Devising a methodology for X-ray image contrast enhancement by combining CLAHE and gamma correction

Abstract

Increasing image contrast is very important for the visual analysis of X-ray images. To improve the contrast of medical images, various contrast enhancement methods are used, such as histogram equalization and histogram modifications, gamma correction, etc. The paper explores adaptive methods for enhancing the contrast of digital X-ray images. Research was carried out on 1000 images from the open Kaggle database. Combinations of sequential application of several methods for enhancing image contrast were evaluated. Experiments using gamma image correction allowed us to select ranges of input and output parameters of the brightness conversion function. To obtain a better result, before performing gamma correction, it is proposed to use the method of equalizing the histogram of an X-ray image. Possibilities of adaptive image histogram equalization are explored. The performed experiments allow us to propose an improved version of increasing the contrast of X-ray images. Combining the adaptive histogram equalization algorithm with contrast clipping has a visually noticeable effect of improving the contrast of X-ray images. Contrast improvement is supported by objective NIQE and BRISQUE quantifications that do not require reference images. A feature of this work is the use of objective non-reference assessments to determine the quality of images. The performed experiments indicate that the NIQE score correlates better with the visual assessment of image contrast changes. As a result of the experiments, recommendations were proposed for choosing the parameters of the gamma correction and adaptive histogram equalization methods, which make it possible to enhance the contrast without the intensification of noise in the image