Automated diagnosis of focal liver lesions using bidirectional empirical mode decomposition features. (1st March 2018)

• Record Type: Journal Article
• Authors: Acharya, U. Rajendra; Koh, Joel En Wei; Hagiwara, Yuki; Tan, Jen Hong; Gertych, Arkadiusz; Vijayananthan, Anushya; Yaakup, Nur Adura; Abdullah, Basri Johan Jeet; Bin Mohd Fabell, Mohd Kamil; Yeong, Chai Hong
• Is Part Of: Computers in biology and medicine. Volume 94(2018)
• Page Start: 11
• Page End: 18
• Publication Date: 2018-03-01
• Subjects: Computer-aided diagnostic system -- Liver lesions -- Benign -- Malignant -- Machine learning -- Ultrasonography; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2017.12.024
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: Liver is the heaviest internal organ of the human body and performs many vital functions. Prolonged cirrhosis and fatty liver disease may lead to the formation of benign or malignant lesions in this organ, and an early and reliable evaluation of these conditions can improve treatment outcomes. Ultrasound imaging is a safe, non-invasive, and cost-effective way of diagnosing liver lesions. However, this technique has limited performance in determining the nature of the lesions. This study initiates a computer-aided diagnosis (CAD) system to aid radiologists in an objective and more reliable interpretation of ultrasound images of liver lesions. In this work, we have employed radon transform and bi-directional empirical mode decomposition (BEMD) to extract features from the focal liver lesions. After which, the extracted features were subjected to particle swarm optimization (PSO) technique for the selection of a set of optimized features for classification. Our automated CAD system can differentiate normal, malignant, and benign liver lesions using machine learning algorithms. It was trained using 78 normal, 26 benign and 36 malignant focal lesions of the liver. The accuracy, sensitivity, and specificity of lesion classification were 92.95%, 90.80%, and 97.44%, respectively. The proposed CAD system is fully automatic as no segmentation of region-of-interest (ROI) is required. Graphical abstract: Highlights: Classification of normal, benign and malignant liver images. Bidirectional empirical mode decomposition performed. Particle swarm optimization is used for feature selection. Obtained accuracy of 92.95% using 29 features with PNN classifier.