Image Processing Algorithm for Virtual Chromoendoscopy (Tone Enhancement) in Clinical Decision Support System

Abstract

Virtual chromoendoscopy is one of the demanded modern direction for increasing the diagnostic value of medical images. The most famous technics are I-SCAN and FICE, and image-processing algorithms that can leverage the unique characteristics of different spectral response in the endoscopic image are actual and relevant, such as TRI-SCAN. The new method of virtual chromoendoscopy based on digital processing of images obtained in the white light was proposed. The main feature of method is local nonlinear processing each color plane. Proposed method was tested on open database of endoscopic images KVASIR. Experiment shows that method can effectively improve color contrast. Proposed method realizes visual effect corresponding visual effect of images obtaining with modern technologies of virtual chromoendoscopy (I-SCAN and FICE) and give possibility to get visual effect superior than modern method of tone enhancement TRI-SCAN.

Keywords

• virtual chromoendoscopy
• color contrast
• local nonlinear processing
• digital image processing