Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

An Integrated Deep Learning Model for Skin Cancer Detection Using Hybrid Feature Fusion Technique

Maksuda Akter, Rabea Khatun, Md. Alamin Talukder, Md. Manowarul Islam, Md. Ashraf Uddin

TL;DR

This work tackles automated skin cancer detection from dermoscopic images. It introduces a hybrid deep-learning framework that fuses two pretrained networks, InceptionV3 and DenseNet121, via a weighted score-level fusion. On a Kaggle/ISIC-derived dataset, it achieves 92.27% accuracy with high sensitivity, specificity, and ROC, outperforming individual models. The study demonstrates the practicality of hybrid models for assisting clinicians in early melanoma detection and guiding future research with larger datasets and enhanced preprocessing.

Abstract

Skin cancer is a serious and potentially fatal disease caused by DNA damage. Early detection significantly increases survival rates, making accurate diagnosis crucial. In this groundbreaking study, we present a hybrid framework based on Deep Learning (DL) that achieves precise classification of benign and malignant skin lesions. Our approach begins with dataset preprocessing to enhance classification accuracy, followed by training two separate pre-trained DL models, InceptionV3 and DenseNet121. By fusing the results of each model using the weighted sum rule, our system achieves exceptional accuracy rates. Specifically, we achieve a 92.27% detection accuracy rate, 92.33% sensitivity, 92.22% specificity, 90.81% precision, and 91.57% F1-score, outperforming existing models and demonstrating the robustness and trustworthiness of our hybrid approach. Our study represents a significant advance in skin cancer diagnosis and provides a promising foundation for further research in the field. With the potential to save countless lives through earlier detection, our hybrid deep-learning approach is a game-changer in the fight against skin cancer.

An Integrated Deep Learning Model for Skin Cancer Detection Using Hybrid Feature Fusion Technique

TL;DR

This work tackles automated skin cancer detection from dermoscopic images. It introduces a hybrid deep-learning framework that fuses two pretrained networks, InceptionV3 and DenseNet121, via a weighted score-level fusion. On a Kaggle/ISIC-derived dataset, it achieves 92.27% accuracy with high sensitivity, specificity, and ROC, outperforming individual models. The study demonstrates the practicality of hybrid models for assisting clinicians in early melanoma detection and guiding future research with larger datasets and enhanced preprocessing.

Abstract

Skin cancer is a serious and potentially fatal disease caused by DNA damage. Early detection significantly increases survival rates, making accurate diagnosis crucial. In this groundbreaking study, we present a hybrid framework based on Deep Learning (DL) that achieves precise classification of benign and malignant skin lesions. Our approach begins with dataset preprocessing to enhance classification accuracy, followed by training two separate pre-trained DL models, InceptionV3 and DenseNet121. By fusing the results of each model using the weighted sum rule, our system achieves exceptional accuracy rates. Specifically, we achieve a 92.27% detection accuracy rate, 92.33% sensitivity, 92.22% specificity, 90.81% precision, and 91.57% F1-score, outperforming existing models and demonstrating the robustness and trustworthiness of our hybrid approach. Our study represents a significant advance in skin cancer diagnosis and provides a promising foundation for further research in the field. With the potential to save countless lives through earlier detection, our hybrid deep-learning approach is a game-changer in the fight against skin cancer.

Paper Structure

This paper contains 19 sections, 1 equation, 6 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Literature Review
  3. Methodology
  4. Dataset
  5. Image Preprocessing
  6. Class Labeling
  7. Feature scaling
  8. Transfer Learning
  9. Proposed Model
  10. Inception V3
  11. Densenet121
  12. Feature Fusion Technique
  13. Feature Fusion Hybrid Model
  14. Result
  15. Environment Setup
  16. ...and 4 more sections

Figures (6)

  • Figure 1: The block diagram of the Hybrid model for Skin cancer detection.
  • Figure 2: InceptionV3 network structure of proposed model.
  • Figure 3: Densenet121 network structure of proposed model.
  • Figure 5: Accuracy and Loss graph of Densenet121 and InceptionV3
  • Figure 6: Confusion Matrix of testing data.
  • ...and 1 more figures