IEEE Trans Med Imaging. 2020 Nov;39(11):3257-3267. doi: 10.1109/TMI.2019.2927182. Epub 2020 Oct 28.
Nuclei mymargin segmentation is a fundamental task for various computational pathology applications including nuclei morphology analysis, cell type classification, and cancer grading. Deep learning has emerged as a powerful approach to segmenting nuclei but the accuracy of convolutional neural networks (CNNs) depends on the volume and the quality of labeled histopathology data for training. In particular, conventional CNN-based approaches lack structured prediction capabilities, which are required to distinguish overlapping and clumped nuclei. Here, we present an approach to nuclei segmentation that overcomes these challenges by utilizing a conditional generative adversarial network (cGAN) trained with synthetic and real data. We generate a large dataset of H&E training images with perfect nuclei segmentation labels using an unpaired GAN framework. This synthetic data along with real histopathology data from six different organs are used to train a conditional GAN with spectral normalization and gradient penalty for nuclei segmentation. This adversarial regression framework enforces higher-order spacial-consistency when compared to conventional CNN models. We demonstrate that this nuclei segmentation approach generalizes across different organs, sites, patients and disease states, and outperforms conventional approaches, especially in isolating individual and overlapping nuclei.
细胞核形态分割是各种计算病理学应用的基础任务，包括细胞核形态分析、细胞类型分类和癌症分级。深度学习已成为分割细胞核的强大方法，但卷积神经网络（CNN）的准确性取决于用于训练的标记组织病理学数据的数量和质量。特别是，传统的基于 CNN 的方法缺乏结构化预测能力，而这种能力对于区分重叠和聚集的细胞核是必需的。在这里，我们提出了一种利用基于合成和真实数据的条件生成对抗网络（cGAN）进行细胞核分割的方法，该方法克服了这些挑战。我们使用非配对 GAN 框架生成了具有完美细胞核分割标签的大量 H&E 训练图像数据集。该合成数据与来自六个不同器官的真实组织病理学数据一起，用于训练具有谱归一化和梯度惩罚的条件 GAN 以进行细胞核分割。与传统的 CNN 模型相比，这种对抗回归框架在更高阶的空间一致性方面具有优势。我们证明了这种细胞核分割方法可以跨不同的器官、部位、患者和疾病状态进行泛化，并且优于传统方法，特别是在分离单个和重叠的细胞核方面。
