Automatic ROI Segmentation in B-mode Ultrasound Image for Liver Fibrosis Classification

Chronic hepatitis is one of the most important health threats worldwide. Although ultrasound is commonly used to diagnosis of various liver diseases, the accuracy of visual diagnosis is very low, and it also strongly depends on the experience of radiologist. The identification and classification of ultrasound images have become very desirable due to the rapid development of computer technology. However, human interaction in the developed method is still inevitable. In this paper, we propose an effective technique to solve this problem. The Otsu's method is first applied to remove the large structure such as vessels, gallbladder and extra-hepatic region, and then the primary region will be obtained. Finally, we extract the secondary ROIs from primary ROI accordingly. Simulation results show that the promising results can be achieved.