Modeling log-compressed ultrasound images for radio frequency signal recovery.

This paper presents an algorithm for recovering the radio frequency (RF) signal provided by the ultrasound probe from the log-compressed ultrasound images displayed in ultrasound equipment. Commercial ecographs perform nonlinear image compression to reduce the dynamic range of the Ultrasound (US) signal in order to improve image visualization. Moreover, the clinician may adjust other parameters, such as brightness, gain and contrast, to improve image quality of a given anatomical detail. These operations significantly change the statistical distribution of the original RF raw signal, which is assumed, based on physical considerations on the signal formation process, to be Rayleigh distributed. Therefore, the image pixels are no longer Rayleigh distributed and the RF signal is not usually available in the common ultrasound equipment. For statistical data processing purposes, more important than having "good looking" images, it is important to have realistic models to describe the data. In this paper, a nonlinear compression parametric function is used to model the pre-processed image in order to recover the original RF image as well the contrast and brightness parameters. Tests using synthetic and real data and statistical measures such as the Kolmogorov-Smirnov and Kullback-Leibler divergences are used to assess the results. It is shown that the proposed estimation model clearly represents better the observed data than by taking the general assumption of the data being modeled by a Rayleigh distribution.