SOUTHAMPTON — Researchers at University Hospital Southampton developed a machine-learning model that estimates radiation dose absorption in tumors and healthy organs before the start of 177Lu-PSMA radiopharmaceutical therapy for metastatic castration-resistant prostate cancer (mCRPC). The model uses data from pre-therapy 18F-PSMA PET/CT scans, which are routinely performed and widely available for prostate cancer patients.
Current dosimetry for 177Lu-PSMA therapy typically relies on post-therapy imaging, a process that is time-consuming and resource-intensive. The new approach seeks to address this limitation by predicting absorbed radiation doses prior to treatment initiation. Researchers developed a machine learning mixed effects model that incorporates uptake-based PET metrics, radiomic features, and clinical biomarkers as predictors.
The study analyzed data from nine patients with mCRPC referred for 177Lu-PSMA therapy, including 57 tumors, 36 salivary glands, and 18 kidneys. Predictive estimates generated by the model were compared with actual dosimetry calculated after one cycle of therapy to evaluate accuracy. Results indicated the model showed a promising ability to predict absorbed dose in both tumors and organs.
"If validated in larger studies, this approach may improve patient selection and support better decision-making during pre-treatment assessment, helping to optimize 177Lu-PSMA therapy for individual patients. More broadly, it highlights how imaging can move beyond diagnosis to actively guide personalized treatment," said Amit Nautiyal, scientist and National Institute for Health and Care Research (NIHR) fellow at University Hospital Southampton and the University of Southampton, United Kingdom.
The research was presented at the Society of Nuclear Medicine and Molecular Imaging 2026 Annual Meeting. It is part of a planned five-year program aimed at collecting additional data to develop a robust, validated model. Future work will focus on larger, multi-center cohorts to refine pre-therapy absorbed dose predictions and conduct independent validation to support patient stratification for personalized 177Lu-PSMA therapy in clinical practice. The study was supported by the National Institute for Health and Care Research (NIHR) in the United Kingdom.