Computational Intelligence and Communication Networks

Cardiovascular diseases are a major health concern worldwide. The left ventricle and in particular the endocardium is a structure of particular interest since it performs the task of pumping oxygenated blood to the entire body. Therefore, segmentation ...
Automated Segmentation of Left Ventricle Using Local and Global Intensity Based Active Contour and Dynamic Programming

The aim of this work is to develop an improved region based active contour and dynamic programming based method for accurate segmentation of left ventricle (LV) from multi-slice cine short axis cardiac magnetic resonance (MR) images. Intensity ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image ACM Other conferences

ISICDM 2019: Proceedings of the Third International Symposium on Image Computing and Digital Medicine

August 2019

370 pages

ISBN:9781450372626

DOI:10.1145/3364836

Copyright © 2019 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

In-Cooperation

Xidian University

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 24 August 2019

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed limited

Conference

ISICDM 2019

ISICDM 2019: The Third International Symposium on Image Computing and Digital Medicine

August 24 - 26, 2019

Xi'an, China

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

2
Total Citations
View Citations
85
Total Downloads

Downloads (Last 12 months)7
Downloads (Last 6 weeks)1

Reflects downloads up to 25 Nov 2024

Other Metrics

View Author Metrics

Citations

Cited By

Du XPei ZLiu YCao XLi LLi S(2024)MultiJSQ: Direct joint segmentation and quantification of left ventricle with deep multitask‐derived regression networkCAAI Transactions on Intelligence Technology10.1049/cit2.12382Online publication date: 27-Sep-2024
https://doi.org/10.1049/cit2.12382
Zhao ZPuybareau EBoutry NGeraud T(2021)Do not Treat Boundaries and Regions Differently: An Example on Heart Left Atrial Segmentation2020 25th International Conference on Pattern Recognition (ICPR)10.1109/ICPR48806.2021.9412755(7447-7453)Online publication date: 10-Jan-2021
https://doi.org/10.1109/ICPR48806.2021.9412755
Chen CBai WDavies RBhuva AManisty CAugusto JMoon JAung NLee ASanghvi MFung KPaiva JPetersen SLukaschuk EPiechnik SNeubauer SRueckert D(2020)Improving the Generalizability of Convolutional Neural Network-Based Segmentation on CMR ImagesFrontiers in Cardiovascular Medicine10.3389/fcvm.2020.001057Online publication date: 30-Jun-2020
https://doi.org/10.3389/fcvm.2020.00105

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Table of Contents