Analysis of Fornix in Structural MR Images of Mild Cognitive Impairment and Alzheimer’s Disease Conditions Using Multifractal Detrended Moving Average Algorithm

Analyzing Alzheimer’s disease (AD) and mild cognitive impairment (MCI) is crucial for early diagnosis and intervention. AD is the most common form of dementia and is characterized by a progressive decline in cognitive abilities, behavioral functions and memory. Analyzing the texture of the fornix can offer valuable insights for diagnosing MCI and AD. In this study, the fornix structure is segmented, and multifractal spectral features are analyzed for texture changes to distinguish between MCI and AD conditions. The images obtained from a public domain database undergo pre-processing steps such as removal of non-brain tissues, including skull stripping, spatial registration and contrast enhancement. Further, the fornix structure is delineated from the pre-processed images using the FreeSurfer pipeline. The slice image with the maximum area is selected for analysis. Subsequently, the 2-dimensional images are converted into a representative 1-dimensional using the Euclidean distance approach. The mass exponent, fluctuation function and generalized Hurst exponent are evaluated using the multifractal detrended moving average (MFDMA) algorithm in order to analyze the multifractal features of the fornix structure. The multifractal spectrum is used to generate characteristics that aid in differentiating between MCI and AD conditions. The results demonstrate that the FreeSurfer pipeline effectively segments the fornix structure in all considered images. The mass exponent shows a nonlinear trend, while the generalized Hurst exponent decreases with order, and the fluctuation function exhibits a linear relationship with scale, highlighting the multifractal nature of the fornix region. The singularity spectral features, such as the minimum Hölder exponent, strength of multifractality and singularity strength, are most effective in distinguishing between normal cognitive (NC) versus MCI and NC versus AD in subject groups. Multifractal analysis appears to be effective in assessing the progressive changes associated with MCI and AD conditions. Therefore, the proposed approach is effective for the early diagnosis of neurocognitive conditions.