Tags

Type your tag names separated by a space and hit enter

Classification of Skin Lesions into Seven Classes Using Transfer Learning with AlexNet.
J Digit Imaging. 2020 Jun 30 [Online ahead of print]JD

Abstract

Melanoma is deadly skin cancer. There is a high similarity between different kinds of skin lesions, which lead to incorrect classification. Accurate classification of a skin lesion in its early stages saves human life. In this paper, a highly accurate method proposed for the skin lesion classification process. The proposed method utilized transfer learning with pre-trained AlexNet. The parameters of the original model used as initial values, where we randomly initialize the weights of the last three replaced layers. The proposed method was tested using the most recent public dataset, ISIC 2018. Based on the obtained results, we could say that the proposed method achieved a great success where it accurately classifies the skin lesions into seven classes. These classes are melanoma, melanocytic nevus, basal cell carcinoma, actinic keratosis, benign keratosis, dermatofibroma, and vascular lesion. The achieved percentages are 98.70%, 95.60%, 99.27%, and 95.06% for accuracy, sensitivity, specificity, and precision, respectively.

Authors+Show Affiliations

Department of Information Technology, Faculty of Computers and Informatics, Zagazig, University, Zagazig 44519, Egypt. k_hosny@yahoo.com.Department of Robotics and Intelligent Machines, Faculty of Artificial Intelligence, KafrElSheikh University, KafrElSheikh, 33511, Egypt.Department of Electronics and Communication, Faculty of Engineering, Zagazig University, Zagazig 44519, Egypt.

Pub Type(s)

Journal Article

Language

eng

PubMed ID

32607904

Citation

Hosny, Khalid M., et al. "Classification of Skin Lesions Into Seven Classes Using Transfer Learning With AlexNet." Journal of Digital Imaging, 2020.
Hosny KM, Kassem MA, Fouad MM. Classification of Skin Lesions into Seven Classes Using Transfer Learning with AlexNet. J Digit Imaging. 2020.
Hosny, K. M., Kassem, M. A., & Fouad, M. M. (2020). Classification of Skin Lesions into Seven Classes Using Transfer Learning with AlexNet. Journal of Digital Imaging. https://doi.org/10.1007/s10278-020-00371-9
Hosny KM, Kassem MA, Fouad MM. Classification of Skin Lesions Into Seven Classes Using Transfer Learning With AlexNet. J Digit Imaging. 2020 Jun 30; PubMed PMID: 32607904.
* Article titles in AMA citation format should be in sentence-case
TY - JOUR T1 - Classification of Skin Lesions into Seven Classes Using Transfer Learning with AlexNet. AU - Hosny,Khalid M, AU - Kassem,Mohamed A, AU - Fouad,Mohamed M, Y1 - 2020/06/30/ PY - 2020/7/2/entrez KW - AlexNet KW - Classification of skin lesions KW - ISIC 2018 KW - Melanoma KW - Transfer learning JF - Journal of digital imaging JO - J Digit Imaging N2 - Melanoma is deadly skin cancer. There is a high similarity between different kinds of skin lesions, which lead to incorrect classification. Accurate classification of a skin lesion in its early stages saves human life. In this paper, a highly accurate method proposed for the skin lesion classification process. The proposed method utilized transfer learning with pre-trained AlexNet. The parameters of the original model used as initial values, where we randomly initialize the weights of the last three replaced layers. The proposed method was tested using the most recent public dataset, ISIC 2018. Based on the obtained results, we could say that the proposed method achieved a great success where it accurately classifies the skin lesions into seven classes. These classes are melanoma, melanocytic nevus, basal cell carcinoma, actinic keratosis, benign keratosis, dermatofibroma, and vascular lesion. The achieved percentages are 98.70%, 95.60%, 99.27%, and 95.06% for accuracy, sensitivity, specificity, and precision, respectively. SN - 1618-727X UR - https://www.unboundmedicine.com/medline/citation/32607904/Classification_of_Skin_Lesions_into_Seven_Classes_Using_Transfer_Learning_with_AlexNet L2 - https://doi.org/10.1007/s10278-020-00371-9 DB - PRIME DP - Unbound Medicine ER -
Try the Free App:
Prime PubMed app for iOS iPhone iPad
Prime PubMed app for Android
Prime PubMed is provided
free to individuals by:
Unbound Medicine.