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: | Ben Sinclair |
Institution: | Monash University |
Department: | Department of Neuroscience |
Country: | |
Proposed Analysis: | We propose to train a deep learning algorithm on AIBL, ADNI and ADNIDOD data to segment perivascular spaces (PVS) on T1 images. Perivascular spaces are fluid filled spaces surrounding the blood vessels in the brain, hypothesised have a central role in waste clearance, including amyloid and tau. Pathological enlargement of these spaces (ePVS), and their subsequent visibility on MRI, is indicative of reduced flow through the PVSs. Characterisation of these spaces is time consuming, and their is a strong need for accurate automated segmentation algorithms. In order to make our deep learning algorithms generalisable to new data sets, we seek to train the models on a diverse range of data, hence our application to access all three data sets. Once the deep learning algorithm is developed we will measure the association between PVS load and amyloid and tau levels, hypothesising that higher ePVS load is asscoiated with higher amyloid and tau levels. Where available we will also seek to associate ePVS load with measures of physical activity levels and physical fitness levels, hypothesising that higher activity in the ageing/dementia population is associated with lower ePVS load. This work will be driven by Meng Law, Terence O'Brien, Ben Sinclair and Lucy Vivash of Monash Univeristy and Alfred Hospital. |
Additional Investigators | |
Investigator's Name: | Debabrata Mishra |
Proposed Analysis: | We propose to train a deep learning algorithm on AIBL, ADNI and ADNIDOD data to segment perivascular spaces (PVS) on T1 images. Perivascular spaces are fluid filled spaces surrounding the blood vessels in the brain, hypothesised have a central role in waste clearance, including amyloid and tau. Pathological enlargement of these spaces (ePVS), and their subsequent visibility on MRI, is indicative of reduced flow through the PVSs. Characterisation of these spaces is time consuming, and their is a strong need for accurate automated segmentation algorithms. In order to make our deep learning algorithms generalisable to new data sets, we seek to train the models on a diverse range of data, hence our application to access all three data sets. Once the deep learning algorithm is developed we will measure the association between PVS load and amyloid and tau levels, hypothesising that higher ePVS load is asscoiated with higher amyloid and tau levels. Where available we will also seek to associate ePVS load with measures of physical activity levels and physical fitness levels, hypothesising that higher activity in the ageing/dementia population is associated with lower ePVS load. This work will be driven by Meng Law, Terence O'Brien, Ben Sinclair and Lucy Vivash of Monash Univeristy and Alfred Hospital. |