论文标题
可分离的孔和实例 - yolo，用于结肠核识别和计数
Separable-HoverNet and Instance-YOLO for Colon Nuclei Identification and Counting
论文作者
论文摘要
核分割，分类和定量在血久和曙红染色的组织学图像中可以提取可解释的基于细胞的特征，这些特征可用于计算病理学（CPATH）中的下游可解释模型。但是，对不同核的自动识别面临着一个重大挑战，因为有几种不同类型的核，其中一些表现出较大的类内变异性。在这项工作中，我们提出了一种结合可分离的通讯网和实例 - Yolov5的方法，以缩小结肠核小且不平衡。我们的方法可以在分段和分类测试数据集上实现MPQ+ 0.389，并且在ISBI 2022 CONIC CANCEADS上的蜂窝组成预测数据集上可以实现R2 0.599。
Nuclear segmentation, classification and quantification within Haematoxylin & Eosin stained histology images enables the extraction of interpretable cell-based features that can be used in downstream explainable models in computational pathology (CPath). However, automatic recognition of different nuclei is faced with a major challenge in that there are several different types of nuclei, some of them exhibiting large intraclass variability. In this work, we propose an approach that combine Separable-HoverNet and Instance-YOLOv5 to indentify colon nuclei small and unbalanced. Our approach can achieve mPQ+ 0.389 on the Segmentation and Classification-Preliminary Test Dataset and r2 0.599 on the Cellular Composition-Preliminary Test Dataset on ISBI 2022 CoNIC Challenge.
