The Robustness of Various Intelligent Models in Patient Positioning at External Beam Radiotherapy

  • Payam Samadi-Miyandoab Department of Electrical and Computer Engineering, Medical Radiation Group, Graduate University of Advanced Technology, Kerman, Iran.
  • Ahmad Esmaili Torshabi Mail Department of Electrical and Computer Engineering, Medical Radiation Group, Graduate University of Advanced Technology, Kerman, Iran AND Medical Radiation Group, Department of Electrical and Computer Engineering, Graduate University of Advanced Technology, Kerman, Iran.
  • Saber Nankali Department of Electrical and Computer Engineering, Medical Radiation Group, Graduate University of Advanced Technology, Kerman, Iran.
  • Mohamadreza Rezai Department of Electrical and Computer Engineering, Medical Radiation Group, Graduate University of Advanced Technology, Kerman, Iran.
Keywords:
Patient setup, Artificial neural network, Adaptive neuro fuzzy interference System, Canonical correlation analysis, Principle component analysis, External radiotherapy.

Abstract

Purpose: Patient setup optimization has been required to fill the gap between individual treatment and uncertainty in the external beam radiotherapy at each of the treatment sessions. This uncertainty error consists of patient body misalignments and patient body displacement between different fractions.
Methods: In this study, the patient geometrical set-up has been simulated comprehensively by 4D XCAT anthropomorphic phantom where the XCAT phantom was used to access 4D modeling of dynamic organs motion. All of the possible roto-translation displacement parameters that were effective on instigate patient position before re-alignment were considered. While the data set was assembled from XCAT phantom including 2D translation and 2D rotation, the parallelisms of the dada set between position of the external markers and reference point (patient couch) were considered. Moreover, the experimental validation models for further investigation were considered. For this aim, the captured data from XCAT phantom was extended to four real patients. In some clinically available strategies, the corrective models have been implemented to estimate patient displacement of patient setup. In this study, four intelligent models were proposed for set-up, realignment, and continuous tracking of the patient positioning.
Results: Final results illustrate that Adaptive Neuro Fuzzy Interference System with all markers can estimate the true patient position with less error.
Conclusion: In this study, the four intelligent models were demonstrated to investigate the robustness of various intelligent models in re-alignment and patient set-up at external beam radiotherapy. Finally, our correlation model “ANFIS” can estimate the true patient position with less error.

Published
2015-03-30
How to Cite
1.
Samadi-Miyandoab P, Torshabi AE, Nankali S, Rezai M. The Robustness of Various Intelligent Models in Patient Positioning at External Beam Radiotherapy. Frontiers Biomed Technol. 2(1):45-54.
Section
Original Article(s)