无需标注数据，用循环一致性实现荧光显微镜下细胞核分割
CyclePose -- Leveraging Cycle-Consistency for Annotation-Free Nuclei Segmentation in Fluorescence Microscopy
- 将分割模型嵌入CycleGAN，通过图像与掩码的循环一致来自监督训练
- 在两个公开数据集上超越其他弱监督/无监督方法，平均DSC达0.86
- 适合缺乏标注数据的生物图像分析场景，代码开源可复现
近年来，许多专为显微图像中细胞核实例分割设计的神经网络架构被提出。这些模型通过嵌入细胞核先验知识，在性能上优于通用架构（如U-Net）；但其训练依赖大规模标注数据，而这类数据常难以获取。生成模型（GAN、扩散模型）被用于合成训练数据以弥补这一缺陷，但此类两阶段方法计算开销大，需先后训练生成模型和分割模型。本文提出CyclePose，一种融合合成数据生成与分割训练的混合框架。该框架基于CycleGAN架构，实现显微图像与分割掩码间的无配对转换。将分割模型嵌入CycleGAN，并利用循环一致性损失实现自监督。在无任何标注数据的情况下，CyclePose在两个公开数据集上的表现优于其他弱监督或无监督方法，平均Dice相似系数（DSC）达到0.86。代码已开源。
原文摘要 · Abstract (English)
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
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。