Back to all news
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.
Key Details
- 1Study involved 486 PSMA PET scans from metastatic prostate cancer patients (2017-2025).
- 2A deep learning (DL) model and a multimodal fusion model (imaging plus clinical data) were evaluated.
- 3Compared against established risk tools: VISION nomogram, Templeton score, NLR, SUVmax, CHAARTED, LATITUDE classifications.
- 4The fusion model achieved highest predictive accuracy: time-dependent AUC of 0.86.
- 5Median overall survival in patient cohort was 2.1 years.
Why It Matters
These findings support the potential of AI-driven PET biomarkers to improve survival prediction for metastatic prostate cancer, potentially enabling better treatment decision-making and patient stratification.

Source
AuntMinnie
Related News

•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.

•AuntMinnie
AI Worklist Prioritization Dramatically Reduces MSK Fracture Reporting Times
AI-driven worklist prioritization lowered turnaround times for musculoskeletal fracture detection on radiographs by over 80%.