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: | Alex Jerves |
| Institution: | Fundación INSPIRE |
| Department: | Research |
| Country: | |
| Proposed Analysis: | We won the Cedia-CEPRA 2021 with the project "Morphological characterization of the hippocampus using artificial intelligence: a first databse in Ecuador". Our objective is to obtain the hippocampi's morphological parameters using computational geometry and image processing algorithms. We use manually traced MRI of Ecuadorian patients, ranged from 18 to 90 ages, obtained from a local imaging center's database. Furthermore, as part of the project, we are also using the MRIs to train a Convolutional Neural Network (CNN) that automatically segments the hippocampus from the images, calculating its morphological parameters and comparing them with the results from the manual traces. To evaluate the performance and scope of our CNN, it is of our interest to use more information as testing data, aside from the images that were already used for training. |
| Additional Investigators | |
| Investigator's Name: | Stefano Buitrón |
| Proposed Analysis: | I'm in charge of implementing the image processing algorithms to obtain a 3D level set-based representation of the hippocampus, also using the computational geometry algorithms to calculate its morphological parameters such as volume, sphericity, roundness, diameter, surface, etc. I'm also responsible of the convolutional neural network's architecture, using the semantic segmentation technique in order to train the CNN to automatically segment the hippocampus from MRI images. As part of the process, I'm interested in evaluate the CNN's scope, needing more MRI images to test the CNN and measure its capabilities. |
