用于神经内分泌肿瘤细胞分割的无监督形状先验建模
UNSUPERVISED SHAPE PRIOR MODELING FOR CELL SEGMENTATION IN NEUROENDOCRINE TUMOR.
作者信息
Xing Fuyong, Yang Lin
机构信息
Department of Electrical and Computer Engineering, University of Florida; J. Crayton Pruitt Family Department of Biomedical Engineering, University of Florida.
J. Crayton Pruitt Family Department of Biomedical Engineering, University of Florida.
出版信息
Proc IEEE Int Symp Biomed Imaging. 2015 Apr;2015:1443-1446. doi: 10.1109/ISBI.2015.7164148. Epub 2015 Jul 23.
Automated and accurate cell segmentation provides support for many quantitative analyses on digitized neuroendocrine tumor (NET) images. It is a challenging task due to complex variations of cell characteristics. In this paper, we incorporate unsupervised shape priors into an efficient repulsive deformable model for automated cell segmentation on NET images. Unlike other supervised learning based shape models, which usually require a large number of annotated data for training, the proposed algorithm is an unsupervised approach that applies group similarity to shape constraints to avoid any labor intensive annotation. The algorithm is extensively tested on 51 NET images, and the comparative experiments with the state of the arts demonstrate the superior performance of this method using an unsupervised shape model.
自动且准确的细胞分割为数字化神经内分泌肿瘤（NET）图像的许多定量分析提供了支持。由于细胞特征的复杂变化，这是一项具有挑战性的任务。在本文中，我们将无监督形状先验纳入一个有效的排斥性可变形模型，用于NET图像上的自动细胞分割。与其他基于监督学习的形状模型不同，后者通常需要大量带注释的数据进行训练，本文提出的算法是一种无监督方法，它将组相似性应用于形状约束，以避免任何劳动密集型的注释工作。该算法在51幅NET图像上进行了广泛测试，与现有技术的对比实验证明了这种使用无监督形状模型的方法具有卓越性能。
Zotero 插件