Classification of Skin Lesions into Seven Classes Using Transfer Learning with AlexNet

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.

[1]  Claus Garbe,et al.  Epidemiology of melanoma and nonmelanoma skin cancer--the role of sunlight. , 2008, Advances in experimental medicine and biology.

[2]  Noel C. F. Codella,et al.  Skin lesion analysis toward melanoma detection: A challenge at the 2017 International symposium on biomedical imaging (ISBI), hosted by the international skin imaging collaboration (ISIC) , 2016, 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).

[3]  Marcel F. Jonkman,et al.  MED-NODE: A computer-assisted melanoma diagnosis system using non-dermoscopic images , 2015, Expert Syst. Appl..

[4]  W V Stoecker,et al.  Texture in skin images: comparison of three methods to determine smoothness. , 1992, Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society.

[5]  Z. She,et al.  Combination of features from skin pattern and ABCD analysis for lesion classification , 2007, Skin research and technology : official journal of International Society for Bioengineering and the Skin (ISBS) [and] International Society for Digital Imaging of Skin (ISDIS) [and] International Society for Skin Imaging.

[6]  Barbara Caputo,et al.  Melanoma Recognition Using Representative and Discriminative Kernel Classifiers , 2006, CVAMIA.

[7]  Mohamed M. Foaud,et al.  Classification of skin lesions using transfer learning and augmentation with Alex-net , 2019, PloS one.

[8]  Rebecca L. Siegel Mph,et al.  Cancer statistics, 2016 , 2016 .

[9]  Reda Kasmi,et al.  Classification of malignant melanoma and benign skin lesions: implementation of automatic ABCD rule , 2016, IET Image Process..

[10]  João Manuel R. S. Tavares,et al.  Computational diagnosis of skin lesions from dermoscopic images using combined features , 2019, Neural Computing and Applications.

[11]  D. Kuijpers,et al.  Basal Cell Carcinoma , 2002, American journal of clinical dermatology.

[12]  Yanhui Guo,et al.  A Novel Skin Lesion Detection Approach Using Neutrosophic Clustering and Adaptive Region Growing in Dermoscopy Images , 2018, Symmetry.

[13]  Sidan Du,et al.  Multi-objective path finding in stochastic networks using a biogeography-based optimization method , 2016, Simul..

[14]  Hao Chen,et al.  Automated Melanoma Recognition in Dermoscopy Images via Very Deep Residual Networks , 2017, IEEE Transactions on Medical Imaging.

[15]  Khalid M. Hosny,et al.  Skin Cancer Classification using Deep Learning and Transfer Learning , 2018, 2018 9th Cairo International Biomedical Engineering Conference (CIBEC).

[16]  Sidan Du,et al.  Cerebral Micro-Bleed Detection Based on the Convolution Neural Network With Rank Based Average Pooling , 2017, IEEE Access.

[17]  K. S. Ravichandran,et al.  Novel Approaches for Diagnosing Melanoma Skin Lesions Through Supervised and Deep Learning Algorithms , 2016, Journal of Medical Systems.

[18]  Achim Hekler,et al.  Skin Cancer Classification Using Convolutional Neural Networks: Systematic Review , 2018, Journal of medical Internet research.

[19]  Ming Yang,et al.  Three-Category Classification of Magnetic Resonance Hearing Loss Images Based on Deep Autoencoder , 2017, Journal of Medical Systems.

[20]  Azriel Rosenfeld,et al.  A Comparative Study of Texture Measures for Terrain Classification , 1975, IEEE Transactions on Systems, Man, and Cybernetics.

[21]  John R. Smith,et al.  Deep Learning, Sparse Coding, and SVM for Melanoma Recognition in Dermoscopy Images , 2015, MLMI.

[22]  W. Jaschke,et al.  Automated melanoma recognition , 2001, IEEE Transactions on Medical Imaging.

[23]  João Manuel R. S. Tavares,et al.  From dermoscopy to mobile teledermatology , 2015 .

[24]  Russell C. Hardie,et al.  Skin Lesion Segmentation and Classification for ISIC 2018 Using Traditional Classifiers with Hand-Crafted Features , 2018, ArXiv.

[25]  Sebastian Thrun,et al.  Dermatologist-level classification of skin cancer with deep neural networks , 2017, Nature.

[26]  Dijana Stojanović,et al.  Understanding sensitivity, specificity and predictive values. , 2014, Vojnosanitetski pregled.

[27]  LinLin Shen,et al.  Skin Lesion Analysis towards Melanoma Detection Using Deep Learning Network , 2017, Sensors.

[28]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[29]  R Saranya,et al.  Automated Melanoma Recognition in Dermoscopy Images via Very Deep Residual Networks , 2019 .

[30]  Nils Gessert,et al.  Skin Lesion Diagnosis using Ensembles, Unscaled Multi-Crop Evaluation and Loss Weighting , 2018, ArXiv.

[31]  Désirée Ratner,et al.  Current concepts : Basal-cell carcinoma , 2005 .

[32]  Zhihai Lu,et al.  Pathological brain detection based on AlexNet and transfer learning , 2019, J. Comput. Sci..

[33]  Ling Wei,et al.  Fitness-scaling adaptive genetic algorithm with local search for solving the Multiple Depot Vehicle Routing Problem , 2016, Simul..

[34]  M. Binder,et al.  Epiluminescence microscopy. A useful tool for the diagnosis of pigmented skin lesions for formally trained dermatologists. , 1995, Archives of dermatology.

[35]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[36]  A. Kalloo,et al.  Results of the 2016 International Skin Imaging Collaboration International Symposium on Biomedical Imaging challenge: Comparison of the accuracy of computer algorithms to dermatologists for the diagnosis of melanoma from dermoscopic images , 2018, Journal of the American Academy of Dermatology.

[37]  A. Jemal,et al.  Cancer statistics, 2016 , 2016, CA: a cancer journal for clinicians.

[38]  Pedro M. Ferreira,et al.  PH2 - A dermoscopic image database for research and benchmarking , 2013, 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[39]  Salah Bourennane,et al.  Texture classification for multi-spectral images using spatial and spectral Gray Level Differences , 2010, 2010 2nd International Conference on Image Processing Theory, Tools and Applications.

[40]  Borko Furht,et al.  Rethinking Skin Lesion Segmentation in a Convolutional Classifier , 2018, Journal of Digital Imaging.

[41]  Amira S. Ashour,et al.  A novel cumulative level difference mean based GLDM and modified ABCD features ranked using eigenvector centrality approach for four skin lesion types classification , 2018, Comput. Methods Programs Biomed..