B超肝脏图像纹理特征提取方法的实验研究

Experimental study of texture feature extraction methods of liver ultrasonic imaging

目的 为脂肪肝的诊断提供量化依据。方法 采用纹理分析法 ,从灰度直方图中提取特征参数 ,对脂肪肝和正常肝脏B超图像进行识别。结果 从直方图分析中提取的均值、斜态均能反映两类图像所特有的纹理特征。结论 将该算法用软件编程实现 ,用在普通B型超声仪上 ,对图像感兴趣区域进行处理 ,可为医师诊断提供量化的诊断依据。

Objective To provide quantitative basis for diagnosis of fatty liver. Methods Ultrasonic images of fatty and normal liver were identified by adopting texture analysis with statistical features and getting features parameter from gray histogram. Results Parameters including mean value and skewness gotten from histogram can reflected the all texture feature of images of fatty and normal liver. Conclusion If the algorithm can be realized by software programming and be used in normal B ultrasonic medicine equipment, the interesting imaging area will be processed, so as to provide quantitatively diagnostic basis of fatty liver for clinic.