International Journal of Advanced Networking and Applications

Open Access Open Access  Restricted Access Subscription Access

A CNN Framework for Classification of Melanoma and Benign Lesions on Dermatoscopic Skin Images


Affiliations
1 Department of Computer Engineering, Firat University, Elazig - 23119, Turkey
2 Department of Software Engineering, Firat University, Elazig - 23119, Turkey
 

Melanoma is the most common type of skin cancer due to a genetic predisposition. In recent years, it has been determined that the number of different types of skin cancer has increased worldwide and caused a large number of deaths. Some skin cancers, such as melanoma and its derivatives, can be prevented, but early and accurate diagnosis is very important for treatment. Image processing techniques in medical applications are frequently used in the diagnosis, follow-up, and treatment processes of skin cancer. However, manual control of medical images is laborious and time-consuming and is vulnerable to expert errors in the interpretation of images. Developing a safe and autonomous classification system for medical applications is a fundamental need. In this study, a CNN-based deep learning framework has been developed in which the HAM10000 dataset, a dermatoscopic clinical skin image collection, has been classified for skin cancer detection. Classification preprocessing using contrast limited adaptive histogram equalization is demonstrated by the accuracy results that improve the recognition of subtle features of class labels. A 45-layer model is proposed for classification. With this developed model, an accuracy rate of 99.69% has been achieved. The results show that the proposed model achieves high accuracies and F-measures with low false-negative compared to known classifiers. This CNN model showed the best two-level performance classifying melanoma and benign cases as nevi and non-nevi. It has emphasized that skin cancer can be detected early with the proposed model and can contribute to the execution of the treatment process.

Keywords

VClassification, CNN, Deep Learning, Image Processing, Melanoma.
User
Notifications
Font Size

  • A. L. Byrd, Y. Belkaid, J. A. Segre, The human skin microbiome. Nature Reviews Microbiology, 16(3), 2018, 143-155.

  • D. E. O’Sullivan, D. R. Brenner, P. A. Demers, P. J. Villeneuve, C. M. Friedenreich, W. D. King, ComPARe Study Group, Indoor tanning and skin cancer in Canada: A meta-analysis and attributable burden estimation. Cancer epidemiology, 59, 2019, 1-7.

  • A. J. Miller,M. C. Mihm, Melanoma, N Engl J Med 355, 2006, 51-65.

  • J. M. Yaiza, R. A. Gloria, G. O. M. Belén, L. R. Elena, J. Gema, M. J. Antonio,B. Houria, Melanoma cancer stem-like cells: Optimization method for culture, enrichment and maintenance. Tissue and Cell, 60, 2019, 48-59.

  • P. H. Viale, The American Cancer Society’s facts & figures: 2020 edition. Journal of the Advanced Practitioner in Oncology, 11(2), 2020, 135.

  • A. F. Jerant, J. T. Johnson, C. D. Sheridan, T. J. Caffrey, Early detection and treatment of skin cancer. American family physician, 62(2), 2000, 357-368.

  • K. Narasimhan, V. Elamaran, Wavelet-based energy features for diagnosis of melanoma from dermoscopic images. International Journal of Biomedical Engineering and Technology, 20(3), 201, 243-252.

  • A. Kulkarni, D. Mukhopadhyay, SVM classifier based melanoma image classification. Research Journal of Pharmacy and Technology, 10(12), 2017, 4391-4392.

  • V. M. Cohen, E. Pavlidou, J. DaCosta, A. K. Arora, T. Szyszko, M. S. Sagoo, P. Szlosarek, Staging uveal melanoma with whole-body positron-emission tomography/computed tomography and abdominal ultrasound: Low incidence of metastatic disease, high incidence of second primary cancers. Middle East African journal of ophthalmology, 25(2), 2018, 91.

  • B. Jan, H. Farman, M. Khan, M. Imran, I. U. Islam, A. Ahmad, G. Jeon, Deep learning in big data analytics: a comparative study. Computers & Electrical Engineering, 75, 2019, 275-287.

  • P. Tschandl, C. Rosendahl, H. Kittler, The HAM10000 dataset, a large collection of multi source dermatoscopic images of common pigmented skin lesions. Scientific Data, 5(1), 2018, 1-9.

