Enhanced performance of Dark-Nets for brain tumor classification and segmentation using colormap-based superpixel techniques

The brain tumor is the deadliest disease in adults as it arises due to an abnormal mass of cells that grows rapidly and it alters the proper functioning of the organs. In clinical practice, radiographic images of different modalities are used to diagnose types of brain tumors, their size, and locati...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Sakshi Ahuja, Bijaya Ketan Panigrahi, Tapan Kumar Gandhi
Formato:	article
Lenguaje:	EN
Publicado:	Elsevier 2022
Materias:	Brain tumor MRI Deep learning Superpixel segmentation Cybernetics Q300-390 Electronic computers. Computer science QA75.5-76.95
Acceso en línea:	https://doaj.org/article/da57e86a318042229067a721d96f8f65
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:da57e86a318042229067a721d96f8f65
record_format	dspace
spelling	oai:doaj.org-article:da57e86a318042229067a721d96f8f652021-11-28T04:39:30ZEnhanced performance of Dark-Nets for brain tumor classification and segmentation using colormap-based superpixel techniques2666-827010.1016/j.mlwa.2021.100212https://doaj.org/article/da57e86a318042229067a721d96f8f652022-03-01T00:00:00Zhttp://www.sciencedirect.com/science/article/pii/S2666827021001067https://doaj.org/toc/2666-8270The brain tumor is the deadliest disease in adults as it arises due to an abnormal mass of cells that grows rapidly and it alters the proper functioning of the organs. In clinical practice, radiographic images of different modalities are used to diagnose types of brain tumors, their size, and location. The proposed work aims to automatically classify, localize, and segment brain tumors from T1W-CE Magnetic Resonance Image (MRI) datasets. The T1W-CE MRI dataset is divided into 8:1:1, i.e., 80% training set, 10% of each validation, and testing set. To address the overfitting issues, the training data set is augmented using 2-levels wavelet decomposition and geometrical operations (scaling, rotation, translation). Performance of pre-trained DarkNet model (DarkNet-19 and DarkNet-53) is evaluated for the multi-class classification and localization of brain tumors. The best performing pre-trained DarkNet model achieved 99.60% of training accuracy and 98.81% of validation accuracy. The performance evaluation parameters confirm the superiority of the proposed methodology in comparison to the state-of-the-art on the T1W-CE MRI dataset. On 1070 T1W-CE testing images, the best-performing pre-trained DarkNet-53 model obtained a testing accuracy of 98.54% and Area Under Curve (AUC) of 0.99. The tumor is segmented using a 2-D superpixel segmentation technique with an average dice index of 0.94 ± 2.6% on the 793 brain tumor testing data. To prove the superiority of the proposed technique, it is implemented on MRI images from the BraTS2018 dataset. The comparative analysis of performance evaluation parameters of the proposed methodology with the state-of-the-art technique proves its robustness and clinical significance.Sakshi AhujaBijaya Ketan PanigrahiTapan Kumar GandhiElsevierarticleBrain tumorMRIDeep learningSuperpixel segmentationCyberneticsQ300-390Electronic computers. Computer scienceQA75.5-76.95ENMachine Learning with Applications, Vol 7, Iss , Pp 100212- (2022)
institution	DOAJ
collection	DOAJ
language	EN
topic	Brain tumor MRI Deep learning Superpixel segmentation Cybernetics Q300-390 Electronic computers. Computer science QA75.5-76.95
spellingShingle	Brain tumor MRI Deep learning Superpixel segmentation Cybernetics Q300-390 Electronic computers. Computer science QA75.5-76.95 Sakshi Ahuja Bijaya Ketan Panigrahi Tapan Kumar Gandhi Enhanced performance of Dark-Nets for brain tumor classification and segmentation using colormap-based superpixel techniques
description	The brain tumor is the deadliest disease in adults as it arises due to an abnormal mass of cells that grows rapidly and it alters the proper functioning of the organs. In clinical practice, radiographic images of different modalities are used to diagnose types of brain tumors, their size, and location. The proposed work aims to automatically classify, localize, and segment brain tumors from T1W-CE Magnetic Resonance Image (MRI) datasets. The T1W-CE MRI dataset is divided into 8:1:1, i.e., 80% training set, 10% of each validation, and testing set. To address the overfitting issues, the training data set is augmented using 2-levels wavelet decomposition and geometrical operations (scaling, rotation, translation). Performance of pre-trained DarkNet model (DarkNet-19 and DarkNet-53) is evaluated for the multi-class classification and localization of brain tumors. The best performing pre-trained DarkNet model achieved 99.60% of training accuracy and 98.81% of validation accuracy. The performance evaluation parameters confirm the superiority of the proposed methodology in comparison to the state-of-the-art on the T1W-CE MRI dataset. On 1070 T1W-CE testing images, the best-performing pre-trained DarkNet-53 model obtained a testing accuracy of 98.54% and Area Under Curve (AUC) of 0.99. The tumor is segmented using a 2-D superpixel segmentation technique with an average dice index of 0.94 ± 2.6% on the 793 brain tumor testing data. To prove the superiority of the proposed technique, it is implemented on MRI images from the BraTS2018 dataset. The comparative analysis of performance evaluation parameters of the proposed methodology with the state-of-the-art technique proves its robustness and clinical significance.
format	article
author	Sakshi Ahuja Bijaya Ketan Panigrahi Tapan Kumar Gandhi
author_facet	Sakshi Ahuja Bijaya Ketan Panigrahi Tapan Kumar Gandhi
author_sort	Sakshi Ahuja
title	Enhanced performance of Dark-Nets for brain tumor classification and segmentation using colormap-based superpixel techniques
title_short	Enhanced performance of Dark-Nets for brain tumor classification and segmentation using colormap-based superpixel techniques
title_full	Enhanced performance of Dark-Nets for brain tumor classification and segmentation using colormap-based superpixel techniques
title_fullStr	Enhanced performance of Dark-Nets for brain tumor classification and segmentation using colormap-based superpixel techniques
title_full_unstemmed	Enhanced performance of Dark-Nets for brain tumor classification and segmentation using colormap-based superpixel techniques
title_sort	enhanced performance of dark-nets for brain tumor classification and segmentation using colormap-based superpixel techniques
publisher	Elsevier
publishDate	2022
url	https://doaj.org/article/da57e86a318042229067a721d96f8f65
work_keys_str_mv	AT sakshiahuja enhancedperformanceofdarknetsforbraintumorclassificationandsegmentationusingcolormapbasedsuperpixeltechniques AT bijayaketanpanigrahi enhancedperformanceofdarknetsforbraintumorclassificationandsegmentationusingcolormapbasedsuperpixeltechniques AT tapankumargandhi enhancedperformanceofdarknetsforbraintumorclassificationandsegmentationusingcolormapbasedsuperpixeltechniques
_version_	1718408287794233344

Enhanced performance of Dark-Nets for brain tumor classification and segmentation using colormap-based superpixel techniques

Ejemplares similares