Abstract
For active-contour-based surgery systems, the success of skin cancer boundary segmentation depends on the initialization point of the snake model, which is a task originally performed by skillful experts, and on the parameters set for the algorithms of active contour. This paper proposes initial geometrical templates and parameter sets for the active contour on skin cancer boundary segmentation. To establish initial geometrical templates and parameter sets for the active contour, first, template candidates, which are geometrically designed by users in advance, are simply calculated based on similarity with a skin cancer boundary, and the candidate with the least difference is selected as an initial template. Initially, all candidate templates are performed before the test with some selected skin cancer samples by randomly varying needed parameters to determine parameter sets for each template. The parameter set is therefore implicitly selected as the suitable set with the selected initial template. Experiments with 227 skin cancer samples were performed based on our proposed initial templates and parameter sets, and the results show 99.46% accuracy, 97.43% sensitivity, and 99.87% specificity approximately in which accuracy, sensitivity, and specificity were improved by 0.26%, 0.36%, and 0.26%, respectively, compared with the conventional method.
Highlights
According to a WHO’s (World Health Organization) report in 2016 [1], cancer is the worst death cause for humans
In case that the segmentation is not properly performed, the skin cancer is not completely removed due to reduced segmentation, and the cancer may subsequently spread throughout the entire body. us, some neighboring normal flesh is removed with the skin cancer as buffer because the medical doctor intends to ensure that all cancer is removed. erefore, if automatic segmentation efficiently functions, it ensures that all of the skin cancer is removed, Journal of Healthcare Engineering and the pain caused by removing some neighboring flesh needlessly is simultaneously eased
Initial template candidates including circle, ellipse, and rectangle, which were automatically selected by our proposed method in terms of similarity with the skin cancer images, were used as candidate templates of initialization, and results of template selection and mapping are shown in the 3rd column of Table 2
Summary
According to a WHO’s (World Health Organization) report in 2016 [1], cancer is the worst death cause for humans. Is was the critical point for the automatic surgery system that medically requires segmenting skin cancer boundaries accurately since the bad segmentation cases were seriously regarded as negative results for the surgery. The complexity of automatic initialization remained as a problem in these mentioned methods for system implementation and to set parameters (weighting factors, iteration steps, etc.) for active contours depending on human skill [15] and it was not clearly reproducible. Initialization whose shape is similar to the skin cancer is the most preference for active contour segmentation, and an appropriate geometric shape is regarded as another choice used as a basic concept in this paper. Erefore, the least difference between geometric initialization and skin cancer image is concluded as the condition for initialization determination in this paper
Sign-in/Register to view highlights & summary 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.
