EUVIMEDEUVIMED entdecken
Crossref

Advanced Melanoma Detection Using the ConvMixer Model on ISIC and PH2 Dermatoscopic Images

Vihan Moodi, Allahyar Taheri, Ali Faridfar, Mohsen Chamanara, Mohsen Rajaeinejad

Journal of Translational Regenerative Medicine · 17.12.2025 · 1 (1)

DOI: 10.32598/jtrm.1.1005 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Translational Regenerative Medicine, online erschienen am 17.12.2025. Verfasst von Vihan Moodi und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Melanoma is the most aggressive form of skin cancer and is associated with high mortality when not diagnosed at an early stage. Recent advances in dermatoscopic image analysis combined with artificial intelligence have demonstrated considerable potential for improving diagnostic accuracy. ConvMixer, a hybrid deep learning architecture that integrates convolutional neural networks with a mixer-style design, has recently emerged as a powerful model for image classification tasks. This study aimed to evaluate the effectiveness of the ConvMixer model for automated melanoma detection using dermatoscopic images.

Methods

Dermatoscopic images were collected from two publicly available datasets: The International Skin Imaging Collaboration (ISIC) and the Public Health (PH2) database. The ISIC dataset comprised 31,696 benign lesions and 7,319 malignant melanoma images, which were divided into training (80%), validation (10%), and test (10%) sets. The PH2 dataset, consisting of 40 melanoma and 160 melanocytic nevi images, was used exclusively for external testing. Image preprocessing, normalization, and data augmentation were performed prior to model training. Model performance was assessed using sensitivity, specificity, accuracy, F1 score, and the area under the receiver operating characteristic curve (AUC).

Results

The ConvMixer model demonstrated strong discriminative ability between malignant and benign skin lesions across both datasets. On the ISIC dataset, the model achieved a sensitivity of 0.9126, specificity of 0.6683, and accuracy of 0.7142. On the PH2 dataset, higher specificity (0.95) and accuracy (0.905) were observed, along with a sensitivity of 0.725. High AUC values further confirmed robust classification performance and generalizability across datasets with differing characteristics.

Conclusion

The ConvMixer model shows strong potential as an effective AI-assisted tool for melanoma detection from dermatoscopic images. Its consistent performance on both large-scale and controlled datasets supports its applicability in diverse clinical settings, highlighting its value for early melanoma screening and decision support in dermatology.

Zitieren

APA

Moodi, V., Taheri, A., Faridfar, A., Chamanara, M., & Rajaeinejad, M. (2025). Advanced Melanoma Detection Using the ConvMixer Model on ISIC and PH2 Dermatoscopic Images. Journal of Translational Regenerative Medicine, 1(1). https://doi.org/10.32598/jtrm.1.1005

Vancouver

Moodi V, Taheri A, Faridfar A, Chamanara M, Rajaeinejad M. Advanced Melanoma Detection Using the ConvMixer Model on ISIC and PH2 Dermatoscopic Images. Journal of Translational Regenerative Medicine. 2025;1(1). doi:10.32598/jtrm.1.1005

BibTeX
@article{Moodi2025,
  author = {Moodi, Vihan and Taheri, Allahyar and Faridfar, Ali and Chamanara, Mohsen and Rajaeinejad, Mohsen},
  title = {Advanced Melanoma Detection Using the ConvMixer Model on ISIC and PH2 Dermatoscopic Images},
  journal = {Journal of Translational Regenerative Medicine},
  year = {2025},
  volume = {1},
  number = {1},
  doi = {10.32598/jtrm.1.1005}
}
Kostenlos starten →