Deep Adversarial Training for Multi-Organ Nuclei Segmentation in Histopathology Images.
Deep Adversarial Training for Multi-Organ Nuclei Segmentation in Histopathology Images.
复制标题
DOI：
10.1109/tmi.2019.2927182
复制
发表时间：
2020-11
影响因子：
10.6
通讯作者：
Durr NJ
中科院分区：
文献类型：
--
作者：
Mahmood F;Borders D;Chen RJ;Mckay GN;Salimian KJ;Baras A;Durr NJ
细胞核分割是各种计算病理学应用的基本任务，包括细胞核形态分析、细胞类型分类和癌症分级。深度学习已经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的方法缺乏结构化的预测能力，这是区分重叠和聚集的细胞核所必需的。在这里，我们提出了一种细胞核分割的方法，通过利用用合成和真实的数据训练的条件生成对抗网络（cGAN）来克服这些挑战。我们使用未配对的GAN框架生成具有完美核分割标签的H&E训练图像的大型数据集。该合成数据沿着以及来自六个不同器官的真实的组织病理学数据用于训练具有谱归一化和梯度惩罚的条件GAN以用于核分割。与传统的CNN模型相比，这种对抗性回归框架强制执行高阶空间一致性。我们证明，这种核分割方法概括了不同的器官，网站，患者和疾病状态，并优于传统的方法，特别是在隔离个人和重叠的核。
Nuclei 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.