EigenHearts: Cardiac Diseases Classification Using EigenFaces Approach

TL;DR

This paper applies the EigenFaces method, adapted as EigenHearts, combined with CNNs to improve cardiac disease classification accuracy from echocardiography images, demonstrating a 50% accuracy boost.

Contribution

It introduces EigenHearts, a novel preprocessing technique using eigenvector analysis to enhance CNN-based cardiac disease classification from echocardiography images.

Findings

EigenHearts preprocessing improves classification accuracy by ~50%.

Combining EigenHearts with CNNs outperforms using raw images.

EigenHearts effectively reduce data complexity for better classification.

Abstract

In the realm of cardiovascular medicine, medical imaging plays a crucial role in accurately classifying cardiac diseases and making precise diagnoses. However, the field faces significant challenges when integrating data science techniques, as a significant volume of images is required for these techniques. As a consequence, it is necessary to investigate different avenues to overcome this challenge. In this contribution, we offer an innovative tool to conquer this limitation. In particular, we delve into the application of a well recognized method known as the EigenFaces approach to classify cardiac diseases. This approach was originally motivated for efficiently representing pictures of faces using principal component analysis, which provides a set of eigenvectors (aka eigenfaces), explaining the variation between face images. As this approach proven to be efficient for face recognition, it motivated us to explore its efficiency on more complicated data bases. In particular, we integrate this approach, with convolutional neural networks (CNNs) to classify echocardiography images taken from mice in five distinct cardiac conditions (healthy, diabetic cardiomyopathy, myocardial infarction, obesity and TAC hypertension). Performing a preprocessing step inspired from the eigenfaces approach on the echocardiography datasets, yields sets of pod modes, which we will call eigenhearts. To demonstrate the proposed approach, we compare two testcases: (i) supplying the CNN with the original images directly, (ii) supplying the CNN with images projected into the obtained pod modes. The results show a substantial and noteworthy enhancement when employing SVD for pre-processing, with classification accuracy increasing by approximately 50%.