REMOD, a new AI model, detects pancreatic cancer on CT scans much earlier and more accurately than radiologists.
Key Details
- 1The AI model, REDMOD, was trained to identify radiomic signatures of pre-diagnostic pancreatic ductal adenocarcinoma (PDAC) on CT scans.
- 2It was trained with imaging data from multiple institutions and developed a 40-feature radiomic signature.
- 3Tested on over 200 abdominal CT scans from patients later diagnosed with PDAC despite no initial radiologist findings.
- 4REMOD detected pancreatic cancer on average 475 days before clinical diagnosis.
- 5The model achieved nearly 75% sensitivity, about twice as high as radiologists' sensitivity.
- 6At a 24-month prediction window, REDMOD's sensitivity was triple that of radiologists.
Why It Matters
Early detection of pancreatic cancer is vital due to its poor prognosis when caught late. AI advancements like REDMOD could revolutionize detection efficacy, potentially improving survival rates and demonstrating the impact of imaging AI in clinical practice.
Source
Radiology Business
Related News
•AuntMinnie
Radiologists Struggle to Spot AI-Generated Radiology Images
Radiologists correctly identify AI-generated images 75% of the time, with CT and MRI images being particularly challenging to spot.
•AuntMinnie
Radiology Leads FDA AI Device Approvals Over Three Decades
Radiology accounts for 76% of all FDA-cleared AI/ML-enabled medical devices as of the end of 2025.
•Radiology Business
Automation Bias: How AI Can Compromise Radiologist Accuracy
AI decision support can induce automation bias, leading radiologists to accept incorrect interpretations and potentially reduce their diagnostic accuracy.