Deep Learning Approach for Left Atrium Segmentation

How to Cite:Moradi S, Ghelich Oghli M, Alizadehasl A, Shabanzadeh A. Deep Learning Approach for Left Atrium Segmentation. I J Radiol. 2019;16(Special Issue):e99140. doi: https://doi.org/10.5812/iranjradiol.99140

Abstract

Background:

Cardiovascular disease is one of the most common causes of death in the world. Cardiovascular risk is often assessed by analyzing parameters extracted from image data taken from different parts of the heart. Transthoracic echocardiography is a non-invasive imaging modality that is usually the first step of diagnosis procedure. Extracting more information from epical and parasternal views can lead the doctor to early diagnosis. The examination analysis, although has a valuable role, relies on the operator experience. To have a more standard analysis, it is important to reduce the variability of the examination analysis. Automatic image analysis, which is very helpful in this context, can be implemented in image segmentation, parameter measurement, and even diagnosis levels. Left atrial measurements (mostly the atrial volume) are strong predictors of cardiac events. Elevated atrial pressure or increased flow can lead to atrial enlargement. There is evidence that patients with high left atrial volume are at risk of ischemic stroke, heart failure, and atrial fibrillation.

Objectives:

The purpose of this paper was to conduct automatic segmentation of left atrium in four-chamber view images to make measurements reliable and independent from expert experience. Generally, most methods of automatic segmentation are based on image processing algorithms that are sometimes too complicated and less accurate. Deep learning models have been widely used in different computer vision areas. These models are mathematically simple and are proven to have better accuracy in computer vision problems. Accordingly, we used one of the famous neural network structures named Unet for left atrium segmentation in 2D echocardiography. Comparing the trained network’s results with the ground truth segmentations made by experts, we showed that neural networks were strong choices for automation.

Methods:

The dataset used in this research was the public echocardiography image dataset published in CAMUS (Cardiac Acquisitions for Multi-structure Ultrasound Segmentation) Challenge. The data included four-chamber view end-systole and end-diastole frames from 450 patients. Unet is a kind of pyramidal network with encoding and decoding paths. The encoder or contraction path was used to capture the context and features in the image. The second path was the symmetric expanding or decoder path that was used to enable precise localization. The whole task of the network was to classify each pixel in the image to the background or left atrium classes. The loss function in the learning procedure was defined as the Dice coefficient, which depicted the ratio of the number of pixels that were correctly classified. For comparing the method with experts, five-fold cross-validation was used. Each time, 10% of the dataset was used as a test set and 90% as a train set. In the training step, the network learned the train set annotations and in the testing procedure, the performance of the trained network was evaluated based on its predictions on the test set. Dice coefficient, Hausdorff distance, and mean absolute distance (MAD) were used to evaluate the accuracy of the method in echocardiography images.

Results:

The calculated metrics were dice coefficient of 91.17%, Hausdorff distance of 3.31, and MAD of 0.71 for the train set and dice coefficient of 88.14%, Hausdorff distance of 4.75, and MAD of 1.67 for the test set.

Conclusion:

We showed that using Unet architecture in four-chamber view echocardiography images for bordering left atrium can be a powerful alternative to remove the variability between different experts. Evaluation metrics analysis proved that we can rely on the method predictions and have a more accurate shape of the left atrium for further analysis and measurements such as volume and other features measurement.

Automatic Myocardial Segmentation in Four-Chamber View Echocardiography Images

Shakiba Moradi,

Mostafa Ghelich Oghli,

Azin Alizadehasl,

Ali Shabanzadeh

Moradi S, Ghelich Oghli M, Alizadehasl A, Shabanzadeh A. Automatic Myocardial Segmentation in Four-Chamber View Echocardiography Images. I J Radiol. 2019;16(Special Issue):e99139. doi: https://doi.org/10.5812/iranjradiol.99139

Jan

2017

Left Ventricle Segmentation Using a Combination of Region Growing and Graph Based Method

