Cargando…

Brain Tumor Segmentation Using Deep Capsule Network and Latent-Dynamic Conditional Random Fields

Because of the large variabilities in brain tumors, automating segmentation remains a difficult task. We propose an automated method to segment brain tumors by integrating the deep capsule network (CapsNet) and the latent-dynamic condition random field (LDCRF). The method consists of three main proc...

Descripción completa

Detalles Bibliográficos
Autores principales: Elmezain, Mahmoud, Mahmoud, Amena, Mosa, Diana T., Said, Wael
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9322984/
https://www.ncbi.nlm.nih.gov/pubmed/35877634
http://dx.doi.org/10.3390/jimaging8070190
_version_ 1784756438405480448
author Elmezain, Mahmoud
Mahmoud, Amena
Mosa, Diana T.
Said, Wael
author_facet Elmezain, Mahmoud
Mahmoud, Amena
Mosa, Diana T.
Said, Wael
author_sort Elmezain, Mahmoud
collection PubMed
description Because of the large variabilities in brain tumors, automating segmentation remains a difficult task. We propose an automated method to segment brain tumors by integrating the deep capsule network (CapsNet) and the latent-dynamic condition random field (LDCRF). The method consists of three main processes to segment the brain tumor—pre-processing, segmentation, and post-processing. In pre-processing, the N4ITK process involves correcting each MR image’s bias field before normalizing the intensity. After that, image patches are used to train CapsNet during the segmentation process. Then, with the CapsNet parameters determined, we employ image slices from an axial view to learn the LDCRF-CapsNet. Finally, we use a simple thresholding method to correct the labels of some pixels and remove small 3D-connected regions from the segmentation outcomes. On the BRATS 2015 and BRATS 2021 datasets, we trained and evaluated our method and discovered that it outperforms and can compete with state-of-the-art methods in comparable conditions.
format Online
Article
Text
id pubmed-9322984
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-93229842022-07-27 Brain Tumor Segmentation Using Deep Capsule Network and Latent-Dynamic Conditional Random Fields Elmezain, Mahmoud Mahmoud, Amena Mosa, Diana T. Said, Wael J Imaging Article Because of the large variabilities in brain tumors, automating segmentation remains a difficult task. We propose an automated method to segment brain tumors by integrating the deep capsule network (CapsNet) and the latent-dynamic condition random field (LDCRF). The method consists of three main processes to segment the brain tumor—pre-processing, segmentation, and post-processing. In pre-processing, the N4ITK process involves correcting each MR image’s bias field before normalizing the intensity. After that, image patches are used to train CapsNet during the segmentation process. Then, with the CapsNet parameters determined, we employ image slices from an axial view to learn the LDCRF-CapsNet. Finally, we use a simple thresholding method to correct the labels of some pixels and remove small 3D-connected regions from the segmentation outcomes. On the BRATS 2015 and BRATS 2021 datasets, we trained and evaluated our method and discovered that it outperforms and can compete with state-of-the-art methods in comparable conditions. MDPI 2022-07-08 /pmc/articles/PMC9322984/ /pubmed/35877634 http://dx.doi.org/10.3390/jimaging8070190 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Elmezain, Mahmoud
Mahmoud, Amena
Mosa, Diana T.
Said, Wael
Brain Tumor Segmentation Using Deep Capsule Network and Latent-Dynamic Conditional Random Fields
title Brain Tumor Segmentation Using Deep Capsule Network and Latent-Dynamic Conditional Random Fields
title_full Brain Tumor Segmentation Using Deep Capsule Network and Latent-Dynamic Conditional Random Fields
title_fullStr Brain Tumor Segmentation Using Deep Capsule Network and Latent-Dynamic Conditional Random Fields
title_full_unstemmed Brain Tumor Segmentation Using Deep Capsule Network and Latent-Dynamic Conditional Random Fields
title_short Brain Tumor Segmentation Using Deep Capsule Network and Latent-Dynamic Conditional Random Fields
title_sort brain tumor segmentation using deep capsule network and latent-dynamic conditional random fields
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9322984/
https://www.ncbi.nlm.nih.gov/pubmed/35877634
http://dx.doi.org/10.3390/jimaging8070190
work_keys_str_mv AT elmezainmahmoud braintumorsegmentationusingdeepcapsulenetworkandlatentdynamicconditionalrandomfields
AT mahmoudamena braintumorsegmentationusingdeepcapsulenetworkandlatentdynamicconditionalrandomfields
AT mosadianat braintumorsegmentationusingdeepcapsulenetworkandlatentdynamicconditionalrandomfields
AT saidwael braintumorsegmentationusingdeepcapsulenetworkandlatentdynamicconditionalrandomfields