A Personalized Computer-Aided Diagnosis System for Mild Cognitive Impairment (MCI) Using Structural MRI (sMRI).
Fatma El-Zahraa A El-Gamal, Mohammed Elmogy, Ali Mahmoud, Ahmed Shalaby, Andrew E Switala, Mohammed Ghazal, Hassan Soliman, Ahmed Atwan, Norah Saleh Alghamdi, Gregory Neal Barnes, Ayman El-Baz
Author Information
Fatma El-Zahraa A El-Gamal: Bioengineering Department, University of Louisville, Louisville, KY 40292, USA. ORCID
Mohammed Elmogy: Information Technology Department, Faculty of Computers and Information, Mansoura University, Mansoura 35516, Egypt. ORCID
Ali Mahmoud: Bioengineering Department, University of Louisville, Louisville, KY 40292, USA. ORCID
Ahmed Shalaby: Bioengineering Department, University of Louisville, Louisville, KY 40292, USA. ORCID
Andrew E Switala: Bioengineering Department, University of Louisville, Louisville, KY 40292, USA.
Mohammed Ghazal: Department of Electrical and Computer Engineering, Abu Dhabi University, Abu Dhabi 59911, United Arab Emirates. ORCID
Hassan Soliman: Information Technology Department, Faculty of Computers and Information, Mansoura University, Mansoura 35516, Egypt.
Ahmed Atwan: Information Technology Department, Faculty of Computers and Information, Mansoura University, Mansoura 35516, Egypt.
Norah Saleh Alghamdi: College of Computer and Information Science, Princess Nourah Bint Abdulrahman University, Riyadh 11564, Saudi Arabia.
Gregory Neal Barnes: Department of Neurology, University of Louisville, Louisville, KY 40292, USA.
Ayman El-Baz: Bioengineering Department, University of Louisville, Louisville, KY 40292, USA. ORCID
Alzheimer's disease (AD) is a neurodegenerative disorder that targets the central nervous system (CNS). Statistics show that more than five million people in America face this disease. Several factors hinder diagnosis at an early stage, in particular, the divergence of 10-15 years between the onset of the underlying neuropathological changes and patients becoming symptomatic. This study surveyed patients with mild cognitive impairment (MCI), who were at risk of conversion to AD, with a local/regional-based computer-aided diagnosis system. The described system allowed for visualization of the disorder's effect on cerebral cortical regions individually. The CAD system consists of four steps: (1) preprocess the scans and extract the cortex, (2) reconstruct the cortex and extract shape-based features, (3) fuse the extracted features, and (4) perform two levels of diagnosis: cortical region-based followed by global. The experimental results showed an encouraging performance of the proposed system when compared with related work, with a maximum accuracy of 86.30%, specificity 88.33%, and sensitivity 84.88%. Behavioral and cognitive correlations identified brain regions involved in language, executive function/cognition, and memory in MCI subjects, which regions are also involved in the neuropathology of AD.
