Performance Evaluation of Vanilla, Residual, and Dense 2D U-Net Architectures for Skull Stripping of Augmented 3D T1-weighted MRI Head Scans

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pimpalkar, Anway S., Patole, Rashmika K., Kamble, Ketaki D., Shindikar, Mahesh H.
Format: Preprint
Published: 2022
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912135272988672
author Pimpalkar, Anway S.
Patole, Rashmika K.
Kamble, Ketaki D.
Shindikar, Mahesh H.
author_facet Pimpalkar, Anway S.
Patole, Rashmika K.
Kamble, Ketaki D.
Shindikar, Mahesh H.
contents Skull Stripping is a requisite preliminary step in most diagnostic neuroimaging applications. Manual Skull Stripping methods define the gold standard for the domain but are time-consuming and challenging to integrate into processing pipelines with a high number of data samples. Automated methods are an active area of research for head MRI segmentation, especially deep learning methods such as U-Net architecture implementations. This study compares Vanilla, Residual, and Dense 2D U-Net architectures for Skull Stripping. The Dense 2D U-Net architecture outperforms the Vanilla and Residual counterparts by achieving an accuracy of 99.75% on a test dataset. It is observed that dense interconnections in a U-Net encourage feature reuse across layers of the architecture and allow for shallower models with the strengths of a deeper network.
format Preprint
id arxiv_https___arxiv_org_abs_2211_16570
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Performance Evaluation of Vanilla, Residual, and Dense 2D U-Net Architectures for Skull Stripping of Augmented 3D T1-weighted MRI Head Scans
Pimpalkar, Anway S.
Patole, Rashmika K.
Kamble, Ketaki D.
Shindikar, Mahesh H.
Image and Video Processing
Computer Vision and Pattern Recognition
Skull Stripping is a requisite preliminary step in most diagnostic neuroimaging applications. Manual Skull Stripping methods define the gold standard for the domain but are time-consuming and challenging to integrate into processing pipelines with a high number of data samples. Automated methods are an active area of research for head MRI segmentation, especially deep learning methods such as U-Net architecture implementations. This study compares Vanilla, Residual, and Dense 2D U-Net architectures for Skull Stripping. The Dense 2D U-Net architecture outperforms the Vanilla and Residual counterparts by achieving an accuracy of 99.75% on a test dataset. It is observed that dense interconnections in a U-Net encourage feature reuse across layers of the architecture and allow for shallower models with the strengths of a deeper network.
title Performance Evaluation of Vanilla, Residual, and Dense 2D U-Net Architectures for Skull Stripping of Augmented 3D T1-weighted MRI Head Scans
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2211.16570