Comparison of Current Deep Convolutional Neural Networks for the Segmentation of Breast Masses in Mammograms

Breast cancer causes approximately 684,996 deaths worldwide, making it the leading cause of female cancer mortality. However, these figures can be reduced with early diagnosis through mammographic imaging, allowing for the timely and effective treatment of this disease. To establish the best tools f...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Andres Anaya-Isaza, Leonel Mera-Jimenez, Johan Manuel Cabrera-Chavarro, Lorena Guachi-Guachi, Diego Peluffo-Ordonez, Jorge Ivan Rios-Patino
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Artificial intelligence biomedical imaging cancer image segmentation machine learning mammography Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/24da7c29b1dc4ff89aab881bc428dc86
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:24da7c29b1dc4ff89aab881bc428dc86
record_format	dspace
spelling	oai:doaj.org-article:24da7c29b1dc4ff89aab881bc428dc862021-11-20T00:02:15ZComparison of Current Deep Convolutional Neural Networks for the Segmentation of Breast Masses in Mammograms2169-353610.1109/ACCESS.2021.3127862https://doaj.org/article/24da7c29b1dc4ff89aab881bc428dc862021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9614200/https://doaj.org/toc/2169-3536Breast cancer causes approximately 684,996 deaths worldwide, making it the leading cause of female cancer mortality. However, these figures can be reduced with early diagnosis through mammographic imaging, allowing for the timely and effective treatment of this disease. To establish the best tools for contributing to the automatic diagnosis of breast cancer, different deep learning (DL) architectures were compared in terms of breast lesion segmentation, lesion type classification, and degree of suspicion of malignancy tests. The tasks were completed with state-of-the-art architectures and backbones. Initially, during segmentation, the base UNet, Visual Geometry Group 19 (VGG19), InceptionResNetV2, EfficientNet, MobileNetv2, ResNet, ResNeXt, MultiResUNet, linkNet-VGG19, DenseNet, SEResNet and SeResNeXt architectures were compared, where “Res” denotes a residual network. In addition, training was performed with 5 of the most advanced loss functions and validated by the Dice coefficient, sensitivity, and specificity. The proposed models achieved Dice values above 90%, with the EfficientNet architecture achieving 94.75% and 99% accuracy on the two tasks. Subsequently, classification was addressed with the ResNet50V2, VGG19, InceptionResNetV2, DenseNet121, InceptionV3, Xception and EfficientNetB7 networks. The proposed models achieved 96.97% and 97.73% accuracy through the VGG19 and ResNet50V2 networks on the lesion classification and degree of suspicion tasks, respectively. All three tasks were addressed with open-access databases, including the Digital Database for Screening Mammography (DDSM), the Mammographic Image Analysis Society (MIAS) database, and INbreast.Andres Anaya-IsazaLeonel Mera-JimenezJohan Manuel Cabrera-ChavarroLorena Guachi-GuachiDiego Peluffo-OrdonezJorge Ivan Rios-PatinoIEEEarticleArtificial intelligencebiomedical imagingcancerimage segmentationmachine learningmammographyElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 152206-152225 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Artificial intelligence biomedical imaging cancer image segmentation machine learning mammography Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Artificial intelligence biomedical imaging cancer image segmentation machine learning mammography Electrical engineering. Electronics. Nuclear engineering TK1-9971 Andres Anaya-Isaza Leonel Mera-Jimenez Johan Manuel Cabrera-Chavarro Lorena Guachi-Guachi Diego Peluffo-Ordonez Jorge Ivan Rios-Patino Comparison of Current Deep Convolutional Neural Networks for the Segmentation of Breast Masses in Mammograms
description	Breast cancer causes approximately 684,996 deaths worldwide, making it the leading cause of female cancer mortality. However, these figures can be reduced with early diagnosis through mammographic imaging, allowing for the timely and effective treatment of this disease. To establish the best tools for contributing to the automatic diagnosis of breast cancer, different deep learning (DL) architectures were compared in terms of breast lesion segmentation, lesion type classification, and degree of suspicion of malignancy tests. The tasks were completed with state-of-the-art architectures and backbones. Initially, during segmentation, the base UNet, Visual Geometry Group 19 (VGG19), InceptionResNetV2, EfficientNet, MobileNetv2, ResNet, ResNeXt, MultiResUNet, linkNet-VGG19, DenseNet, SEResNet and SeResNeXt architectures were compared, where “Res” denotes a residual network. In addition, training was performed with 5 of the most advanced loss functions and validated by the Dice coefficient, sensitivity, and specificity. The proposed models achieved Dice values above 90%, with the EfficientNet architecture achieving 94.75% and 99% accuracy on the two tasks. Subsequently, classification was addressed with the ResNet50V2, VGG19, InceptionResNetV2, DenseNet121, InceptionV3, Xception and EfficientNetB7 networks. The proposed models achieved 96.97% and 97.73% accuracy through the VGG19 and ResNet50V2 networks on the lesion classification and degree of suspicion tasks, respectively. All three tasks were addressed with open-access databases, including the Digital Database for Screening Mammography (DDSM), the Mammographic Image Analysis Society (MIAS) database, and INbreast.
format	article
author	Andres Anaya-Isaza Leonel Mera-Jimenez Johan Manuel Cabrera-Chavarro Lorena Guachi-Guachi Diego Peluffo-Ordonez Jorge Ivan Rios-Patino
author_facet	Andres Anaya-Isaza Leonel Mera-Jimenez Johan Manuel Cabrera-Chavarro Lorena Guachi-Guachi Diego Peluffo-Ordonez Jorge Ivan Rios-Patino
author_sort	Andres Anaya-Isaza
title	Comparison of Current Deep Convolutional Neural Networks for the Segmentation of Breast Masses in Mammograms
title_short	Comparison of Current Deep Convolutional Neural Networks for the Segmentation of Breast Masses in Mammograms
title_full	Comparison of Current Deep Convolutional Neural Networks for the Segmentation of Breast Masses in Mammograms
title_fullStr	Comparison of Current Deep Convolutional Neural Networks for the Segmentation of Breast Masses in Mammograms
title_full_unstemmed	Comparison of Current Deep Convolutional Neural Networks for the Segmentation of Breast Masses in Mammograms
title_sort	comparison of current deep convolutional neural networks for the segmentation of breast masses in mammograms
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/24da7c29b1dc4ff89aab881bc428dc86
work_keys_str_mv	AT andresanayaisaza comparisonofcurrentdeepconvolutionalneuralnetworksforthesegmentationofbreastmassesinmammograms AT leonelmerajimenez comparisonofcurrentdeepconvolutionalneuralnetworksforthesegmentationofbreastmassesinmammograms AT johanmanuelcabrerachavarro comparisonofcurrentdeepconvolutionalneuralnetworksforthesegmentationofbreastmassesinmammograms AT lorenaguachiguachi comparisonofcurrentdeepconvolutionalneuralnetworksforthesegmentationofbreastmassesinmammograms AT diegopeluffoordonez comparisonofcurrentdeepconvolutionalneuralnetworksforthesegmentationofbreastmassesinmammograms AT jorgeivanriospatino comparisonofcurrentdeepconvolutionalneuralnetworksforthesegmentationofbreastmassesinmammograms
_version_	1718419823692611584

Comparison of Current Deep Convolutional Neural Networks for the Segmentation of Breast Masses in Mammograms

Ejemplares similares