An efficient 3D color-texture feature and neural network technique for melanoma detection

Malignant melanoma is the deadliest form of skin cancer, but can be more readily treated successfully if detected in its early stages. Due to the increasing incidence of melanoma, research in the field of autonomous melanoma detection has accelerated. In this paper, a new method for feature extracti...

Full description

Bibliographic Details
Main Authors:	Firoz Warsi, Ruqaiya Khanam, Suraj Kamya, Carmen Paz Suárez-Araujo
Format:	Article
Language:	English
Published:	Elsevier 2019-01-01
Series:	Informatics in Medicine Unlocked
Online Access:	http://www.sciencedirect.com/science/article/pii/S2352914818302284

id	doaj-917cae07d9354726844b5dd570ff2fb1
record_format	Article
spelling	doaj-917cae07d9354726844b5dd570ff2fb12020-11-25T02:12:29ZengElsevierInformatics in Medicine Unlocked2352-91482019-01-0117An efficient 3D color-texture feature and neural network technique for melanoma detectionFiroz Warsi0Ruqaiya Khanam1Suraj Kamya2Carmen Paz Suárez-Araujo3Department of ECE, Galgotia University, Greater Noida, IndiaDepartment of ECE, Galgotia University, Greater Noida, India; Corresponding author.Department of ECE, IIMT College of Engineering, Greater Noida, IndiaInstituto Universitario de Ciencias y Tecnologías Cibernéticas, Universidad de Las Palmas de Gran Canaria, Las Palmas de Gran Canaria, SpainMalignant melanoma is the deadliest form of skin cancer, but can be more readily treated successfully if detected in its early stages. Due to the increasing incidence of melanoma, research in the field of autonomous melanoma detection has accelerated. In this paper, a new method for feature extraction from dermoscopic images, termed multi-direction 3D color-texture feature (CTF), is proposed, and detection is performed using a back propagation multilayer neural network (NN) classifier. The proposed method is tested on the PH2 dataset (publicly available) in terms of accuracy, sensitivity, and specificity. The extracted combined CTF is fairly discriminative. When it is input and tested in a neural network classifier that is provided, encouraging results are obtained, i.e. accuracy = 97.5%, sensitivity = 98.1% and specificity = 93.84%. Comparative result analyses with other methods are also discussed, and the results are also improved over benchmarking results for the PH2 dataset. Keywords: Melanoma, Color texturefeature, Dermoscopic image, Neural network classifier and skin cancerhttp://www.sciencedirect.com/science/article/pii/S2352914818302284
collection	DOAJ
language	English
format	Article
sources	DOAJ
author	Firoz Warsi Ruqaiya Khanam Suraj Kamya Carmen Paz Suárez-Araujo
spellingShingle	Firoz Warsi Ruqaiya Khanam Suraj Kamya Carmen Paz Suárez-Araujo An efficient 3D color-texture feature and neural network technique for melanoma detection Informatics in Medicine Unlocked
author_facet	Firoz Warsi Ruqaiya Khanam Suraj Kamya Carmen Paz Suárez-Araujo
author_sort	Firoz Warsi
title	An efficient 3D color-texture feature and neural network technique for melanoma detection
title_short	An efficient 3D color-texture feature and neural network technique for melanoma detection
title_full	An efficient 3D color-texture feature and neural network technique for melanoma detection
title_fullStr	An efficient 3D color-texture feature and neural network technique for melanoma detection
title_full_unstemmed	An efficient 3D color-texture feature and neural network technique for melanoma detection
title_sort	efficient 3d color-texture feature and neural network technique for melanoma detection
publisher	Elsevier
series	Informatics in Medicine Unlocked
issn	2352-9148
publishDate	2019-01-01
description	Malignant melanoma is the deadliest form of skin cancer, but can be more readily treated successfully if detected in its early stages. Due to the increasing incidence of melanoma, research in the field of autonomous melanoma detection has accelerated. In this paper, a new method for feature extraction from dermoscopic images, termed multi-direction 3D color-texture feature (CTF), is proposed, and detection is performed using a back propagation multilayer neural network (NN) classifier. The proposed method is tested on the PH2 dataset (publicly available) in terms of accuracy, sensitivity, and specificity. The extracted combined CTF is fairly discriminative. When it is input and tested in a neural network classifier that is provided, encouraging results are obtained, i.e. accuracy = 97.5%, sensitivity = 98.1% and specificity = 93.84%. Comparative result analyses with other methods are also discussed, and the results are also improved over benchmarking results for the PH2 dataset. Keywords: Melanoma, Color texturefeature, Dermoscopic image, Neural network classifier and skin cancer
url	http://www.sciencedirect.com/science/article/pii/S2352914818302284
work_keys_str_mv	AT firozwarsi anefficient3dcolortexturefeatureandneuralnetworktechniqueformelanomadetection AT ruqaiyakhanam anefficient3dcolortexturefeatureandneuralnetworktechniqueformelanomadetection AT surajkamya anefficient3dcolortexturefeatureandneuralnetworktechniqueformelanomadetection AT carmenpazsuarezaraujo anefficient3dcolortexturefeatureandneuralnetworktechniqueformelanomadetection AT firozwarsi efficient3dcolortexturefeatureandneuralnetworktechniqueformelanomadetection AT ruqaiyakhanam efficient3dcolortexturefeatureandneuralnetworktechniqueformelanomadetection AT surajkamya efficient3dcolortexturefeatureandneuralnetworktechniqueformelanomadetection AT carmenpazsuarezaraujo efficient3dcolortexturefeatureandneuralnetworktechniqueformelanomadetection
_version_	1724909039576416256

An efficient 3D color-texture feature and neural network technique for melanoma detection

Similar Items