Parameter Estimation for Automatic Dose Control in Radioscopy

During a medical radioscopic examination, the X-ray dose needs to be adjusted continuously to the body region examined. In current systems, this adjustment is based on the mean grayvalue of the central part of the current image. Basing the control of the X-ray dose on this parameter alone leads to incorrect exposure, if direct radiation enters the central part of the image. We present the application of different regression methods to estimate this parameter more robustly, based on approaches from object classification. Robustness of the estimation is especially important in order to achieve high image quality during the dynamic examination.