用零样本模型实现跨数据集的细胞追踪，无需训练。
Segment Anything for Cell Tracking
- 引入SAM2构建无监督细胞追踪框架。
- 在2D与大规模3D时间序列中表现优异，无需微调。
- 适合处理多样微观图像，避免标注依赖。
在时间序列显微成像中追踪细胞并检测有丝分裂事件是生物医学研究的关键任务。然而，由于细胞分裂、信噪比低、边界模糊、密集簇以及细胞外观相似等问题，该任务仍极具挑战性。现有基于深度学习的方法依赖人工标注数据集进行训练，成本高且耗时长，同时在未见数据集上的泛化能力有限。为此，我们提出一种零样本细胞追踪框架，将为通用图像与视频分割设计的大规模基础模型SAM2整合至追踪流程中。作为完全无监督方法，该框架不依赖或继承任何特定训练数据集的偏差，可在无需微调的情况下跨多种显微图像数据集实现良好泛化。该方法在2D和大规模3D时间序列显微视频中均达到具有竞争力的准确率，且无需针对特定数据集进行适应。
原文摘要 · Abstract (English)
Tracking cells and detecting mitotic events in time-lapse microscopy image sequences is a crucial task in biomedical research. However, it remains highly challenging due to dividing objects, low signal-tonoise ratios, indistinct boundaries, dense clusters, and the visually similar appearance of individual cells. Existing deep learning-based methods rely on manually labeled datasets for training, which is both costly and time-consuming. Moreover, their generalizability to unseen datasets remains limited due to the vast diversity of microscopy data. To overcome these limitations, we propose a zero-shot cell tracking framework by integrating Segment Anything 2 (SAM2), a large foundation model designed for general image and video segmentation, into the tracking pipeline. As a fully-unsupervised approach, our method does not depend on or inherit biases from any specific training dataset, allowing it to generalize across diverse microscopy datasets without finetuning. Our approach achieves competitive accuracy in both 2D and large-scale 3D time-lapse microscopy videos while eliminating the need for dataset-specific adaptation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。