Hybrid Interpretable Deep Learning Framework for Skin Cancer Diagnosis: Integrating Radial Basis Function Networks with Explainable AI

2025-01-24

AI Summary

To address the subjectivity, experience-dependence, and limited interpretability in early skin cancer diagnosis, this paper proposes an interpretable deep learning framework integrating CNNs with Radial Basis Function (RBF) networks. Methodologically, it introduces an RBF-driven local prototype mapping mechanism, synergizing medical image segmentation and K-Medoids clustering to attribute model predictions precisely to clinically salient lesion regions. Active learning is incorporated to enhance annotation efficiency, while gradient-weighted class activation mapping (Grad-CAM) visualizations provide clinically verifiable decision evidence. Evaluated on the ISIC 2016 and 2017 benchmark datasets, the framework achieves classification accuracies of 83.02% and 72.15%, respectively—significantly outperforming the VGG16 baseline. By jointly optimizing predictive accuracy and inference transparency, this work establishes a novel paradigm for AI-assisted dermatological diagnosis that balances high performance with clinical trustworthiness.

Technology Category

• Computer Vision: Interpretability, Explainability, and Transparency
• Machine Learning: Active Learning
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Algorithmic accountability and transparency on the web
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

Abstract

Skin cancer is one of the most prevalent and potentially life-threatening diseases worldwide, necessitating early and accurate diagnosis to improve patient outcomes. Conventional diagnostic methods, reliant on clinical expertise and histopathological analysis, are often time-intensive, subjective, and prone to variability. To address these limitations, we propose a novel hybrid deep learning framework that integrates convolutional neural networks (CNNs) with Radial Basis Function (RBF) Networks to achieve high classification accuracy and enhanced interpretability. The motivation for incorporating RBF Networks lies in their intrinsic interpretability and localized response to input features, which make them well-suited for tasks requiring transparency and fine-grained decision-making. Unlike traditional deep learning models that rely on global feature representations, RBF Networks allow for mapping segments of images to chosen prototypes, exploiting salient features within a single image. This enables clinicians to trace predictions to specific, interpretable patterns. The framework incorporates segmentation-based feature extraction, active learning for prototype selection, and K-Medoids clustering to focus on these salient features. Evaluations on the ISIC 2016 and ISIC 2017 datasets demonstrate the model's effectiveness, achieving classification accuracies of 83.02% and 72.15% using ResNet50, respectively, and outperforming VGG16-based configurations. By generating interpretable explanations for predictions, the framework aligns with clinical workflows, bridging the gap between predictive performance and trustworthiness. This study highlights the potential of hybrid models to deliver actionable insights, advancing the development of reliable AI-assisted diagnostic tools for high-stakes medical applications.

Problem

• Skin Cancer
• Early Diagnosis
• Accuracy Improvement

Innovation

• Convolutional Neural Network
• Radial Basis Function Network
• Interpretable AI