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: | Rui Camacho |
| Institution: | Faculdade de Engenharia da Universidade do Porto |
| Department: | Department of Informatics Engineering |
| Country: | |
| Proposed Analysis: | My research group develop and work with a flavour of Multi-Relational Data Mining (MRDM) called Inductive Logic Programming (ILP). This technology uses First Order Logic (FOL) to encode both data and models. The use of FOL allows ILP systems to use any kind of knowledge that a domain expert might provide to improve the data analysis (graphs like Metabolic Networks, Ontologies like Gene Ontology and any other types of knowledge that might require complex encoded schemes), and makes the induced models highly comprehensible (models are encode as logical formulae and usually easily translated to English). Using the ADNI data we will test a data mining system that we are developing that is based on ILP and Deep Learning. This MRDM system uses Deep Learning for the medical image analysis and the ILP for the analysis of any other types of data. The system will be able to combine the results of ILP and Deep Learning. We area also working on techniques for extracting intelligible knowledge from Deep Learning models that will improve the comprehensibility of the models that will be constructed by the system. We believe that ADNI data will be an excellent test bed. We are also in the process to establish a collaboration with our university medical school to get advise on extra medical knowledge to provide to the ILP system and assess the usefulness of the system's constructed models. |
| Additional Investigators | |
| Investigator's Name: | Luís Teixeira |
| Proposed Analysis: | Expert in Deep Learning for medical image analysis |
| Investigator's Name: | Mafalda Falcão |
| Proposed Analysis: | Expert in Deep Learning for medical image analysis |
