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: | Sara Colantonio |
Institution: | National Research Council of Italy |
Department: | Institute of Information Science and Technologies |
Country: | |
Proposed Analysis: | The purpose of our research is to investigate the feasibility of automatic AI-driven classification of AD and MCI with respect of normal control. One of the major issues of AI models applied to medical images is their black-box nature and therefore the possible lack of trust by physicians. Recent advances in the literature suggest that explainable models are available and could be adopted to overcome this limitation. Moreover, another frequently arising problem in this field is the performance drop due to dataset-shift. This can arise when trained models are deployed in different institutions possibly with different scanners. We plan to carry out our analysis by means of Convolutional Neural Networks (CNNs), but by leveraging the explaining capabilities featured by the ProtoPNet architecture. In addition, a modified version of ProtoPNet will be designed and implemented to address the dataset-shift issue and to provide the user with causality-based explanations. |
Additional Investigators | |
Investigator's Name: | Gianluca Carloni |
Proposed Analysis: | Ph.D. student at Pisa University and research fellow at ISTI-CNR. The analysis will be the same as for the principal investigator. |
Investigator's Name: | Andrea Berti |
Proposed Analysis: | Ph.D. student at Pisa University and research fellow at ISTI-CNR. The analysis will be the same as for the principal investigator. |