Adaptative Histogram Equalization for Contrast and Illumination Enhancement of Diffuse Opacities in Digital Radiographic Chest Images Associated with COVID 19

COVID 19 produces diffuse opacity patterns in the pulmonary airspace, which are difficult to detect with the naked eye on digital radiographic images if the chest is moved during the scan, radiation scattering occurs, compromising image quality by introducing a low frequency background signal that induce noise. The result is an image whit contrast problems and poor detail visibility (Carroll, in Radiography in the digital age: Physics, exposure, radiation biology, 2018; Siracusano et al., in Pipeline for advanced contrast enhancement (PACE) of chest X-Ray in evaluating COVID-19 patients by combining bidimensional empirical mode decomposition and contrast limited histogram equialization (CLAHE). Sustainaibity J 12:2–17, 2020). The solve this problem, placing a patient an anti-scatter grid made of lead strips and strips of radiolucent material is placed on the patient; however, the use of this technology requires a higher dose of radiation exposure because the X-ray beam is attenuated by the lead strips (Koonsanit et al., in Image enhacement of digital X-Ray images using N_CLAHE, 2017). To reduce the use gratings, recent research is proposing to embed advanced post-processing algorithms in X-ray equipment to help correct contrast and improve the visibility of details, (Maryann and Hugh, in Artificial intelligence in diagnostic imaging: impact on the radiography profession. Dig Br J Radiol 93, 2020; Valdés et al., in Mejora de contraste en imagenes de rayos X: un método basado en wavelets logaritmicas y morfología matemática, Universidad de la Habana, Habana, Cuba, pp 123–135, 2021). This paper discusses the CLAHE and RMSHE algorithms, which use adaptive histogram equalization to manipulate the spatial and contrast resolution in COVID19 digital radiography and improve the visibility of details. To evaluate their feasibility to solve contrast and visibility problems, they are applied to a bank of X-ray images containing diffuse opacity related to COVID19, and the entropy metric is used to evaluate their performance. To assess the feasibility of these algorithms, a database of 20 x-rays with diffuse opacity related to COVID19 was analysed, and the entropy measure was applied to evaluate the performance of these algorithms to resolve contrast and illumination enhancement issues. The results show that the adaptive equalization algorithm, CLAHE, achieves a better spatial distribution of the pixels forming a Gaussian bell-shaped contrast correction and a better visibility of the details of the diffuse opacities associated with COVID 19 in the processed X-ray images.