Activity Number:
|
390
- Functional and High-Dimensional Data
|
Type:
|
Contributed
|
Date/Time:
|
Wednesday, August 10, 2022 : 8:30 AM to 10:20 AM
|
Sponsor:
|
IMS
|
Abstract #322983
|
|
Title:
|
Minimax Lower Bounds in High Order Tensor Models with Applications to Neuroimaging
|
Author(s):
|
Chitrak Banerjee* and LYUDMILA SAKHANENKO and David C Zhu
|
Companies:
|
Wells Fargo N A and Michigan State University and Michigan State University
|
Keywords:
|
Minimax lower bounds;
Diffusion tensor imaging;
Tensor modeling
|
Abstract:
|
High angular resonance diffusion imaging (HARDI) is a popular in-vivo neuroimaging technique used by clinicians for understanding the anatomy of neural fiber structure inside a live human brain. We develop a minimax bound for the integral curve estimator of neural fibers that has an optimal width. Using this minimax bound, we also develop a novel method to compare different neuroimaging protocols. We discuss some interesting simulation results and finally implement this methodology on the HARDI data obtained from a live human brain.
|
Authors who are presenting talks have a * after their name.