PathoSCOPE：通过自监督对比学习和病理信息合成嵌入实现的小样本病理检测
PathoSCOPE: Few-Shot Pathology Detection via Self-Supervised Contrastive Learning and Pathology-Informed Synthetic Embeddings
AI总结：
PathoSCOPE提出小样本无监督病理检测框架，仅需少量非病理样本，通过全局-局部对比损失和病理信息嵌入生成模块，在BraTS2020和ChestXray8上达到最先进性能且计算高效。
摘要：
无监督病理检测在非病理数据上训练模型，以将偏差标记为病理，为识别新疾病提供了强大的泛化能力，并避免了昂贵的标注。然而，构建可靠的正常性模型需要大量的健康数据集，因为医院的数据固有地偏向有症状的人群，而隐私法规阻碍了代表性健康队列的组装。为了解决这一限制，我们提出了PathoSCOPE，一种小样本无监督病理检测框架，仅需少量非病理样本（最少2个样本），显著提高了数据效率。我们引入了全局-局部对比损失（GLCL），由局部对比损失和全局对比损失组成，前者用于减少非病理嵌入的变异性，后者用于增强病理区域的判别性。我们还提出了一个病理信息嵌入生成（PiEG）模块，该模块在全局损失的指导下合成病理嵌入，更好地利用有限的非病理样本。在BraTS2020和ChestXray8数据集上的评估表明，PathoSCOPE在无监督方法中达到了最先进的性能，同时保持了计算效率（2.48 GFLOPs，166 FPS）。
英文摘要：
Unsupervised pathology detection trains models on non-pathological data to flag deviations as pathologies, offering strong generalizability for identifying novel diseases and avoiding costly annotations. However, building reliable normality models requires vast healthy datasets, as hospitals' data is inherently biased toward symptomatic populations, while privacy regulations hinder the assembly of representative healthy cohorts. To address this limitation, we propose PathoSCOPE, a few-shot unsupervised pathology detection framework that requires only a small set of non-pathological samples (minimum 2 shots), significantly improving data efficiency. We introduce Global-Local Contrastive Loss (GLCL), comprised of a Local Contrastive Loss to reduce the variability of non-pathological embeddings and a Global Contrastive Loss to enhance the discrimination of pathological regions. We also propose a Pathology-informed Embedding Generation (PiEG) module that synthesizes pathological embeddings guided by the global loss, better exploiting the limited non-pathological samples. Evaluated on the BraTS2020 and ChestXray8 datasets, PathoSCOPE achieves state-of-the-art performance among unsupervised methods while maintaining computational efficiency (2.48 GFLOPs, 166 FPS).
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
