Markov model combined with MR diffusion tensor imaging for predicting the onset of Alzheimer’s disease

Abstract

Abstract Alzheimer’s disease (AD) affects cognition, behavior, and memory of brain. It causes 60–80% of dementia cases. Cross-sectional imaging investigations of AD show that magnetic resonance (MR) with diffusion tensor image (DTI)-detected lesion locations in AD patients are heterogeneous and distributed across the imaging area. This study suggested that Markov model (MM) combined with MR-DTI (MM + MR-DTI) was offered as a method for predicting the onset of AD. In 120 subjects (normal controls [NCs], amnestic mild cognitive impairment [aMCI] patients, and AD patients) from a discovery dataset and 122 subjects (NCs, aMCI, and AD) from a replicated dataset, we used them to evaluate the white matter (WM) integrity and abnormalities. We did this by using automated fiber quantification, which allowed us to identify 20 central WM tracts. Point-wise alterations in WM tracts were shown using discovery and replication datasets. The statistical analysis revealed a substantial correlation between microstructural WM alterations and output in the patient groups and cognitive performance, suggesting that this may be a potential biomarker for AD. The MR-based classifier demonstrated the following performance levels for the basis classifiers, with DTI achieving the lowest performance. The following outcomes were seen in MM + MR-DTI using multimodal techniques when combining two modalities. Finally, a combination of every imaging method produced results with an accuracy of 98%, a specificity of 97%, and a sensitivity of 99%. In summary, DTI performs better when paired with structural MR, despite its relatively weak performance when used alone. These findings support the idea that WM modifications play a significant role in AD.