Home About Login Current Archives Announcements Editorial Board
Submit Now For Authors Call for Submissions Statistics Contact
Home > Archives > Volume 20, No 8 (2022) > Article

DOI: 10.14704/nq.2022.20.8.NQ44538

Classification of Alzheimer’s disease Using DBN, SVM and Random Forest Models

M.Rajendiran, Dr.K.P. Sanal Kumar, Dr.S.Anu H Nair


In Alzheimer's disease detection, the early detection of morphological differences is challenging to provide pre-treatment. MRI imaging technique is utilised to detect the severity level of AD in patients. Hence, by analysing hippocampus volume using magnetic resonance imaging (MRI), the AD disease level can detect. Measuring hippocampus volume requires a great deal of time and is not feasible for manual segmentation [1]. Automatic segmentation is required to bypass these restrictions and obtain the AD biomarkers. MRI is widely preferred for obtaining detailed structural brain images in three dimensions (3-D). In this imaging technique, vivo voxel dimensions of certain structures influenced by disease progressions can be obtained. Structural MRI is broadly accessible, provides better accuracy of diagnosis and has reasonable costs. Furthermore, MRIs indicate higher associations with the progression of mild cognitive impairments (MCI) to AD. However, the dissimilarities between progressive MCI (pMCI) and stable MCI (sMCI) are too minute to be discovered via MRI. This refined dissimilarity has emerged from huge inter subject inconsistencies and age-linked deviations. Hence, predicting MCI-to-AD conversion by MRI scanning is an arduous task. In the current comprehensive literature, the particle swarm optimisation-based fuzzy c-means technique has been appraised for segmenting the brain region. This process utilised a limited number of validation parameters to validate the segmentation accuracy.


Alzheimer, Detection, Classification, Histogram Normalization

Full Text