利用条件随机场优化细胞学预测
Refining Cytology Predictions with Conditional Random Fields
浏览论文内容
中文总结 AI 辅助
针对视觉语言模型在细胞学分类上的不足，提出CytoCRF，通过调整条件随机场的成对项并融合多骨干网络邻域信息，在十个数据集上以少量标注显著提升预测精度。
中文摘要 AI 辅助
视觉语言模型（VLMs）在组织学图像上实现了强大的零样本（ZS）分类，但在细胞学上表现不佳，因为细胞学的染色和细胞形态与组织学相比有显著差异。条件随机场（CRFs）可以通过跨图像块传播信息来细化嘈杂的VLM预测，但现有的CRF框架是为组织病理学设计的，不能迁移到细胞学数据集，这些数据集以独立的图像块池形式发布，涵盖多种染色方案。我们提出了CytoCRF，通过针对染色质和细胞学特异性染色来调整成对项以适应细胞学，并通过结合多个骨干网络进一步丰富每个势能项的邻域。在十个细胞学数据集上，CytoCRF在每个标注预算下都优于现有的CRF框架，在仅使用50个标注时，相比最佳基线提高了+13.6个百分点，相比零样本提高了+33.7个百分点。结合多个骨干网络的信息带来了进一步的提升，表明邻域拓扑结构比在其上计算的成对势能更为重要。
英文摘要
Vision-language models (VLMs) achieve strong zero-shot (ZS) classification on histology images but do not perform as well on cytology, whose stains and cell morphology differ markedly compared to histology. Conditional random fields (CRFs) can refine noisy VLM predictions by propagating information across patches, but existing CRF frameworks were designed for histopathology and do not transfer to cytology datasets, released as independent patch pools spanning multiple staining protocols. We introduce CytoCRF, which adapts the pairwise terms to cytology by targeting chromatin and cytology-specific staining, and further enrich the neighborhood of each potential term by combining multiple backbones. Across ten cytology datasets, CytoCRF outperforms existing CRF frameworks at every annotation budget, reaching +13.6 percentage points over the best baseline and +33.7 over ZS with only 50 annotations. Combining information from multiple backbones brings further gains, showing that the neighborhood topology matters more than the pairwise potential computed over it.
发表机构
- Université Catholique de Louvain（鲁汶天主教大学）
机构由 AI 辅助整理，请以论文原文为准。
