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.

Radiomics and Artificial Intelligence in Radiotheranostics: A Review of Applications for Radioligands Targeting SSTR and PSMA

“…This idea was first proposed in 2012 to find a correlation between conventional parameters of pre-therapy [ 68 Ga]Ga-DOTA-TOC PET scan with dose distribution of post-RPT and has continued until now [75]. As a preliminary study, Xue et al [81,82] recently used ML techniques with RFs extracted from [ 68 Ga]Ga-PSMA PET/CT imaging and proved the feasibility of pre-therapeutic RLT dosimetry estimation.…”

“…AI models play a critical role in personalized RPT planning. In this regard, Xue et al [81,82] investigated the feasibility of individual dose prediction of [ 177 Lu]Lu-PSMA-I&T based on pre-therapy [ 68 Ga]Ga-PSMA PET/CT imaging employing ML techniques (ANN and RFR). The authors compared the accuracy of their dose prediction results with population-based estimation and found a significant error in the latter.…”

Radiomics and Artificial Intelligence in Radiotheranostics: A Review of Applications for Radioligands Targeting Somatostatin Receptors and Prostate-Specific Membrane Antigens

“…As a proof of concept, Xue et al [63,64] investigated the feasibility of the individual dose prediction of [ 177 Lu]Lu-PSMA-I&T based on pre-therapy [ 68 Ga]Ga-PSMA PET/CT imaging employing ML techniques (ANN and RFR). The authors compared the accuracy of their dose prediction results with population-based estimation and found a significant error in the latter.…”

“…[ 18 F]PSMA-1007 has the potential for a drastic impact on precision medicine in the coming years. 64 Cu SSTR and PSMA Image-Guided RPTS Somatostatin analogues labeled with 64 Cu have been developed, and a head-to-head comparison of [ 64 Cu]Cu-DOTA-TATE and [ 68 Ga]Ga-DOTA-TOC revealed the former's advantages in identifying lesions in patients with NETs [103]. For centers lacking 68 Ge/ 68 Ga generators, 64 Cu ligands with a half-life of 12.7 h offer practical benefits because these ligands can be efficiently delivered from other production facilities.…”

“…Patients with NETs showing high SSTR expression are appropriate candidates f [ 68 Ga]Ga-/[ 177 Lu]Lu-SSTR applications [20]. Several PET-labeled peptides, including [ 68 Ga]Ga-DOTA-Tyr3 octreotide ([ 68 Ga]G DOTA-TATE), [ 68 Ga]Ga-DOTA-Phe1 Tyr3 octreotide ([ 68 Ga]Ga-DOTA-TOC), [ 68 Ga]G DOTA-1-NaI3 octreotide ([ 68 Ga]Ga-DOTA-NOC), and [ 64 Cu]Cu bound DOTA-TATE an DOTA-TOC are synthesized for diagnostic applications. Additionally compounds such Lutetium-177 ( 177 Lu), Yttrium-90 ( 90 Y), and Actinium-225 ( 225 Ac) bound DOTA-TATE an DOTA-TOC, are produced for therapeutic purposes.…”