AUTOMATIC BACKGROUND RECOGNITION AND REMOVAL (ABRR) IN COMPUTED RADIOGRAPHY IMAGES

A novel method to automatically recognize and remove background signal s in computed radiography (CR) images caused by X-ray collimation duri ng projection radiographic examinations is presented, There are three major steps in this method, In the first step, a statistical curve is derived based on many hierarchical CR sample images as a first approxi mation to loosely separate image and background pixels, Second, signal processing methods, including specific sampling, filtering, and angle recognition, are used to determine edges between image and background pixels, Third, adaptive parameter adjustments and consistent and reli able estimation rules are used to finalize the location of edges and r emove the background, In addition, this step also evaluates the reliab ility of the complete background removal operation, With this novel me thod implemented in a clinical picture archiving and communication sys tem (PACS) at the University of California at San Francisco, we achiev ed 99% correct recognition of CR image background, and 91% full backgr ound removal without removing any valid image information.