TY - GEN
T1 - Predicting the diagnosis of dementia from MRI data
T2 - 7th International Conference on Arab Women in Computing, ArabWIC 2021
AU - Habuza, Tetiana
AU - Zaki, Nazar
AU - Statsenko, Yauhen
AU - Alnajjar, Fady
AU - Elyassami, Sanaa
N1 - Funding Information:
The authors would like to acknowledge the College of Information Technology; United Arab Emirates University for for the support provided and the facilities used for conducting this research.
Publisher Copyright:
© 2021 Association for Computing Machinery.
PY - 2021/8/25
Y1 - 2021/8/25
N2 - Neuroimaging data may reflect the mental status of both cognitively preserved individuals and patients with neurodegenerative diseases. To find the relationship between cognitive performance and the difference between predicted and observed functional test results, we developed a Convolutional Neural Network (CNN) based regression model to estimate the level of cognitive decline from preprocessed T1-weighted MRI images. In this study, we considered the Predicted Cognitive Gap (PCG) as the measure to accurately segregate Cognitively Normal (CN) versus Alzheimer disease (AD) subjects. The proposed model was tested on a dataset that includes 422 CN and 377 AD cases. The performance of the proposed solution was measured using Receiver Operating Characteristic (ROC) Area Under the Curve (AUC) and achieved 0.987 (ADAS-cog), 0.978 (MMSE), 0.898 (RAVLT), 0.848 (TMT), 0.829 (DSST) for averaged brain images; and 0.985 (ADAS-cog), 0.987 (MMSE), 0.901 (RAVLT), 0.8474 (TMT), 0.796 (DSST) for middle slice skull stripped brain images. The results achieved indicate that PCG can accurately separate healthy subjects from demented ones. The structure of the brain contributes to the level of human cognition and their functional abilities. Proposed PCG may aid in diagnostics of dementia.
AB - Neuroimaging data may reflect the mental status of both cognitively preserved individuals and patients with neurodegenerative diseases. To find the relationship between cognitive performance and the difference between predicted and observed functional test results, we developed a Convolutional Neural Network (CNN) based regression model to estimate the level of cognitive decline from preprocessed T1-weighted MRI images. In this study, we considered the Predicted Cognitive Gap (PCG) as the measure to accurately segregate Cognitively Normal (CN) versus Alzheimer disease (AD) subjects. The proposed model was tested on a dataset that includes 422 CN and 377 AD cases. The performance of the proposed solution was measured using Receiver Operating Characteristic (ROC) Area Under the Curve (AUC) and achieved 0.987 (ADAS-cog), 0.978 (MMSE), 0.898 (RAVLT), 0.848 (TMT), 0.829 (DSST) for averaged brain images; and 0.985 (ADAS-cog), 0.987 (MMSE), 0.901 (RAVLT), 0.8474 (TMT), 0.796 (DSST) for middle slice skull stripped brain images. The results achieved indicate that PCG can accurately separate healthy subjects from demented ones. The structure of the brain contributes to the level of human cognition and their functional abilities. Proposed PCG may aid in diagnostics of dementia.
KW - Aging
KW - Alzheimer's disease
KW - Cognitive decline
KW - Convolutional Neural Network
KW - Dementia
KW - Predicted Cognitive Gap marker
UR - http://www.scopus.com/inward/record.url?scp=85121550091&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85121550091&partnerID=8YFLogxK
U2 - 10.1145/3485557.3485564
DO - 10.1145/3485557.3485564
M3 - Conference contribution
AN - SCOPUS:85121550091
T3 - ACM International Conference Proceeding Series
BT - Proceedings of the 7th International Conference on Arab Women in Computing, ArabWIC 2021
PB - Association for Computing Machinery
Y2 - 25 August 2021
ER -
