Deep Learning Framework to Detect Ischemic Stroke Lesion in Brain MRI Slices of Flair/DW/T1 Modalities

Ischemic stroke lesion (ISL) is a brain abnormality. Studies proved that early detection and treatment could reduce the disease impact. This research aimed to develop a deep learning (DL) framework to detect the ISL in multi-modality magnetic resonance image (MRI) slices. It proposed a convolutional...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Venkatesan Rajinikanth, Shabnam Mohamed Aslam, Seifedine Kadry
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	ischemic stroke brain MRI VGG16 VGG-SegNet segmentation classification Mathematics QA1-939
Acceso en línea:	https://doaj.org/article/ecb00d3ea9654999b7cb02d2681b8335
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:ecb00d3ea9654999b7cb02d2681b8335
record_format	dspace
spelling	oai:doaj.org-article:ecb00d3ea9654999b7cb02d2681b83352021-11-25T19:06:36ZDeep Learning Framework to Detect Ischemic Stroke Lesion in Brain MRI Slices of Flair/DW/T1 Modalities10.3390/sym131120802073-8994https://doaj.org/article/ecb00d3ea9654999b7cb02d2681b83352021-11-01T00:00:00Zhttps://www.mdpi.com/2073-8994/13/11/2080https://doaj.org/toc/2073-8994Ischemic stroke lesion (ISL) is a brain abnormality. Studies proved that early detection and treatment could reduce the disease impact. This research aimed to develop a deep learning (DL) framework to detect the ISL in multi-modality magnetic resonance image (MRI) slices. It proposed a convolutional neural network (CNN)-supported segmentation and classification to execute a consistent disease detection framework. The developed framework consisted of the following phases; (i) visual geometry group (VGG) developed VGG16 scheme supported SegNet (VGG-SegNet)-based ISL mining, (ii) handcrafted feature extraction, (iii) deep feature extraction using the chosen DL scheme, (iv) feature ranking and serial feature concatenation, and (v) classification using binary classifiers. Fivefold cross-validation was employed in this work, and the best feature was selected as the final result. The attained results were separately examined for (i) segmentation; (ii) deep-feature-based classification, and (iii) concatenated feature-based classification. The experimental investigation is presented using the Ischemic Stroke Lesion Segmentation (ISLES2015) database. The attained result confirms that the proposed ISL detection framework gives better segmentation and classification results. The VGG16 scheme helped to obtain a better result with deep features (accuracy > 97%) and concatenated features (accuracy > 98%).Venkatesan RajinikanthShabnam Mohamed AslamSeifedine KadryMDPI AGarticleischemic strokebrain MRIVGG16VGG-SegNetsegmentationclassificationMathematicsQA1-939ENSymmetry, Vol 13, Iss 2080, p 2080 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	ischemic stroke brain MRI VGG16 VGG-SegNet segmentation classification Mathematics QA1-939
spellingShingle	ischemic stroke brain MRI VGG16 VGG-SegNet segmentation classification Mathematics QA1-939 Venkatesan Rajinikanth Shabnam Mohamed Aslam Seifedine Kadry Deep Learning Framework to Detect Ischemic Stroke Lesion in Brain MRI Slices of Flair/DW/T1 Modalities
description	Ischemic stroke lesion (ISL) is a brain abnormality. Studies proved that early detection and treatment could reduce the disease impact. This research aimed to develop a deep learning (DL) framework to detect the ISL in multi-modality magnetic resonance image (MRI) slices. It proposed a convolutional neural network (CNN)-supported segmentation and classification to execute a consistent disease detection framework. The developed framework consisted of the following phases; (i) visual geometry group (VGG) developed VGG16 scheme supported SegNet (VGG-SegNet)-based ISL mining, (ii) handcrafted feature extraction, (iii) deep feature extraction using the chosen DL scheme, (iv) feature ranking and serial feature concatenation, and (v) classification using binary classifiers. Fivefold cross-validation was employed in this work, and the best feature was selected as the final result. The attained results were separately examined for (i) segmentation; (ii) deep-feature-based classification, and (iii) concatenated feature-based classification. The experimental investigation is presented using the Ischemic Stroke Lesion Segmentation (ISLES2015) database. The attained result confirms that the proposed ISL detection framework gives better segmentation and classification results. The VGG16 scheme helped to obtain a better result with deep features (accuracy > 97%) and concatenated features (accuracy > 98%).
format	article
author	Venkatesan Rajinikanth Shabnam Mohamed Aslam Seifedine Kadry
author_facet	Venkatesan Rajinikanth Shabnam Mohamed Aslam Seifedine Kadry
author_sort	Venkatesan Rajinikanth
title	Deep Learning Framework to Detect Ischemic Stroke Lesion in Brain MRI Slices of Flair/DW/T1 Modalities
title_short	Deep Learning Framework to Detect Ischemic Stroke Lesion in Brain MRI Slices of Flair/DW/T1 Modalities
title_full	Deep Learning Framework to Detect Ischemic Stroke Lesion in Brain MRI Slices of Flair/DW/T1 Modalities
title_fullStr	Deep Learning Framework to Detect Ischemic Stroke Lesion in Brain MRI Slices of Flair/DW/T1 Modalities
title_full_unstemmed	Deep Learning Framework to Detect Ischemic Stroke Lesion in Brain MRI Slices of Flair/DW/T1 Modalities
title_sort	deep learning framework to detect ischemic stroke lesion in brain mri slices of flair/dw/t1 modalities
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/ecb00d3ea9654999b7cb02d2681b8335
work_keys_str_mv	AT venkatesanrajinikanth deeplearningframeworktodetectischemicstrokelesioninbrainmrislicesofflairdwt1modalities AT shabnammohamedaslam deeplearningframeworktodetectischemicstrokelesioninbrainmrislicesofflairdwt1modalities AT seifedinekadry deeplearningframeworktodetectischemicstrokelesioninbrainmrislicesofflairdwt1modalities
_version_	1718410314058301440

Deep Learning Framework to Detect Ischemic Stroke Lesion in Brain MRI Slices of Flair/DW/T1 Modalities

Ejemplares similares