⚡ Quick Summary
This study provides a comprehensive analysis of deep learning and transfer learning techniques for the classification of skin cancer, specifically melanoma. The research achieved a remarkable accuracy of 92.87% by combining pre-trained networks with machine learning classifiers.
🔍 Key Details
- 📊 Dataset: ISIC 2018 dataset with 3,300 images of skin lesions
- 🧩 Techniques used: Deep learning approaches including VGG19, ResNet18, and MobileNet_V2
- ⚙️ Classifiers: SVM, Decision Trees (DT), Naïve Bayes, and KNN
- 🏆 Performance: Maximum accuracy of 92.87% achieved with ResNet-18 and MobileNet_V2
🔑 Key Takeaways
- 🖼️ Image Segmentation: Active contour approach was used for image segmentation.
- 🔍 Preprocessing: Included scaling, denoising, and enhancing images before classification.
- 📈 Training Split: 80% of images were used for training, while 20% were for testing.
- 🤖 Combination Techniques: Combining feature extractors with classifiers yielded superior results.
- 🌟 Breakthrough Accuracy: The study highlights the potential of deep learning in medical image analysis.
- 📅 Publication: Published in Sci Rep, 2025.
- 👩🔬 Authors: Shakya M, Patel R, Joshi S.
📚 Background
The early and accurate diagnosis of melanoma is crucial due to its unique characteristics and varying shapes of skin lesions. Traditional diagnostic methods can be subjective and time-consuming, which necessitates the exploration of advanced technologies like deep learning to enhance diagnostic accuracy and efficiency.
🗒️ Study
This study investigates three distinct approaches for classifying skin cancer images. The first approach utilizes three fine-tuned pre-trained networks (VGG19, ResNet18, and MobileNet_V2) as classifiers. The second approach employs these networks as feature extractors in combination with four machine learning classifiers. The third approach combines the aforementioned networks as feature extractors with the same classifiers, aiming to improve classification performance.
📈 Results
The results indicate that the combination of ResNet-18 and MobileNet_V2 using an SVM classifier achieved the highest accuracy of 92.87%. This demonstrates the effectiveness of using pre-trained networks in conjunction with machine learning classifiers for skin cancer classification.
🌍 Impact and Implications
The findings of this study have significant implications for the field of dermatology. By leveraging deep learning techniques, healthcare professionals can enhance the accuracy of skin cancer diagnoses, potentially leading to earlier interventions and improved patient outcomes. This research paves the way for further exploration of AI technologies in medical imaging and diagnostics.
🔮 Conclusion
This comprehensive analysis underscores the transformative potential of deep learning in the classification of skin cancer. The impressive accuracy achieved in this study highlights the importance of integrating advanced technologies into clinical practice. Continued research in this area is essential for developing more effective diagnostic tools that can ultimately save lives.
💬 Your comments
What are your thoughts on the use of deep learning for skin cancer classification? We invite you to share your insights and engage in a discussion! 💬 Leave your comments below or connect with us on social media:
A comprehensive analysis of deep learning and transfer learning techniques for skin cancer classification.
Abstract
Accurately and early diagnosis of melanoma is one of the challenging tasks due to its unique characteristics and different shapes of skin lesions. So, in order to solve this issue, the current study examines various deep learning-based approaches and provide an effective approach for classifying dermoscopic images into two categories of skin lesions. This research focus on skin cancer images and provides solution using deep learning approaches. This research investigates three approaches for classifying skin cancer images. (1) Utilizing three fine-tuned pre-trained networks (VGG19, ResNet18, and MobileNet_V2) as classifiers. (2) Employing three pre-trained networks (ResNet-18, VGG19, and MobileNet v2) as feature extractors in conjunction with four machine learning classifiers (SVM, DT, Naïve Bayes, and KNN). (3) Utilizing a combination of the aforementioned pre-trained networks as feature extractors in conjunction with same machine learning classifiers. All these algorithms are trained using segmented images which are achieved by using the active contour approach. Prior to segmentation, preprocessing step is performed which involves scaling, denoising, and enhancing the image. Experimental performance is measured on the ISIC 2018 dataset which contains 3300 images of skin disease including benign and malignant type cancer images. 80% of the images from the ISIC 2018 dataset are allocated for training, while the remaining 20% are designated for testing. All approaches are trained using different parameters like epoch, batch size, and learning rate. The results indicate that combining ResNet-18 and MobileNet pre-trained networks using concatenation with an SVM classifier achieved the maximum accuracy of 92.87%.
Author: [‘Shakya M’, ‘Patel R’, ‘Joshi S’]
Journal: Sci Rep
Citation: Shakya M, et al. A comprehensive analysis of deep learning and transfer learning techniques for skin cancer classification. A comprehensive analysis of deep learning and transfer learning techniques for skin cancer classification. 2025; 15:4633. doi: 10.1038/s41598-024-82241-w