TU-H-207A-02: Relative Importance of the Various Factors Influencing the Accuracy of Monte Carlo Simulated CT Dose Index

Authors


Abstract

Purpose:

Monte Carlo simulation is a frequently used technique for assessing patient dose in CT. The accuracy of a Monte Carlo program is often validated using the standard CT dose index (CTDI) phantoms by comparing simulated and measured CTDI100. To achieve good agreement, many input parameters in the simulation (e.g., energy spectrum and effective beam width) need to be determined. However, not all the parameters have equal importance. Our aim was to assess the relative importance of the various factors that influence the accuracy of simulated CTDI100.

Methods:

A Monte Carlo program previously validated for a clinical CT system was used to simulate CTDI100. For the standard CTDI phantoms (32 and 16 cm in diameter), CTDI100 values from central and four peripheral locations at 70 and 120 kVp were first simulated using a set of reference input parameter values (treated as the truth). To emulate the situation in which the input parameter values used by the researcher may deviate from the truth, additional simulations were performed in which intentional errors were introduced into the input parameters, the effects of which on simulated CTDI100 were analyzed.

Results:

At 38.4-mm collimation, errors in effective beam width up to 5.0 mm showed negligible effects on simulated CTDI100 (<1.0%). Likewise, errors in acrylic density of up to 0.01 g/cm3 resulted in small CTDI100 errors (<2.5%). In contrast, errors in spectral HVL produced more significant effects: slight deviations (±0.2 mm Al) produced errors up to 4.4%, whereas more extreme deviations (±1.4 mm Al) produced errors as high as 25.9%. Lastly, ignoring the CT table introduced errors up to 13.9%.

Conclusion:

Monte Carlo simulated CTDI100 is insensitive to errors in effective beam width and acrylic density. However, they are sensitive to errors in spectral HVL. To obtain accurate results, the CT table should not be ignored.

This work was supported by a Faculty Research and Development Award from Cleveland State University.

Ancillary