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
AI-CAD Boosts Specificity and Efficiency in Asia-Pacific Mammography Study
AI-CAD systems increased specificity and cut interpretation times in a multicenter Asia-Pacific mammography study.
•AuntMinnie
AI-Driven Mammogram Analysis Boosts Cardiovascular Risk Prediction in Women
AI quantification of breast arterial calcifications (BACs) on mammograms enhances prediction of cardiovascular events beyond traditional risk models.
•AuntMinnie
ChatGPT Demonstrates High Diagnostic Agreement on FDG-PET/CT Reports
ChatGPT-4o and ChatGPT-5 matched or surpassed nuclear medicine experts in diagnosing neurodegenerative diseases using textual FDG-PET/CT scan descriptions.