Estimation of mitral valve hinge point coordinates -- deep neural net for echocardiogram segmentation

TL;DR

This paper presents a deep learning approach using a U-Net model to automatically detect mitral valve hinge points in echocardiograms, improving accuracy and automation in cardiac image segmentation.

Contribution

It introduces a fully automatic method combining U-Net segmentation with hinge point extraction, advancing cardiac imaging analysis.

Findings

Median absolute errors: 1.35 mm (x) and 0.75 mm (y)

Effective automatic detection in low-contrast echocardiograms

Improved accuracy over manual or feature-based methods

Abstract

Cardiac image segmentation is a powerful tool in regard to diagnostics and treatment of cardiovascular diseases. Purely feature-based detection of anatomical structures like the mitral valve is a laborious task due to specifically required feature engineering and is especially challenging in echocardiograms, because of their inherently low contrast and blurry boundaries between some anatomical structures. With the publication of further annotated medical datasets and the increase in GPU processing power, deep learning-based methods in medical image segmentation became more feasible in the past years. We propose a fully automatic detection method for mitral valve hinge points, which uses a U-Net based deep neural net to segment cardiac chambers in echocardiograms in a first step, and subsequently extracts the mitral valve hinge points from the resulting segmentations in a second step. Results measured with this automatic detection method were compared to reference coordinate values, which with median absolute hinge point coordinate errors of 1.35 mm for the x- (15-85 percentile range: [0.3 mm; 3.15 mm]) and 0.75 mm for the y- coordinate (15-85 percentile range: [0.15 mm; 1.88 mm]).