×
  • 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: Linda Shapiro
Institution: University of Washington
Department: Computer Science and Engineering
Country:
Proposed Analysis: n our project, we plan to use the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset that combines many selective biomarkers together for a population of ~1600 participants aged between 55-91 with an aim to detect Alzheimer's Disease (AD). Our aim is to detect the Mild Cognitive Impairment and early AD stages by fusing different modalities such as MRI, PET, genetics, and demographics. We are planning to contribute to the field in three distinct ways: First, we will work on an end-to-end model that incorporates these different modalities in a meaningful way. Second, instead of using a small 'related' Single-nucleotide polymorphisms (SNP) subset, we will develop a model that non-linearly embeds a whole SNP sequence into a lower-dimensional vector by exploiting the pre-known related gene information. Lastly, the current state of the art of artificial learning is struggling to infer correlations between distant genes, so we argue that instead of representing the SNP data as a sequence, it may be useful to represent in the form of a grid-like structure that contains the gene interrelations.
Additional Investigators  
Investigator's Name: Su-In Lee
Proposed Analysis: Analysis of the SNP data and gene exoression data to find correlations with the image data.
Investigator's Name: Sheng Wang
Proposed Analysis: Integrating SNP data in the visual model
Investigator's Name: Nicholas Nuechterlein
Proposed Analysis: MRI analysis and usage of sota imaging algorithms
Investigator's Name: Pranav Kamath
Proposed Analysis: Will help to implement dataloaders and helper functions
Investigator's Name: Mehmet Saygin Seyfioglu
Proposed Analysis: Working on the integration of multi-modality data
Investigator's Name: Zucks Lui
Proposed Analysis: Will work on multi modal transformers
Investigator's Name: Sadjyot Gangolli
Proposed Analysis: Will work on imaging modalities
Investigator's Name: Dylan Geva
Proposed Analysis: Visualization
Investigator's Name: Roy Seo
Proposed Analysis: Research on data augmentation techniques for structural MRI