Brain tumor segmentation based on deep learning and an attention mechanism using MRI multi-modalities brain images

Abstract Brain tumor localization and segmentation from magnetic resonance imaging (MRI) are hard and important tasks for several applications in the field of medical analysis. As each brain imaging modality gives unique and key details related to each part of the tumor, many recent approaches used...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Ramin Ranjbarzadeh, Abbas Bagherian Kasgari, Saeid Jafarzadeh Ghoushchi, Shokofeh Anari, Maryam Naseri, Malika Bendechache
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/e1eabcc6d67b479c952258f2c8ace76a
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:e1eabcc6d67b479c952258f2c8ace76a
record_format	dspace
spelling	oai:doaj.org-article:e1eabcc6d67b479c952258f2c8ace76a2021-12-02T15:49:35ZBrain tumor segmentation based on deep learning and an attention mechanism using MRI multi-modalities brain images10.1038/s41598-021-90428-82045-2322https://doaj.org/article/e1eabcc6d67b479c952258f2c8ace76a2021-05-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-90428-8https://doaj.org/toc/2045-2322Abstract Brain tumor localization and segmentation from magnetic resonance imaging (MRI) are hard and important tasks for several applications in the field of medical analysis. As each brain imaging modality gives unique and key details related to each part of the tumor, many recent approaches used four modalities T1, T1c, T2, and FLAIR. Although many of them obtained a promising segmentation result on the BRATS 2018 dataset, they suffer from a complex structure that needs more time to train and test. So, in this paper, to obtain a flexible and effective brain tumor segmentation system, first, we propose a preprocessing approach to work only on a small part of the image rather than the whole part of the image. This method leads to a decrease in computing time and overcomes the overfitting problems in a Cascade Deep Learning model. In the second step, as we are dealing with a smaller part of brain images in each slice, a simple and efficient Cascade Convolutional Neural Network (C-ConvNet/C-CNN) is proposed. This C-CNN model mines both local and global features in two different routes. Also, to improve the brain tumor segmentation accuracy compared with the state-of-the-art models, a novel Distance-Wise Attention (DWA) mechanism is introduced. The DWA mechanism considers the effect of the center location of the tumor and the brain inside the model. Comprehensive experiments are conducted on the BRATS 2018 dataset and show that the proposed model obtains competitive results: the proposed method achieves a mean whole tumor, enhancing tumor, and tumor core dice scores of 0.9203, 0.9113 and 0.8726 respectively. Other quantitative and qualitative assessments are presented and discussed.Ramin RanjbarzadehAbbas Bagherian KasgariSaeid Jafarzadeh GhoushchiShokofeh AnariMaryam NaseriMalika BendechacheNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-17 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Ramin Ranjbarzadeh Abbas Bagherian Kasgari Saeid Jafarzadeh Ghoushchi Shokofeh Anari Maryam Naseri Malika Bendechache Brain tumor segmentation based on deep learning and an attention mechanism using MRI multi-modalities brain images
description	Abstract Brain tumor localization and segmentation from magnetic resonance imaging (MRI) are hard and important tasks for several applications in the field of medical analysis. As each brain imaging modality gives unique and key details related to each part of the tumor, many recent approaches used four modalities T1, T1c, T2, and FLAIR. Although many of them obtained a promising segmentation result on the BRATS 2018 dataset, they suffer from a complex structure that needs more time to train and test. So, in this paper, to obtain a flexible and effective brain tumor segmentation system, first, we propose a preprocessing approach to work only on a small part of the image rather than the whole part of the image. This method leads to a decrease in computing time and overcomes the overfitting problems in a Cascade Deep Learning model. In the second step, as we are dealing with a smaller part of brain images in each slice, a simple and efficient Cascade Convolutional Neural Network (C-ConvNet/C-CNN) is proposed. This C-CNN model mines both local and global features in two different routes. Also, to improve the brain tumor segmentation accuracy compared with the state-of-the-art models, a novel Distance-Wise Attention (DWA) mechanism is introduced. The DWA mechanism considers the effect of the center location of the tumor and the brain inside the model. Comprehensive experiments are conducted on the BRATS 2018 dataset and show that the proposed model obtains competitive results: the proposed method achieves a mean whole tumor, enhancing tumor, and tumor core dice scores of 0.9203, 0.9113 and 0.8726 respectively. Other quantitative and qualitative assessments are presented and discussed.
format	article
author	Ramin Ranjbarzadeh Abbas Bagherian Kasgari Saeid Jafarzadeh Ghoushchi Shokofeh Anari Maryam Naseri Malika Bendechache
author_facet	Ramin Ranjbarzadeh Abbas Bagherian Kasgari Saeid Jafarzadeh Ghoushchi Shokofeh Anari Maryam Naseri Malika Bendechache
author_sort	Ramin Ranjbarzadeh
title	Brain tumor segmentation based on deep learning and an attention mechanism using MRI multi-modalities brain images
title_short	Brain tumor segmentation based on deep learning and an attention mechanism using MRI multi-modalities brain images
title_full	Brain tumor segmentation based on deep learning and an attention mechanism using MRI multi-modalities brain images
title_fullStr	Brain tumor segmentation based on deep learning and an attention mechanism using MRI multi-modalities brain images
title_full_unstemmed	Brain tumor segmentation based on deep learning and an attention mechanism using MRI multi-modalities brain images
title_sort	brain tumor segmentation based on deep learning and an attention mechanism using mri multi-modalities brain images
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/e1eabcc6d67b479c952258f2c8ace76a
work_keys_str_mv	AT raminranjbarzadeh braintumorsegmentationbasedondeeplearningandanattentionmechanismusingmrimultimodalitiesbrainimages AT abbasbagheriankasgari braintumorsegmentationbasedondeeplearningandanattentionmechanismusingmrimultimodalitiesbrainimages AT saeidjafarzadehghoushchi braintumorsegmentationbasedondeeplearningandanattentionmechanismusingmrimultimodalitiesbrainimages AT shokofehanari braintumorsegmentationbasedondeeplearningandanattentionmechanismusingmrimultimodalitiesbrainimages AT maryamnaseri braintumorsegmentationbasedondeeplearningandanattentionmechanismusingmrimultimodalitiesbrainimages AT malikabendechache braintumorsegmentationbasedondeeplearningandanattentionmechanismusingmrimultimodalitiesbrainimages
_version_	1718385723420180480

Brain tumor segmentation based on deep learning and an attention mechanism using MRI multi-modalities brain images

Ejemplares similares