Multi-Estimator Full Left Ventricle Quantification through Ensemble Learning

TL;DR

This paper introduces an ensemble learning framework combining CNN-based direct estimation and segmentation modules for accurate left ventricle quantification from cardiac images, demonstrating improved performance on a benchmark dataset.

Contribution

The work presents a novel ensemble approach integrating direct CNN estimation and segmentation with linear regression for robust LV quantification.

Findings

Ensemble model outperforms individual modules on LVQuan18 dataset.

The framework achieves higher accuracy in cardiac parameter estimation.

Preliminary results validate the effectiveness of combining multiple estimation strategies.

Abstract

Cardiovascular disease accounts for 1 in every 4 deaths in United States. Accurate estimation of structural and functional cardiac parameters is crucial for both diagnosis and disease management. In this work, we develop an ensemble learning framework for more accurate and robust left ventricle (LV) quantification. The framework combines two 1st-level modules: direct estimation module and a segmentation module. The direct estimation module utilizes Convolutional Neural Network (CNN) to achieve end-to-end quantification. The CNN is trained by taking 2D cardiac images as input and cardiac parameters as output. The segmentation module utilizes a U-Net architecture for obtaining pixel-wise prediction of the epicardium and endocardium of LV from the background. The binary U-Net output is then analyzed by a separate CNN for estimating the cardiac parameters. We then employ linear regression between the 1st-level predictor and ground truth to learn a 2nd-level predictor that ensembles the results from 1st-level modules for the final estimation. Preliminary results by testing the proposed framework on the LVQuan18 dataset show superior performance of the ensemble learning model over the two base modules.