Mostafa Ghelich Oghli,

Maryam Mohammadzadeh,

Vahid Mohammadzadeh,

Sakineh Kadivar,

Ali Mohammad Zadeh

Ghelich Oghli M, Mohammadzadeh M, Mohammadzadeh V, Kadivar S, Mohammad Zadeh A. Left Ventricle Segmentation Using a Combination of Region Growing and Graph Based Method. I J Radiol. 2017;14(2):e42272. doi: https://doi.org/10.5812/iranjradiol.42272

Jan

2024

Advancements in Artificial Intelligence for ECG Signal Analysis and Arrhythmia Detection: A Review

Fatemeh Kazemi Lichaee,

Arsalan Salari,

Jalil Jalili,

Sedigheh Beikmohammad Dalivand,

Mahdis Roshanfekr Rad,

Mohadeseh Mojarad

Kazemi Lichaee F, Salari A, Jalili J, Beikmohammad Dalivand S, Roshanfekr Rad M, et al. Advancements in Artificial Intelligence for ECG Signal Analysis and Arrhythmia Detection: A Review. Int J Cardiovasc Pract. 2023;8(2):e143437. doi: https://doi.org/10.5812/intjcardiovascpract-143437

Dec

2019

Automatic Fetal Biometry Evaluation in Ultrasound Images Using a Deep Learning-Based Approach

Mostafa Ghelich Oghli,

Shakiba Moradi,

Reza Gerami,

Ali Shabanzadeh

Ghelich Oghli M, Moradi S, Gerami R, Shabanzadeh A. Automatic Fetal Biometry Evaluation in Ultrasound Images Using a Deep Learning-Based Approach. I J Radiol. 2019;16(Special Issue):e99138. doi: https://doi.org/10.5812/iranjradiol.99138

Nov

2022

A Multi-centric Evaluation of Deep Learning Models for Segmentation of COVID-19 Lung Lesions on Chest CT Scans

Saman Sotoudeh-Paima,

Navid Hasanzadeh,

Ali Bashirgonbadi,

Amin Aref,

Mehran Naghibi,

Mostafa Zoorpaikar

,et al.

Sotoudeh-Paima S, Hasanzadeh N, Bashirgonbadi A, Aref A, Naghibi M, et al. A Multi-centric Evaluation of Deep Learning Models for Segmentation of COVID-19 Lung Lesions on Chest CT Scans. I J Radiol. 2022;19(4):e117992. doi: https://doi.org/10.5812/iranjradiol-117992

Import into EndNote Import into BibTex

Crossmark

Checking

Share on

Comments

Number of Comments:0

Cited by

Scopus by DOI: 0
Last Update: 3 weeks ago
Scopus by Title: 1
Last Update: 3 weeks ago
Scopus by Title (Ref): 0
Last Update: 3 weeks ago
CrossRef: 0
Last Update: 3 days ago

Metrics

Licensing and reuse information

Ordering Reprints

Articles are published under the Creative Commons license stated on each article. No permission or royalty fee is required for uses permitted by that license. CCC handles optional bulk and customized reprint orders. Any quotation covers production and delivery services only, not copyright permission. > Request Reprints from CCC

Search Relations

Author(s):

Shakiba Moradi:[PubMed][Scholar]
Mostafa Ghelich Oghli:[PubMed][Scholar]
Azin Alizadehasl:[PubMed][Scholar]
Ali Shabanzadeh:[PubMed][Scholar]

An Innovative Journal in the Field of Radiology

Outlines

Deep Learning Approach for Left Atrium Segmentation

Abstract

Background:

Objectives:

Methods:

Results:

Conclusion:

Similar Articles

Automatic Myocardial Segmentation in Four-Chamber View Echocardiography Images

Left Ventricle Segmentation Using a Combination of Region Growing and Graph Based Method

Advancements in Artificial Intelligence for ECG Signal Analysis and Arrhythmia Detection: A Review

Automatic Fetal Biometry Evaluation in Ultrasound Images Using a Deep Learning-Based Approach

A Multi-centric Evaluation of Deep Learning Models for Segmentation of COVID-19 Lung Lesions on Chest CT Scans

Crossmark

Checking

Last Update: 3 weeks ago

Last Update: 3 weeks ago

Last Update: 3 weeks ago

Last Update: 3 days ago