Stanford University is looking to solve the problem of decoding the heterogeneity of Alzheimer’s disease (AD) and modeling the disease progression through innovative methods for integrating multi-modal data.
Requirements
- Experience with neuroimaging data analysis packages (FSL, SPM, MRTrix, NODDI, GBBS, etc.)
- Experience with programming languages such as Python, R, Matlab, etc.
- Experience with advanced statistical modeling techniques
- Familiarity with multimodal data integration modeling and advanced machine learning techniques (e.g. multiplex networks, deep learning)
- Familiarity with PET, proteomics, and genetic data analysis
- Experience with cloud computing
- Strong experience in multimodal neuroimaging techniques
Responsibilities
- Integrating MRI measures of gray and white matter microstructural and macromolecular properties with PET and plasma/protemoics measures of AD pathology
- Causal modeling for characterizing AD development in preclinical stage
- Multimodal network modeling for integrating brain imaging (MRI, PET), clinical, cognitive, biospecimen, proteomics and genetic data for characterization of neurodegenerative subtypes
- Contributing to ongoing multi-modal imaging studies in the lab
- Working on large, multi-modal datasets (brain, csf, plasma, proteomics, genetics, etc.) available through Stanford Alzheimer’s Disease Research Center (ADRC)
- Developing and applying advanced computational modeling and data analytic methods
- Integrating multi-modal data for decoding the heterogeneity of Alzheimer’s disease (AD) and modeling the disease progression
Other
- PhD (or MD) or equivalent in neuroscience, radiology, psychology, computer science, statistics, physics, engineering or a related field
- Strong writing skills demonstrated by peer reviewed publications
- Strong interpersonal, organizational and mentoring skills
- Seniority level: Internship
- Employment type: Full-time
