Abstract:
Since some progressive MCI patients will develop Alzheimer’s disease, early diagnosis is crucial. A patch-based imaging-fed multi-stream deep convolutional neural network classifies stable and progressive MCI. First, we use a multivariate statistical test to identify anatomical landmarks in Alzheimer’s disease MRIs. The proposed multi-stream convolutional neural network classifies MRI images using patches extracted from landmarks. To compensate for the lack of progressive MCI training data, we train the architecture in a separate scenario using Alzheimer’s disease images, which are anatomically similar to progressive MCI images, and cognitively normal images. Finally, we transfer the trained model weights to the proposed architecture to fine-tune the model using progressive and stable MCI data. Our MCI classification method outperforms others on the ADNI-1 dataset with an F1-score of 85.96%.
Note: Please discuss with our team before submitting this abstract to the college. This Abstract or Synopsis varies based on student project requirements.
Did you like this final year project?
To download this project Code with thesis report and project training... Click Here
