面向组织病理学图像的组织感知细胞核检测与分类模型
Tissue Aware Nuclei Detection and Classification Model for Histopathology Images
AI总结：
针对计算病理中核检测分类依赖精细标注、组织上下文利用不足的问题，提出TAND框架，结合ConvNeXt编解码器与冻结Virchow-2分支，通过Spatial-FiLM调制分类流，在PUMA基准上取得SOTA，降低标注负担。
摘要：
精准的细胞核检测与分类是计算病理学的基础，但现有方法受限于对详细专家标注的依赖，且对组织上下文的利用不足。本文提出Tissue-Aware Nuclei Detection（TAND，组织感知细胞核检测）这一新型框架，通过组织掩码条件增强的点级监督实现联合细胞核检测与分类。TAND将基于ConvNeXt的编解码器与冻结的Virchow-2组织分割分支耦合，其中语义组织概率通过新型多尺度空间特征线性调制（Spatial-FiLM）选择性调节分类流。在PUMA基准上，TAND取得了当前最优性能，超越了组织无关基线方法与掩码监督方法。值得注意的是，本方法在上皮、内皮、基质等组织依赖细胞类型上表现出显著提升。据我们所知，这是首个将逐细胞分类条件建立在学习得到的组织掩码上的方法，为降低标注负担提供了实用路径。
英文摘要：
Accurate nuclei detection and classification are fundamental to computational pathology, yet existing approaches are hindered by reliance on detailed expert annotations and insufficient use of tissue context. We present Tissue-Aware Nuclei Detection (TAND), a novel framework achieving joint nuclei detection and classification using point-level supervision enhanced by tissue mask conditioning. TAND couples a ConvNeXt-based encoder-decoder with a frozen Virchow-2 tissue segmentation branch, where semantic tissue probabilities selectively modulate the classification stream through a novel multi-scale Spatial Feature-wise Linear Modulation (Spatial-FiLM). On the PUMA benchmark, TAND achieves state-of-the-art performance, surpassing both tissue-agnostic baselines and mask-supervised methods. Notably, our approach demonstrates remarkable improvements in tissue-dependent cell types such as epithelium, endothelium, and stroma. To the best of our knowledge, this is the first method to condition per-cell classification on learned tissue masks, offering a practical pathway to reduce annotation burden.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
