Researchers developed machine learning models that outperform PSA testing in predicting abnormal prostate MRI findings for suspected prostate cancer.
Key Details
- 1Study involved 11,879 prostate MRI scans for suspected prostate cancer.
- 2Two ML models were trained, with AUCs of 0.711 (Model A) and 0.616 (Model B), compared to 0.593 for PSA testing alone.
- 3Model A included prostate volume in addition to clinical variables; Model B did not.
- 4Model A had higher specificity (28.3%) and comparable sensitivity (89%) versus PSA testing (>4 ng/mL).
- 5False negative rates: 8% for Model A, 16.8% for Model B; most were clinically insignificant or benign.
Why It Matters
By improving risk stratification with prostate MRI, machine learning models can help triage patients more effectively, optimizing resource use and potentially reducing unnecessary imaging. This supports more personalized and efficient approaches in prostate cancer diagnosis within radiology.
Source
AuntMinnie
Related News
•AuntMinnie
Toronto Study: LLMs Must Cite Sources for Radiology Decision Support
University of Toronto researchers found that large language models (LLMs) such as DeepSeek V3 and GPT-4o offer promising support for radiology decision-making in pancreatic cancer when their recommendations cite guideline sources.
•AuntMinnie
AI Model Using Mammograms Enhances Five-Year Breast Cancer Risk Assessment
A new image-only AI model more accurately predicts five-year breast cancer risk than breast density alone, according to multinational research presented at RSNA 2025.
•Radiology Business
AI Model Uses CT Scans to Reveal Biomarker for Chronic Stress
Researchers developed an AI model to measure chronic stress using adrenal gland volume on routine CT scans.