In recent times, accurate and early diagnosis of Alzheimer's disease (AD) plays a vital role in patient care and further treatment. Predicting AD from mild cognitive impairment (MCI) and cognitive normal (CN) has become popular. Neuroimaging and computer‐aided diagnosis techniques are used for classification of AD by physicians in the early stage. Most of the previous machine learning techniques work on handpicked features. In the recent days, deep learning has been applied for many medical image applications. Existing deep learning systems work on raw magnetic resonance imaging (MRI) images and cortical surface as an input to the convolution neural network (CNN) to perform classification of AD. AD affects the brain volume and changes the gray matter texture. In our work, we used 1820 T2‐weighted brain magnetic resonance volumes including 635 AD MRIs, 548 MCI MRIs, and 637 CN MRIs, sliced into 18,017 voxels. We proposed an approach to extract the gray matter from brain voxels and perform the classification using the CNN. A Gaussian filter is used to enhance the voxels, and skull stripping algorithm is used to remove the irrelevant tissues from enhanced voxels. Then, those voxels are segmented by hybrid enhanced independent component analysis. Segmented gray matter is used as an input to the CNN. We performed clinical valuation using our proposed approach and achieved 90.47% accuracy, 86.66% of recall, and 92.59% precision.
Diagnosing Alzheimer's disease at early stage required an effective classification mechanism to differentiate mild cognitive impairment from cognitive normal and AD. In this paper, we used data set collected from ADNI and OASIS. Instead of using the whole volume of the MRI, high informative slices are selected using entropy. The selected slices are pre-processed by removing unwanted tissues using skull stripping algorithm and extracted gray matter using EICA. In this work, we used CNN model with inception blocks to extract deep features from the GM slices used to predict AD at early stage. The model avoids data leakage by considering all the slices of an MRI as a unit. The model trained with 80% of ADNI subject MRI volumes and tested with the remaining 20% subject MRI volumes, to provide great variance in training and testing data, the model further tested with OASIS data sets. 10-fold cross-validation is used to test the model without biasing. The model performance is evaluated using accuracy. The model achieves 98.73%, 100%, 93.72%, and 95.6% of accuracy for differentiating CN-MCI, CN-AD, AD-MCI and CN-MCI and AD. At 10-fold cross-validation it gives 92.92 ± 3%, 98 ± 2%, 90 ± 4% and 94.9 ± 2% accuracy to differentiate CN-MCI, CN-AD, AD-MCI, and CN-MCI-AD using ADNI. We further tested the model with 135 MRI volumes selected from OASIS data set, we achieved 92%, 91.76%, 88.23%, 81.48% of accuracy with CN-AD, MCI-AD, CN-MCI, and three-way classification. The model gives good accuracy and sensitivity of early AD Diagnosis.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.