• 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.
Principal Investigator  
Principal Investigator's Name: Haixing Dai
Institution: University of Georgia
Department: Computer Science
Proposed Analysis: Introduction: Importance of an accurate graph for GCN, and in general, all graph-based analysis, covering: • Our hypothesis and observation that there exists a better graph (lower-dimensional manifold), comparing with a correlation-derived graph, where the imaging data resides on, that can lead to better representation of imaging data (in our case, PET in AD classification). • Our approach: searching a better graph based on GCN • Previous work on graph discovery from imaging (e.g., Bayesian network, partial correlation, etc.) • Previous work on optimization of a process, where we are using a greedy approach (e.g., dynamic programing, reinforcement learning) • Previous work on the importance of thresholding for brain networks study • Previous work on GCN application in medical imaging
Additional Investigators