Publication Type:

Journal Article


IET Image Processing, Institution of Engineering and Technology, Volume 11, Number 7, p.530-538 (2017)



Active contour segmentation, Biorthogonal wavelet transforms, Classification accuracy, Co-occurrence-matrix, Computer-based approach, Decision trees, extraction, Feature extraction, image classification, Image compression, Image processing, Image segmentation, Image texture, Intensity histograms, Segmented regions, Texture feature extraction, Ultrasonic applications, Wavelet transforms


This study presents a computer-based approach to classify ten different kinds of focal and diffused liver disorders using ultrasound images. The diseased portion is isolated from the ultrasound image by applying active contour segmentation technique. The segmented region is further decomposed into horizontal, vertical and diagonal component images by applying biorthogonal wavelet transform. From the above wavelet filtered component images, grey level run-length matrix features are extracted and classified using random forests by applying ten-fold cross-validation strategy. The results are compared with spatial feature extraction techniques such as intensity histogram, invariant moment features and spatial texture features such as grey-level co-occurrence matrices, grey-level run length matrices and fractal texture features. The proposed technique, which is an application of texture feature extraction on transform domain images, gives an overall classification accuracy of 91% for a combination of ten classes of similar looking diseases which is appreciable than the spatial domain only techniques for liver disease classification from ultrasound images. © The Institution of Engineering and Technology.


cited By 0

Cite this Research Publication

K. Raghesh Krishnan and Radhakrishnan, S., “Hybrid approach to classification of focal and diffused liver disorders using ultrasound images with wavelets and texture features”, IET Image Processing, vol. 11, pp. 530-538, 2017.