There are many active research projects accessing and applying shared ADNI data. Use the search above to find specific research focuses on the active ADNI investigations. This information is requested annually as a requirement for data access.
Principal Investigator | |
Principal Investigator's Name: | Benjamin Lambert |
Institution: | Pixyl Medical |
Department: | Deep learning |
Country: | |
Proposed Analysis: | We propose to study anomaly detection in brain MRI using Deep Learning. Our method is based on the unsupervised training of a Variational Autoencoder. We train the network to reconstruct healthy brain FLAIR scans to learn the distribution of healthy subjects. Anomalies are then detected as outliers of the distribution. For this work, a dataset of healthy patient is needed, therefore we propose to use FLAIR scans from the Control Normal group of the ADNI database (< 50 scans). Anomaly detection will then be tested on a private dataset composed of Multiple-Sclerosis patients. Results will be presented in a short paper. |
Additional Investigators |