Open AccessUsing K-Means Algorithm and Convolutional Neural Networks to Identify Alzheimer’s Disease in Coronal Brain Scans
Author(s) -
Hanquan Qiao
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1802/3/032050
Subject(s) - convolutional neural network , computer science , artificial intelligence , data set , set (abstract data type) , coronal plane , pattern recognition (psychology) , artificial neural network , convolution (computer science) , bitmap , neuroimaging , disease , medicine , pathology , psychology , radiology , neuroscience , programming language
Accurate diagnosis of Alzheimer’s Disease (AD) is of great importance to patient care, especially in the early stage, because it enables patients to take preventive measures before irreversible brain damage occurs. Obviously, if computer-based diagnostic models can make better predictions than doctors, the future of health care will change dramatically from the current system. Based on magnetic resonance imaging (MRI), this paper realizes a classification algorithm to distinguish AD patients from normal people. OASIS Brain Imaging Data Set is an open source online data set, which is a coronal bitmap of the human brain. Canny edge detection algorithm is used to extract image information, and K-Means and convolution neural network (CNN) are used to train the data set. The results show that the recognition accuracy of the training set is 99%, and 26% higher than that of the K-Means algorithm, which can be effectively used in the early diagnosis of Alzheimer’s disease.