用条件随机场提升病理图像预测准确率，无需重新训练模型
Conditional Random Fields for Interactive Refinement of Histopathological Predictions
- 用新定义的成对势函数构建CRF框架，增强标签多样性
- 无标注时平均提升16.0%，仅用100个专家标注提升27.5%
- 人机协同迭代标注可再增32.6%准确率，适合病理辅助诊断
辅助病理科医生分析组织病理图像具有重要临床价值，有助于癌症检测与分期。近年来，视觉-语言模型（VLMs）在该领域兴起，能提供强但不完美的零样本预测。本文提出将条件随机场（CRFs）适配于病理学任务，无需额外模型训练。我们设计了HistoCRF框架，引入新型成对势函数，促进标签多样性并利用专家标注。在五个覆盖不同器官和疾病的图像块分类数据集上进行三类实验：无标注、有专家标注、以及迭代式人机协同标注。结果表明，无标注条件下平均准确率提升16.0%，仅使用100个标注时提升27.5%；引入人类反馈后，相同标注量下准确率进一步提升至32.6%。代码将公开于https://github.com/tgodelaine/HistoCRF。
原文摘要 · Abstract (English)
Assisting pathologists in the analysis of histopathological images has high clinical value, as it supports cancer detection and staging. In this context, histology foundation models have recently emerged. Among them, Vision-Language Models (VLMs) provide strong yet imperfect zero-shot predictions. We propose to refine these predictions by adapting Conditional Random Fields (CRFs) to histopathological applications, requiring no additional model training. We present HistoCRF, a CRF-based framework, with a novel definition of the pairwise potential that promotes label diversity and leverages expert annotations. We consider three experiments: without annotations, with expert annotations, and with iterative human-in-the-loop annotations that progressively correct misclassified patches. Experiments on five patch-level classification datasets covering different organs and diseases demonstrate average accuracy gains of 16.0% without annotations and 27.5% with only 100 annotations, compared to zero-shot predictions. Moreover, integrating a human in the loop reaches a further gain of 32.6% with the same number of annotations. The code will be made available on https://github.com/tgodelaine/HistoCRF.
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。