A hybrid technique for enhancement of Periductal fibrosis ultrasound images for Cholangiocacinoma surveillance

Abstract

The Cholangiocarcinoma (CCA) is the most common in northeast Thailand that is second most common worldwide. The Periductal fibrosis (PDF) ultrasound images can be applied for the CCA surveillance system which increased patient in endemic area of Opisthorchis viverrini (OV). However, the ultrasound images are lack of contrast and a lot of speckle noise. This paper presented the enhanced algorithm of PDF ultrasound images (EPDF) for the CCA surveillance system in which consist of the Histogram equalization (HE), Speckle reduction method, and Anisotropic diffusion. Firstly, the HE method performed to improve the lack of contrast of the PDF ultrasound images. Then, the speckle reduction method performed to reduce the speckle noise and preserving the edge in the PDF ultrasound images. Finally, the Anisotropic diffusion performed to smooth region in the PDF ultrasound images. The data set in the experimental studies consist of 30 pictures. The performance of the EPDF algorithm from the experimental results gave the best for the CCA surveillance. A successful percentage of the EPDF system achieved at 80.36%. Thus, the EPDF system has the potential to increase the performance for enhancing the PDF in ultrasound images for CCA surveillance system.