EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

AI-driven skin cancer detection from smartphone images: A hybrid model using ViT, adaptive thresholding, black-hat transformation, and XGBoost

Adil El Mertahi, Hind Ezzine, Samira Douzi iD, Khadija Douzi

PLOS One · 28.07.2025 · 20 (7) · e0328402

DOI: 10.1371/journal.pone.0328402 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 28.07.2025. Verfasst von Adil El Mertahi und 3 weiteren Autor:innen. Beteiligte Einrichtung: LIM Laboratory, FSTM, Hassan II University in Casablanca, Morocco. Hauptthemen laut MEDLINE: Skin Neoplasms, Smartphone, Artificial Intelligence, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Skin cancer is a significant global public health issue, with millions of new cases identified each year. Recent breakthroughs in artificial intelligence, especially deep learning, possess considerable potential to enhance the accuracy and efficiency of screening. This study proposes an approach that employs smartphone images, which are preprocessed using adaptive learning and Black-Hat transformation. ViT is utilized for feature extraction, and a stacking model is constructed employing these features in conjunction with image-related variables, like patient age and sex, for final classification. The model’s efficacy in identifying cancer-associated skin diseases was evaluated across six categories of skin lesions: actinic keratosis, basal cell carcinoma, melanoma, nevus, squamous cell carcinoma, and seborrheic keratosis. The suggested model attained an overall accuracy of 97.61%, with a PVV of 96.88%, a recall of 97.63%, and an F1 score of 97.19%, so illustrating its efficacy in detecting malignant skin lesions. This method could greatly aid dermatologists by enhancing diagnostic sensitivity and specificity, reducing delays in identifying the most suspicious lesions, and ultimately reaching more patients in need of timely screenings and patient care, thus saving lives.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Skin NeoplasmsSmartphoneArtificial IntelligenceImage Processing, Computer-AssistedHumansMaleFemaleDeep LearningMelanomaMiddle AgedBasal Cell CarcinomaKeratosis, SeborrheicAlgorithmsBoosting Machine Learning Algorithms

Autor:innen und Institutionen

  • LIM Laboratory, FSTM, Hassan II University in Casablanca, Morocco.
  • IPSS Laboratory, FSR, Mohammed V University in Rabat, Morocco.
  • FMPR, Mohammed V University in Rabat, Morocco.

ORCID-Profile: Samira Douzi

Zitieren

APA

El Mertahi, A., Ezzine, H., Douzi, S., & Douzi, K. (2025). AI-driven skin cancer detection from smartphone images: A hybrid model using ViT, adaptive thresholding, black-hat transformation, and XGBoost. PLOS One, 20(7), e0328402. https://doi.org/10.1371/journal.pone.0328402

Vancouver

El Mertahi A, Ezzine H, Douzi S, Douzi K. AI-driven skin cancer detection from smartphone images: A hybrid model using ViT, adaptive thresholding, black-hat transformation, and XGBoost. PLOS One. 2025;20(7):e0328402. doi:10.1371/journal.pone.0328402

BibTeX
@article{ElMertahi2025,
  author = {El Mertahi, Adil and Ezzine, Hind and Douzi, Samira and Douzi, Khadija},
  title = {AI-driven skin cancer detection from smartphone images: A hybrid model using ViT, adaptive thresholding, black-hat transformation, and XGBoost},
  journal = {PLOS One},
  year = {2025},
  volume = {20},
  number = {7},
  pages = {e0328402},
  doi = {10.1371/journal.pone.0328402}
}
Kostenlos starten →