A machine learning PET/CT model shows promise for predicting radiation dose prior to Lu-177 PSMA therapy in prostate cancer patients.
Key Details
- 1Study presented at SNMMI evaluated a machine learning model using F-18 PSMA PET/CT imaging.
- 2Nine patients with metastatic castration-resistant prostate cancer were included, analyzing a total of 57 tumors, 36 salivary glands, and 18 kidneys.
- 3The model used uptake-based PET metrics, radiomic features, and clinical biomarkers for dose prediction.
- 4Predictions closely tracked absorbed dose values obtained from traditional post-therapy dosimetry.
- 5Using pre-therapy PET/CT data could eliminate need for additional scans and reduce patient burden.
- 6The approach is part of a larger, ongoing 5-year research program for validation.
Why It Matters
This approach suggests standard diagnostic imaging can be repurposed with AI to deliver patient-specific radiation dose estimates before therapy, potentially improving safety, efficacy, and workflow efficiency in radiopharmaceutical therapy.
Source
AuntMinnie
Related News
•Radiology Business
Framework Assesses Real-World Financial Impact of Radiology AI Adoption
A new analysis presents a financial calculator for objectively assessing the return on investment (ROI) of implementing radiology AI solutions.
•Radiology Business
AI Technique Unveils Previously Hidden MS Gray Matter Lesions on MRI
Researchers developed an AI-enhanced method to detect previously invisible gray matter lesions in multiple sclerosis using MRI.
•Radiology Business
Majority of Patients Want Disclosure When AI Used in Imaging
A new survey finds that nearly all patients want to be informed when AI is utilized in medical imaging interpretation.