Neural architecture search of echocardiography view classifiers

Azarmehr, Neda, Ye, Xujiong, Howard, James P., Lane, Elisabeth S., Labs, Robert, Shun-Shin, Matthew J., Cole, Graham D., Bidaut, Luc, Francis, Darrel P. and Zolgharni, Massoud ORCID: https://orcid.org/0000-0003-0904-2904 (2021) Neural architecture search of echocardiography view classifiers. Journal of Medical Imaging, 8 (03). ISSN 2329-4302

[thumbnail of Echo_View_Classification_SPIE.pdf]
Preview
PDF
Echo_View_Classification_SPIE.pdf - Accepted Version

Download (1MB) | Preview

Abstract

Purpose: Echocardiography is the most commonly used modality for assessing the heart in clinical practice. In an echocardiographic exam, an ultrasound probe samples the heart from different orientations and positions, thereby creating different viewpoints for assessing the cardiac function. The determination of the probe viewpoint forms an essential step in automatic echocardiographic image analysis.

Approach: In this study, convolutional neural networks are used for the automated identification of 14 different anatomical echocardiographic views (larger than any previous study) in a dataset of 8732 videos acquired from 374 patients. Differentiable architecture search approach was utilized to design small neural network architectures for rapid inference while maintaining high accuracy. The impact of the image quality and resolution, size of the training dataset, and number of echocardiographic view classes on the efficacy of the models were also investigated.

Results: In contrast to the deeper classification architectures, the proposed models had significantly lower number of trainable parameters (up to 99.9% reduction), achieved comparable classification performance (accuracy 88.4% to 96%, precision 87.8% to 95.2%, recall 87.1% to 95.1%) and real-time performance with inference time per image of 3.6 to 12.6 ms.

Conclusion: Compared with the standard classification neural network architectures, the proposed models are faster and achieve comparable classification performance. They also require less training data. Such models can be used for real-time detection of the standard views.

Item Type: Article
Identifier: 10.1117/1.JMI.8.3.034002
Additional Information: Copyright (2021) Society of Photo‑Optical Instrumentation Engineers (SPIE). One print or electronic copy may be made for personal use only. Systematic reproduction and distribution, duplication of any material in this publication for a fee or for commercial purposes, and modification of the contents of the publication are prohibited. Neda Azarmehr, Xujiong Ye, James P. Howard, Elisabeth S. Lane, Robert Labs, Matthew J. Shun-Shin, Graham D. Cole, Luc Bidaut, Darrel P. Francis, and Massoud Zolgharni, “Neural architecture search of echocardiography view classifiers,” Journal of Medical Imaging 8(3), 034002 (22 June 2021). https://doi.org/10.1117/1.JMI.8.3.034002
Keywords: Data modeling, Echocardiography, Image classification, Image quality, Image resolution, Performance modeling, Surgery, Image processing, Video, Neural networks
Subjects: Computing > Intelligent systems
Related URLs:
Depositing User: Massoud Zolgharni
Date Deposited: 01 Jul 2021 15:05
Last Modified: 06 Feb 2024 16:06
URI: https://repository.uwl.ac.uk/id/eprint/8041

Downloads

Downloads per month over past year

Actions (login required)

View Item View Item

Menu