【摘 要】
：
为了提高计算机辅助诊断系统的颅内出血病灶分割准确率,提出一种新的颅脑CT图像分割方法,被怀疑为出血的区域可快速而有效地分割出来。首先利用颅内结构提取算法提取颅内区域;然后利用两次模糊c均值聚类算法完成出血区域分割。第一次模糊c均值聚类确定疑似颅内出血的区域,根据脑出血CT图像特点,将中心点灰度值最高的类作为第二次模糊c均值聚类对象,第二次模糊c均值聚类分割出疑似出血区域,最后对颅脑CT图像进行实验
论文部分内容阅读
为了提高计算机辅助诊断系统的颅内出血病灶分割准确率,提出一种新的颅脑CT图像分割方法,被怀疑为出血的区域可快速而有效地分割出来。首先利用颅内结构提取算法提取颅内区域;然后利用两次模糊c均值聚类算法完成出血区域分割。第一次模糊c均值聚类确定疑似颅内出血的区域,根据脑出血CT图像特点,将中心点灰度值最高的类作为第二次模糊c均值聚类对象,第二次模糊c均值聚类分割出疑似出血区域,最后对颅脑CT图像进行实验,验证方法的可行性。实验结果表明该方法对颅脑出血CT图像病灶的分割是有效的。
其他文献
The signal-to-noise ratio may be increased by the cross-range coherence integration so as to detect the moving target in low signal-to-noise ratio (SNR) condition. But, the radial velocity, accelerati
提出了基于支持向量机(SVM)和决策树(DT)的几种新分类器算法。首先对支持向量机和模糊支持向量机(FSVM)处理多类分类问题的传统算法进行介绍,然后在DT-FSVM和最近邻分类器的基础之上,提出基于样本区域分析(SRA)的混合分类器算法(SRA-DT-FSVM),该算法中样本区域分析的概念被提出。在线性鉴别分析(LDA)的人脸特征空间中,分别对算法FSVM,DT-FSVM,SRA-DT-FSVM
Based on the idea of second generation image coding, a novel scheme for coding still images is pre- sented. At first, an image was partitioned with a pulse-coupled neural network; and then an improved
在深入分析指纹图像的基本特征及其对正弦曲面相似性的基础上,构造符合指纹局部区域纹线灰度分布规律的正弦曲面滤波器模型,并提出了基于该模型的指纹增强算法.实验结果表明,相比于加博增强算法,该算法具有更好的纹线连接能力,能有效提高指纹图像增强的实际效果和细节特征信息提取结果的准确性.
针对目前大多数空间聚类算法主要是针对关系数据且没有考虑空间拓扑关系相似性的问题,对基于空间拓扑关系的空间聚类方法进行研究.提出了一种基于线面包含关系的GML(geography markup language)空间聚类算法SCGML-LRI(spatial clustering in GML data based on line-region inclusion relations).算法将GML
Self-affine multiplicity scaling is investigated in the framework of a two-dimensional factorial moment methodology using the concept of the Hurst exponent(H).Analyzing the experimental data of target
This paper focuses mainly on the vertex reconstruction of resonance particles with a relatively long lifetime such as KS0,Λ,as well as on lifetime measurements using a 3-dimensional fit.The kinematic
Geological body structure is the product of the geological evolution in the time dimension, which is presented in 3D configuration in the natural world. However, many geologists still record and proce
High-contrast imaging provided by a coronagraph is critical for the direction imaging of the Earth-like planet orbiting its bright parent star.A major limitation for such direct imaging is the speckle
Mainstream line is significant for the Yellow River situation forecasting and flood control.An effective statistical feature extraction method is proposed in this paper.In this method, a between-class