Check out the updated conference hotel
See the transformation
>
Conference 12032 > Paper 12032-46
Paper 12032-46

Human brain extraction with deep learning

22 February 2022 • 1:20 PM - 1:40 PM PST | Town & Country B

Abstract

Brain extraction, also known as skull stripping, from magnetic resonance images (MRIs) is an essential preprocessingstep for many medical image analysis tasks and is also useful as a stand-alone task for estimating the total brain volume.Currently, many proposed methods have excellent performance on T1-weighted images, especially for healthy adults. However, such methods do not always generalize well to more challenging datasets such as pediatric, severely pathological, or heterogeneous. In this paper, we propose an automatic deep learning framework for brain extraction on T1-weighted MRIs of adult healthy controls, Huntington’s disease patients and pediatric Aicardi Gouti`eres Syndrome (AGS) patients.We examine our method on the PREDICT-HD and the AGS datasets, which are multi-site datasets with different protocols/scanners. Compared to current state-of-the-art methods, our method has better accuracy and generalizability for heterogeneous T1-w MRI datasets.

Presenter

Vanderbilt Univ. (United States)
Hao Li is a phd student at vanderbilt university. Hao works on medical image analysis, and advised by Dr.Oguz.
Presenter/Author
Vanderbilt Univ. (United States)
Author
Vanderbilt Univ. (United States)
Author
Vanderbilt Univ. (United States)
Author
Vanderbilt Univ. (United States)
Author
Hans Johnson
The Univ. of Iowa (United States)
Author
The Children's Hospital of Philadelphia (United States)
Author
The Children's Hospital of Philadelphia (United States)
Author
The Children's Hospital of Philadelphia (United States)
Author
The Children's Hospital of Philadelphia (United States)
Author
The Univ. of Iowa (United States)
Author
Jane S. Paulsen
Univ. of Wisconsin-Madison (United States)
Author
Ipek Oguz
Vanderbilt Univ. (United States)