Convolutional neural networks application in cardiovascular decision support systems

Natalia Konnova; Mikhail Basarab; Michael Khachatryan; Anna Domracheva; Igor Ivanov

doi:10.1117/12.2548193

27 November 2019 Convolutional neural networks application in cardiovascular decision support systems

Natalia Konnova, Mikhail Basarab, Michael Khachatryan, Anna Domracheva, Igor Ivanov

Proceedings Volume 11321, 2019 International Conference on Image and Video Processing, and Artificial Intelligence; 113212D (2019) https://doi.org/10.1117/12.2548193
Event: The Second International Conference on Image, Video Processing and Artifical Intelligence, 2019, Shanghai, China

Abstract

The paper considers the possibilities of using neural network methods of machine learning to diagnose the states of the human cardiovascular system and support decision-making in cardiology and cardiac surgery. The issues of processing and preparation of electrocardiography signals, selection of architecture and tuning of neural network parameters for automation of diagnosis are discussed. Here, the results obtained with the help of multilayer perceptrons and convolutional neural networks to assign the submitted input cardiovascular data to one of the classes of states in the selected space are examined. Based on a specialized developed software, the proprietary numerical experiments with real clinical data were carried out. Given the above results, demonstrating the applicability of the used deep learning methods and algorithms to diagnostic automation, a model of a hierarchical decision support system is proposed.

Citation Download Citation

Natalia Konnova, Mikhail Basarab, Michael Khachatryan, Anna Domracheva, and Igor Ivanov "Convolutional neural networks application in cardiovascular decision support systems", Proc. SPIE 11321, 2019 International Conference on Image and Video Processing, and Artificial Intelligence, 113212D (27 November 2019); https://doi.org/10.1117/12.2548193

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available