Skin Cancer Detection Using Deep Learning

  • Unique Paper ID: 165617
  • Volume: 11
  • Issue: 1
  • PageNo: 1537-1543
  • Abstract:
  • My work presents a cutting-edge Convolutional Neural Network (CNN) based Skin Cancer Identification system that is improved by Batch Normalization methods. With CNNs being well known for image analysis, the model's adoption guarantees a strong basis, which is intended to solve the worldwide health concern of skin cancer[12].Batch Normalization mitigates issues associated with internal covariate shifts in the CNN architecture by normalizing inputs and enhancing stability. An important breakthrough in the identification of skin cancer has been made by the model, which consistently adapts to a variety of datasets.The imbalances in datasets connected to skin cancer are also subjected to modern imbalance learning algorithms. The model greatly increases sensitivity and accuracy, especially for minority classes, by taking into consideration class imbalances through the use of SMOTE, under sampling, and oversampling. The CNN- based model performs better in recognizing lesions associated with skin illnesses than earlier benchmarks, according to experiments. Intentionally using imbalanced learning techniques improves generalization, whereas group normalization [9] guarantees stability. Because of its versatility, the model may be used in real-world scenarios and effectively solves the complicated issues faced by healthcare practitioners. The study [15] raises the bar for technological integration in the ongoing fight against skin disorders by highlighting the wider impact of state-of-the-art deep learning algorithms in medical picture interpretation, beyond local applications . with in the medical field.

Cite This Article

  • ISSN: 2349-6002
  • Volume: 11
  • Issue: 1
  • PageNo: 1537-1543

Skin Cancer Detection Using Deep Learning

Related Articles