Pre-trained on a large and diverse dataset, the segment anything model (SAM)
is the first promptable foundation model in computer vision aiming at object
segmentation tasks. In this work, we evaluate SAM for the task of nuclear
instance segmentation performance with zero-shot learning and finetuning. We
compare SAM with other representative methods in nuclear instance segmentation,
especially in the context of model generalisability. To achieve automatic
nuclear instance segmentation, we propose using a nuclei detection model to
provide bounding boxes or central points of nu-clei as visual prompts for SAM
in generating nuclear instance masks from histology images.

通过在大规模多样化数据集上进行预训练，SAM 模型是计算机视觉领域针对目标分割任务的第一个可提示的基础模型。本文评估了 SAM 在零样本学习和微调下的核实例分割性能，将其与其他代表性方法在核实例分割中尤其是模型泛化能力的背景下进行比较，并提出使用核实例检测模型来为 SAM 提供核实例的边界框或中心点作为视觉提示，从组织学图像中生成核实例掩模。