An improved method for liver diseases detection by ultrasound image analysis

Abstract

Ultrasound imaging is a popular and noninvasive tool frequently used in the diagnoses of liver diseases. A system to characterize normal, fatty and heterogeneous liver, using textural analysis of liver Ultrasound images, is proposed in this paper. The proposed approach is able to select the optimum regions of interest of the liver images. These optimum regions of interests are analyzed by two level wavelet packet transform to extract some statistical features, namely, median, standard deviation, and interquartile range. Discrimination between heterogeneous, fatty and normal livers is performed in a hierarchical approach in the classification stage. This stage, first, classifies focal and diffused livers and then distinguishes between fatty and normal ones. Support vector machine and k-nearest neighbor classifiers have been used to classify the images into three groups, and their performance is compared. The Support vector machine classifier outperformed the compared classifier, attaining an overall accuracy of 97.9%, with a sensitivity of 100%, 100% and 95.1% for the heterogeneous, fatty and normal class, respectively. The Acc 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 and experts in liver diseases interpretation.

Machine Learning with Abstention for Automated Liver Disease Diagnosis

“…We compare the performance of our method to the one proposed by Owjimehr et al [14] because they have used the same dataset and evaluation protocol and offer state of the art accuracy. These results are shown in Table 1.…”

“…These results are shown in Table 1. It is important to note that the approach by Owjimehr et al [14] uses conventional classification techniques with a sophisticated feature extraction step. Table 2 shows the proposed LWA model gives better accuracy than the previous state of the art using normalized raw pixel values as features for normal vs. abnormal classification.…”

“…Minhas et al [13] proposed a wavelet transform based technique for completely automated classification of normal, heterogenous and fatty liver disorders with an accuracy of 95%. Owjimehr et al [14] improved upon this approach by using a hierarchical classifier with an accuracy of 97.9%. In this work, we have identified a major issue with all existing automated diagnosis methods in this domain.…”

A high performance algorithm to diagnosis of skin lesions deterioration in dermatoscopic images using new feature extraction

“…Another advantage of SVMs is that they provide a unified framework in which different learning machine architectures (e.g., RBF networks and feed forward neural networks) can be generated through an appropriate choice of kernel [2]. In recent years, SVM classifier is used in to classify the medical images, because of its advantages for example in [10] SVM is used for Bone age assessment (BAA) on hand images and in [11] SVM and k-nearest neighbor classifiers have been used to classify the ultrasound images, and their performance is compared. The SVM classifier outperformed the compared classifier.…”

Untitled

“…In case simple Steatosis leads to Steato Hepatitis, it increases the risk of cirrhosis or Hepato Cellular Carcinoma [6,7]. The prevalence of fatty liver in the general population of the Middle East is about 20 to 30% [8]. Knowing that fatty liver can be recovered in early stages, the early diagnosis is of particular importance [9].…”