Share Email Print
cover

Proceedings Paper • new

Designing lightweight deep learning models for echocardiography view classification
Author(s): Hooman Vaseli; Zhibin Liao; Amir H. Abdi; Hany Girgis; Delaram Behnami; Christina Luong; Fatemeh Taheri Dezaki; Neeraj Dhungel; Robert Rohling; Ken Gin; Purang Abolmaesumi; Teresa Tsang
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Transthoracic echocardiography (echo) is the most common imaging modality for diagnosis of cardiac conditions. Echo is acquired from a multitude of views, each of which distinctly highlights specific regions of the heart anatomy. In this paper, we present an approach based on knowledge distillation to obtain a highly accurate lightweight deep learning model for classification of 12 standard echocardiography views. The knowledge of several deep learning architectures based on the three common state-of-the-art architectures, VGG-16, DenseNet, and Resnet, are distilled to train a set of lightweight models. Networks were developed and evaluated using a dataset of 16,612 echo cines obtained from 3,151 unique patients across several ultrasound imaging machines. The best accuracy of 89.0% is achieved by an ensemble of the three very deep models while we show an ensemble of lightweight models has a comparable accuracy of 88.1%. The lightweight models have approximately 1% of the very deep model parameters and are six times faster in run-time. Such lightweight view classification models could be used to build fast mobile applications for real-time point-of-care ultrasound diagnosis.

Paper Details

Date Published: 8 March 2019
PDF: 7 pages
Proc. SPIE 10951, Medical Imaging 2019: Image-Guided Procedures, Robotic Interventions, and Modeling, 109510F (8 March 2019); doi: 10.1117/12.2512913
Show Author Affiliations
Hooman Vaseli, The Univ. of British Columbia (Canada)
Zhibin Liao, The Univ. of British Columbia (Canada)
Amir H. Abdi, The Univ. of British Columbia (Canada)
Hany Girgis, The Univ. of British Columbia (Canada)
Vancouver General Hospital (Canada)
Delaram Behnami, The Univ. of British Columbia (Canada)
Christina Luong, Vancouver General Hospital (Canada)
Fatemeh Taheri Dezaki, The Univ. of British Columbia (Canada)
Neeraj Dhungel, The Univ. of British Columbia (Canada)
Robert Rohling, The Univ. of British Columbia (Canada)
Ken Gin, The Univ. of British Columbia (Canada)
Vancouver General Hospital (Canada)
Purang Abolmaesumi, The Univ. of British Columbia (Canada)
Teresa Tsang, The Univ. of British Columbia (Canada)
Vancouver General Hospital (Canada)


Published in SPIE Proceedings Vol. 10951:
Medical Imaging 2019: Image-Guided Procedures, Robotic Interventions, and Modeling
Baowei Fei; Cristian A. Linte, Editor(s)

© SPIE. Terms of Use
Back to Top