Forward selection-based ensemble of deep neural networks for melanoma classification in dermoscopy images

Basit Öğe Kaydı
dc.contributor.authorSöylemez, Ömer Faruk
dc.contributor.orcid0000-0002-4076-5230
dc.date.accessioned2024-04-24T15:59:25Z
dc.date.available2024-04-24T15:59:25Z
dc.date.issued2023
dc.departmentDicle Üniversitesi, Mühendislik Fakültesi, Bilgisayar Mühendisliği Ana Bilim Dalıen_US
dc.description.abstractMelanoma is a rare skin cancer that constitutes only 1% of skin cancer cases. However, its ability to spread to other organs makes it deadliest among the four major cancer types. Early diagnosis of melanoma is essential, as it prevents cancer from spreading to other body parts, therefore significantly reducing mortality rates. In this study, we presented a forward selection-based ensembling strategy for deep neural networks to aid the diagnosis of melanoma in dermoscopy images. The proposed approach uses an ensemble of neural networks with varying input sizes to effectively capture size-related various properties of dermoscopy images. To this end, EfficientNet models B3-B7 are used with input resolutions of 256, 384, 512, and 768. Training and validation are carried out in a triple stratified cross-validation style with folds providing patient isolation, balance in the percentage of classes and balanced patient count distribution. Ensembles are formed by a modified form of forward selection algorithm. Experimental results show that the AUC for classification is increased by 2.01% using the proposed ensembling scheme.en_US
dc.identifier.citationSöylemez, Ö. F. (2023). Forward selection-based ensemble of deep neural networks for melanoma classification in dermoscopy images. International Journal of Imaging Systems and Technology, 33(6), 1929-1943.
dc.identifier.doi10.1002/ima.22912
dc.identifier.endpage1943en_US
dc.identifier.issn0899-9457
dc.identifier.issn1098-1098
dc.identifier.issue6en_US
dc.identifier.scopus2-s2.0-85159832957
dc.identifier.scopusqualityQ1
dc.identifier.startpage1929en_US
dc.identifier.urihttps://doi.org/10.1002/ima.22912
dc.identifier.urihttps://hdl.handle.net/11468/14050
dc.identifier.urihttps://onlinelibrary.wiley.com/doi/10.1002/ima.22912
dc.identifier.volume33en_US
dc.identifier.wosWOS:000991855600001
dc.identifier.wosqualityN/A
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.institutionauthorSöylemez, Ömer Faruk
dc.language.isoenen_US
dc.publisherWileyen_US
dc.relation.ispartofInternational Journal of Imaging Systems and Technology
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectDeep learningen_US
dc.subjectEnsemblingen_US
dc.subjectForward selectionen_US
dc.subjectMelanomaen_US
dc.subjectSkin canceren_US
dc.titleForward selection-based ensemble of deep neural networks for melanoma classification in dermoscopy imagesen_US
dc.titleForward selection-based ensemble of deep neural networks for melanoma classification in dermoscopy images
dc.typeArticleen_US

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
[ X ]
İsim:
Forward selection-based ensemble of deep neural networks for melanoma classification in dermoscopy images.pdf
Boyut:
3.51 MB
Biçim:
Adobe Portable Document Format
Açıklama:
Makale Dosyası
İndir

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu