Home // INTELLI 2022, The Eleventh International Conference on Intelligent Systems and Applications // View article

Applying Deep Learning Techniques in Automated Analysis of Echocardiograms, CMRs and Phonocardiograms for the Detection and Localization of Cardiac Diseases

Authors:
Arvind Bansal
Racheal Mukisa

Keywords: Artificial Intelligence; CMR; deep learning; echocardiogram; heart diseases; machine learning; Phonocardiogram

Abstract:
Echocardiography (echoCG), Cardiac Magnetic Resonance (CMR) and phonocardiograms (PCG) are becoming indispensable tools in the diagnostics and management of cardiac diseases due to advancements in imaging techniques, improvement in processing power, availability of large multimedia databases in Electronic Medical Records (EMR) and rapid lowering of cost. Image-based and video-based data in echoCG and CMR are multi-dimensional and exceed the capabilities of traditional statistical learning. Deep learning technologies provide new possibilities for accurate, consistent and automated interpretation of echoCG, CMR, and PCG, reducing the risk of human error. Deep learning and signal analysis techniques are being applied to analyze these complex data for improved diagnosis of cardiac diseases involving heart muscles, valvular defects, cardiac chamber deformities negatively affecting blood-oxygenation and blood-flow. This review describes applications of deep learning techniques, such as Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Long Short-term Memory Neural Network (LSTM), transfer learning, and their variations in enhancing the classification of heart diseases from echoCG, CMR and PCG.

Pages: 36 to 42

Copyright: Copyright (c) IARIA, 2022

Publication date: May 22, 2022

Published in: conference

ISSN: 2308-4065

ISBN: 978-1-61208-977-5

Location: Venice, Italy

Dates: from May 22, 2022 to May 26, 2022