An approach to edge detection in medical imaging through histogram analysis and morphological gradient

Edge detection takes importance in image processing systems for computer-aided diagnosis, where sharp changes in pixel intensity are analyzed to obtain fast and accurate information about regions of interest to the specialist. A method for feature enhancement and edge detection in medical images was developed using image processing by analyzing the pixel distribution histogram and morphological gradient operation. Images from the MINI MIAS dataset and the COVID-CT dataset were used. The method is based on image processing and is applied to mammography and chest CT images, where blur filtering steps are accompanied by morphological gradient filtering, in addition to obtaining the threshold for edge detection by analyzing the point of maximum pixel concentration according to the distribution histogram. The processing is presented in a graphical user interface developed in Python language. The method is validated by comparison with other edge detection techniques such as the Canny Algorithm, and with deep learning methods such as Holistically-Nested Edge Detection. The proposed method improves image quality in both mammograms and CT scans compared to other techniques. It also presents the best performance considering internal and external edge detection, as well as an average response time of 1.054 seconds and 2.63 % of Central Processing Unit requirement. The developed system is presented as a support tool for use in computer-aided diagnosis processes due to its high efficiency in edge detection.