DPA-P2PNet: 用于精准基于点的细胞检测的可变形提议感知P2PNet
DPA-P2PNet: Deformable Proposal-aware P2PNet for Accurate Point-based Cell Detection
AI总结：
针对P2PNet在基于点的细胞检测中存在的多尺度信息利用不足、点提议位置偏差问题，提出可变形提议感知的DPA-P2PNet及其多视场变体，结合自监督预训练，在多个数据集上实现了优于现有最优方法的检测性能。
摘要：
基于点的细胞检测（Point-based cell detection, PCD）旨在低成本数据标注下实现高性能细胞感知，已在计算病理学领域受到越来越多的关注。与主流依赖中间密度图表示的PCD方法不同，点对点网络（Point-to-Point network, P2PNet）是近期出现的PCD端到端解决方案，展现出优异的细胞检测精度与效率。然而，由于点提议的尺度无关特性，P2PNet仅能从单级特征图进行解码，无法充分利用多尺度信息。此外，预设点提议的空间分布与细胞的空间分布存在偏差，导致细胞定位不准确。为解决这些局限，本文提出了DPA-P2PNet。该方法根据层级特征图上点提议的坐标，直接提取多尺度特征用于解码。在此基础上，我们进一步设计了可变形点提议，以缓解提议与潜在细胞之间的位置偏差，提升细胞定位效果。受实际病理诊断通常结合高层组织结构与低层细胞形态来实现准确细胞分类的启发，我们提出了DPA-P2PNet的多视场（multi-field-of-view, mFoV）变体，可纳入带有组织信息的大视场图像作为模型额外输入。最后，我们首次在免疫组织化学病理图像数据上开展自监督预训练，并评估了四种代表性自监督方法在PCD任务上的适用性。在三个基准数据集以及一个大规模真实世界间隔数据集上的实验结果表明，我们提出的模型优于现有最优同类方法。代码与预训练权重将公开发布。
英文摘要：
Point-based cell detection (PCD), which pursues high-performance cell sensing under low-cost data annotation, has garnered increased attention in computational pathology community. Unlike mainstream PCD methods that rely on intermediate density map representations, the Point-to-Point network (P2PNet) has recently emerged as an end-to-end solution for PCD, demonstrating impressive cell detection accuracy and efficiency. Nevertheless, P2PNet is limited to decoding from a single-level feature map due to the scale-agnostic property of point proposals, which is insufficient to leverage multi-scale information. Moreover, the spatial distribution of pre-set point proposals is biased from that of cells, leading to inaccurate cell localization. To lift these limitations, we present DPA-P2PNet in this work. The proposed method directly extracts multi-scale features for decoding according to the coordinates of point proposals on hierarchical feature maps. On this basis, we further devise deformable point proposals to mitigate the positional bias between proposals and potential cells to promote cell localization. Inspired by practical pathological diagnosis that usually combines high-level tissue structure and low-level cell morphology for accurate cell classification, we propose a multi-field-of-view (mFoV) variant of DPA-P2PNet to accommodate additional large FoV images with tissue information as model input. Finally, we execute the first self-supervised pre-training on immunohistochemistry histopathology image data and evaluate the suitability of four representative self-supervised methods on the PCD task. Experimental results on three benchmarks and a large-scale and real-world interval dataset demonstrate the superiority of our proposed models over the state-of-the-art counterparts. Codes and pre-trained weights will be available.
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。
