Computer-aided diagnostic system for diffuse liver diseases with ultrasonography by neural networks

The aim of the study is to establish a computer-aided diagnostic system for diffuse liver diseases such as chronic active hepatitis (CAH) and liver cirrhosis (LC). The authors introduced an artificial neural network in the classification of these diseases. In this system the neural network was trained by feature parameters extracted from B-mode ultrasonic images of normal liver (NL), CAH and LC. For input data the authors used six parameters calculated by a region of interest (ROI) and a parameter calculated by five ROIs in each image. They were variance of pixel values, coefficient of variation, annular Fourier power spectrum, longitudinal Fourier power spectrum which were calculated for the ROI, and variation of the means of the five ROIs. In addition, the authors used two more parameters calculated from a co-occurrence matrix of pixel values in the ROI. The results showed that the neural network classifier was 83.8% in sensitivity for LC, 90.0% in sensitivity for CAH and 93.6% in specificity, and the system was considered to be helpful for clinical and educational use.

[1]  Joie Pierce Jones,et al.  Ultrasonic tissue characterization: A Review , 1986 .

[2]  U Ranft,et al.  Random field models in the textural analysis of ultrasonic images of the liver , 1996, IEEE Trans. Medical Imaging.

[3]  K. Dewbury,et al.  Ultrasound in the detection of chronic liver disease (the "bright liver"). , 1979, The British journal of radiology.

[4]  R. L. Romijn,et al.  Ultrasound attenuation and texture analysis of diffuse liver disease: methods and preliminary results. , 1991, Physics in medicine and biology.

[5]  Yung-Chang Chen,et al.  Texture features for classification of ultrasonic liver images , 1992, IEEE Trans. Medical Imaging.

[6]  Berkman Sahiner,et al.  Classification of mass and normal breast tissue: a convolution neural network classifier with spatial domain and texture images , 1996, IEEE Trans. Medical Imaging.

[7]  R. F. Wagner,et al.  Quantitative ultrasonic detection and classification of diffuse liver disease. Comparison with human observer performance. , 1989, Investigative radiology.

[8]  T. Hall,et al.  Characterising the microstructure of random media using ultrasound. , 1990, Physics in medicine and biology.

[9]  W. J. Lorenz,et al.  Diagnostic accuracy of computerized B‐scan texture analysis and conventional ultrasonography in diffuse parenchymal and malignant liver disease , 1985, Journal of clinical ultrasound : JCU.

[10]  Jacek M. Zurada,et al.  Classification algorithms for quantitative tissue characterization of diffuse liver disease from ultrasound images , 1996, IEEE Trans. Medical Imaging.

[11]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[12]  David M. Skapura,et al.  Neural networks - algorithms, applications, and programming techniques , 1991, Computation and neural systems series.

[13]  Athina P. Petropulu,et al.  On modeling the tissue response from ultrasonic B-scan images , 1996, IEEE Trans. Medical Imaging.

[14]  A Lorenz,et al.  Echographic Tissue Characterization in Diffuse Parenchymal Liver Disease: Correlation of Image Structure with Histology , 1990, Ultrasonic imaging.