Gender and age detection assist convolutional neural networks in classification of thorax diseases

Conventionally, convolutional neural networks (CNNs) have been used to identify and detect thorax diseases on chest x-ray images. To identify thorax diseases, CNNs typically learn two types of information: disease-specific features and generic anatomical features. CNNs focus on disease-specific feat...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Mumtaz Ali, Riaz Ali
Formato:	article
Lenguaje:	EN
Publicado:	PeerJ Inc. 2021
Materias:	Gender Age Thorax disease classification Convolutional neural networks Electronic computers. Computer science QA75.5-76.95
Acceso en línea:	https://doaj.org/article/3c91a42470f14b0e92a9b4af49ed205f
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:3c91a42470f14b0e92a9b4af49ed205f
record_format	dspace
spelling	oai:doaj.org-article:3c91a42470f14b0e92a9b4af49ed205f2021-11-11T15:05:17ZGender and age detection assist convolutional neural networks in classification of thorax diseases10.7717/peerj-cs.7382376-5992https://doaj.org/article/3c91a42470f14b0e92a9b4af49ed205f2021-11-01T00:00:00Zhttps://peerj.com/articles/cs-738.pdfhttps://peerj.com/articles/cs-738/https://doaj.org/toc/2376-5992Conventionally, convolutional neural networks (CNNs) have been used to identify and detect thorax diseases on chest x-ray images. To identify thorax diseases, CNNs typically learn two types of information: disease-specific features and generic anatomical features. CNNs focus on disease-specific features while ignoring the rest of the anatomical features during their operation. There is no evidence that generic anatomical features improve or worsen the performance of convolutional neural networks for thorax disease classification in the current research. As a consequence, the relevance of general anatomical features in boosting the performance of CNNs for thorax disease classification is investigated in this study. We employ a dual-stream CNN model to learn anatomical features before training the model for thorax disease classification. The dual-stream technique is used to compel the model to learn structural information because initial layers of CNNs often learn features of edges and boundaries. As a result, a dual-stream model with minimal layers learns structural and anatomical features as a priority. To make the technique more comprehensive, we first train the model to identify gender and age and then classify thorax diseases using the information acquired. Only when the model learns the anatomical features can it detect gender and age. We also use Non-negative Matrix Factorization (NMF) and Contrast Limited Adaptive Histogram Equalization (CLAHE) to pre-process the training data, which suppresses disease-related information while amplifying general anatomical features, allowing the model to acquire anatomical features considerably faster. Finally, the model that was earlier trained for gender and age detection is retrained for thorax disease classification using original data. The proposed technique increases the performance of convolutional neural networks for thorax disease classification, as per experiments on the Chest X-ray14 dataset. We can also see the significant parts of the image that contribute more for gender, age, and a certain thorax disease by visualizing the features. The proposed study achieves two goals: first, it produces novel gender and age identification results on chest X-ray images that may be used in biometrics, forensics, and anthropology, and second, it highlights the importance of general anatomical features in thorax disease classification. In comparison to state-of-the-art results, the proposed work also produces competitive results.Mumtaz AliRiaz AliPeerJ Inc.articleGenderAgeThorax disease classificationConvolutional neural networksElectronic computers. Computer scienceQA75.5-76.95ENPeerJ Computer Science, Vol 7, p e738 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Gender Age Thorax disease classification Convolutional neural networks Electronic computers. Computer science QA75.5-76.95
spellingShingle	Gender Age Thorax disease classification Convolutional neural networks Electronic computers. Computer science QA75.5-76.95 Mumtaz Ali Riaz Ali Gender and age detection assist convolutional neural networks in classification of thorax diseases
description	Conventionally, convolutional neural networks (CNNs) have been used to identify and detect thorax diseases on chest x-ray images. To identify thorax diseases, CNNs typically learn two types of information: disease-specific features and generic anatomical features. CNNs focus on disease-specific features while ignoring the rest of the anatomical features during their operation. There is no evidence that generic anatomical features improve or worsen the performance of convolutional neural networks for thorax disease classification in the current research. As a consequence, the relevance of general anatomical features in boosting the performance of CNNs for thorax disease classification is investigated in this study. We employ a dual-stream CNN model to learn anatomical features before training the model for thorax disease classification. The dual-stream technique is used to compel the model to learn structural information because initial layers of CNNs often learn features of edges and boundaries. As a result, a dual-stream model with minimal layers learns structural and anatomical features as a priority. To make the technique more comprehensive, we first train the model to identify gender and age and then classify thorax diseases using the information acquired. Only when the model learns the anatomical features can it detect gender and age. We also use Non-negative Matrix Factorization (NMF) and Contrast Limited Adaptive Histogram Equalization (CLAHE) to pre-process the training data, which suppresses disease-related information while amplifying general anatomical features, allowing the model to acquire anatomical features considerably faster. Finally, the model that was earlier trained for gender and age detection is retrained for thorax disease classification using original data. The proposed technique increases the performance of convolutional neural networks for thorax disease classification, as per experiments on the Chest X-ray14 dataset. We can also see the significant parts of the image that contribute more for gender, age, and a certain thorax disease by visualizing the features. The proposed study achieves two goals: first, it produces novel gender and age identification results on chest X-ray images that may be used in biometrics, forensics, and anthropology, and second, it highlights the importance of general anatomical features in thorax disease classification. In comparison to state-of-the-art results, the proposed work also produces competitive results.
format	article
author	Mumtaz Ali Riaz Ali
author_facet	Mumtaz Ali Riaz Ali
author_sort	Mumtaz Ali
title	Gender and age detection assist convolutional neural networks in classification of thorax diseases
title_short	Gender and age detection assist convolutional neural networks in classification of thorax diseases
title_full	Gender and age detection assist convolutional neural networks in classification of thorax diseases
title_fullStr	Gender and age detection assist convolutional neural networks in classification of thorax diseases
title_full_unstemmed	Gender and age detection assist convolutional neural networks in classification of thorax diseases
title_sort	gender and age detection assist convolutional neural networks in classification of thorax diseases
publisher	PeerJ Inc.
publishDate	2021
url	https://doaj.org/article/3c91a42470f14b0e92a9b4af49ed205f
work_keys_str_mv	AT mumtazali genderandagedetectionassistconvolutionalneuralnetworksinclassificationofthoraxdiseases AT riazali genderandagedetectionassistconvolutionalneuralnetworksinclassificationofthoraxdiseases
_version_	1718437124172152832

Gender and age detection assist convolutional neural networks in classification of thorax diseases

Ejemplares similares