Machine Learning-Based Dose Prediction in [177Lu]Lu-Psma-617 Therapy by Integrating Biomarkers and Radiomic Features From [68Ga]Ga-Psma-11 Positron Emission Tomography/Computed Tomography Publisher Pubmed



E Yazdani ELMIRA ; M Sadeghi MAHDI ; N Karamzadeziarati NAJME ; P Jabari PARMIDA ; P Amini PAYAM ; H Vosoughi HABIBEH ; Ms Akbari Malihe SHAHBAZI ; M Asadi MAHBOOBEH ; Sr Kheradpisheh Saeed REZA ; P Geramifar PARHAM
Source: International Journal of Radiation Oncology Biology Physics Published:2025

Abstract

Purpose: The study aimed to develop machine learning (ML) models for pretherapy prediction of absorbed doses (ADs) in kidneys and tumoral lesions for patients with metastatic castration-resistant prostate cancer (mCRPC) undergoing [177Lu]Lu-PSMA-617 (Lu-PSMA) radioligand therapy (RLT). By leveraging radiomic features (RFs) from [68Ga]Ga-PSMA-11 (Ga-PSMA) positron emission tomography/computed tomography (PET/CT) scans and clinical biomarkers (CBs), the approach has the potential to improve patient selection and tailor dosimetry-guided therapy. Methods and Materials: Twenty patients with mCRPC underwent Ga-PSMA PET/CT scans before the administration of an initial 6.8 ± 0.4 GBq activity of the first Lu-PSMA RLT cycle. Posttherapy dosimetry involved sequential scintigraphy imaging at ∼4, 48, and 72 hours, along with a single photon emission computed tomography (SPECT)/CT image at around 48 hours, to calculate time-integrated activity coefficients. Monte Carlo (MC) simulations, leveraging the Geant4 application for tomographic emission toolkit, were employed to derive ADs. The ML models were trained using pretherapy RFs from Ga-PSMA PET/CT and CBs as input, whereas the ADs in kidneys and lesions (n = 130), determined using MC simulations from scintigraphy and SPECT imaging, served as the ground truth. Model performance was assessed through leave-one-out cross-validation, with evaluation metrics including R² and root mean squared error (RMSE). Results: The mean delivered ADs were 0.88 ± 0.34 Gy/GBq for kidneys and 2.36 ± 2.10 Gy/GBq for lesions. Combining CBs with the best RFs produced optimal results: the extra trees regressor was the best ML model for predicting kidney ADs, achieving an RMSE of 0.11 Gy/GBq and an R² of 0.87. For lesion ADs, the gradient-boosting regressor performed best, with an RMSE of 1.04 Gy/GBq and an R² of 0.77. Conclusions: Integrating pretherapy Ga-PSMA PET/CT RFs with CBs shows potential in predicting ADs in RLT. To personalize treatment planning and enhance patient stratification, it is crucial to validate these preliminary findings with a larger sample size and an independent cohort. © 2025 Elsevier B.V., All rights reserved.