EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Skin Cancer Image Classification Using Deep Learning with Data Segmentation Technique

Akhilesh Kumar Shrivas, Hema Vastrakar

Karbala International Journal of Modern Science · 13.10.2025 · 11 (4)

DOI: 10.33640/2405-609x.3435 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Karbala International Journal of Modern Science, online erschienen am 13.10.2025. Verfasst von Akhilesh Kumar Shrivas und 1 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The human skin is an impressive organ and structural element often impacted by a diverse range of recognized and unknown diseases. Diagnosing disorders that affect the outermost layer of the body is the most uncertain and difficult component in the scientific field. Dermatological diseases are one of the most significant health concerns in the 21st century since their identification is challenging and costly, plagued with challenges and the subjectivity that comes with human interpretation. The main objective of this piece of research work is to develop a robust model for the classification of skin cancer diseases using deep convolution neural networks (CNN) and transfer learning models. This research work uses convolutional neural networks(CNN), ResNet50, and VGG-16 techniques for the classifications of skin lesions. Data augmentation and UNet++ techniques are used to improve the quality of images and the performance of CNN, VGG16, and RestNet50 models. This research work is divided into three cases to analyze and evaluate the performance of models. In the first case, the deep learning and transfer learning models are used for the classification of skin cancer. In the second case, the data augmentation technique is applied to the skin cancer dataset and improves the model performance in terms of accuracy. In the third case, the deep learning and transfer learning models with data augmentation and UNet++ segmentation techniques are applied to develop a proposed model with high accuracy for the classification of skin cancer. The proposed VGG16-DAUNPP model achieved better 98.83% and 98.63% accuracy in the case of the Ham10000 dataset and Malignant vs. Benign ISIC dataset respectively. Similarly, the ResNet50-DAUNPP model achieved the highest 98.87% accuracy as compared to others in the case of Melanoma skin cancer dataset. Finally, our proposed transfer learning models VGG16-DAUNPP and ResNet50-DAUNPP are robust and recommended for the classification of skin cancer diseases.

Zitieren

APA

Shrivas, A. K., & Vastrakar, H. (2025). Skin Cancer Image Classification Using Deep Learning with Data Segmentation Technique. Karbala International Journal of Modern Science, 11(4). https://doi.org/10.33640/2405-609x.3435

Vancouver

Shrivas AK, Vastrakar H. Skin Cancer Image Classification Using Deep Learning with Data Segmentation Technique. Karbala International Journal of Modern Science. 2025;11(4). doi:10.33640/2405-609x.3435

BibTeX
@article{Shrivas2025,
  author = {Shrivas, Akhilesh Kumar and Vastrakar, Hema},
  title = {Skin Cancer Image Classification Using Deep Learning with Data Segmentation Technique},
  journal = {Karbala International Journal of Modern Science},
  year = {2025},
  volume = {11},
  number = {4},
  doi = {10.33640/2405-609x.3435}
}
Kostenlos starten →