×
  • Select the area you would like to search.
  • ACTIVE INVESTIGATIONS Search for current projects using the investigator's name, institution, or keywords.
  • EXPERTS KNOWLEDGE BASE Enter keywords to search a list of questions and answers received and processed by the ADNI team.
  • ADNI PDFS Search any ADNI publication pdf by author, keyword, or PMID. Use an asterisk only to view all pdfs.

Active Investigations

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: Raima Adhikary
Institution: Jahangirnagar University
Department: Information Technology
Country:
Proposed Analysis: Early detection of Alzheimer’s disease (AD) has been in research areas for decades due to Alzheimer’s being the most dangerous form of dementia. Since there is no cure for this disease, the earliest detection of AD is one of the most important tasks. Research works using various diagnostic tools such as structural MRI, functional MRI, FDG-PET, CT scan have been used for detecting or classifying Alzheimer patient. Thus, the very limited information extracted from single or multiple diagnostic tools play a vital part. With this limitation in mind, this research work aims to extract feature related information from singular modality as much as possible and apply deep learning and machine learning networks in order to classify between the stages of Alzheimer’s Disease. In this research, structural magnetic resonance data has been selected for binary and multiclass classification task. Voxel based image pre-processing and partial voxel segmentation (GM-WM) of sMRI data are to be implemented using cat12 and SPM12 integrated toolkit. Feature concatenation as well as classification networks are built using VGG-16 and residual network with depth-wise separable convolution in order to separate AD patients from cognitively normal and mildly cognitively normal subjects. On the pre-processed and segmented data, an estimation of total intracranial volume and relative volume of (GM-WM-CSF) has been included with the imaging feature in order to add more information. Using these features, the Ensemble net of previously mentioned classifiers is expected to learn the inter-relation between imaging data with respect to volumetric data and help in distinguishing the difference of AD patients with the normal and mild cognitively impaired.
Additional Investigators