Researchers introduce the COCA AI tool to detect colorectal cancer opportunistically on routine noncontrast CT scans.
Key Details
- 1COCA (COlorectal Cancer detection with AI) uses routine noncontrast CT images to spot colorectal cancer.
- 2Tool repurposes scans originally completed for other indications (e.g., trauma, abdominal pain).
- 3The solution aims to provide a cost-effective, scalable platform for proactive cancer detection.
- 4Tens of millions of abdominal and pelvic CTs are performed annually, many unintentionally capturing views of the colorectum.
- 5Historically, noncontrast CT was considered unsuitable for CRC detection, but AI now reveals subtle predictive patterns.
Why It Matters
This approach could significantly expand colorectal cancer screening by leveraging already acquired CT data, increasing early detection rates without added patient burden or procedural invasiveness. It demonstrates the growing potential of AI to unlock value from existing radiology workflows.
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.