EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Hybrid Vision Transformer–CNN Architecture with Optimized Feature Selection for Skin Cancer Classification

Abrar Almjally iD, Munazza Aziz, Shaheryar Najam, Alaa Menshawi iD, Meteb Altaf, Abdullah Fawaz Aljulayfi iD, Ahmad Jalal

Diagnostics · 27.07.2026 · 16 (15) · 2351

DOI: 10.3390/diagnostics16152351 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Diagnostics, online erschienen am 27.07.2026. Verfasst von Abrar Almjally und 6 weiteren Autor:innen. Beteiligte Einrichtung: Information Technology Department, College of Computer and Information Sciences, Imam Mohammad Ibn Saud Islamic University (IMSIU), Riyadh 13318, Sau…. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background/Objectives: Melanoma is a life-threatening skin cancer characterized by aggressive progression and high metastatic potential, making early diagnosis essential for improving patient survival and treatment outcomes. However, accurate automated skin lesion classification remains challenging due to variations in lesion appearance, illumination, image quality, and the presence of artifacts. This study proposes a unified framework for robust multi-class skin cancer classification by integrating preprocessing, lesion segmentation, feature extraction, optimization, and classification within a single end-to-end architecture.

Methods

The proposed framework employs an iterative hair artifact removal strategy based on the fusion of Frangi vesselness filtering, Gabor texture filtering, morphological refinement, and Telea inpainting to preserve lesion integrity. A novel dermoscopic lesion segmentation network (CutisNet) is introduced to accurately delineate lesion boundaries. Hybrid representation learning combines deep features extracted using MobileNetV2 with uniquely selected handcrafted descriptors to capture complementary texture, structural, and contextual information. Gray Wolf Optimization is utilized for feature fusion and refinement, while a hybrid GNN–CNN classifier performs robust multi-class skin lesion classification.

Results

Extensive experiments conducted on multiple benchmark dermoscopic datasets demonstrate the effectiveness and generalization capability of the proposed framework. The proposed model consistently outperformed existing state-of-the-art methods, achieving a maximum classification accuracy of 96.7% on the PH2 dataset while maintaining competitive performance across other benchmark datasets.

Conclusions

The proposed framework effectively integrates novel preprocessing, segmentation, hybrid feature representation, feature optimization, and classification strategies to improve the robustness and accuracy of automated skin cancer classification. These results demonstrate its potential to support reliable computer-aided diagnosis and assist clinicians in the early detection of skin cancer.

Schlagwörter

Stichwörter der Autor:innen

attention mechanismdeep learningdermoscopic image analysisfeature extractionmedical image processingmelanoma detectionskin lesion classification

Autor:innen und Institutionen

  • Information Technology Department, College of Computer and Information Sciences, Imam Mohammad Ibn Saud Islamic University (IMSIU), Riyadh 13318, Saudi Arabia.
  • Department of Biomedical Engineering, Riphah International University, I-14, Islamabad 44000, Pakistan.
  • Department of Electrical Engineering, Bahria University, H-11, Islamabad 44000, Pakistan.
  • Information Systems Department, College of Computer and Information Sciences, Imam Mohammad Ibn Saud Islamic University (IMSIU), Riyadh 13318, Saudi Arabia.
  • Disability Research Institute, Health Sector, King Abdulaziz City for Science and Technology Riyadh, Riyadh 11442, Saudi Arabia.
  • Department of Software Engineering, College of Computer Engineering and Sciences, Prince Sattam Bin Abdulaziz University, Al-Kharj 16273, Saudi Arabia.

ORCID-Profile: Abrar Almjally, Alaa Menshawi, Abdullah Fawaz Aljulayfi

Zitieren

APA

Almjally, A., Aziz, M., Najam, S., Menshawi, A., Altaf, M., Aljulayfi, A. F., & Jalal, A. (2026). Hybrid Vision Transformer–CNN Architecture with Optimized Feature Selection for Skin Cancer Classification. Diagnostics, 16(15), 2351. https://doi.org/10.3390/diagnostics16152351

Vancouver

Almjally A, Aziz M, Najam S, Menshawi A, Altaf M, Aljulayfi AF, et al. Hybrid Vision Transformer–CNN Architecture with Optimized Feature Selection for Skin Cancer Classification. Diagnostics. 2026;16(15):2351. doi:10.3390/diagnostics16152351

BibTeX
@article{Almjally2026,
  author = {Almjally, Abrar and Aziz, Munazza and Najam, Shaheryar and Menshawi, Alaa and Altaf, Meteb and Aljulayfi, Abdullah Fawaz and Jalal, Ahmad},
  title = {Hybrid Vision Transformer–CNN Architecture with Optimized Feature Selection for Skin Cancer Classification},
  journal = {Diagnostics},
  year = {2026},
  volume = {16},
  number = {15},
  pages = {2351},
  doi = {10.3390/diagnostics16152351}
}
Kostenlos starten →