Show simple item record

dc.contributor.authorKavitha, P.
dc.contributor.authorAyyappan, G.
dc.contributor.authorJayagopal, P.
dc.contributor.authorMathivanan, S.K.
dc.contributor.authorMallik, S.
dc.contributor.authorAl-Rasheed, A.
dc.contributor.authorAlqahtani, M.S.
dc.contributor.authorSoufiene, B.O.
dc.date.accessioned2024-03-22T02:46:41Z
dc.date.available2024-03-22T02:46:41Z
dc.date.issued2023-12-06
dc.identifier.citationKavitha, 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.issn1471-2105
dc.identifier.pmid38053030
dc.identifier.doi10.1186/s12859-023-05584-7
dc.identifier.urihttp://hdl.handle.net/10150/671566
dc.description.abstractIntense 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.isoen
dc.publisherBioMed 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.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectAttribute selection classifier
dc.subjectAuto color correlogram filter
dc.subjectBagging
dc.subjectBinary pattern pyramid filter
dc.subjectColor layout filter
dc.titleDetection for melanoma skin cancer through ACCF, BPPF, and CLF techniques with machine learning approach
dc.typeArticle
dc.typetext
dc.contributor.departmentDepartment of Pharmacology and Toxicology, The University of Arizona
dc.identifier.journalBMC Bioinformatics
dc.description.noteOpen access journal
dc.description.collectioninformationThis 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.versionFinal Published Version
dc.source.journaltitleBMC Bioinformatics
refterms.dateFOA2024-03-22T02:46:41Z


Files in this item

Thumbnail
Name:
s12859-023-05584-7.pdf
Size:
2.181Mb
Format:
PDF
Description:
Final Published Version

This item appears in the following Collection(s)

Show simple item record

© The Author(s) 2023. Open Access This article is licensed under a Creative Commons Attribution 4.0 International License.
Except where otherwise noted, this item's license is described as © The Author(s) 2023. Open Access This article is licensed under a Creative Commons Attribution 4.0 International License.