A multimodal AI algorithm predicts response to Pluvicto therapy in mCRPC patients using PSMA-PET imaging and lab data.
Key Details
- 1Researchers developed an AI model combining PSMA-PET imaging features with routine lab values to predict Pluvicto response in metastatic castration-resistant prostate cancer (mCRPC).
- 2The retrospective analysis included 302 mCRPC patients with evaluable pretreatment PSMA-PET scans and at least three cycles of Pluvicto therapy.
- 3Key imaging features included lesion shape, standardized uptake value (SUV) metrics, and uptake heterogeneity.
- 4Ten laboratory parameters, such as PSA and lymphocyte count, were included from the EHR.
- 5The combined model achieved an area under the curve (AUC) of 0.80, outperforming models using only clinical (AUC 0.73) or only imaging features (AUC 0.76).
- 6Responders identified by the model showed much higher 30-month survival (79%) than nonresponders (34%).
Why It Matters
This research highlights the potential for AI-driven, multimodal decision support to personalize radioligand therapy in prostate cancer. Accurate prediction of treatment response could improve patient selection and outcomes in high-impact oncology workflows.

Source
AuntMinnie
Related News

•AuntMinnie
Deep Learning PET Biomarkers Outperform Clinical Tools in Prostate Cancer Survival Prediction
Deep learning-derived PET biomarkers more accurately predict metastatic prostate cancer survival than standard clinical risk models.

•AuntMinnie
Multinational AI Model Flags Osteoporosis on Chest X-rays
AI can opportunistically detect osteoporosis from chest x-rays across diverse international populations.

•AuntMinnie
Two-Stage LLM Pipeline Boosts Patient-Friendly Radiology Reports
A two-stage LLM process significantly improves the readability and accuracy of radiology reports for patients.