Goal: To measure real-time improvement in patients with dementia depending on lifestyle changes, transcranial stimulation or avoiding pollution
Data: Neuroimaging representation obtained by EEG and FNIRS daily streaming of elderly people in daily activities
Human resources: 1 PhD student and 1 Postdoctoral researcher
This project considers 3 possible scenarios:
- Low-cost accessible EEG (Muse) and fNIRS (Mendi) devices to be given to patients to acquire long term data in a federated learning scenario.
- The purchase or use of professional EEG and fNIRS devices to be kept by Sano facility to have weekly acquisitions
- The design of a fNIRS device to create a startup around it after the initial clinical trials.
Part 1 and 2 are not identical, as the low cost device will allow long acquisition during the day and the possibility to identify triggers and small changes while they happen in real world. While the expensive professional device will allow the longitudinal acquisitions similar to other modalities as MRI.
Building an fNIRS has enormous financial possibilities as this technology is expected to replace both EEG and fMRI together.
Therefore for all 3 subparts of the project it is required to purchase unexpensive portable EEG/fNIRS (ranging between 100-300 USD) devices. Purchase/rent/borrow a professional fNIRS device (ranging from 30.000-60.000 USD if purchased, otherwise simply rented or borrowed), and purchase component to create a prototype for the built device as a basis for the startup (approximatively 200 USD).
This is the main tool necessary to conduct a project on neuroimaging. It will allow data collection to determine the effectiveness of therapy or assess the impact of SMOG on elderly people through monitoring patients before and after exposure. This will be combined with equipment offered by Jagiellonian University, which is collaborating on this project.
Reference to Research Agenda
This project is connected with the general plan set for Computer Vision Team in Sano Research Agenda in Section 2.3.3 Computer Vision Data Science, particularly through description of Teams’ goals: “These technologies will provide support to radiologists to reach accurate and consistent expert-level decisions or provide a second opinion about a potential pathology in longitudinal imaging data.”