Lightweight and Interpretable Left Ventricular Ejection Fraction Estimation using Mobile U-Net

TL;DR

This paper introduces a lightweight, interpretable deep learning framework using Mobile U-Net to accurately estimate left ventricular ejection fraction from echocardiogram videos, emphasizing efficiency and clinical relevance.

Contribution

The study develops a novel Mobile U-Net based segmentation and LVEF estimation pipeline that is both interpretable and significantly more efficient than existing methods.

Findings

Achieves comparable accuracy to state-of-the-art methods.

Uses five times fewer parameters and ten times fewer FLOPS.

Demonstrates effectiveness on a large public dataset.

Abstract

Accurate LVEF measurement is important in clinical practice as it identifies patients who may be in need of life-prolonging treatments. This paper presents a deep learning based framework to automatically estimate left ventricular ejection fraction from an entire 4-chamber apical echocardiogram video. The aim of the proposed framework is to provide an interpretable and computationally effective ejection fraction prediction pipeline. A lightweight Mobile U-Net based network is developed to segment the left ventricle in each frame of an echocardiogram video. An unsupervised LVEF estimation algorithm is implemented based on Simpson's mono-plane method. Experimental results on a large public dataset show that our proposed approach achieves comparable accuracy to the state-of-the-art while being significantly more space and time efficient (with 5 times fewer parameters and 10 times fewer FLOPS).