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: | Bjørn Jensen |
Institution: | University of Glasgow |
Department: | School of Computing Science |
Country: | |
Proposed Analysis: | The proposed research aims at investigating the robustness of Deep Learning in the diagnosis of Alzheimer’s disease and identifying distinct brain atrophy patterns. The first study will make use of 3D MRI scans, which will parse pre-processed scans into a Deep Learning algorithm, specifically, variations of Convolutional Neural Networks (CNNs) used to predict the likelihood of developing the disease. The study will be a close replication of the Xiu et al., 2018 (https://doi.org/10.1016/j.neucom.2018.11.111) albeit focusing specifically on the robustness and interpretability of the results. - The first step, consisting of image preprocessing, will be carried out using Statistical Parametric Mapping software package (https://www.fil.ion.ucl.ac.uk/spm/), and the DPAB toolbox (http://rfmri.org/dpabi). - In the second step, different variations of CNN models (similar to LeNet) will be trained on the preprocessed images, learning the features that will be used to predict the diagnosis of unseen MRI scans. The outputs from the different CNN might be elaborated a step further, using clustering, to produce more meaningful results. The accuracy of the models will then be compared to find the best performing model. In your second study, we will investigate the use of Deep Learning to identify distinct brain atrophy patterns, allowing a) the identification and b) classification in distinct Alzheimer’s Disease subtypes (leveraging results from https://www.nature.com/articles/srep46263). We will apply similar computational methods as in our first study augmented with clustering methods. |
Additional Investigators | |
Investigator's Name: | Martina Cocco |
Proposed Analysis: | Same as PI (part of the student's final year project) |