Postdoctoral Scholar

A significant challenge to cross-study data analysis is the lack of consistency in
measurement among studies, especially for important outcome measures. In
the context of neuroimaging, this includes different scanners and acquisition
protocols. Harmonization of neuroimaging data across epidemiology cohorts,
the Alzheimer’s Disease Centers, and convenience cohort phenotypic data has
not been done in a substantive manner. In this appointment the candidate will
develop deep learning and machine-learning approaches for the harmonization
of neuroimaging data, including Diffusion Tensor Imaging (DTI). The goal of this
position is to generate harmonized DTI imaging data sets that will be shared
through a central data repository for data (genetic, genomic, annotation,
analysis, statistical, and phenotypic) collected by other NIA-funded studies.

RESPONSABILITIES
You will develop, test and validate novel algorithms with neuroimaging data
You will apply your validated methods to large scale research and real life
everyday clinical routine neuroimaging data
Willingness to work in teams
You will communicate your research results to the larger communities
through publications in international conferences
You will initiate academic publications in peer-reviewed journals; prepare
training grant proposals and other applications for future research.
You will communicate your research results to the larger communities
through publications in international conferences
You will engage in lab meetings and mentor trainees, and closely interact
with the PI

APPOINTMENT DETAILS
This appointment will be at the highly collaborative empirical computational
and clinical environments at UC Davis. The full-time appointment is for 1-2
years with possibility of renewal. Position level and salary commensurate with
training and experience, according to NIH scales. Review of applications will
begin immediately and continue until the position is filled