Computer aided diagnostic system for ultrasound liver images: A systematic review

Abstract

In this article an in-depth overview is presented on Computer aided diagnostic (CAD) system's usage for liver cancer. Besides, in a broader sense highlighting the technical aspects developed for medical ultrasound images is also discussed. CAD system is a process that provides adequate information that helps to analyze the Ultrasound images and helps to accurately detecting different types of liver cancer. However, the system performance is still not significantly improved. In this paper, firstly, we categorize the CAD system according to the four primary stages including data preprocessing, lesion segmentation, feature extraction, selection, and Classifier. In each stage, we review specific methods that are commonly used in most of the algorithms proposed for computerized tissue characterization and discuss their advantages and drawbacks. Then, recent proposed algorithms are presented in summarize form that have shown clinical value or specific possibility to the computerized analysis of setback for ultrasound liver images. These techniques or their combinations are the ones that are mostly used in the past few decades by the majority of work published in the Computer aided diagnosis domain. (C) 2017 Elsevier GmbH. All rights reserved.