  • F. Nachbar, W. Stolz, T. Merkle, A. B. Cognetta, T. Vogt, M. Landthaler, G. Plewig, The ABCD rule of dermatoscopy: high prospective value in the diagnosis of doubtful melanocytic skin lesions. Journal of the American Academy of Dermatology, 30(4), 1994, 551-559.

  • E. Harrington, B. Clyne, N. Wesseling, H. Sandhu, L. Armstrong, H. Bennett, T. Fahey, (2017). Diagnosing malignant melanoma in ambulatory care: a systematic review of clinical prediction rules. BMJ open, 7(3), 2017, e014096.

  • M. H. Jafari, N. Karimi, E. Nasr-Esfahani, S. Samavi, S. M. R. Soroushmehr, K. Ward, K. Najarian, Skin lesion segmentation in clinical images using deep learning. In 2016 23rd International conference on pattern recognition (ICPR), 337-342.

  • V. Yadav, V. D. Kaushik, Detection of melanoma skin disease by extracting high level features for skin lesions. International Journal of Advanced Intelligence Paradigms, 11(3-4), 2018, 397-408.

  • M. Ruela, C. Barata, J. S. Marques, J. Rozeira, A system for the detection of melanomas in dermoscopy images using shape and symmetry features. Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, 5(2), 2017, 127-137.

  • M.P.P. Meena, T.Balaji, Advanced Method Using Find and Detection Skin Cancer Classification. International Journal of Advanced Networking & Applications (IJANA), 08(05), 2017, 24-27.

  • K. Thurnhofer-Hemsi, Domínguez, Analyzing digital image by deep learning for melanoma diagnosis. In 2019 International Work-Conference on Artificial Neural Networks, 270-279.

  • A. Esteva, B. Kuprel, R. A. Novoa, J. Ko, S. M. Swetter, H. M. Blau, S. Thrun, Dermatologist-level classification of skin cancer with deep neural networks. Nature, 542(7639), 2017, 115-118.

  • T. Zhou, K. H. Thung, X. Zhu, D. Shen, Effective feature learning and fusion of multimodality data using stage‐wise deep neural network for dementia diagnosis. Human brain mapping, 40(3), 2019, 1001-1016.

  • L. Zhang, F. F. Yin, J. Cai, A multi-source adaptive MR image fusion technique for MR-Guided radiation therapy. International Journal of Radiation Oncology, Biology, Physics, 102(3), 2018, e552.

  • M. El Adoui, S. A. Mahmoudi, M. A. Larhmam, M. Benjelloun, MRI breast tumor segmentation using different encoder and decoder CNN architectures. Computers, 8(3), 2019, 52.

  • R. Rouhi, M. Jafari, S. Kasaei, P. Keshavarzian, Benign and malignant breast tumors classification based on region growing and CNN segmentation. Expert Systems with Applications, 42(3), 2015, 9901002.

  • R. Guerrero, C. Qin, O. Oktay, C. Bowles, L. Chen, R. Joules, D. Rueckert, White matter hyperintensity and stroke lesion segmentation and differentiation using convolutional neural networks. NeuroImage: Clinical, 17, 2018, 918-934.

  • Z. Gao, X. Wang, S. Sun, D. Wu, J. Bai, Y. Yin, V. H. C. de Albuquerque, Learning physical properties in complex visual scenes: an intelligent machine for perceiving blood flow dynamics from static CT angiography imaging. Neural Networks, 123, 2020, 82-93.

  • Z. Gao, J. Chung, M. Abdelrazek, S. Leung, W. K. Hau, Z. Xian, S. Li, S. Privileged modality distillation for vessel border detection in intracoronary imaging. IEEE transactions on medical imaging, 39(5), 2019, 1524-1534.

  • M. Prathiba, D. Jose, R. Saranya, Automated melanoma recognition in dermoscopy images via very deep residual networks. In 2019 IOP Conference Series: Materials Science and Engineering.

  • M. Abd El Aziz, A. A. Ewees, A. E. Hassanien, Whale optimization algorithm and moth-flame optimization for multilevel thresholding image segmentation. Expert Systems with Applications, 83, 2017, 242-256.

  • S. Mirjalili, A. Lewis, The whale optimization algorithm. Advances in engineering software, 95, 2016, 51-67.

  • Y. D. Zhang, C. Pan, J. Sun, C. Tang, Multiple sclerosis identification by convolutional neural network with dropout and parametric ReLU. Journal of computational science, 28, 2018, 1-10.

