IoT-Enabled Classification of Echocardiogram Images for Cardiovascular Disease Risk Prediction with Pre-Trained...

Area of Science:

• Medical Image Processing
• Artificial Intelligence in Healthcare
• Cardiovascular Disease Research

Background:

• Cardiovascular diseases are a leading cause of global mortality.
• Early disease identification and timely treatment are critical for improving patient outcomes.
• Advancements in medical image analysis are crucial for healthcare research.

Purpose of the Study:

• To develop an automated system for early identification and risk forecasting of heart disease.
• To leverage deep learning techniques for enhanced medical image classification.
• To improve the accuracy of cardiovascular disease diagnosis through advanced image processing.

Main Methods:

• Utilized Internet of Things (IoT) devices and patient health records alongside echocardiogram images.
• Implemented fuzzy C-means clustering (FCM) for image segmentation.
• Employed a pretrained recurrent neural network (PRCNN) for image classification and risk forecasting.

Main Results:

• The proposed deep learning approach achieved a high accuracy of 99.5% in classifying heart disease.
• The method demonstrated superior performance compared to existing state-of-the-art techniques.
• Successful segmentation and classification of echocardiogram images were performed.

Conclusions:

• The developed system shows significant potential for early and accurate heart disease detection.
• Deep learning models, combined with IoT data, can enhance diagnostic capabilities in cardiovascular medicine.
• This research contributes to advancing AI applications in medical image analysis for critical health concerns.