Enhancing Mild Cognitive Impairment Detection through Efficient Magnetic Resonance Image Analysis.

Neuroimaging has emerged over the last few decades as a crucial tool in diagnosing Alzheimer's disease (AD). Mild cognitive impairment (MCI) is a condition that falls between the spectrum of normal cognitive function and AD. However, previous studies have mainly used handcrafted features to classify MCI, AD, and normal control (NC) individuals. This paper focuses on using gray matter (GM) scans obtained through magnetic resonance imaging (MRI) for the diagnosis of individuals with MCI, AD, and NC. To improve classification performance, we developed two transfer learning strategies with data augmentation (i.e. shear range, rotation, zoom range, channel shift). The first approach is a deep Siamese network (DSN), and the second approach involves using a cross-domain strategy with customized VGG-16. We performed experiments on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset to evaluate the performance of our proposed models. Our experimental results demonstrate superior performance in classifying the three binary classification tasks: NC vs. AD, NC vs. MCI, and MCI vs. AD. Specifically, we achieved a classification accuracy of 97.68%, 94.25%, and 92.18% for the three cases, respectively. Our study proposes two transfer learning strategies with data augmentation to accurately diagnose MCI, AD, and normal control individuals using GM scans. Our findings provide promising results for future research and clinical applications in the early detection and diagnosis of AD. [ABSTRACT FROM AUTHOR]