Cite Article

Skin Lesion Detection and Classification Using Convolutional Neural Network for Deep Feature Extraction and Support Vector Machine

Choose citation format

BibTeX

@article{IJASEIT13679,
   author = {Oscar P. Yanchatuña and Jackeline P. Pereira and Kevin O. Pila and Paola A. Vásquez and Keiko S. Veintimilla and Gandhi F. Villalba-Meneses and Omar Alvarado-Cando and Diego Almeida-Galárraga},
   title = {Skin Lesion Detection and Classification Using Convolutional Neural Network for Deep Feature Extraction and Support Vector Machine},
   journal = {International Journal on Advanced Science, Engineering and Information Technology},
   volume = {11},
   number = {3},
   year = {2021},
   pages = {1260--1267},
   keywords = {Skin lesions; melanoma; image segmentation; image preprocessing; convolutional neural network; HAM10000.},
   abstract = {Pigmented skin lesion identification is essential for detecting harmful pathologies related to this large organ, especially cancer. An analysis of the different methods and projects developed to diagnose these illnesses throughout the years showed that they had become very useful tools to identify melanoma, dermatofibroma, and basal cell carcinoma, among other types of cancer, are seen through the use of new computer-aided technologies. The most common diagnosis is based on dermoscopy and the dermatologist expertise that can improve accuracy with image detection techniques and classification by computer. Therefore, this study aims to develop software models able to detect and classify skin cancer. The following work is based on the use of dermoscopy images obtained from the HAM10000 dataset, a database with 10000 images previously tested and validated for research use. The main process is divided into three relevant parts: image segmentation, feature extraction (FE) using ten different pre-trained Convolutional Neural Networks (CNNs), and Support Vector Machine (SVM) to establish a classification model. According to the results, the models of classification performed very well using the image segmentation step, showing average accuracies between 80.67% (Xception) and 90% (Alexnet). In contrast to the process without using image segmentation, where no method reached 60%. AlexNet plus SVM model showed the minor running time and presented the higher accuracy rate (90.34%) for the correct identification and classification of the seven categories of cutaneous lesions taken into account.},
   issn = {2088-5334},
   publisher = {INSIGHT - Indonesian Society for Knowledge and Human Development},
   url = {http://ijaseit.insightsociety.org/index.php?option=com_content&view=article&id=9&Itemid=1&article_id=13679},
   doi = {10.18517/ijaseit.11.3.13679}
}

EndNote

%A Yanchatuña, Oscar P.
%A Pereira, Jackeline P.
%A Pila, Kevin O.
%A Vásquez, Paola A.
%A Veintimilla, Keiko S.
%A Villalba-Meneses, Gandhi F.
%A Alvarado-Cando, Omar
%A Almeida-Galárraga, Diego
%D 2021
%T Skin Lesion Detection and Classification Using Convolutional Neural Network for Deep Feature Extraction and Support Vector Machine
%B 2021
%9 Skin lesions; melanoma; image segmentation; image preprocessing; convolutional neural network; HAM10000.
%! Skin Lesion Detection and Classification Using Convolutional Neural Network for Deep Feature Extraction and Support Vector Machine
%K Skin lesions; melanoma; image segmentation; image preprocessing; convolutional neural network; HAM10000.
%X Pigmented skin lesion identification is essential for detecting harmful pathologies related to this large organ, especially cancer. An analysis of the different methods and projects developed to diagnose these illnesses throughout the years showed that they had become very useful tools to identify melanoma, dermatofibroma, and basal cell carcinoma, among other types of cancer, are seen through the use of new computer-aided technologies. The most common diagnosis is based on dermoscopy and the dermatologist expertise that can improve accuracy with image detection techniques and classification by computer. Therefore, this study aims to develop software models able to detect and classify skin cancer. The following work is based on the use of dermoscopy images obtained from the HAM10000 dataset, a database with 10000 images previously tested and validated for research use. The main process is divided into three relevant parts: image segmentation, feature extraction (FE) using ten different pre-trained Convolutional Neural Networks (CNNs), and Support Vector Machine (SVM) to establish a classification model. According to the results, the models of classification performed very well using the image segmentation step, showing average accuracies between 80.67% (Xception) and 90% (Alexnet). In contrast to the process without using image segmentation, where no method reached 60%. AlexNet plus SVM model showed the minor running time and presented the higher accuracy rate (90.34%) for the correct identification and classification of the seven categories of cutaneous lesions taken into account.
%U http://ijaseit.insightsociety.org/index.php?option=com_content&view=article&id=9&Itemid=1&article_id=13679
%R doi:10.18517/ijaseit.11.3.13679
%J International Journal on Advanced Science, Engineering and Information Technology
%V 11
%N 3
%@ 2088-5334

IEEE

Oscar P. Yanchatuña,Jackeline P. Pereira,Kevin O. Pila,Paola A. Vásquez,Keiko S. Veintimilla,Gandhi F. Villalba-Meneses,Omar Alvarado-Cando and Diego Almeida-Galárraga,"Skin Lesion Detection and Classification Using Convolutional Neural Network for Deep Feature Extraction and Support Vector Machine," International Journal on Advanced Science, Engineering and Information Technology, vol. 11, no. 3, pp. 1260-1267, 2021. [Online]. Available: http://dx.doi.org/10.18517/ijaseit.11.3.13679.

