Influence of dosimetry method on bone lesion absorbed dose estimates in PSMA therapy: application to mCRPC patients receiving Lu-177-PSMA-I&T

Background Patients with metastatic, castration-resistant prostate cancer (mCRPC) present with an increased tumor burden in the skeleton. For these patients, Lutetium-177 (Lu-177) radioligand therapy targeting the prostate-specific membrane antigen (PSMA) has gained increasing interest with promising outcome data. Patient-individualized dosimetry enables improvement of therapy success with the aim of minimizing absorbed dose to organs at risk while maximizing absorbed dose to tumors. Different dosimetric approaches with varying complexity and accuracy exist for this purpose. The Medical Internal Radiation Dose (MIRD) formalism applied to tumors assumes a homogeneous activity distribution in a sphere with unit density for derivation of tumor S values (TSV). Voxel S value (VSV) approaches can account for heterogeneous activities but are simulated for a specific tissue. Full patient-individual Monte Carlo (MC) absorbed dose simulation addresses both, heterogeneous activity and density distributions. Subsequent CT-based density weighting has the potential to overcome the assumption of homogeneous density in the MIRD formalism with TSV and VSV methods, which could be a major limitation for the application in bone metastases with heterogeneous density. The aim of this investigation is a comparison of these methods for bone lesion dosimetry in mCRPC patients receiving Lu-177-PSMA therapy. Results In total, 289 bone lesions in 15 mCRPC patients were analyzed. Percentage difference (PD) of average absorbed dose per lesion compared to MC, averaged over all lesions, was + 14 +/- 10% (min: - 21%; max: + 56%) for TSVs. With lesion-individual density weighting using Hounsfield Unit (HU)-to-density conversion on the patient's CT image, PD was reduced to - 8 +/- 1% (min: - 10%; max: - 3%). PD on a voxel level for three-dimensional (3D) voxel-wise dosimetry methods, averaged per lesion, revealed large PDs of + 18 +/- 11% (min: - 27%; max: + 58%) for a soft tissue VSV approach compared to MC; after voxel-wise density correction, this was reduced to - 5 +/- 1% (min: - 12%; max: - 2%). Conclusion Patient-individual MC absorbed dose simulation is capable to account for heterogeneous densities in bone lesions. Since the computational effort prevents its routine clinical application, TSV or VSV dosimetry approaches are used. This study showed the necessity of lesion-individual density weighting for TSV or VSV in Lu-177-PSMA therapy bone lesion dosimetry.