Alzheimer disease detection by 3D MRI analysis
This project focuses on medical imaging and computer vision. The goal is to develop a machine learning model able to detect the state of development of the Alzheimer disease, using 3D MRI data from real patients. In order to do so, we tried different approaches, including the ‘2D epsilon’ method, which is the use of 2D Convolutionnal neural networks on 2D slices of the MRI, and also the use of 3D CNN. We led our analysis on the whole brain, but also tried to only analyze the hippocampus, which is an important brain region in the detection of Alzheimer disease. We also tried to demonstrate the importance of specific brain regions by evaluating our performance on other random regions.
Our training on sick and healthy patients permitted us to apply our models on other persons with an intermediate state of the disease, in order to predict how Alzheimer could evolve in their case. The project has been done in TensorFlow.
- Team size : 3 persons