Intelligent Data Analytics for Diagnosing Melanoma Skin Lesions via Deep Learning in IoT System

Melanoma is considered to be one of the most dangerous human malignancy, which is diagnosed visually or by dermoscopic analysis and histopathological examination. However, as these traditional methods are based on human experience and implemented manually, there have been great limitations for gener...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Shixiang Zhang, Shuaiqi Huang, Hongkai Wu, Zicong Yang, Yinda Chen
Formato:	article
Lenguaje:	EN
Publicado:	Hindawi Limited 2021
Materias:	Telecommunication TK5101-6720
Acceso en línea:	https://doaj.org/article/bc0bca85f77f4f99a85732b47d3b9f3d
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:bc0bca85f77f4f99a85732b47d3b9f3d
record_format	dspace
spelling	oai:doaj.org-article:bc0bca85f77f4f99a85732b47d3b9f3d2021-11-29T00:56:28ZIntelligent Data Analytics for Diagnosing Melanoma Skin Lesions via Deep Learning in IoT System1875-905X10.1155/2021/8700506https://doaj.org/article/bc0bca85f77f4f99a85732b47d3b9f3d2021-01-01T00:00:00Zhttp://dx.doi.org/10.1155/2021/8700506https://doaj.org/toc/1875-905XMelanoma is considered to be one of the most dangerous human malignancy, which is diagnosed visually or by dermoscopic analysis and histopathological examination. However, as these traditional methods are based on human experience and implemented manually, there have been great limitations for general usability in current clinical practice. In this paper, a novel hybrid machine learning approach is proposed to identify melanoma for skin healthcare in various cases. The proposed approach consists of classic machine learning methods, including convolutional neural networks (CNNs), EfficientNet, and XGBoost supervised machine learning. In the proposed approach, a deep learning model is trained directly from raw pixels and image labels for classification of skin lesions. Then, solely based on modeling of various features from patients, an XGBoost model is adopted to predict skin cancer. Following that, a diagnostic system which composed of the deep learning model and XGBoost model is developed to further improve the prediction efficiency and accuracy. Different from experience-based methods and solely image-based machine learning methods, the proposed approach is developed based on the theory of deep learning and feature engineering. Experiments show that the hybrid model outperforms single model like the traditional deep learning model or XGBoost model. Moreover, the data-driven-based characteristics can help the proposed approach develop a guideline for image analysis in other medical applications.Shixiang ZhangShuaiqi HuangHongkai WuZicong YangYinda ChenHindawi LimitedarticleTelecommunicationTK5101-6720ENMobile Information Systems, Vol 2021 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Telecommunication TK5101-6720
spellingShingle	Telecommunication TK5101-6720 Shixiang Zhang Shuaiqi Huang Hongkai Wu Zicong Yang Yinda Chen Intelligent Data Analytics for Diagnosing Melanoma Skin Lesions via Deep Learning in IoT System
description	Melanoma is considered to be one of the most dangerous human malignancy, which is diagnosed visually or by dermoscopic analysis and histopathological examination. However, as these traditional methods are based on human experience and implemented manually, there have been great limitations for general usability in current clinical practice. In this paper, a novel hybrid machine learning approach is proposed to identify melanoma for skin healthcare in various cases. The proposed approach consists of classic machine learning methods, including convolutional neural networks (CNNs), EfficientNet, and XGBoost supervised machine learning. In the proposed approach, a deep learning model is trained directly from raw pixels and image labels for classification of skin lesions. Then, solely based on modeling of various features from patients, an XGBoost model is adopted to predict skin cancer. Following that, a diagnostic system which composed of the deep learning model and XGBoost model is developed to further improve the prediction efficiency and accuracy. Different from experience-based methods and solely image-based machine learning methods, the proposed approach is developed based on the theory of deep learning and feature engineering. Experiments show that the hybrid model outperforms single model like the traditional deep learning model or XGBoost model. Moreover, the data-driven-based characteristics can help the proposed approach develop a guideline for image analysis in other medical applications.
format	article
author	Shixiang Zhang Shuaiqi Huang Hongkai Wu Zicong Yang Yinda Chen
author_facet	Shixiang Zhang Shuaiqi Huang Hongkai Wu Zicong Yang Yinda Chen
author_sort	Shixiang Zhang
title	Intelligent Data Analytics for Diagnosing Melanoma Skin Lesions via Deep Learning in IoT System
title_short	Intelligent Data Analytics for Diagnosing Melanoma Skin Lesions via Deep Learning in IoT System
title_full	Intelligent Data Analytics for Diagnosing Melanoma Skin Lesions via Deep Learning in IoT System
title_fullStr	Intelligent Data Analytics for Diagnosing Melanoma Skin Lesions via Deep Learning in IoT System
title_full_unstemmed	Intelligent Data Analytics for Diagnosing Melanoma Skin Lesions via Deep Learning in IoT System
title_sort	intelligent data analytics for diagnosing melanoma skin lesions via deep learning in iot system
publisher	Hindawi Limited
publishDate	2021
url	https://doaj.org/article/bc0bca85f77f4f99a85732b47d3b9f3d
work_keys_str_mv	AT shixiangzhang intelligentdataanalyticsfordiagnosingmelanomaskinlesionsviadeeplearninginiotsystem AT shuaiqihuang intelligentdataanalyticsfordiagnosingmelanomaskinlesionsviadeeplearninginiotsystem AT hongkaiwu intelligentdataanalyticsfordiagnosingmelanomaskinlesionsviadeeplearninginiotsystem AT zicongyang intelligentdataanalyticsfordiagnosingmelanomaskinlesionsviadeeplearninginiotsystem AT yindachen intelligentdataanalyticsfordiagnosingmelanomaskinlesionsviadeeplearninginiotsystem
_version_	1718407731513131008

Intelligent Data Analytics for Diagnosing Melanoma Skin Lesions via Deep Learning in IoT System

Ejemplares similares