Automated mitral inflow Doppler peak velocity measurement using deep learning

Jevsikov, Jevgeni, Ng, Tiffany, Lane, Elisabeth S., Alajrami, Eman, Naidoo, Preshen, Fernandes, Patricia, Sehmi, Joban S., Alzetani, Maysaa, Demetrescu, Camelia D., Azarmehr, Neda, Serej, Nasim Dadashi, Stowell, Catherine C., Shun-Shin, Matthew J., Francis, Darrel P. and Zolgharni, Massoud (2024) Automated mitral inflow Doppler peak velocity measurement using deep learning. Computers in Biology and Medicine, 171. p. 108192. ISSN 00104825

[thumbnail of 2024-Mitral.pdf]
2024-Mitral.pdf - Published Version
Available under License Creative Commons Attribution.

Download (3MB) | Preview


Doppler echocardiography is a widely utilised non-invasive imaging modality for assessing the functionality
of heart valves, including the mitral valve. Manual assessments of Doppler traces by clinicians introduce
variability, prompting the need for automated solutions. This study introduces an innovative deep learning
model for automated detection of peak velocity measurements from mitral inflow Doppler images, independent
from Electrocardiogram information. A dataset of Doppler images annotated by multiple expert cardiologists
was established, serving as a robust benchmark. The model leverages heatmap regression networks, achieving
96% detection accuracy. The model discrepancy with the expert consensus falls comfortably within the range
of inter- and intra-observer variability in measuring Doppler peak velocities. The dataset and models are
open-source, fostering further research and clinical application.

Item Type: Article
Identifier: 10.1016/j.compbiomed.2024.108192
Keywords: Automated analysis Deep learning Doppler echocardiography Mitral inflow
Subjects: Computing
Depositing User: Massoud Zolgharni
Date Deposited: 04 Mar 2024 15:39
Last Modified: 04 Mar 2024 15:39


Downloads per month over past year

Actions (login required)

View Item View Item