Main Article Content
Bile Ducts Cancer (Cholangiocarcinoma: CCA) is a serious public health problem. The surgical resection is one of the curative treatments for CCA. The surgical resection in the early stage of the CCA gives a good chance for recovery; therefore, early detection in the surgical resection stage is of a critical importance. Periductal fibrosis (PDF) in the bile duct is one factor which is considered about CCA in Thailand. It can be detected using the liver ultrasound images; however, the liver ultrasound images contain speckle noise which decreases PDF detection performance. This paper proposes a new method for enhancement of bile duct ultrasound image (EBDU). The main idea of the EBDU method is to reduce the speckle noise and enhance clear structures of the liver ultrasound images. The proposed method consists of three processes which are the speckle reduction, edge preservation, and intraregion smoothing. The speckle reduction is performed in frequency domain to filter out the high frequency and low frequency noise out of the ultrasound image by using the bandpass filter. The criterion of the bandpass filter is the size of the structures in the ultrasound image, which could be large structures (mirrored edges) and small structures (smoothing). Edge preservation is then performed by applying the statistics filter to distinctly increase the boundary structure; it sorts out all pixel values from the surrounding neighborhood into a numerical order. Finally, intraregions of the liver ultrasound images are smoothed by intra-region smoothing process which can diffuse the homogeneous region. The enhanced liver ultrasound images were tested by computer-aided detection on PDF regions (CADPDF). Variety of liver ultrasound images were used. To evaluate and compare the performance of the proposed method, four measurements are applied which are the scan line pixel (SLP), the Slope-Smooth Speckle Index (SLSI), Equivalent number of looks (ENL), Speckle suppression index (SSI), and the accuracy achieved through the PDF regions segmentation. The experimental results show that the proposed method is able to give higher success rate of enhancing liver ultrasound images compared to other methods. Moreover, the accuracy of CADPDF system was evaluated. The proposed EBDU method and other methods are applied in CADPDF system. The experimental results show that the proposed EBDU method achieved better performance than other methods, giving an accuracy of 80.36%.