Husam Khalaf Salih Juboori*
Department of Computer Engineering Techniques, Al-Rasheed University College, Baghdad, Iraq
*Husam.k.k.salih@alrasheedcol.edu.iq
Received: Nov 24, 2021 / Revised: Dec 04, 2021/ Accepted: Dec 25, 2021
DOI: http://dx.doi.org/10.47587/SA.2021.2410
Abstract
Skin cancer is now well recognized as a leading cause of death in humans. Skin cancer is defined as the abnormal proliferation of skin cells on the human body that has been exposed to sunlight for an extended period. Skin cancer can develop in any place on the female organism. Most malignancies are treatable if caught in their early stages. As a result, it is critical to discover skin cancer at an early stage to save the patient’s life. With modern technology, it is feasible to detect skin cancer at an early stage and treat it effectively. In this paper, we present a system for the identification of microscopic images that are based on a deep learning technique and an entity encoding scheme, both of which are implemented in Python. Note that the deep interpretation of a rescaled dermoscopic image is first retrieved by an extraordinarily deep residual human brain, which already has previously been trained on a large natural ImageNet dataset before being applied to the dermoscopic image. Local deep descriptors are then gathered by ordered less visual statistic characteristics, which are then used to construct a global picture representation based on a fisher vector encoding scheme. Finally, we used the fisher vector coded interpretations to arrange melanoma photos using a convolution neural network, which was trained on the data (CNN). This system can provide more discriminatory information despite its limited training examples because of its limited ability to distinguish between significant changes inside the same class of skin cancer and tiny changes between skin cancer and other types of skin cancer.
Keywords: Dermoscopic, Image Recognition, CNN Algorithm, Melanoma Detection, Segmentation
How to cite this article
Juboori, H.K.S. (2021). Detection of skin melanoma using deep learning approach. Science Archives, Vol. 2 (4) 330-334. http://dx.doi.org/10.47587/SA.2021.2410
References
Ali, A. A., & Al-Marzouqi, H. (2017, November). Melanoma detection using regular convolutional neural networks. In 2017 International Conference on Electrical and Computing Technologies and Applications (ICECTA) (pp. 1-5). IEEE.
Abbas, Q., Garcia, I. F., Emre Celebi, M., & Ahmad, W. (2013). A feature‐preserving hair removal algorithm for dermoscopy images. Skin Research and Technology, 19(1), e27-e36.
Bissoto, A., Perez, F., Ribeiro, V., Fornaciali, M., Avila, S., & Valle, E. (2018). Deep-learning ensembles for skin-lesion segmentation, analysis, classification: RECOD titans at ISIC challenge 2018. arXiv preprint arXiv:1808.08480.
Esteva, A., Kuprel, B., Novoa, R. A., Ko, J., Swetter, S. M., Blau, H. M., & Thrun, S. (2017). Dermatologist-level classification of skin cancer with deep neural networks. nature, 542(7639), 115-118.
Gaikwad, M., Gaikwad, P., Jagtap, P., Kadam, S., & Patil, R. R. (2020). Melanoma Cancer Detection using Deep Learning.
https://www.isicarchive.com/#!/topWithHeader/onlyHeaderTop/gallery
Kamboj, A. (2018, December). A color-based approach for melanoma skin cancer detection. In 2018 First International Conference on Secure Cyber Computing and Communication (ICSCCC) (pp. 508-513). IEEE.
Leelarani, K., Sangeetha, K., Nilofer, B., & Sangeetha, M. (2020). Bone Fracture Detection System using Image processing.
Patil, R., & Bellary, S. (2020). Machine learning approach in melanoma cancer stage detection. Journal of King Saud University-Computer and Information Sciences.
Patil, R., & Bellary, S. (2021). Transfer Learning Based System for Melanoma Type Detection. Revue d’Intelligence Artificielle, 35(2), 123-130.
Shen, J., Hao, X., Liang, Z., Liu, Y., Wang, W., & Shao, L. (2016). Real-time superpixel segmentation by DBSCAN clustering algorithm. IEEE transactions on image processing, 25(12), 5933-5942.
Yu, L., Chen, H., Dou, Q., Qin, J., & Heng, P. A. (2016). Automated melanoma recognition in dermoscopy images via very deep residual networks. IEEE transactions on medical imaging, 36(4), 994-1004.
License Article Metadata
This work is licensed under a Creative Commons Attribution 4.0 International License.
