A deep learning model named Sybil can predict future lung cancer risk from a single low-dose chest CT scan, as validated in a large Asian cohort.
Key Details
- 1The Sybil model was validated using data from over 21,000 individuals aged 50-80 who underwent LDCT screening between 2009 and 2021.
- 2Sybil demonstrated strong predictive performance for lung cancer diagnosis both at one and six years following the scan.
- 3The model was effective even for never-smokers, a group for whom conventional screening guidelines may not apply.
- 4The research was presented at the ATS 2025 International Conference.
- 5Continued prospective validation is planned to assess clinical use and prediction of lung cancer-specific mortality.
Why It Matters
This advancement could help tailor lung cancer screening strategies, especially benefiting populations (such as Asian never-smokers) not well-served by current guidelines. A validated AI risk tool from a single scan could make screening more efficient and personalized in routine radiological practice.
Source
EurekAlert
Related News
•EurekAlert
University of Michigan AI Achieves Near-Instant Brain MRI Diagnosis
University of Michigan's AI model, Prima, can diagnose brain MRI scans in seconds, achieving up to 97.5% accuracy in identifying neurological conditions.
•EurekAlert
BrainIAC AI Model Excels in Brain MRI Analysis and Disease Prediction
BrainIAC, a new foundation model from Mass General Brigham, outperforms traditional AI approaches in analyzing brain MRI for tasks like brain age estimation and cancer prognosis.
•EurekAlert
Janus Meta-Imager Leverages Neural Networks for Asymmetric Optical Imaging
Researchers unveil a passive all-optical device using neural networks for asymmetric image transmission and transformation.