ANATOMIC REGION-BASED DYNAMIC-RANGE COMPRESSION FOR CHEST RADIOGRAPHSUSING WARPING TRANSFORMATION OF CORRELATED DISTRIBUTION

The purpose of this paper is to investigate the effectiveness of our n ovel dynamic range compression (DRC) for chest radiographs. The purpos e of DRC is to compress the gray scale range of the image when using n arrow dynamic range viewing systems such as monitors. First, an automa ted segmentation method was used to detect the lung region. The combin ed region of mediastinum, heart, and subdiaphragm was defined based on the lung region. The correlated distributions, between a pixel value and its neighboring averaged pixel value, for the lung region and the combined region were calculated. According to the appearance of overla pping of two distributions, the warping function was decided, After pi xel values were warped, the pixel value range of the lung region was c ompressed while preserving the detail information, because the warping function compressed the range of the averaged pixel values while pres erving the pixel value range for the pixels which had had the same ave raged pixel value. The performance was evaluated with our criterion fu nction which was the contrast divided by the moment, where the contras t and the moment represent the sum of the differences between the pixe l values and the averaged values of eight pixels surrounding that pixe l, and the sum of the differences between the pixel values and the ave raged value of all pixels in the region-of-interest, respectively. For 71 screening chest images from Johns Hopkins University Hospital (Bal timore, MD), this method improved our criterion function at 11.7% on a verage, The warping transformation algorithm based on the correlated d istribution was effective in compressing the dynamic range while simul taneously preserving the detail information.