CyclePose——利用循环一致性实现荧光显微镜中无标注细胞核分割
CyclePose -- Leveraging Cycle-Consistency for Annotation-Free Nuclei Segmentation in Fluorescence Microscopy
AI总结：
针对显微图像细胞核实例分割需大量标注数据的问题，提出整合合成数据生成与分割训练的混合框架CyclePose，基于CycleGAN架构实现自监督，无标注时性能优于其他弱/无监督方法。
摘要：
近年来，众多专为显微图像中细胞核实例分割设计的神经网络架构已被发布。这些模型嵌入细胞核特定先验，性能优于U-Net等通用架构；但它们需要大型标注数据集，而这类数据集往往不可得。生成模型（GAN、扩散模型）已被用于通过合成训练数据弥补这一不足。这类两阶段方法计算成本高昂，因为需先训练生成模型，再训练分割模型。我们提出CyclePose，一个整合合成数据生成与分割训练的混合框架。CyclePose基于CycleGAN架构，支持显微图像与分割掩码间的无配对转换。我们将分割模型嵌入CycleGAN，并利用循环一致性损失实现自监督。在无标注数据情况下，CyclePose在两个公开数据集上优于其他弱监督或无监督方法。代码可在https://github.com/jonasutz/CyclePose获取
英文摘要：
In recent years, numerous neural network architectures specifically designed for the instance segmentation of nuclei in microscopic images have been released. These models embed nuclei-specific priors to outperform generic architectures like U-Nets; however, they require large annotated datasets, which are often not available. Generative models (GANs, diffusion models) have been used to compensate for this by synthesizing training data. These two-stage approaches are computationally expensive, as first a generative model and then a segmentation model has to be trained. We propose CyclePose, a hybrid framework integrating synthetic data generation and segmentation training. CyclePose builds on a CycleGAN architecture, which allows unpaired translation between microscopy images and segmentation masks. We embed a segmentation model into CycleGAN and leverage a cycle consistency loss for self-supervision. Without annotated data, CyclePose outperforms other weakly or unsupervised methods on two public datasets. Code is available at https://github.com/jonasutz/CyclePose
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
