A Method for Enhancing the Contrast of Medical Video Images with Adaptive Correction Depth for Clinical Decision Support Systems

Abstract

Introduction. When conducting diagnostic examination of patients, various technological means are used to identify pathological conditions timely and accurately. The rapid development of sensors and imaging devices, as well as the advancement of modern diagnostic methods, facilitate the transition from the visual examination of images performed by a medical specialist towards the widespread use of automated diagnostic systems referred to as clinical decision support systems.Aim. To develop a method for enhancing the contrast of endoscopic images taking into account their features with the purpose of increasing the efficiency of medical diagnostic systems.Materials and methods. Contrast enhancement inevitably leads to an increase in the noise level. Despite the large number of different methods for noise reduction, their use at the preliminary stage of correction leads to the loss of small but important details. The development of a method for enhancing the contrast of endoscopic images was based on a nonlinear transformation of the intensity of pixels, taking into account their local neighborhood. Regression analysis was used to obtain a functional dependence between the depth of contrast correction and the degree of detail of the processed pixel neighborhood.Results. The results of experimental evaluation and comparison with conventional methods show that, under a comparable level of contrast enhancement, the proposed method provides a greater value of the structural similarity index towards to the original image (0.71 versus 0.63), with the noise level reduced by 17 %.Conclusion. In comparison with conventional methods, the developed method provides a simultaneous contrast correction of both light and dark image fragments and limits the growth of the noise level (typical of similar methods) by adapting the correction depth to the neighborhood features of the processed image element.