Object Segmentation is an important step in the work-flow of computational pathology. Deep learning based models as the best forming models require huge amount of labeled data for precise and reliable prediction. However, collecting labeled data is expensive, because it necessarily involves expert knowledge. This is perhaps best illustrated by medical tasks where measurements call for expensive machinery and labels are the fruit of a time-consuming analysis that draws from multiple human experts. As nuclei, cells and glands are fundamental objects for downstream analysis in histology, in this paper we propose a simple CNN-based approach to speed up collecting segmentation annotation for these objects by utilizing minimum input from an annotator. We show for nuclei and cells as small objects, one click inside objects is enough to have precise annotation. For glands as large objects, providing a squiggle to show the extend of gland can guide the model to outline the exact boundaries. This supervisory signals are fed to network as an auxiliary channels along with RGB channels. With detailed experiments, we show that our approach is generalizable, robust against variations in the user input and that it can be used to obtain annotations for completely different domains. Practically, a model trained on the masks generated by NuClick could achieve first rank in LYON19 challenge. Furthermore, as the output of our framework, we release two data-sets: 1) a dataset of lymphocyte annotations within IHC images and 2) a dataset of WBCs annotated in blood sample images.

本论文提出了一种基于CNN的方法NuClick，可以快速收集核、细胞，以及腺体细胞等许多应用于计算机病理学/细胞学的计算机处理对象的注释，并提出了一种新的引导信号，使NuClick能够分割腺体的边界。在实验证明，NuClick能够适应不同的目标尺度，对用户输入的不同变化具有强大的鲁棒性，并且提供可靠的标注，对它标准产生的实例分割模型在LYON19挑战中获得了第一名。

NuClick:一个用于显微镜图像交互式分割的深度学习框架