基于多层贝叶斯网络的医学图像语义建模  

A Medical Image Semantic Modeling Based on Hierarchical Bayesian Networks

作　　者：林春漪[1,2] 马丽红[2] 尹俊勋[2] 陈建宇[3] 

机构地区：[1]中山大学生物医学工程系,广州510080 [2]华南理工大学电子与信息学院,广州510640 [3]中山大学第二附属医院,广州510120

出　　处：《生物医学工程学杂志》2009年第2期400-404,共5页Journal of Biomedical Engineering

基　　金：国家自然科学基金资助项目(60472063);广东省博士启动基金资助项目(8451008901000615)

摘　　要：针对医学图像的特点,提出一种基于多层贝叶斯网络的医学图像语义建模方法。该方法的特点是采用了混合高斯模型(Gaussian mixture models,GMM)实现从低层视觉特征到对象语义的映射,并用概率表达语义的置信度,然后使用贝叶斯网络(Bayesian networks,BN)融合对象语义,从而建立一个多层的医学图像语义模型,目的在于支持多层次的医学图像语义自动标注及其检索。为了验证此方法的有效性,将其用于星形细胞瘤恶性程度的语义提取,实验表明了该方法用于医学图像语义建模是有效的,并且具有直观的结构性知识表达。A semantic modeling approach for medical image semantic retrieval based on hierarchical Bayesian net- works was proposed, in allusion to characters of medical images. It used GMM （Gaussian mixture models） to map low-level image features into object semantics with probabilities, then it captured high-level semantics through fusing these object semantics using a Bayesian network, so that it built a multi-layer medical image semantic model, aiming to enable automatic image annotation and semantic retrieval by using various keywords at different semantic levels. As for the validity of this method, we have built a multi-level semantic model from a small set of astroeytoma MRI （magnetic resonance imaging） samples, in order to extract semantics of astrocytoma in malignant degree. Experiment results show that this is a superior approach.

关 键 词：多层贝叶斯网络混合高斯模型语义建模 医学图像 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]