RefMan/ProCite (RIS)

TY  - JOUR
AU  - Yanchatuña, Oscar P.
AU  - Pereira, Jackeline P.
AU  - Pila, Kevin O.
AU  - Vásquez, Paola A.
AU  - Veintimilla, Keiko S.
AU  - Villalba-Meneses, Gandhi F.
AU  - Alvarado-Cando, Omar
AU  - Almeida-Galárraga, Diego
PY  - 2021
TI  - Skin Lesion Detection and Classification Using Convolutional Neural Network for Deep Feature Extraction and Support Vector Machine
JF  - International Journal on Advanced Science, Engineering and Information Technology; Vol. 11 (2021) No. 3
Y2  - 2021
SP  - 1260
EP  - 1267
SN  - 2088-5334
PB  - INSIGHT - Indonesian Society for Knowledge and Human Development
KW  - Skin lesions; melanoma; image segmentation; image preprocessing; convolutional neural network; HAM10000.
N2  - Pigmented skin lesion identification is essential for detecting harmful pathologies related to this large organ, especially cancer. An analysis of the different methods and projects developed to diagnose these illnesses throughout the years showed that they had become very useful tools to identify melanoma, dermatofibroma, and basal cell carcinoma, among other types of cancer, are seen through the use of new computer-aided technologies. The most common diagnosis is based on dermoscopy and the dermatologist expertise that can improve accuracy with image detection techniques and classification by computer. Therefore, this study aims to develop software models able to detect and classify skin cancer. The following work is based on the use of dermoscopy images obtained from the HAM10000 dataset, a database with 10000 images previously tested and validated for research use. The main process is divided into three relevant parts: image segmentation, feature extraction (FE) using ten different pre-trained Convolutional Neural Networks (CNNs), and Support Vector Machine (SVM) to establish a classification model. According to the results, the models of classification performed very well using the image segmentation step, showing average accuracies between 80.67% (Xception) and 90% (Alexnet). In contrast to the process without using image segmentation, where no method reached 60%. AlexNet plus SVM model showed the minor running time and presented the higher accuracy rate (90.34%) for the correct identification and classification of the seven categories of cutaneous lesions taken into account.
UR  - http://ijaseit.insightsociety.org/index.php?option=com_content&view=article&id=9&Itemid=1&article_id=13679
DO  - 10.18517/ijaseit.11.3.13679

RefWorks

RT Journal Article
ID 13679
A1 Yanchatuña, Oscar P.
A1 Pereira, Jackeline P.
A1 Pila, Kevin O.
A1 Vásquez, Paola A.
A1 Veintimilla, Keiko S.
A1 Villalba-Meneses, Gandhi F.
A1 Alvarado-Cando, Omar
A1 Almeida-Galárraga, Diego
T1 Skin Lesion Detection and Classification Using Convolutional Neural Network for Deep Feature Extraction and Support Vector Machine
JF International Journal on Advanced Science, Engineering and Information Technology
VO 11
IS 3
YR 2021
SP 1260
OP 1267
SN 2088-5334
PB INSIGHT - Indonesian Society for Knowledge and Human Development
K1 Skin lesions; melanoma; image segmentation; image preprocessing; convolutional neural network; HAM10000.
AB Pigmented skin lesion identification is essential for detecting harmful pathologies related to this large organ, especially cancer. An analysis of the different methods and projects developed to diagnose these illnesses throughout the years showed that they had become very useful tools to identify melanoma, dermatofibroma, and basal cell carcinoma, among other types of cancer, are seen through the use of new computer-aided technologies. The most common diagnosis is based on dermoscopy and the dermatologist expertise that can improve accuracy with image detection techniques and classification by computer. Therefore, this study aims to develop software models able to detect and classify skin cancer. The following work is based on the use of dermoscopy images obtained from the HAM10000 dataset, a database with 10000 images previously tested and validated for research use. The main process is divided into three relevant parts: image segmentation, feature extraction (FE) using ten different pre-trained Convolutional Neural Networks (CNNs), and Support Vector Machine (SVM) to establish a classification model. According to the results, the models of classification performed very well using the image segmentation step, showing average accuracies between 80.67% (Xception) and 90% (Alexnet). In contrast to the process without using image segmentation, where no method reached 60%. AlexNet plus SVM model showed the minor running time and presented the higher accuracy rate (90.34%) for the correct identification and classification of the seven categories of cutaneous lesions taken into account.
LK http://ijaseit.insightsociety.org/index.php?option=com_content&view=article&id=9&Itemid=1&article_id=13679
DO  - 10.18517/ijaseit.11.3.13679