FTU-Seek：基于基础模型的硬负样本学习用于稀疏功能组织单元分割
FTU-Seek: Foundation Model-Guided Hard-Negative Learning for Sparse Functional Tissue Unit Segmentation
- Clinical Oncology School, Fujian Medical University（福建医科大学临床肿瘤学院）
- Innovation Center for Cancer Research, Clinical Oncology School, Fujian Medical University（福建医科大学临床肿瘤学院癌症研究创新中心）
- Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
- University of Chinese Academy of Sciences（中国科学院大学）
- College of Engineering, Boston University（波士顿大学工程学院）
- Northeastern University（东北大学）
- Fujian Cancer Hospital（福建省肿瘤医院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
该研究针对全玻片图像中稀疏功能组织单元分割的挑战，提出FTU-Seek框架，基于UNI病理学基础模型的硬负样本学习实现精准分割，在多任务及队列中验证了有效性。
AI中文摘要：
功能组织单元（FTU）包括三级淋巴结构（TLS）、血管和腺体，编码了组织病理学中局部的免疫、血管和上皮组织结构，准确量化这些结构对研究组织结构和疾病相关的组织结构具有重要意义。然而，FTU通常是稀疏、异质的，且被大量形态相似的背景组织包围，这使得全玻片图像（WSI）中的自动分割极具挑战性。为此，我们开发了FTU-Seek，一种病理学基础模型引导的框架，将形态感知的负样本块选择作为稀疏FTU分割的关键组成部分。FTU-Seek使用来自UNI病理学基础模型的冻结多深度特征来训练一个块级分类器，该分类器可区分含FTU和不含FTU的组织。随后，根据预测的含目标概率对不含目标的块进行排序，通过静态TopK策略选择得分最高的硬负样本，以构建紧凑的分割训练集。该框架通过五折交叉验证和内部测试队列在TLS、血管和腺体分割任务上进行评估，另外还有一个包含30张WSI的独立保留队列用于TLS评估。我们将仅正样本、全组织、随机负样本和匹配随机TopK采样策略作为对比方法，还在外部TCGA队列中进一步探索了分割衍生的表型。
英文摘要：
Functional tissue units (FTUs), including tertiary lymphoid structures (TLSs), blood vessels, and glands, encode localized immune, vascular, and epithelial organization in histopathology. Accurate quantification of these structures is important for studying tissue architecture and disease-associated tissue organization. However, FTUs are frequently sparse, heterogeneous, and surrounded by large amounts of morphologically similar background tissue, making automated segmentation in whole-slide images (WSIs) challenging. We therefore developed FTU-Seek, a pathology foundation model-guided framework that treats morphology-aware negative-patch selection as a key component of sparse FTU segmentation. FTU-Seek uses frozen multi-depth features from the UNI pathology foundation model to train a patch-level classifier that distinguishes FTU-containing from FTU-absent tissue. Target-absent patches are subsequently ranked according to their predicted target-containing probabilities, and the highest-scoring hard negatives are selected through a static Top$K$ strategy to construct compact segmentation training sets. The framework was evaluated using five-fold cross-validation and internal test cohorts across TLS, blood-vessel, and gland segmentation tasks, with an additional independent 30-WSI held-out cohort for TLS. Positive-only, all-tissue, random-negative, and matched random Top$K$ sampling strategies served as comparators. Segmentation-derived phenotypes were further explored in external TCGA cohorts.
