Automated characterization of fatty liver disease and cirrhosis using curvelet transform and entropy features extracted from ultrasound images. (1st December 2016)

• Record Type: Journal Article
• Authors: Acharya, U. Rajendra; Raghavendra, U.; Fujita, Hamido; Hagiwara, Yuki; Koh, Joel EW; Jen Hong, Tan; Sudarshan, Vidya K.; Vijayananthan, Anushya; Yeong, Chai Hong; Gudigar, Anjan; Ng, Kwan Hoong
• Is Part Of: Computers in biology and medicine. Volume 79(2016)
• Page Start: 250
• Page End: 258
• Publication Date: 2016-12-01
• Subjects: Cirrhosis -- Curvelet transform -- Fatty liver disease -- Probabilistic neural network -- Locality sensitive discriminant analysis -- Ultrasound; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2016.10.022
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: Fatty liver disease (FLD) is reversible disease and can be treated, if it is identified at an early stage. However, if diagnosed at the later stage, it can progress to an advanced liver disease such as cirrhosis which may ultimately lead to death. Therefore, it is essential to detect it at an early stage before the disease progresses to an irreversible stage. Several non-invasive computer-aided techniques are proposed to assist in the early detection of FLD and cirrhosis using ultrasound images. In this work, we are proposing an algorithm to discriminate automatically the normal, FLD and cirrhosis ultrasound images using curvelet transform (CT) method. Higher order spectra (HOS) bispectrum, HOS phase, fuzzy, Kapoor, max, Renyi, Shannon, Vajda and Yager entropies are extracted from CT coefficients. These extracted features are subjected to locality sensitive discriminant analysis (LSDA) feature reduction method. Then these LSDA coefficients ranked based on F-value are fed to different classifiers to choose the best performing classifier using minimum number of features. Our proposed technique can characterize normal, FLD and cirrhosis using probabilistic neural network (PNN) classifier with an accuracy of 97.33%, specificity of 100.00% and sensitivity of 96.00% using only six features. In addition, these chosen features are used to develop a liver disease index (LDI) to differentiate the normal, FLD and cirrhosis classes using a single number. This can significantly help the radiologists to discriminate FLD and cirrhosis in their routine liver screening. Highlights: Automated identification of normal, FLD and cirrhosis using ultrasound images. Curvelet Transform-based nonlinear features are extracted. Achieved classification accuracy of 97.33% using PNN classifier. Liver disease index is proposed to discriminate three classes.