Please use this identifier to cite or link to this item: https://ir.swu.ac.th/jspui/handle/123456789/11921
Title: Alzheimer Screening using Drawing Test Scores
Authors: Khonthapagdee S.
Lownoppakul S.
Chotchoey N.
Wiwatwattana N.
Mongkolluksamee S.
Sa-Ing V.
Keywords: Diagnosis
Image processing
Neurodegenerative diseases
Testing
Alzheimer
Alzheimer's
Alzheimer's disease
Classifier models
Cognitive assessments
Image processing technique
Rule based
Screening tests
Clocks
Issue Date: 2020
Abstract: Screening for Alzheimer's disease is an important step in the effort to detect and inhibit the progress of Alzheimer's disease. The purpose of this research is to develop an application for a clock drawing test which is often seen as a part of the Alzheimer's screening tests such as the Montreal Cognitive Assessment (MoCA) test and the Clock Drawing Test (CDT). For our clock drawing testing, the full score is three points. The first point is from drawing the rounded contour. The second point is from drawing the clock numbers in the correct order. The third point is from drawing the clock hands correctly according to the test command. For the contour drawing and the clock hands drawing, a series of Image Processing techniques are used to check the roundness property of the contour and the shape of the clock hands. MNIST Classifier Model is used to detect the clock numbers and rule-based checking is then employed to give the score. During the evaluation, the application gives a score between 0 and 3 points, and this score is added up with the rest of the application. The results from 50 low-risk people showed that 74 percent of them received 3 points, 22 percent received 2 points and 4 percent received only 1 point. © 2020 IEEE.
URI: https://ir.swu.ac.th/jspui/handle/123456789/11921
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85091887221&doi=10.1109%2fECTI-CON49241.2020.9158244&partnerID=40&md5=34be34b77a8fcf27addafc9871ccdaf4
Appears in Collections:Scopus 1983-2021

Files in This Item:
There are no files associated with this item.


Items in SWU repository are protected by copyright, with all rights reserved, unless otherwise indicated.