Southampton researchers developed an AI that surpassed radiologists in detecting hard-to-see airway obstructions on chest CT scans.
Key Details
- 1AI tool developed at University of Southampton detects radiolucent airway foreign bodies on chest CT.
- 2In study of 70 CT scans (14 positive for radiolucent FBA), radiologists detected 36% of cases; AI detected 71%.
- 3Radiologists had 100% precision but lower recall, while AI had 77% precision (some false positives).
- 4AI's F1 score (74%) exceeded that of radiologists (53%).
- 5Model tested on over 400 patient scans across three cohorts; aims to support, not replace, radiologists.
- 6Study published in npj Digital Medicine; research collaboration included UK and China.
Why It Matters
AI support can significantly improve detection of subtle, life-threatening foreign bodies in airways that are often missed on standard imaging, enhancing patient safety and outcomes. This work highlights the growing role of AI as an assistive tool in challenging radiological diagnoses.
Source
EurekAlert
Related News
•EurekAlert
NIH-Backed AI Model Predicts Cancer Survival Using Single-Cell Data
Researchers have developed scSurvival, a machine learning tool that uses single-cell tumor data to accurately predict cancer patient survival and identify high-risk cell populations.
•EurekAlert
Deep Learning Pathomics Platform Improves Immunotherapy Prediction in Lung Cancer
A deep learning pathomics platform accurately predicts immunotherapy response in metastatic NSCLC using routine pathology slides.
•EurekAlert
AI Pathology Model Outperforms PD-L1 in Predicting NSCLC Immunotherapy Response
MD Anderson's Path-IO machine learning platform accurately predicts immunotherapy responses in metastatic non-small cell lung cancer, surpassing current biomarker standards.