从通用到特定：动态知识引导的多实例学习用于少样本全切片图像分类
Universal-to-Specific: Dynamic Knowledge-Guided Multiple Instance Learning for Few-Shot Whole Slide Image Classification
将通用病理视觉语言知识动态实例化为切片特异性的图像块级特征，为少样本全切片图像分类提供可复用的知识检索与对齐机制。
原文依据 we propose DyKo, a Dynamic Knowledge-guided MIL framework that adapts universal knowledge to slide-specific evidence for few-shot WSI classification.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论多实例学习（MIL）已成为分析千兆像素级全切片图像（WSI）的主流范式。然而，近期利用视觉语言模型引导的方法往往依赖静态且通用的病理描述。这种一刀切的策略未能考虑单个WSI内巨大的形态学异质性，因为其统一的引导并未针对切片特定的视觉证据进行定制。为解决这一问题，我们提出DyKo，一种动态知识引导的MIL框架，它将通用知识适配为切片特定的证据，用于少样本WSI分类。DyKo的核心是WSI自适应知识实例化模块（WAKI）。WAKI首先在特定WSI的组织学中识别关键视觉原型。这些切片特定的原型随后作为查询，从病理知识库中检索相关概念。检索到的知识接着被用于为每个实例合成独特的、知识实例化的特征，从而在图像块级别有效实例化定制引导。为确保保真度并防止语义漂移，我们引入结构一致性损失，强制知识实例化特征与视觉特征之间的对齐。在四个公开真实癌症数据集上的综合实验表明，DyKo在少样本病理诊断中优于最优方法。代码见 https://github.com/junjianli106/DyKo。
英文原文摘要 1482 字符
Multiple Instance Learning (MIL) has emerged as the dominant paradigm for the analysis of gigapixel-scale Whole Slide Images (WSIs). However, recent methods leveraging guidance from Vision-Language Models often rely on static and universal pathological descriptions. This one-size-fits-all strategy fails to account for the vast morphological heterogeneity within individual WSIs, as its uniform guidance is not tailored to slide-specific visual evidence. To address this, we propose DyKo, a Dynamic Knowledge-guided MIL framework that adapts universal knowledge to slide-specific evidence for few-shot WSI classification. The core of DyKo is the WSI-Adaptive Knowledge Instantiation module (WAKI). WAKI begins by identifying key visual prototypes within a specific WSI's histology. These slide-specific prototypes then serve as queries to retrieve relevant concepts from a pathology knowledge base. This retrieved knowledge is then used to synthesize unique, knowledge-instantiated features for each instance, effectively instantiating tailored guidance at the patch level. To ensure fidelity and prevent semantic drift, we introduce a Structural Consistency loss that enforces alignment between knowledge-instantiated and visual features. Comprehensive experiments on four public real-world cancer datasets demonstrate that DyKo achieves superior performance over state-of-the-art methods in few-shot pathology diagnosis. Code is available at https://github.com/junjianli106/DyKo.