美国霍华德休斯医学研究所Carsen Stringer和Marius Pachitariu共同合作近期取得重要工作进展，他们研究提出了Cellpose 2.0，即如何训练自己的模型。相关论文2022年11月7日在线发表于《自然—方法学》杂志上。

研究人员介绍了Cellpose 2.0，一个新的软件包，包括各种预训练模型的集成，以及用于新定制模型快速原型制作的human-in-the-loop方法。研究人员表明，在Cellpose数据集上预训练的模型可以通过500–1000个用户注释的感兴趣区域（ROI）进行微调，以实现几乎与在整个数据集上训练的模型一样的性能，ROI高达200000。

human-in-the-loop方法进一步将所需的用户注释减少到100–200 ROI，同时保持高质量的分割。研究人员提供软件工具，如注释图形用户界面、模型动物园和human-in-the-loop方法，以促进Cellpose 2.0的采用。

据介绍，用于生物分割的预训练神经网络模型可以为许多图像类型提供便捷良好的分析结果。然而，这样的模型不允许用户根据其特定需求调整分割样式，并且对与训练图像差异较大的测试图像达不到理想的检测效果。

附：英文原文

Title: Cellpose 2.0: how to train your own model

Author: Pachitariu, Marius, Stringer, Carsen

Issue&Volume: 2022-11-07

Abstract: Pretrained neural network models for biological segmentation can provide good out-of-the-box results for many image types. However, such models do not allow users to adapt the segmentation style to their specific needs and can perform suboptimally for test images that are very different from the training images. Here we introduce Cellpose 2.0, a new package that includes an ensemble of diverse pretrained models as well as a human-in-the-loop pipeline for rapid prototyping of new custom models. We show that models pretrained on the Cellpose dataset can be fine-tuned with only 500–1,000 user-annotated regions of interest (ROI) to perform nearly as well as models trained on entire datasets with up to 200,000 ROI. A human-in-the-loop approach further reduced the required user annotation to 100–200 ROI, while maintaining high-quality segmentations. We provide software tools such as an annotation graphical user interface, a model zoo and a human-in-the-loop pipeline to facilitate the adoption of Cellpose 2.0.

DOI: 10.1038/s41592-022-01663-4

Source: https://www.nature.com/articles/s41592-022-01663-4