An Automatic Learning-Based Framework for Robust Nucleus Segmentation
An Automatic Learning-Based Framework for Robust Nucleus Segmentation
复制标题
DOI：
10.1109/tmi.2015.2481436
复制
发表时间：
2016-02-01
影响因子：
10.6
通讯作者：
Yang, Lin
中科院分区：
文献类型：
--
作者：
Xing, Fuyong;Xie, Yuanpu;Yang, Lin
组织病理学标本的计算机辅助图像分析可能为脑肿瘤、胰腺神经内分泌肿瘤(NET)和乳腺癌等疾病的早期发现和改进定性提供支持。细胞核的自动分割是包括自动形态特征计算在内的各种定量分析的前提。然而，由于组织病理学图像的复杂性，这仍然是一个具有挑战性的问题。在本文中，我们提出了一种基于学习的稳健的、具有形状保持的自动核分割框架。对于给定的核图像，首先使用深度卷积神经网络(CNN)模型生成概率图，然后在概率图上采用迭代区域合并方法进行形状初始化。接下来，采用一种新的分割算法来分离单个核，该分割算法结合了稳健的基于选择的稀疏形状模型和局部排斥变形模型。所提出的框架的显著优点之一是它适用于不同的染色组织病理学图像。由于深层细胞神经网络的特征学习特性和较高的形状先验建模能力，该方法具有较强的通用性，能够很好地适用于多种场景。我们使用一系列不同的组织和染色准备在三个大规模的病理图像数据集上测试了所提出的算法，并且通过与最新技术的对比实验证明了所提出的方法的优越性能。
Computer-aided image analysis of histopathology specimens could potentially provide support for early detection and improved characterization of diseases such as brain tumor, pancreatic neuroendocrine tumor (NET), and breast cancer. Automated nucleus segmentation is a prerequisite for various quantitative analyses including automatic morphological feature computation. However, it remains to be a challenging problem due to the complex nature of histopathology images. In this paper, we propose a learning-based framework for robust and automatic nucleus segmentation with shape preservation. Given a nucleus image, it begins with a deep convolutional neural network (CNN) model to generate a probability map, on which an iterative region merging approach is performed for shape initializations. Next, a novel segmentation algorithm is exploited to separate individual nuclei combining a robust selection-based sparse shape model and a local repulsive deformable model. One of the significant benefits of the proposed framework is that it is applicable to different staining histopathology images. Due to the feature learning characteristic of the deep CNN and the high level shape prior modeling, the proposed method is general enough to perform well across multiple scenarios. We have tested the proposed algorithm on three large-scale pathology image datasets using a range of different tissue and stain preparations, and the comparative experiments with recent state of the arts demonstrate the superior performance of the proposed approach.