Yayın:
Deep Learning Approach to Improve Skin Lesion Classification for Early Skin Cancer Detection

Basit öğe sayfası
dc.contributor.authorNairi, Chaimaa
dc.contributor.authorBilgin, Gokhan
dc.date.accessioned2026-06-27T15:30:26Z
dc.date.issued2025
dc.description.abstractSkin cancer is a common and deadly disease, highlighting the need for early detection. This study evaluates five CNN architectures (DenseNet201, EfficientNetB0, XceptionNet, ResNet50, InceptionV3) and several Vision Transformer (ViT) models (ViT, Swin Transformer V2, DINOv2, PVT, ViT Hybrid) using the HAM10000 dataset. A 5-fold cross-validation assesses performance, and two Weighted Voting ensemble methods-one for CNNs and one for ViTs-are applied to enhance accuracy. Results are compared with transfer learning on ResNet50 and EfficientNetB0, showing that ensemble methods improve classification performance for early skin cancer detection.en
dc.description.urihttps://doi.org/10.1109/siu66497.2025.11111771
dc.identifier.doi10.1109/siu66497.2025.11111771
dc.identifier.isbn979-8-3315-6656-2; 979-8-3315-6655-5
dc.identifier.issn2165-0608
dc.identifier.urihttps://hdl.handle.net/20.500.14981/71307
dc.identifier.wos001575462500014
dc.language.isoeng
dc.publisherIEEE
dc.relation.conference33rd Conference on Signal Processing and Communications Applications-SIU-Annual
dc.relation.ispartof2025 33RD SIGNAL PROCESSING AND COMMUNICATIONS APPLICATIONS CONFERENCE, SIU
dc.subjectDeep learning
dc.subjectskin lesion classification
dc.subjecttransfer learning
dc.subjectensemble learning
dc.subjectmedical image analysis
dc.subjectComputer Science
dc.subjectEngineering
dc.subjectTelecommunications
dc.titleDeep Learning Approach to Improve Skin Lesion Classification for Early Skin Cancer Detection
dc.typeProceedings Paper
dspace.entity.typePublication
local.import.sourceWOS

Dosyalar

Koleksiyonlar

Yayınlar