Detection for melanoma skin cancer through ACCF, BPPF, and CLF techniques with machine learning approach
dc.contributor.author | Kavitha, P. | |
dc.contributor.author | Ayyappan, G. | |
dc.contributor.author | Jayagopal, P. | |
dc.contributor.author | Mathivanan, S.K. | |
dc.contributor.author | Mallik, S. | |
dc.contributor.author | Al-Rasheed, A. | |
dc.contributor.author | Alqahtani, M.S. | |
dc.contributor.author | Soufiene, B.O. | |
dc.date.accessioned | 2024-03-22T02:46:41Z | |
dc.date.available | 2024-03-22T02:46:41Z | |
dc.date.issued | 2023-12-06 | |
dc.identifier.citation | Kavitha, P., Ayyappan, G., Jayagopal, P. et al. Detection for melanoma skin cancer through ACCF, BPPF, and CLF techniques with machine learning approach. BMC Bioinformatics 24, 458 (2023). https://doi.org/10.1186/s12859-023-05584-7 | |
dc.identifier.issn | 1471-2105 | |
dc.identifier.pmid | 38053030 | |
dc.identifier.doi | 10.1186/s12859-023-05584-7 | |
dc.identifier.uri | http://hdl.handle.net/10150/671566 | |
dc.description.abstract | Intense sun exposure is a major risk factor for the development of melanoma, an abnormal proliferation of skin cells. Yet, this more prevalent type of skin cancer can also develop in less-exposed areas, such as those that are shaded. Melanoma is the sixth most common type of skin cancer. In recent years, computer-based methods for imaging and analyzing biological systems have made considerable strides. This work investigates the use of advanced machine learning methods, specifically ensemble models with Auto Correlogram Methods, Binary Pyramid Pattern Filter, and Color Layout Filter, to enhance the detection accuracy of Melanoma skin cancer. These results suggest that the Color Layout Filter model of the Attribute Selection Classifier provides the best overall performance. Statistics for ROC, PRC, Kappa, F-Measure, and Matthews Correlation Coefficient were as follows: 90.96% accuracy, 0.91 precision, 0.91 recall, 0.95 ROC, 0.87 PRC, 0.87 Kappa, 0.91 F-Measure, and 0.82 Matthews Correlation Coefficient. In addition, its margins of error are the smallest. The research found that the Attribute Selection Classifier performed well when used in conjunction with the Color Layout Filter to improve image quality. © 2023, The Author(s). | |
dc.language.iso | en | |
dc.publisher | BioMed Central Ltd | |
dc.rights | © The Author(s) 2023. Open Access This article is licensed under a Creative Commons Attribution 4.0 International License. | |
dc.rights.uri | https://creativecommons.org/licenses/by/4.0/ | |
dc.subject | Attribute selection classifier | |
dc.subject | Auto color correlogram filter | |
dc.subject | Bagging | |
dc.subject | Binary pattern pyramid filter | |
dc.subject | Color layout filter | |
dc.title | Detection for melanoma skin cancer through ACCF, BPPF, and CLF techniques with machine learning approach | |
dc.type | Article | |
dc.type | text | |
dc.contributor.department | Department of Pharmacology and Toxicology, The University of Arizona | |
dc.identifier.journal | BMC Bioinformatics | |
dc.description.note | Open access journal | |
dc.description.collectioninformation | This item from the UA Faculty Publications collection is made available by the University of Arizona with support from the University of Arizona Libraries. If you have questions, please contact us at repository@u.library.arizona.edu. | |
dc.eprint.version | Final Published Version | |
dc.source.journaltitle | BMC Bioinformatics | |
refterms.dateFOA | 2024-03-22T02:46:41Z |