Araştırma Makalesi

A Hybrid Swin Transformer–ResNet50 Architecture for Skin Lesion Classification

Cilt: 14 19 Ekim 2026
PDF İndir
TR EN

A Hybrid Swin Transformer–ResNet50 Architecture for Skin Lesion Classification

Öz

This study presents a hybrid architecture combining local attention and deep feature extraction for the classification of skin lesions. A hybrid structure was developed by integrating the shifted window-based local attention mechanism of Swin Transformer with the deep feature extraction capability of ResNet50. In experiments conducted on the HAM10000 dataset, the standalone Swin Transformer model achieved a maximum validation accuracy of 88.82%, while the proposed Swin Transformer–ResNet50 hybrid model reached a maximum validation accuracy of 90.01%. When evaluated on the independent test set, the Swin Transformer and hybrid models achieved classification accuracies of 89.0% and 90.0%, respectively. The performance of the proposed model was comprehensively evaluated using ROC curves, confusion matrices, and class-based performance metrics. To improve classification performance in minority classes, focal loss, class-based data augmentation, CutMix, and MixUp techniques were employed. The results demonstrate that the proposed hybrid model provides an effective and reliable solution for skin lesion classification, achieving high accuracy and balanced performance across different lesion categories.

Anahtar Kelimeler

Kaynakça

  1. [1] R. L. Siegel, K. D. Miller, H. E. Fuchs, and A. Jemal, "Cancer statistics, 2021," CA: A Cancer Journal for Clinicians, vol. 71, no. 1, pp. 7–33, 2021, doi: 10.3322/caac.21654.
  2. [2] H. W. Rogers, M. A. Weinstock, S. R. Feldman, and B. M. Coldiron, "Incidence estimate of nonmelanoma skin cancer (keratinocyte carcinomas) in the US population, 2012," JAMA Dermatology, vol. 151, no. 10, pp. 1081–1086, 2015, doi: 10.1001/jamadermatol.2015.1187.
  3. [3] American Cancer Society, "Cancer Facts & Figures 2022," American Cancer Society, Atlanta, GA, 2022.
  4. [4] American Cancer Society, "Key statistics for basal and squamous cell skin cancers," 2019. [Online]. Available: https://www.cancer.org
  5. [5] M. Vestergaard, P. Macaskill, P. Holt, and S. Menzies, "Dermoscopy compared with naked eye examination for the diagnosis of primary melanoma: a meta-analysis of studies performed in a clinical setting," British Journal of Dermatology, vol. 159, no. 3, pp. 669–676, 2008, doi: 10.1111/j.1365-2133.2008.08713.x.
  6. [6] M. Binder et al., "Epiluminescence microscopy: a useful tool for the diagnosis of pigmented skin lesions for formally trained dermatologists," Archives of Dermatology, vol. 131, no. 3, pp. 286–291, 1995, doi: 10.1001/archderm.1995.01690150050007.
  7. [7] P. Tschandl, C. Rosendahl, and H. Kittler, "The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions," Scientific Data, vol. 5, no. 1, pp. 1–9, 2018, doi: 10.1038/sdata.2018.161.
  8. [8] O. Russakovsky et al., "ImageNet large scale visual recognition challenge," International Journal of Computer Vision, vol. 115, no. 3, pp. 211–252, 2015, doi: 10.1007/s11263-015-0816-y.

Ayrıntılar

Birincil Dil

İngilizce

Konular

Biyoelektronik

Bölüm

Araştırma Makalesi

Yayımlanma Tarihi

19 Ekim 2026

Gönderilme Tarihi

7 Nisan 2026

Kabul Tarihi

13 Haziran 2026

Yayımlandığı Sayı

Yıl 2026 Cilt: 14

Kaynak Göster

APA
Bulduk, H., & Sabancı, K. (2026). A Hybrid Swin Transformer–ResNet50 Architecture for Skin Lesion Classification. Balkan Journal of Electrical and Computer Engineering, 14, 267-276. https://doi.org/10.17694/bajece.1925042
AMA
1.Bulduk H, Sabancı K. A Hybrid Swin Transformer–ResNet50 Architecture for Skin Lesion Classification. Balkan Journal of Electrical and Computer Engineering. 2026;14:267-276. doi:10.17694/bajece.1925042
Chicago
Bulduk, Hüseyin, ve Kadir Sabancı. 2026. “A Hybrid Swin Transformer–ResNet50 Architecture for Skin Lesion Classification”. Balkan Journal of Electrical and Computer Engineering 14 (Ekim): 267-76. https://doi.org/10.17694/bajece.1925042.
EndNote
Bulduk H, Sabancı K (01 Ekim 2026) A Hybrid Swin Transformer–ResNet50 Architecture for Skin Lesion Classification. Balkan Journal of Electrical and Computer Engineering 14 267–276.
IEEE
[1]H. Bulduk ve K. Sabancı, “A Hybrid Swin Transformer–ResNet50 Architecture for Skin Lesion Classification”, Balkan Journal of Electrical and Computer Engineering, c. 14, ss. 267–276, Eki. 2026, doi: 10.17694/bajece.1925042.
ISNAD
Bulduk, Hüseyin - Sabancı, Kadir. “A Hybrid Swin Transformer–ResNet50 Architecture for Skin Lesion Classification”. Balkan Journal of Electrical and Computer Engineering 14 (01 Ekim 2026): 267-276. https://doi.org/10.17694/bajece.1925042.
JAMA
1.Bulduk H, Sabancı K. A Hybrid Swin Transformer–ResNet50 Architecture for Skin Lesion Classification. Balkan Journal of Electrical and Computer Engineering. 2026;14:267–276.
MLA
Bulduk, Hüseyin, ve Kadir Sabancı. “A Hybrid Swin Transformer–ResNet50 Architecture for Skin Lesion Classification”. Balkan Journal of Electrical and Computer Engineering, c. 14, Ekim 2026, ss. 267-76, doi:10.17694/bajece.1925042.
Vancouver
1.Hüseyin Bulduk, Kadir Sabancı. A Hybrid Swin Transformer–ResNet50 Architecture for Skin Lesion Classification. Balkan Journal of Electrical and Computer Engineering. 01 Ekim 2026;14:267-76. doi:10.17694/bajece.1925042

All articles published by BAJECE are licensed under the Creative Commons Attribution 4.0 International License. This permits anyone to copy, redistribute, remix, transmit and adapt the work provided the original work and source is appropriately cited.Creative Commons Lisans