基于阈值分割的脂肪肝超声图像分类方法  

Classification method of ultrasonic images of fatty livers based on threshold segmentation

作　　者：刘金珠[1] 王江河[2] 洪慧闻[2] 刘燕玲[2] 闵乐泉[1,3] 

机构地区：[1]北京科技大学信息工程学院,北京100083 [2]中国中医研究院西苑医院肝病科,北京100091 [3]北京科技大学应用科学学院,北京100083

出　　处：《计算机工程与应用》2010年第36期198-201,共4页Computer Engineering and Applications

基　　金：国家自然科学基金(No.60674059)~~

摘　　要：研究了一种基于阈值分割的脂肪肝超声图像分类方法。该方法在最小化假阴性错误率的基础上尽量减小假阳性错误,获得服从正态分布的正常肝和脂肪肝图像灰度的置信区间。利用各自的区间阈值对超声图像进行分割,通过比较两幅分割图像进行分类。实验验证表明,不论是测试数据还是训练数据,该方法对正常肝正确识别率均为100%,对脂肪肝正确识别率均为96.3%。与BP神经网络方法比较表明,该方法在分类准确性上与神经网络方法相当,但比BP网络方法花费了更少的时间。A classification method of ultrasonic liver image is studied based on threshold segmentation.Under the condition of minimizing the false-negative probabilityt,he confidence intervals of gray levels which are normal distributions in normal and fatty liver images can be obtained by minimizing the false-positive rate.Then classify the images by comparing the seg-mented images with the interval thresholds.The experimental results show that the classification rate of normal livers reaches to 100% for testing or training datat,he classification rate of fatty livers reaches to 96.3% for testing or training data.Com-pared with the Back Propagation Neural Network（BP NN） methodt,he method costs less time than BP NN method when they have the same performance.

关 键 词：脂肪肝 超声肝图像 分类 阈值分割 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]