Personalized Computer-Aided Diagnosis for Mild Cognitive Impairment in Alzheimer’s Disease Based on sMRI and ¹¹C PiB-PET Analysis

摘要: Alzheimer’s disease (AD) is a neurodegenerative condition that affects the central nervous system and represents 60% to 70% of all dementia cases. Due an increased aging population, number patients diagnosed with AD expected exceed 131 million worldwide by 2050. The characterized various clinical symptoms pathological features define three main sequential decline stages, namely, early/mild, intermediate/moderate late/severe stages. Although it considered irreversible, early diagnosis highly desirable help preserve cognitive function. However, difficult due different factors, including patient-specific development AD. contribution proposed work present personalized (i.e., local/brain regional) computer-aided (CAD) for from two perspectives, functional structural assist diagnosis. In other words, uniquely yields local/regional combining 11C PiB positron emission tomography (11C PET), which provides diagnosis, magnetic resonance imaging (sMRI), To best our knowledge, this first combine sMRI PET processes modalities through steps: pre-processing, brain labeling (parcellation), feature extraction, A presented each modality separately, followed final global obtained integrating results modalities. Evaluation shows average 97.5%, 100%, 96.77% accuracy, specificity, sensitivity, respectively. With further development, envisioned could contribute in setting.