Enhancing the Quality of Low Contrast CT Images Using TBCSSR Algorithm

In the digital imaging field, contrast enhancement is an important factor that enables an image to be clearly recognized by allowing a proper distinction of its details through a suitable contrast improvement to provide a better visual representation for the low-contrast images. The process of contrast enhancement is very similar to removing a layer of fog from such degraded images. In computed tomography (CT), acquired images are usually low-contrast in which such degradation would severely corrupt the visual quality of the images making them difficult to interpret in clinical routines by reducing the lucidity of the image details and hindering the procedure for extracting valuable information. A new algorithm for contrast enhancement is introduced in this study, which is suitable for low contrast CT images. The novelties of the proposed algorithm consist of tuning the standard single-scale Retinex, adding a normalized-ameliorated Sigmoid function and adapting some parameters to improve its enhancement ability.In order to compare the clarity of the processed images against their original observations, the human vision is often used to assess the amount of contrast improvement.