Biomedical Instrumentation Laboratory, Department of Electrical Engineering, Indian Institute of Technology Roorkee, Roorkee, Uttarakhand, India 247667.
J Digit Imaging. 2013 Jun;26(3):530-43. doi: 10.1007/s10278-012-9537-8.
A system to characterize normal liver, cirrhotic liver and hepatocellular carcinoma (HCC) evolved on cirrhotic liver is proposed in this paper. The study is performed with 56 real ultrasound images (15 normal, 16 cirrhotic and 25 HCC liver images) taken from 56 subjects. A total of 180 nonoverlapping regions of interest (ROIs), i.e. 60 from each image class, are extracted by an experienced participating radiologist. The multiresolution wavelet packet texture descriptors, i.e. mean, standard deviation and energy features, are computed from all 180 ROIs by using various compact support wavelet filters including Haar, Daubechies (db4 and db6), biorthogonal (bior3.1,bior3.3 and bior4.4), symlets (sym3 and sym5) and coiflets (coif1 and coif2). It is observed that a combined texture descriptor feature vector of length 48 consisting of 16 mean, 16 standard deviation and 16 energy features estimated from all 16 subband feature images (wavelet packets) obtained by second-level decomposition with two-dimensional wavelet packet transform by using Haar wavelet filter gives the best characterization performance of 86.6 %. Feature selection by genetic algorithm-support vector machine method increased the classification accuracy to 88.8 % with sensitivity of 90 % for detecting normal and cirrhotic cases and sensitivity of 86.6 % for HCC cases. Considering limited sensitivity of B-mode ultrasound for detecting HCCs evolved on cirrhotic liver, the sensitivity of 86.6 % for HCC lesions obtained by the proposed computer-aided diagnostic system is quite promising and suggests that the proposed system can be used in a clinical environment to support radiologists in lesion interpretation.
本文提出了一种用于描述正常肝、肝硬化和肝癌（HCC）的系统，该系统是在肝硬化基础上发展而来的。本研究使用了 56 幅来自 56 名受试者的真实超声图像（15 幅正常肝图像、16 幅肝硬化图像和 25 幅 HCC 肝图像）。由一位经验丰富的参与放射科医生提取了总共 180 个互不重叠的感兴趣区域（ROI），即每个图像类别 60 个 ROI。使用各种紧凑支撑小波滤波器（包括 Haar、Daubechies（db4 和 db6）、双正交（bior3.1、bior3.3 和 bior4.4）、symlets（sym3 和 sym5）和 coiflets（coif1 和 coif2））从所有 180 个 ROI 计算出多分辨率小波包纹理描述符，即均值、标准差和能量特征。观察到，由二维小波包变换的第二级分解用 Haar 小波滤波器获得的 16 个均值、16 个标准差和 16 个能量特征组成的 48 个长度的组合纹理描述符特征向量，给出了最佳的特征描述性能为 86.6%。使用遗传算法-支持向量机方法进行特征选择，将分类精度提高到 88.8%，正常和肝硬化病例的检测灵敏度为 90%，HCC 病例的检测灵敏度为 86.6%。考虑到 B 型超声对检测肝硬化基础上发生的 HCC 的敏感性有限，该计算机辅助诊断系统检测到的 HCC 病变的 86.6%敏感性非常有前景，表明该系统可在临床环境中使用，以支持放射科医生进行病变解释。