  • E. Limonova, A. Sheshkus, A. Ivanova, D. Nikolaev, Convolutional neural network structure transformations for complexity reduction and speed improvement. Pattern Recognition and Image Analysis, 28(1), 2018, 24-33.

  • M. V. Valueva, N. N.Nagornov, P. A. Lyakhov, G. V. Valuev, N. I. Chervyakov, N. I. Application of the residue number system to reduce hardware costs of the convolutional neural network implementation. Mathematics and Computers in Simulation, 177, 2020, 232-243.

  • K. Thurnhofer-Hemsi, E. Dominguez, A convolutional neural network framework for accurate skin cancer detection. Neural Processing Letters, 2020, 1-21.

  • N. Zhang, Y. X. Cai, Y. Y. Wang, Y. T. Tian, X. L. Wang, B. Badami, Skin cancer diagnosis based on optimized convolutional neural network. Artificial intelligence in medicine, 102, 2020, 101756.

  • D. Jain, V. Singh, Feature selection and classification systems for chronic disease prediction: A review. Egyptian Informatics Journal, 19(3), 2018, 179-189.

  • A. Luque, A. Carrasco,A. Martín, A. de las Heras, The impact of class imbalance in classification performance metrics based on the binary confusion matrix. Pattern Recognition, 91, 2019, 216-231.

  • A. H. Shahin, A. Kamal, M. A. Elattar, Deep ensemble learning for skin lesion classification from dermoscopic images. In 2018 9th Cairo International Biomedical Engineering Conference (CIBEC), 2018, 150-153.

  • M. A. Khan,M. Y. Javed, M. Sharif, T. Saba, A. Rehman, Multi-model deep neural network based features extraction and optimal selection approach for skin lesion classification,In 2019 international conference on computer and information sciences (ICCIS), 2019, 1-7.

  • D. Moldovan, Transfer learning based method for two-step skin cancer images classification. In 2019 E-Health and Bioengineering Conference (EHB),2019, 1-4.

  • A. Mobiny, A. Singh, H. Van Nguyen, Risk-aware machine learning classifier for skin lesion diagnosis. Journal of clinical medicine, 8(8), 2019, 1241.

  • W. Sae-Lim, W. Wettayaprasit, P. Aiyarak, Convolutional neural networks using mobilenet for skin lesion classification,In 2019 16th international joint conference on computer science and software engineering (JCSSE)2019, 242-247, IEEE.

  • K. Pai,A. Giridharan, Convolutional Neural Networks for classifying skin lesions,In TENCON 2019-2019 IEEE Region 10 Conference 2019, 1794-1796.


Abstract Views: 346

PDF Views: 2




  • A CNN Framework for Classification of Melanoma and Benign Lesions on Dermatoscopic Skin Images

Abstract Views: 346  |  PDF Views: 2

Authors

Erdal Özbay
Department of Computer Engineering, Firat University, Elazig - 23119, Turkey
Feyza Altunbey Özbay
Department of Software Engineering, Firat University, Elazig - 23119, Turkey

Abstract


Melanoma is the most common type of skin cancer due to a genetic predisposition. In recent years, it has been determined that the number of different types of skin cancer has increased worldwide and caused a large number of deaths. Some skin cancers, such as melanoma and its derivatives, can be prevented, but early and accurate diagnosis is very important for treatment. Image processing techniques in medical applications are frequently used in the diagnosis, follow-up, and treatment processes of skin cancer. However, manual control of medical images is laborious and time-consuming and is vulnerable to expert errors in the interpretation of images. Developing a safe and autonomous classification system for medical applications is a fundamental need. In this study, a CNN-based deep learning framework has been developed in which the HAM10000 dataset, a dermatoscopic clinical skin image collection, has been classified for skin cancer detection. Classification preprocessing using contrast limited adaptive histogram equalization is demonstrated by the accuracy results that improve the recognition of subtle features of class labels. A 45-layer model is proposed for classification. With this developed model, an accuracy rate of 99.69% has been achieved. The results show that the proposed model achieves high accuracies and F-measures with low false-negative compared to known classifiers. This CNN model showed the best two-level performance classifying melanoma and benign cases as nevi and non-nevi. It has emphasized that skin cancer can be detected early with the proposed model and can contribute to the execution of the treatment process.

Keywords


VClassification, CNN, Deep Learning, Image Processing, Melanoma.

References