LAUSR

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 (eg. 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 workow is proposed to carry out an assessment of the CT conversion solely on the basis of proton radiographs of real tissues measured with a multi-layer ionization chamber (MLIC). The workow consists of a series of four stages: (1) CT and proton radiography acquisitions, (2) CT and proton radiography registration in post-processing, (3) sample-specific validation of the semi-empirical model both used in the registration and to estimate the water equivalent path length (WEPL), and (4) 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 wellestablished 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 workow 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 workow on patients or in a generalized study on different types of animal tissues could shed suffcient 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 workow were implemented in the computational tool named openPR which is part of openREGGUI, an open-source image processing platform for adaptive proton therapy.