Title: PSq-Net: parallel SqueezeNet for myocardial infarction detection using echocardiography

Authors: Shamal Bulbule; Shridevi Soma

Addresses: Department of Computer Science and Engineering, Gokaraju Rangaraju Institute of Engineering and Technology, Bachupally, Survey No. 288, Nizampet Rd., Kukatpally, Hyderabad, Telangana 500090, India ' Department of Computer Science and Engineering, Poojya Doddappa Appa College of Engineering, Kalaburagi, Aiwan-E-Shahi Area, Shambhognlli, Karnataka, 585102, India

Abstract: Nowadays, myocardial infarction has become a major cause of sudden and unexpected deaths globally, which is caused by the death of heart muscle cells due to blocked coronary arteries. In this study, parallel SqueezeNet (PSq-Net) is introduced for the detection of myocardial infarction (MI) from echocardiography videos. Initially, the input video is obtained and then, pre-processing the video frames using median and Gaussian filters to eliminate unwanted noise. Next, the left ventricular (LV) wall and endocardial boundary regions are segmented using stack attention U-Net (SAUN). From the segmented endocardial boundary region, the features are extracted using local binary patterns (LBP), local optimal oriented patterns (LOOP), and statistical measures. Finally, myocardial infarction is detected from these features using PSq-Net, and it is the hybridisation of parallel convolutional neural network (PCNN) and SqueezeNet. The PSq-Net demonstrates a high sensitivity of 94.18%, accuracy of 93.09%, and specificity of 93.64%.

Keywords: stack attention U-Net; SAUN; parallel SqueezeNet; SqueezeNet; parallel convolutional neural network; PCNN; median filter.

DOI: 10.1504/IJBET.2025.146414

International Journal of Biomedical Engineering and Technology, 2025 Vol.48 No.1, pp.1 - 26

Received: 06 Jul 2024
Accepted: 30 Sep 2024
Published online: 28 May 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article