The problem AI-Scan solves

Brain Imaging via magnetic resonance imaging (MRI), is used for evaluation of patients with suspected brain diseases.However in order to reach that stage clinicians and researchers will have to make use of advanced deep learning techniques those can detect the diseases in their early stages. Thus, providing a common platform for doctors all over the world to detect brain tumor, Alzheimer and Parkinson’s.

Challenges we ran into

1. A lot of image preprocessing is required to generate the data to train the model.
2. Models like VGGnet and deeper convolutional networks require high-end graphic accelerated machines to train.
3. Very few datasets available for complex tasks like Alzheimer's prediction. Thus, we obtained lower accuracy due to a lack of a good dataset.
4. Not being able to use the premium version of dependencies, our scope was comparatively limited.