An improved SIFT algorithm based method for detecting of tumor tissue movement in respiratory motion

Background This paper intends to make use of the excellent performance of the SIFT algorithm to accurately calculate the displacement of tumor tissues during respiratory movement.

and method First, we moved phantoms to up,down,right,left respectively to simulate the different directions of movement during respiratory. And rotated phantom to left and right respectively by the angle of 5,10,30,45. Then, used SIFT and cross-correlation algorithms to search the phantoms. Last, use the t-test to check the differences between different directions. Resul The t-test result proved that there was no significant difference in the detection of moving phantom in all directions. There was no statistical difference between the SIFT of the moving motif and the cross-correlation. The detection results of rotating phantom indicated that the SIFT test results could be used to detect distortion.

SIFT algorithm can be used to calculate the distortion caused by the thoracic tissue during respiratory movement. Competing Interest Statement The authors have declared no competing interest. Footnotes phone: +8613643299250, E-mail: panqingya2012{at}126.com phone:+8615131397959, E-mail: lsjradiation2025{at}126.com phone: +8613785954998, E-mail: 378749431{at}126.com phone: +8613785970872, E-mail: 378749431{at}126.com phone: +8618832955120, E-mail: 59959132{at}qq.com phone: +8613831988991, E-mail: docfan888{at}126.com