The purpose of this study is to replace the manual process (selecting the landmarks on mesh and anchor points on the video) by Intensity-based Automatic Registration method to reach registration accuracy and low processing time. The proposed system consists of an Enhanced Intensity-based Automatic Registration (EIbAR) using Modified Zero Normalized Cross Correlation (MZNCC) algorithm. The proposed system was implemented on videos of breast cancer tumors. Results showed that the proposed algorithm—as compared to a reference—improved registration accuracy by an average of 2 mm. In addition, the proposed algorithm—as compared to a reference—reduced the number of pixel matching, thereby reducing processing time on the video by an average of 22 ms/frame. The proposed system can, thus, provide an acceptable accuracy and processing time during scene augmentation of videos, which provides a seamless use of augmented-reality for surgeons in visualizing cancer tumors.
|Number of pages||15|
|Journal||International Journal of Medical Robotics and Computer Assisted Surgery|
|Early online date||01 Nov 2019|
|Publication status||Published - Apr 2020|