FCM-DNN: Diagnosing Coronary Artery Disease by Deep Accuracy Fuzzy C-Means Clustering Model

EasyChair Preprint 6771, version 1

Abstract

Cardiovascular disease is one of the most challenging diseases in middle-aged and older people, which causes high mortality. Coronary Artery Disease (CAD) is known as a common cardiovascular disease. A standard clinical tool for diagnosing CAD is angiography. The main challenge is the dangerous side effects of this tool, which the situation of the disease can worsen. Today, the development of artificial intelligence-based decision-making methods is a valuable achievement for diagnosing clinical images. In this paper, artificial intelligence methods such as Neural Network (NN), Deep Neural Network (DNN), and Fuzzy C-Means clustering combined with Deep Neural Network (FCM-DNN) were developed for diagnosing CAD on Cardiac Magnetic Resonance Imaging (CMRI) dataset. To train the models, 10-fold cross-validation, 7-fold cross-validation, and 5-fold cross-validation techniques were used. As a result, the proposed FCM-DNN model has the best performance regarding the accuracy of 99.91% through the 10-FCV technique compared to the DNN and NN models reaching 99.63% and 92.18%, respectively, on the CMRI dataset. To the best of our knowledge, no studies have been conducted using artificial intelligence methods for CAD diagnosis on the CMRI dataset. The results confirm that the proposed FCM-DNN method can be useful for CAD diagnosis in scientific and research centers.

Keyphrases: Artificial Intelligence, Deep Neural Network, coronary artery disease, fuzzy c-means clustering, image analysis, neural network

@booklet{EasyChair:6771,
  author    = {Javad Hassannataj Joloudari and Hamid Saadatfar and Mohammad Ghasemigol and Roohallah Alizadehsani and Zahra Alizadeh Sani and Fereshteh Hasanzadeh and Edris Hassannataj and Danial Sharifrazi},
  title     = {FCM-DNN: Diagnosing Coronary Artery Disease by Deep Accuracy Fuzzy C-Means Clustering Model},
  howpublished = {EasyChair Preprint 6771},
  year      = {EasyChair, 2021}}