Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

XAI-Driven Skin Disease Classification: Leveraging GANs to Augment ResNet-50 Performance

Kim Gerard A. Villanueva, Priyanka Kumar

TL;DR

The paper tackles the problem of accurate seven-class skin lesion classification amid dataset imbalance and deep-learning opacity. It proposes a workflow that uses per-class DCGANs to augment minority classes and a fine-tuned ResNet-50 classifier, enhanced by LIME and SHAP explanations to ensure clinical interpretability. The approach achieves 92.50% overall accuracy and a Macro-AUC of 98.82%, outperforming prior benchmarks, and demonstrates explainability through concrete visualizations. While highly effective, Melanoma_NOS remains challenging, indicating a need for targeted improvements to minimize dangerous false negatives and support deployment in clinical settings.

Abstract

Accurate and timely diagnosis of multi-class skin lesions is hampered by subjective methods, inherent data imbalance in datasets like HAM10000, and the "black box" nature of Deep Learning (DL) models. This study proposes a trustworthy and highly accurate Computer-Aided Diagnosis (CAD) system to overcome these limitations. The approach utilizes Deep Convolutional Generative Adversarial Networks (DCGANs) for per class data augmentation to resolve the critical class imbalance problem. A fine-tuned ResNet-50 classifier is then trained on the augmented dataset to classify seven skin disease categories. Crucially, LIME and SHAP Explainable AI (XAI) techniques are integrated to provide transparency by confirming that predictions are based on clinically relevant features like irregular morphology. The system achieved a high overall Accuracy of 92.50 % and a Macro-AUC of 98.82 %, successfully outperforming various prior benchmarked architectures. This work successfully validates a verifiable framework that combines high performance with the essential clinical interpretability required for safe diagnostic deployment. Future research should prioritize enhancing discrimination for critical categories, such as Melanoma NOS (F1-Score is 0.8602).

XAI-Driven Skin Disease Classification: Leveraging GANs to Augment ResNet-50 Performance

TL;DR

The paper tackles the problem of accurate seven-class skin lesion classification amid dataset imbalance and deep-learning opacity. It proposes a workflow that uses per-class DCGANs to augment minority classes and a fine-tuned ResNet-50 classifier, enhanced by LIME and SHAP explanations to ensure clinical interpretability. The approach achieves 92.50% overall accuracy and a Macro-AUC of 98.82%, outperforming prior benchmarks, and demonstrates explainability through concrete visualizations. While highly effective, Melanoma_NOS remains challenging, indicating a need for targeted improvements to minimize dangerous false negatives and support deployment in clinical settings.

Abstract

Accurate and timely diagnosis of multi-class skin lesions is hampered by subjective methods, inherent data imbalance in datasets like HAM10000, and the "black box" nature of Deep Learning (DL) models. This study proposes a trustworthy and highly accurate Computer-Aided Diagnosis (CAD) system to overcome these limitations. The approach utilizes Deep Convolutional Generative Adversarial Networks (DCGANs) for per class data augmentation to resolve the critical class imbalance problem. A fine-tuned ResNet-50 classifier is then trained on the augmented dataset to classify seven skin disease categories. Crucially, LIME and SHAP Explainable AI (XAI) techniques are integrated to provide transparency by confirming that predictions are based on clinically relevant features like irregular morphology. The system achieved a high overall Accuracy of 92.50 % and a Macro-AUC of 98.82 %, successfully outperforming various prior benchmarked architectures. This work successfully validates a verifiable framework that combines high performance with the essential clinical interpretability required for safe diagnostic deployment. Future research should prioritize enhancing discrimination for critical categories, such as Melanoma NOS (F1-Score is 0.8602).

Paper Structure

This paper contains 14 sections, 9 figures, 4 tables.

Table of Contents

  1. Introduction and Motivation
  2. Literature Survey
  3. Methodology
  4. Data collection
  5. Data Pre-processing
  6. Synthetic Data Generation
  7. CNN model Resnet-50
  8. Class-Wise Performance Analysis
  9. Comparison with Previous Studies
  10. Integration of XAI
  11. Visual Validation using LIME and SHAP
  12. Conclusion and Future Work
  13. Acknowledgments
  14. Funding

Figures (9)

  • Figure 1: Workflow of the proposed methodology
  • Figure 2: Representative images of skin lesions per category
  • Figure 3: Generative Adversarial Network (GAN) Framework
  • Figure 4: Resnet50 Architecture
  • Figure 5: Training and Validation Accuracy Curve
  • ...and 4 more figures