Abstract
Combination of digital X-ray with image processing techniques has the potential to extract useful information for healthcare professionals (physicians). From all the information that can be extracted from X-ray images, information concerning the human cervical vertebrae is relevant for the medical area. Therefore, in this work we present a simple enhanced region of interest (ROI) selection tool to select automatically the region that contains most of the information concerning to cervical vertebrae. The ROI-selection method reduces the size of a lateral or frontal digital X-ray by 30–60% without losing significance in the resulting image. This is achieved by an adjustment of dimensions in the image while the cervical area is preserved. Moreover, the visual quality is improved by performing a contrast enhancement in the region of interest.•Automatic threshold selection is computationally more efficient than traditional image segmentation techniques.•Reduce size in comparison with original image (enhancing ROI).•Independence of depth gray scale space.
Highlights
The following pseudocode describes the required steps to find out the right and left limits from the image, a matrix scan is performed over the binary image in order to determine the narrowest useful area in the region of interest (ROI) image
The original complement image (Fig. 1d) is resized according to the boundaries obtained from results of the previous stage in what is described as ROI
Taking into account the results obtained, the method adequately reduces the size of the image while preserving the area of the cervical vertebrae of lateral or frontal digital X-ray images
Summary
The algorithm performs a scan all over the image matrix in order to identify the coordinates of the object-background boundary. The output of the process is an image section which size-to-useful information ratio is improved regarding the original image. Due to the reduction of the gray-level dynamic range in the output image, it is performed a contrast enhancement based on histogram equalization, in order to use all the available range.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
