Document Type : Original Paper
Department of Electrical and Computer Engineering, Medical Radiation Group, Graduate University of Advanced Technology, Haft Bagh Highway, Knowledge Paradise, Kerman, Iran.
Medical Radiation Division, Dept. of Electrical and Computer Eng. Graduate University of Advanced Technology, Kerman, Iran
Introduction: A new method based on image registration technique and an intelligent correlation model to calculate. The present study aimed to propose inter- and intra-fraction motion errors in order to address the limitations of conventional Patient positioning methods.
Material and Methods: The configuration of the markerless method was accomplished by using four-dimensional computed tomography (4DCT) datasets. Firstly, the MeVisLab software package was used to extract a three-dimensional (3D) surface model of the patient and determine the tumor location. Then, the patient-specific 3D surface model which also included the breathing phases was imported into the MATLAB software package in order to define several control points on the thorax region as virtual external markers. Finally, based on the correlation of breathing signals/patient position with breathing signals/tumor coordinate, an adaptive neuro fuzzy inference system was proposed to both verify and align the inter- and intra-fraction motion errors in radiotherapy, if needed. In order to validate the proposed method, the 4DCT data acquired from four real patients was considered.
Results: Final results revealed that our hybrid configuration method was capable of aligning patient setup with lower uncertainties, compared to other available methods. In addition, the 3D root-mean-square error has been reduced from 5.26 to 1.5 mm for all patients.
Conclusion: In this study, a markerless method based on the image registration technique in combination with a correlation model was proposed to address the limitations of the available methods, including dependence on operator’s attention, use of passive markers, and rigid-only constraint for patient setup.