Early Detection of Melanoma using Optimized Segmentation-based CNN Classification
Keywords:
Mayfly Optimization (MFO), Active Contour Method (ACM), Ant Lion Optimization (ALO), Convolutional Neural Network (CNN) with Rectified Linear Unit (ReLU).Abstract
Skin cancer is among the most dangerous types of cancer, posing a significant threat to global mortality rates. Initial recognition is crucial in reducing the fatalities linked to this disease. However, the traditional diagnostic approach, which relies on visual inspection, has limitations in accuracy. This research investigates skin cancer detection and classification by incorporating Deep Learning and image processing tools. The initial step focuses on preprocessing dermoscopic images. To accomplish this, the Dull Razor technique is applied to effectively remove unwanted hair particles from the skin lesion. Subsequently, the Anisotropic Diffusion filter (ADF) is employed to attain image smoothing while preserving image edges. The refinement of the ADF is achieved by incorporating the Mayfly Optimization (MFO) algorithm to optimize gradient weight samples. Segmentation of the preprocessed skin images is carried out using the Active Contour Method (ACM), followed by morphological post-processing to refine the segmented output. The subsequent stage entails the utilization of the ALO algorithm to extract and select optimal features, ultimately enhancing classification accuracy. The culmination of this process involves the classification of chosen features using a CNN with ReLU activation function. The experimental analysis conducted on the Dermnet dataset, comprising nine distinct dermoscopic image types, yields an impressive accuracy rate of approximately 98.25%.
Downloads
References
Jerant AF, Johnson JT, Sheridan CD, Caffrey TJ (2000) Early detection and treatment of skin cancer. Am Fam Physician 62(2):357–368
Khaledyan D, Tajally A, Sarkhosh A, Shamsi A, Asgharnezhad H, Khosravi A, Nahavandi S (2021) Confidence aware neural networks for skin cancer detection. arXiv preprint arXiv:2107.09118
Rehman A, Naz S, Razzak I (2021) Leveraging big data analytics in healthcare enhancement: trends, challenges and opportunities. Multimed Syst 1–33:1339–1371
Razzak MI, Imran M, Xu G (2020) Big data analytics for preventive medicine. Neural Comput Appl 32(9):4417–4451
Shamsi A, Asgharnezhad H, Jokandan SS, Khosravi A, Kebria PM, Nahavandi D, Nahavandi S, Srinivasan D (2021) An uncertainty-aware transfer learning-based framework for covid-19 diagnosis. IEEE Trans on Neural Netw and Learning Syst 32(4):1408–1417
Brinker, T. J., Hekler, A., Enk, A. H., Klode, J., Hauschild, A., Berking, C., … Frohling, S. (2019). A convolutional neural network trained with dermoscopic images performed on par with 145 dermatologists in a clinical melanoma image classification task. European Journal of Cancer, 111, 148–154. doi:10.1016/j.ejca.2019.02.005
Goyal, M., Knackstedt, T., Yan, S., & Hassanpour, S. (2020). Artificial intelligence-based image classification methods for diagnosis of skin cancer: Challenges and opportunities. Computers in Biology and Medicine, 127,104065. doi:10.1016/j.compbiomed.2020.104065
Sagar, A., &Dheeba, J. (2020). Convolutional neural networks for classifying melanoma images. Cold Spring Harbour Laboratory. bioRxiv. doi:10.1101/2020.05.22.110973
Haenssle, H. A., Fink, C., Schneiderbauer, R., Toberer, F., Buhl, T., Blum, A., … Uhlmann, L. (2018). Man against machine: Diagnostic performance of a deep learning convolutional neural network for dermoscopic melanoma recognition in comparison to 58 dermatologists. Annals of Oncology : Official Journal of the European Society for Medical Oncology, 29(8), 1836–1842. doi:10.1093/annonc/mdy166 [Crossref] [PubMed] [Web of Science ®], [Google Scholar]
Haenssle, H. A., Fink, C., Toberer, F., Winkler, J., Stolz, W., Deinlein, T., … Zutt, M. (2020). Man against machine reloaded: Performance of a market-approved convolutional neural network in classifying a broad spectrum of skin lesions in comparison with 96 dermatologists working under less artificial conditions. Annals of Oncology : Official Journal of the European Society for Medical Oncology, 31(1), 137–143. doi:10.1016/j.annonc.2019.10.013
Adegun, A., &Viriri, S. (2021). Deep learning techniques for skin lesion analysis and melanoma cancer detection: A survey of state-of-the-art. Artificial Intelligence Review, 54(2), 811–841. doi:10.1007/s10462-020-09865-y
Akkoca-Gazioğlu, B. S., &Kamasak, M. (2020). Effects of objects and image quality on melanoma classification using deep neural networks. Biomedical Signal Processing and Control, 67, 102530. doi:10.21203/rs.3.rs-35907/v1
Jojoa Acosta, M. F., Caballero Tovar, L. Y., Garcia-Zapirain, M. B., &Percybrooks, W. S. (2021). Melanoma diagnosis using deep learning techniques on dermatoscopic images. BMC Medical Imaging, 21(1), 6. doi:10.1186/s12880-020-00534-8
Dildar, M., Akram, S., Irfan, M., Khan, H. U., Ramzan, M., Mahmood, A. R., … Mahnashi, M. H. (2021). Skin cancer detection: A review using deep learning techniques. International Journal of Environmental Research and Public Health, 18(10), 5479. doi:10.3390/ijerph18105479
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
