基于检测引导的细胞表示学习框架，实现高精度病理图像细胞级分析
CellDETR: A Detection-Guided Framework for Scalable Cell Representation Learning from Histopathology Images
- 采用可变形 DETR 架构，结合位置解耦与框约束注意力机制
- 在 PanNuke 数据集上超越现有最优方法，分类准确率提升显著
- 支持无标注数据预训练，跨数据集迁移能力出色，适合生物发现研究
近期病理学基础模型在全切片图像（WSIs）的块级和切片级表征学习方面取得显著进展，但细胞级表征学习仍处于探索阶段，限制了细胞级别的可解释性、生物学发现和临床转化。我们提出 CellDETR，一种基于可变形 DETR 的检测引导框架，用于从 WSIs 中进行可扩展的细胞级表征学习。通过引入位置特征解耦和框约束注意力机制，CellDETR 实现了细胞级嵌入的自动化提取，在 PanNuke 数据集上的监督细胞分类任务中优于现有最先进方法。此外，通过引入对比学习设计，我们构建了一个基于 CellDETR 的无标签 WSIs 预训练模型，显著提升了下游细胞分类性能。进一步表明，使用 Xenium 空间转录组学生成的细胞标注进行预训练后，CellDETR 能实现高精度的跨数据集细胞分类，证明了所学细胞嵌入具有良好的可迁移性和生物学相关性。综上，CellDETR 为可解释性计算病理学提供了通用的细胞级表征学习可扩展路径。
原文摘要 · Abstract (English)
Recent advances in pathology foundation models have substantially improved patch and slide level representation learning from whole-slide images (WSIs).However, cell-level representations learning remain underexplored, limiting cell resolved interpretability, biological discovery, and clinical translation. We propose CellDETR, a detection-guided framework built on Deformable DETR for scalable cell representation learning from WSIs. By introducing location feature decoupling and box-constrained attention mechanism, CellDETR enables automated extraction of cell-level embeddings, and outperform existing state-of-the-art methods in supervised cell classification on PanNuke data. In addition, by incorporating contrastive learning design, we build a CellDETR-based pretraining model for scalable cell representation learning from unlabeled WSIs, which improves downstream cell classification performance. Furthermore, we show that after pretraining with Xenium spatial transcriptomics-derived cell annotations, CellDETR achieves accurate cross-dataset cell classification, demonstrating the transferability and biological relevance of the learned cell embeddings. Together, CellDETR provides a scalable route toward general cell-level representation learning framework for interpretable computational patholog
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。