Study on Integrated Setup System with Computer Vision for Breast Cancer Radiotherapy

Abstract:

Purpose: To discuss a setup verification method based on computer stereo vision for the repeat setup in breast cancer fractional irradiation. Methods and Materials: A photogrammetric system is composed of two cameras and one computer. First, multiple characteristic markers’ coordinates are gotten by the two cameras, then the three-dimensional coordinates of the markers are calculated according to the basic principle of binocular calculated, which can construct breast and chest surface stereo features shape, thus the setup error can judge and correct before radiation therapy. At the tracking process, we use SITF (Scale Invariant Feature Transform) as the registration algorithm, which has strong robustness and accurate matching performance, meanwhile, dynamic choice matching image and local searching strategy are used in the process of calculation and mergence in order to make the target image matching more precisely. Results: Experimental results show that in breast cancer fractional irradiation, the system can accurately display setup error and can achieve real-time calculation. Conclusion: The proposed method can reduce setup error in breast cancer fractional irradiation, and has good stability and high precision.

• Periodical: Advanced Materials Research (Volumes 328-330)
• Pages: 2333-2336
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.328-330.2333
• Online since: September 2011
• Authors: Lei Tong, Chao Hua Zhu, Zhi Qiang He
• Keywords: Breast Cancer Radiotherapy Setup, Computer Stereo Vision, Fractionation Radiotherapy Surface Imaging

References

[1] Karger C P, J¨ akel O, Debus J, et al. Three-dimensional accuracy and interfractional reproducibility of patient fixation and positioning using a stereotactic head mask system [J]. Radiat Oncol Biol Phys, 2001, 49: 1493–1504.

DOI: 10.1016/s0360-3016(00)01562-5

[2] Berbeco R , Jiang SB , Sharp GC , et al. Integrated radiotherapy imaging system (IRIS): design considerations of tumour tracking with linac gantry-mounted diagnostic x-ray systems with flat-panel detectors [J] . Physics in Medicine and Biology. 2004; 49: 243-255.

DOI: 10.1088/0031-9155/49/2/005

[3] Smitsmans MHP, de Bois J, Sonke JJ, et al. Automatic prostate localization on cone-beam CT scans for high precision image-guided radiotherapy [J]. International Journal of Radiation Oncology* Biology* Physics. 2005; 63(4): 975-984.

DOI: 10.1016/j.ijrobp.2005.07.973

[4] Endo M, Mori S , K andatsu S , et al . Development of Real 4D CT with real-time reconstruction and display [A] . In : IEEE Nuclear Science Symposium C on ference Record [ C] . San Diego, USA: IEEE Publication Int , 2005. 2603 - 2606.

DOI: 10.1109/nssmic.2005.1596871

[5] Yilmaz A, Javed O, Shah M. Object tracking: A survey[J]. Acm Computing Surveys. 2006; 38(4): 31-35.

DOI: 10.1145/1177352.1177355

[6] Peng K, Chen X, Zhou D, et al. 3D reconstruction based on SIFT and Harris feature points[J]. 2010. IEEE; : 960-964.