Résumé: Alzheimer disease (AD) is an irreversible neurogenerative disorder which undergoes progressive decline in memory and cognitive function and is characterized by structural brain Magnetic Resonance Images (sMRI). In recent years, sMRI data plays a vital role in the evaluation of brain anatomical changes leads to early detection of AD through deep networks. The existing AD problems such as preprocessing complexity and unreliability are major concern at present. To overcome, a model (FEESCTL) is been proposed with an entropy slicing for feature extraction and Transfer Learning for classification. In the present study, the entropy image slicing method is attempted for selecting the most informative MRI slices during training stages. The ADNI dataset is trained on Transfer Learning adopted by VGG-16 network for classifying the AD with normal individuals. The experimental results reveals that the proposed model have achieved an accuracy level of 93.05%, 86.39%, 92.00% for 2-way classifications (AD/MCI, MCI/CN, AD/CN) and 93.12% for 3-way classification (AD/MCI/CN) respectively, and henceforth the efficiency in diagnosing AD is proved through comparative analysis.

Langue: Anglais