仅用2张健康图像实现高效病理检测，突破数据瓶颈。
PathoSCOPE: Few-Shot Pathology Detection via Self-Supervised Contrastive Learning and Pathology-Informed Synthetic Embeddings
- 通过对比学习缩小健康样本差异，增强病理区域区分度。
- 在脑瘤和胸部X光数据集上超越现有无监督方法性能。
- 适合标注稀缺的医学影像场景，尤其适合小样本病理发现。
无监督病理检测通过训练健康数据来识别异常，具有识别新病种和避免标注成本的优势。但构建可靠正常模型需大量健康数据，而医院数据本就偏向有症状人群，且隐私法规限制代表性健康队列的建立。为此，我们提出PathoSCOPE，一种仅需少量非病理样本（最低2张）的少样本无监督病理检测框架，显著提升数据效率。引入全局-局部对比损失（GLCL），其中局部对比损失降低非病理嵌入的变异性，全局对比损失增强病理区域的判别力。同时提出病理引导嵌入生成（PiEG）模块，基于全局损失合成病理嵌入，更充分挖掘有限的非病理样本。在BraTS2020和ChestXray8数据集上评估，PathoSCOPE在无监督方法中达到最优性能，同时保持高计算效率（2.48 GFLOPs，166 FPS）。
原文摘要 · Abstract (English)
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).
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。