openPR — A computational tool for CT conversion assessment with proton radiography

Abstract

Purpose One of the main sources of uncertainty in proton therapy is the conversion of the Hounsfield Units of the planning CT to (relative) proton stopping powers. Proton radiography provides range error maps but these can be affected by other sources of errors as well as the CT conversion (e.g., residual misalignment). To better understand and quantify range uncertainty, it is desirable to measure the individual contributions and particularly those associated to the CT conversion. Methods A workflow is proposed to carry out an assessment of the CT conversion solely on the basis of proton radiographs of real tissues measured with a multilayer ionization chamber (MLIC). The workflow consists of a series of four stages: (a) CT and proton radiography acquisitions, (b) CT and proton radiography registration in postprocessing, (c) sample‐specific validation of the semi‐empirical model both used in the registration and to estimate the water equivalent path length (WEPL), and (d) WEPL error estimation. The workflow was applied to a pig head as part of the validation of the CT calibration of the proton therapy center PARTICLE at UZ Leuven, Belgium. Results The CT conversion‐related uncertainty computed based on the well‐established safety margin rule of 1.2 mm + 2.4% were overestimated by 71% on the pig head. However, the range uncertainty was very much underestimated where cavities were encountered by the protons. Excluding areas with cavities, the overestimation of the uncertainty was 500%. A correlation was found between these localized errors and HUs between −1000 and −950, suggesting that the underestimation was not a consequence of an inaccurate conversion but was probably rather due to the resolution of the CT leading to material mixing at interfaces. To reduce these errors, the CT calibration curve was adapted by increasing the HU interval corresponding to the air up to −950. Conclusion The application of the workflow as part of the validation of the CT conversion to RSPs showed an overall overestimation of the expected uncertainty. Moreover, the largest WEPL errors were found to be related to the presence of cavities which nevertheless are associated with low WEPL values. This suggests that the use of this workflow on patients or in a generalized study on different types of animal tissues could shed sufficient light on how the contributions to the CT conversion‐related uncertainty add up to potentially reduce up to several millimeters the uncertainty estimations taken into account in treatment planning. All the algorithms required to perform the workflow were implemented in the computational tool named openPR which is part of openREGGUI, an open‐source image processing platform for adaptive proton therapy.

A Comparison of Proton Stopping Power Measured with Proton CT and x-ray CT in Fresh Post-Mortem Porcine Structures

“…Our results confirm several recent reports [7][8] [9][10] indicating that it may be possible to reduce the standard uncertainty margins used in proton therapy. For example, our pRad and pCT images of the pig's head show that the RSP map derived from the X-Ray CT is generally accurate, although with discrepancies in some regions such the sinus and tympanic bullae.…”

“…The most notable anatomical WET differences are in the sinus region and the tympanic bullae, where the measured WET from pRad is 4 to 8 mm lower than the expected WET from the X-Ray CT. The sinus result is similar to that reported for a pig's head in [7], while their image does not contain the tympanic bullae. The sinus and tympanic bullae are similar in that they are are both heterogeneous regions with large variations in density and composition, suggesting that conversions from X-Ray Hounsfield units to RSP may be less accurate in such structures than in more uniform ones.…”

“…In a recent publication, Deffet et al have assessed the accuracy of HU to RSP conversion with a pRad of a pig's head [7]. Using a detector that integrates the contribution of every proton during the irradiation of a pencil beam shot, they applied a deconvolution algorithm to improve the spatial resolution to better than the pencil beam size, and registered the resulting pRad with an X-Ray CT.…”

“…We present herein measurements of RSP in a fresh postmortem pig's head as well as a sample of pork shoulder and ribs, comparing the RSP determination from proton images and X-Ray CT images taken close in time. In contrast to [7] we obtain proton images with a list-mode proton imaging system, which measures trajectories and residual ranges of individual protons. Tracking detectors measure the transverse positions of individual protons before and after the patient, and a residual range detector determines the proton energy absorbed within the object.…”

A comparison of proton stopping power measured with proton CT and x‐ray CT in fresh postmortem porcine structures

“…In a recent publication, Deffet et al have assessed the accuracy of HU to RSP conversion with a pRad of a pig's head. 8 Using a detector that integrates the contribution of every proton during the irradiation of a pencil beam shot, they applied a deconvolution algorithm to improve the spatial resolution to better than the pencil beam size and registered the resulting pRad with an x-ray CT. Comparing the pRad to the expectation from the CT, they find range uncertainties generally well below the typical safety margins by about a factor of five, with the exception of regions including sinus cavities, where the range discrepancies are larger.…”