A comparison study between single- and dual-energy CT density extraction methods for neurological proton monte carlo treatment planning

B. van der Heyden, I. P. Almeida, G. Vilches-Freixas, C. Van Beveren, A. Vaniqui, C. Ares, K. Terhaag, G. P. Fonseca, D. B. P. Eekers, F. Verhaegen*

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review


Monte Carlo proton dose calculations requires mass densities calculated from the patient CT image. This work investigates the impact of different single-energy CT (SECT) and dual-energy CT (DECT) to density conversion methods in proton dose distributions for brain tumours. Material and methods: Head CT scans for four patients were acquired in SECT and DECT acquisition modes. Commercial software was used to reconstruct DirectDensity((TM)) images in Relative Electron Densities (RED, ) and to obtain DECT-based pseudo-monoenergetic images (PMI). PMI and SECT images were converted to RED using piecewise linear interpolations calibrated on a head-sized phantom, these fits were referred to as "PMI2RED" and "CT2RED". Two DECT-based calibration methods ("Hunemohr-15it" and "Saito-15it") were also investigated. images were converted to mass-densities () to investigate differences and one representative patient case was used to make a proton treatment plan. Using CT2RED as reference method, dose distribution differences in the target and in five organs-at-risk (OARs) were quantified. Results: In the phantom study, Saito-15it and Hunemohr-15it produced the lowest root-mean-square error (0.7%) and DirectDensity((TM)) the highest error (2.7%). The proton plan evaluated in the Saito-15it and Hunemohr-15it datasets showed the largest relative differences compared to initial CT2RED plan down to -6% of the prescribed dose. Compared to CT2RED, average range differences were calculated: -0.1 +/- 0.3 mm for PMI2RED; -0.8 +/- 0.4 mm for Hunemohr-15it, and -1.2 +/- 0.4 mm for Saito-15it. Conclusion: Given the wide choice of available conversion methods, studies investigating the density accuracy for proton dose calculations are necessary. However, there is still a gap between performing accuracy studies in reference phantoms and applying these methods in human CT images. For this treatment case, the PMI2RED method was equivalent to the conventional CT2RED method in terms of dose distribution, CTV coverage and OAR sparing, whereas Hunemohr-15it and Saito-15it presented the largest differences.

Original languageEnglish
Pages (from-to)171-179
Number of pages9
JournalActa Oncologica
Issue number2
Early online date23 Oct 2019
Publication statusPublished - 1 Feb 2020


  • MED. PHYS. 44(1)
  • HEAD

Cite this