🤖 AI Summary
Medical image classification faces two critical challenges: scarcity of labeled samples in clinical settings and insufficient interpretability for medical practitioners. This paper presents a systematic review of recent advances and proposes a novel few-shot learning framework that synergistically integrates Vision Transformers (ViTs) with vision-language models (VLMs)—the first such integration for medical image classification. To enhance clinical trustworthiness, the framework incorporates explainable AI (XAI) techniques to generate human-interpretable visualizations (e.g., attention heatmaps) and natural-language explanations aligned with clinical reasoning. Extensive experiments on multiple public medical imaging benchmarks demonstrate that our method significantly improves few-shot classification accuracy—achieving an average gain of +5.2%—while delivering clinically coherent, multimodal explanations. The approach advances the practical deployment of AI-assisted diagnosis by bridging the gap between high-performance deep learning and domain-specific interpretability requirements.
📝 Abstract
Medical image classification is crucial for diagnosis and treatment, benefiting significantly from advancements in artificial intelligence. The paper reviews recent progress in the field, focusing on three levels of solutions: basic, specific, and applied. It highlights advances in traditional methods using deep learning models like Convolutional Neural Networks and Vision Transformers, as well as state-of-the-art approaches with Vision Language Models. These models tackle the issue of limited labeled data, and enhance and explain predictive results through Explainable Artificial Intelligence.