This paper addresses the problem of few-shot skin disease classification by introducing a novel approach called the Sub-Cluster-Aware Network (SCAN) that enhances accuracy in diagnosing rare skin diseases. The key insight motivating the design of SCAN is the observation that skin disease images within a class often exhibit multiple sub-clusters, characterized by distinct variations in appearance. To improve the performance of few-shot learning, we focus on learning a high-quality feature encoder that captures the unique sub-clustered representations within each disease class, enabling better characterization of feature distributions. Specifically, SCAN follows a dual-branch framework, where the first branch learns class-wise features to distinguish different skin diseases, and the second branch aims to learn features which can effectively partition each class into several groups so as to preserve the sub-clustered structure within each class. To achieve the objective of the second branch, we present a cluster loss to learn image similarities via unsupervised clustering. To ensure that the samples in each sub-cluster are from the same class, we further design a purity loss to refine the unsupervised clustering results. We evaluate the proposed approach on two public datasets for few-shot skin disease classification. The experimental results validate that our framework outperforms the state-of-the-art methods by around 2% to 5% in terms of sensitivity, specificity, accuracy, and F1-score on the SD-198 and Derm7pt datasets.

翻译：本文针对小样本皮肤病分类问题，提出一种名为子簇感知网络（SCAN）的新方法，以提升罕见皮肤病的诊断准确率。SCAN设计的关键动机源于观察到同一类别的皮肤病图像通常包含多个子簇，这些子簇表现为外观上的显著差异。为提升小样本学习的性能，我们致力于学习高质量的特征编码器，以捕捉每个疾病类别内独特的子簇表征，从而更好地刻画特征分布。具体而言，SCAN采用双分支框架：第一个分支学习类别级特征以区分不同皮肤病，第二个分支则旨在学习能有效将每个类别划分为若干组的特征，从而保留类别内的子簇结构。为实现第二个分支的目标，我们提出聚类损失，通过无监督聚类学习图像相似性。为确保每个子簇内的样本来自同一类别，我们进一步设计了纯度损失以优化无监督聚类结果。我们在两个公开数据集上评估了所提方法在小样本皮肤病分类中的性能。实验结果表明，在SD-198和Derm7pt数据集上，我们的框架在敏感性、特异性、准确率和F1分数方面均超越现有最优方法约2%至5%。