Influence of Loss Function on Left Ventricular Volume and Ejection Fraction Estimation in Deep Neural Networks

Naidoo, Preshen, Alajrami, Eman I, Lane, Elisabeth Sarah, Jevsikov, Jevgeni, Shun-shin, Matthew J, Francis, Darrel P and Zolgharni, Massoud (2022) Influence of Loss Function on Left Ventricular Volume and Ejection Fraction Estimation in Deep Neural Networks. In: Medical Imaging with Deep Learning, 6 – 8 July 2022, Zurich, Switzerland.

[thumbnail of PDF/A]
Preview
PDF (PDF/A)
A.influence_of_loss_function_on_.pdf - Accepted Version
Available under License Creative Commons Attribution.

Download (109kB) | Preview

Abstract

Quantification of the left ventricle shape is crucial in evaluating cardiac function from 2D echocardiographic images. This study investigates the applicability of established loss
functions when optimising the U-Net model for 2D echocardiographic left ventricular segmentation. Our results indicate loss functions are a significant component for optimal left ventricle volume measurements when established segmentation metrics could be imperceptible.

Item Type: Conference or Workshop Item (Paper)
Keywords: Echocardiography; Left Ventricle Segmentation; Deep learning
Subjects: Computing > Intelligent systems
Depositing User: Massoud Zolgharni
Date Deposited: 22 Sep 2023 08:44
Last Modified: 04 Nov 2024 12:23
URI: https://repository.uwl.ac.uk/id/eprint/9076

Downloads

Downloads per month over past year

Actions (login required)

View Item View Item

Menu