Proof-of-concept Study to Estimate Individual Post-Therapy Dosimetry in Men with Advanced Prostate Cancer Treated with 177Lu-PSMA I&T Therapy

Abstract It is still debating if individualized dose should be applied for the emerging PSMA-targeted radionuclide therapy (RLT). A critical consideration in this debate is the necessity and feasibility of individual estimation of post-therapy dosimetry before the treatment. In this study, we aimed to prove the concept of individual dosimetry prediction based on pre-therapy imaging and laboratory measurements. Methods: 23 patients with metastatic castration-resistant prostate cancer (mCRPC) treated with 177Lu-PSMA-I&T RLT were included retrospectively. Included patients had available pre-therapeutic 68Ga-PSMA-HEBD-CC PET/CT and at least 3 planar and 1 SPECT/CT dosimetry imaging. Overall, 43 cycles of 177Lu-PSMA I&T RLT were applied. Organ-based standard uptake value (SUV) uptake was obtained from pretherapy PET/CT scans. Patient individual dosimetry was calculated for kidney, liver, spleen, and salivary glands using Hermes Hybrid Dosimetry 4.0 from the post-treatment 177Lu-PSMA I&T imaging studies. Machine learning methods were explored for individual dose prediction from PET images. The accuracy of these dose predictions was compared with the accuracy of population-based dosimetry estimates. Mean absolute percentage error was used to assess the prediction error of estimated dosimetry. Results: An optimal machine learning method achieved a dosimetry prediction error of 15.8 ± 13.2% for kidney, 29.6%±13.7% for liver, 23.8%±13.1% for salivary glands and 32.1 ± 31.4% for spleen. In contrast, the prediction based on literature population mean has significantly larger error (p < 0.01), 25.5 ± 17.3% for kidney, 139.1%±111.5% for liver, 67.0 ± 58.3% for salivary glands, and 54.1 ± 215.3% for spleen. Conclusion: The preliminary results confirmed the feasibility of individual estimation of post-therapy dosimetry before the RLT and its added value to empirical population-based estimation. The exploration of individual dose prediction may support the identification of the role of treatment planning for RLT.