Classification of Fetal Heart Based on Images Augmentation Using Convolutional Neural Network Method

• Published in: Journal of information systems and informatics (Palembang.Online) Vol. 4; no. 2; pp. 252 - 265
• Main Authors: Roseno, Muhammad Taufik, Syaputra, Hadi
• Format: Journal Article
• Language: English
• Published: Informatics Department, Faculty of Computer Science Bina Darma University 03-06-2022
• Subjects: convolutional neural networks, deep learning, echocardiography, classification
• ISSN: 2656-5935; 2656-4882
• DOI: 10.51519/journalisi.v4i2.247

Standard fetal heart echocardiography view consists of several specific views that can be prolific to optimize the visualization of various structures and anomalies including three vessel and trachea view, right ventricular outflow tract view, four chamber view, left ventricular outflow tract, and right ventricular outflow tract. With the use of current technological developments specifically deep learning, it can classify images from the visualization of the echocardiography point of view obtained. One of the deep learning models that has the best performance in image recognition and classification is the Convolutional Neural Network. Research consists of several stages, namely data collection, data pre-processing, data augmentation, data sharing designing the Convolutional Neural Network model architecture, training, testing, and results. 5 types of echocardiography videos were used based on the echocardiography point of view, resulting in 3,995 images consisting of 3,196 training data and 799 test data. The implementation of convolutional neural networks for the classification of fetal echocardiography images based on point of view obtained good results. The Convolutional Neural Network used consists of 2 convolution layers, 2 layers, 1 flatten layer, 2 dense layers, and 2 Dropout layers. The accuracy rate obtained from the CNN model with a learning rate value of 0.01 and the number of epochs of 50 gets an accuracy value of 98%.