|
Activity Number:
|
306
- Statistical Challenges in Large-Scale Imaging Studies
|
|
Type:
|
Invited
|
|
Date/Time:
|
Tuesday, August 9, 2022 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Statistics in Imaging
|
|
Abstract #320408
|
|
|
Title:
|
Prediction Models and Pipelines for Biobank-Scale Imaging Data
|
|
Author(s):
|
Hongtu Zhu* and Tengfei Li
|
|
Companies:
|
University of North Carolina at Chapel Hill and The University of North Carolina at Chapel Hill
|
|
Keywords:
|
large-scale imaging study;
prediction models;
preprocessing pipeline
|
|
Abstract:
|
The aim of this talk is to present a series of prediction models and pipelines for processing biobank-scale imaging data obtained from UK Biobank and ABCE. We systematically compare standard statistical prediction models with modern machine learning models (e.g., deepFM and brainNet) for several categories of phenotypes, such as intelligence, by using a large number of subjects obtained from UKB and ABCD. We also show a series of preprocessing pipelines for major neuroimaging data for large-scale biobank data sets.
|
Authors who are presenting talks have a * after their name.
