Multi-views Fusion CNN for Left Ventricular Volumes Estimation on Cardiac MR Images

TL;DR

This paper introduces a novel end-to-end CNN approach with multi-view fusion and new preprocessing techniques for accurate left ventricular volume estimation from cardiac MRI images, outperforming existing methods.

Contribution

It presents a new data preprocessing method, a novel CNN architecture, and a multi-view fusion strategy for improved LV volume prediction.

Findings

Outperforms state-of-the-art methods on benchmark datasets.

Achieves high correlation with ground truth in clinical indexes.

Demonstrates potential for large-scale cardiac disease screening.

Abstract

Left ventricular (LV) volumes estimation is a critical procedure for cardiac disease diagnosis. The objective of this paper is to address direct LV volumes prediction task. Methods: In this paper, we propose a direct volumes prediction method based on the end-to-end deep convolutional neural networks (CNN). We study the end-to-end LV volumes prediction method in items of the data preprocessing, networks structure, and multi-views fusion strategy. The main contributions of this paper are the following aspects. First, we propose a new data preprocessing method on cardiac magnetic resonance (CMR). Second, we propose a new networks structure for end-to-end LV volumes estimation. Third, we explore the representational capacity of different slices, and propose a fusion strategy to improve the prediction accuracy. Results: The evaluation results show that the proposed method outperforms other state-of-the-art LV volumes estimation methods on the open accessible benchmark datasets. The clinical indexes derived from the predicted volumes agree well with the ground truth (EDV: R2=0.974, RMSE=9.6ml; ESV: R2=0.976, RMSE=7.1ml; EF: R2=0.828, RMSE =4.71%). Conclusion: Experimental results prove that the proposed method may be useful for LV volumes prediction task. Significance: The proposed method not only has application potential for cardiac diseases screening for large-scale CMR data, but also can be extended to other medical image research fields