AWEU-Net: An Attention-Aware Weight Excitation U-Net for Lung Nodule Segmentation

Lung cancer is a deadly cancer that causes millions of deaths every year around the world. Accurate lung nodule detection and segmentation in computed tomography (CT) images is a vital step for diagnosing lung cancer early. Most existing systems face several challenges, such as the heterogeneity in...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Syeda Furruka Banu, Md. Mostafa Kamal Sarker, Mohamed Abdel-Nasser, Domenec Puig, Hatem A. Raswan
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	artificial intelligence computer-aided diagnosis computed tomography lung cancer deep learning lung nodule detection Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
Acceso en línea:	https://doaj.org/article/42f0b75d487e478abce7b0996cf5f2d4
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:42f0b75d487e478abce7b0996cf5f2d4
record_format	dspace
spelling	oai:doaj.org-article:42f0b75d487e478abce7b0996cf5f2d42021-11-11T15:11:43ZAWEU-Net: An Attention-Aware Weight Excitation U-Net for Lung Nodule Segmentation10.3390/app1121101322076-3417https://doaj.org/article/42f0b75d487e478abce7b0996cf5f2d42021-10-01T00:00:00Zhttps://www.mdpi.com/2076-3417/11/21/10132https://doaj.org/toc/2076-3417Lung cancer is a deadly cancer that causes millions of deaths every year around the world. Accurate lung nodule detection and segmentation in computed tomography (CT) images is a vital step for diagnosing lung cancer early. Most existing systems face several challenges, such as the heterogeneity in CT images and variation in nodule size, shape, and location, which limit their accuracy. In an attempt to handle these challenges, this article proposes a fully automated deep learning framework that consists of lung nodule detection and segmentation models. Our proposed system comprises two cascaded stages: (1) nodule detection based on fine-tuned Faster R-CNN to localize the nodules in CT images, and (2) nodule segmentation based on the U-Net architecture with two effective blocks, namely position attention-aware weight excitation (PAWE) and channel attention-aware weight excitation (CAWE), to enhance the ability to discriminate between nodule and non-nodule feature representations. The experimental results demonstrate that the proposed system yields a Dice score of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>89.79</mn><mo>%</mo></mrow></semantics></math></inline-formula> and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>90.35</mn><mo>%</mo></mrow></semantics></math></inline-formula>, and an intersection over union (IoU) of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>82.34</mn><mo>%</mo></mrow></semantics></math></inline-formula> and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>83.21</mn><mo>%</mo></mrow></semantics></math></inline-formula> on the publicly available LUNA16 and LIDC-IDRI datasets, respectively.Syeda Furruka BanuMd. Mostafa Kamal SarkerMohamed Abdel-NasserDomenec PuigHatem A. RaswanMDPI AGarticleartificial intelligencecomputer-aided diagnosiscomputed tomographylung cancerdeep learninglung nodule detectionTechnologyTEngineering (General). Civil engineering (General)TA1-2040Biology (General)QH301-705.5PhysicsQC1-999ChemistryQD1-999ENApplied Sciences, Vol 11, Iss 10132, p 10132 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	artificial intelligence computer-aided diagnosis computed tomography lung cancer deep learning lung nodule detection Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
spellingShingle	artificial intelligence computer-aided diagnosis computed tomography lung cancer deep learning lung nodule detection Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999 Syeda Furruka Banu Md. Mostafa Kamal Sarker Mohamed Abdel-Nasser Domenec Puig Hatem A. Raswan AWEU-Net: An Attention-Aware Weight Excitation U-Net for Lung Nodule Segmentation
description	Lung cancer is a deadly cancer that causes millions of deaths every year around the world. Accurate lung nodule detection and segmentation in computed tomography (CT) images is a vital step for diagnosing lung cancer early. Most existing systems face several challenges, such as the heterogeneity in CT images and variation in nodule size, shape, and location, which limit their accuracy. In an attempt to handle these challenges, this article proposes a fully automated deep learning framework that consists of lung nodule detection and segmentation models. Our proposed system comprises two cascaded stages: (1) nodule detection based on fine-tuned Faster R-CNN to localize the nodules in CT images, and (2) nodule segmentation based on the U-Net architecture with two effective blocks, namely position attention-aware weight excitation (PAWE) and channel attention-aware weight excitation (CAWE), to enhance the ability to discriminate between nodule and non-nodule feature representations. The experimental results demonstrate that the proposed system yields a Dice score of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>89.79</mn><mo>%</mo></mrow></semantics></math></inline-formula> and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>90.35</mn><mo>%</mo></mrow></semantics></math></inline-formula>, and an intersection over union (IoU) of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>82.34</mn><mo>%</mo></mrow></semantics></math></inline-formula> and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>83.21</mn><mo>%</mo></mrow></semantics></math></inline-formula> on the publicly available LUNA16 and LIDC-IDRI datasets, respectively.
format	article
author	Syeda Furruka Banu Md. Mostafa Kamal Sarker Mohamed Abdel-Nasser Domenec Puig Hatem A. Raswan
author_facet	Syeda Furruka Banu Md. Mostafa Kamal Sarker Mohamed Abdel-Nasser Domenec Puig Hatem A. Raswan
author_sort	Syeda Furruka Banu
title	AWEU-Net: An Attention-Aware Weight Excitation U-Net for Lung Nodule Segmentation
title_short	AWEU-Net: An Attention-Aware Weight Excitation U-Net for Lung Nodule Segmentation
title_full	AWEU-Net: An Attention-Aware Weight Excitation U-Net for Lung Nodule Segmentation
title_fullStr	AWEU-Net: An Attention-Aware Weight Excitation U-Net for Lung Nodule Segmentation
title_full_unstemmed	AWEU-Net: An Attention-Aware Weight Excitation U-Net for Lung Nodule Segmentation
title_sort	aweu-net: an attention-aware weight excitation u-net for lung nodule segmentation
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/42f0b75d487e478abce7b0996cf5f2d4
work_keys_str_mv	AT syedafurrukabanu aweunetanattentionawareweightexcitationunetforlungnodulesegmentation AT mdmostafakamalsarker aweunetanattentionawareweightexcitationunetforlungnodulesegmentation AT mohamedabdelnasser aweunetanattentionawareweightexcitationunetforlungnodulesegmentation AT domenecpuig aweunetanattentionawareweightexcitationunetforlungnodulesegmentation AT hatemaraswan aweunetanattentionawareweightexcitationunetforlungnodulesegmentation
_version_	1718436743718371328

AWEU-Net: An Attention-Aware Weight Excitation U-Net for Lung Nodule Segmentation

Ejemplares similares