• 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: Ayodeji Ijishakin
Institution: University College London
Department: Computer Science
Proposed Analysis: I will be using data from ADNI in-order to train a state of the art deep generative modelling called a Diffusion model. This model will be able to generate high-resolution brains which look like those of individuals with Alzheimer's disease as well as healthy controls and individuals who have suffered traumatic Brian injury. This generative model will be multi-task, as it will have a generative component and well as a classification component. The utility of a model of this sort is that the classification is based on the similarity of individual brains to a 'prototypical' version of the disease which is learnt by the model. The idea is by learning prototypes you can infer in a data-driven way variants of the diseases which are detectable in MRI. You can also use this approach to understand why neural networks classify one brain image as one disease type over another, because the final prediction is a linear combination of the similarity scores.
Additional Investigators