发表机构
Digital Technologies Research Centre; National Research Council Canada（数字技术研究中心; 加拿大国家研究委员会）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出ProtoCAM，一种结合掩码引导特征编码、原型度量学习和梯度可视化的可解释少样本框架，在BUSI数据集上以3-way 5-shot取得宏F1 0.910，实现数据稀缺下可靠的乳腺超声病变分类。
AI 中文摘要
乳腺超声成像在乳腺癌的早期检测和诊断中发挥着重要作用，特别是对于乳腺组织致密的患者。然而，由于标注医学数据有限以及对可解释预测的需求，开发用于超声分析的可靠深度学习模型具有挑战性。为应对这些挑战，本文提出了ProtoCAM，一种用于乳腺病变分类的可解释少样本学习框架，该框架整合了掩码引导的特征编码、原型度量学习和基于梯度的视觉解释。所提出的方法利用病变掩码来引导特征提取，并在嵌入空间中构建类别原型，从而在有限训练样本下实现稳健的分类。该框架在BUSI数据集上使用分层组k折交叉验证协议进行评估，以防止患者级数据泄漏。实验结果表明，ProtoCAM在低数据场景下具有高性能。在3-way 5-shot设置下，所提出的方法达到了0.910的宏F1分数，相较于标准监督CNN模型有显著提升。在评估的骨干网络中，ResNet18在15-shot配置下取得了最佳性能，宏F1分数达到91.65%，并为分类决策提供了可解释的见解。这些结果凸显了可解释少样本学习框架在数据稀缺的医学成像环境中进行可靠计算机辅助乳腺癌诊断的潜力。
英文摘要
Breast ultrasound imaging plays an important role in the early detection and diagnosis of breast cancer, particularly for patients with dense breast tissue. However, developing reliable deep learning models for ultrasound analysis is challenging due to limited annotated medical data and the need for interpretable predictions. To address these challenges, this paper proposes ProtoCAM, an explainable few-shot learning framework for breast lesion classification that integrates mask-guided feature encoding, prototypical metric learning, and gradient-based visual explanations. The proposed approach leverages lesion masks to guide feature extraction and constructs class prototypes within an embedding space to enable robust classification under limited training samples. The framework was evaluated on the BUSI dataset using a stratified group k-fold cross-validation protocol to prevent patient-level data leakage. Experimental results demonstrate ProtoCAM's high performance in low-data scenarios. In a 3-way 5-shot setting, the proposed method achieves a macro F1-score of 0.910, representing a substantial improvement over standard supervised CNN models. Among the evaluated backbone networks, ResNet18 achieved the best performance, reaching a macro F1-score of 91.65% under a 15-shot configuration, providing interpretable insights into the classification decisions. These results highlight the potential of explainable few-shot learning frameworks for reliable computer-aided breast cancer diagnosis in data-scarce medical imaging environments.
Comments11 pages, 3 figures
