Conference proceeding
Human brain extraction with deep learning
Vol.12032, pp.120321D-120321D-7
04/04/2022
DOI: 10.1117/12.2613277
Abstract
Brain extraction, also known as skull stripping, from magnetic resonance images (MRIs) is an essential preprocessing step 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 data. 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 produced the best segmentations with the highest Dice score, lowest average surface distance and lowest 95-percent Hausdorff distance on both datasets. These results indicate that our method has better accuracy and generalizability for heterogeneous T1-w MRI datasets.
Details
- Title: Subtitle
- Human brain extraction with deep learning
- Creators
- Hao Li - Vanderbilt UniversityQibang Zhu - Vanderbilt UniversityDewei Hu - Vanderbilt UniversityManasvi R. Gunnala - Vanderbilt UniversityHans Johnson - University of IowaOmar Sherbini - Children's Hospital of PhiladelphiaFrancesco Gavazzi - Children's Hospital of PhiladelphiaRussell D’Aiello - Children's Hospital of PhiladelphiaAdeline Vanderver - Children's Hospital of PhiladelphiaJeffrey D. Long - University of IowaJane S. Paulsen - University of Wisconsin–MadisonIpek Oguz - Vanderbilt University
- Contributors
- Olivier Colliot (Editor) - Ctr. National de la Recherche Scientifique (France)Ivana Išgum (Editor) - Amsterdam UMC (Netherlands)
- Resource Type
- Conference proceeding
- Publication Details
- Vol.12032, pp.120321D-120321D-7
- Publisher
- SPIE
- DOI
- 10.1117/12.2613277
- ISSN
- 1605-7422
- Language
- English
- Date published
- 04/04/2022
- Academic Unit
- Biostatistics; Psychiatry; The Iowa Institute for Biomedical Imaging; Electrical and Computer Engineering; Roy J. Carver Department of Biomedical Engineering; The Iowa Initiative for Artificial Intelligence; Iowa Informatics Initiative; Psychological and Brain Sciences
- Record Identifier
- 9984259366202771
Metrics
23 Record Views