A robust medical image segmentation method using KL distance and local neighborhood information
A robust medical image segmentation method using KL distance and local neighborhood information
复制标题
一种利用KL距离和局部邻域信息的鲁棒医学图像分割方法
DOI：
10.1016/j.compbiomed.2013.01.002
复制
发表时间：
2013-06-01
影响因子：
7.7
通讯作者：
Chen, Wufan
中科院分区：
文献类型：
--
作者：
Zheng, Qian;Lu, Zhentai;Chen, Wufan
在本文中，我们提出了一种改进的Chan-Vese（CV）模型，使用Kullback-Leibler（KL）距离和局部邻域信息（LNI）。由于异质性和复杂结构的影响，水平集分割的性能受到附近相似强度结构的存在的干扰，从而阻止其识别对象的确切边界。此外，CV模型通常不能在控制参数的最佳配置的情况下获得准确的医学图像分割结果，这需要大量的人工干预。为了克服上述不足，我们利用KL距离和LNI提高分割精度，从而引入图像的局部特征。通过对合成图像和一系列真实的医学图像的实验，对本方法的性能进行了评价。大量的实验结果表明，所提出的方法优于国家的最先进的方法，在鲁棒性和效率方面的上级性能。皇冠版权所有（C）2013由爱思唯尔有限公司出版。保留所有权利。
In this paper, we propose an improved Chan-Vese (CV) model that uses Kullback-Leibler (KL) distances and local neighborhood information (LNI). Due to the effects of heterogeneity and complex constructions, the performance of level set segmentation is subject to confounding by the presence of nearby structures of similar intensity, preventing it from discerning the exact boundary of the object. Moreover, the CV model cannot usually obtain accurate results in medical image segmentation in cases of optimal configuration of controlling parameters, which requires substantial manual intervention. To overcome the above deficiency, we improve the segmentation accuracy by the usage of KL distance and LNI, thereby introducing the image local characteristics. Performance evaluation of the present method was achieved through experiments on the synthetic images and a series of real medical images. The extensive experimental results showed the superior performance of the proposed method over the state-of-the-art methods, in terms of both robustness and efficiency. Crown Copyright (C) 2013 Published by Elsevier Ltd. All rights reserved.