Google AI Studio demonstrates moderate accuracy in identifying lung malignancy on CT, but requires further refinement before clinical use.
Key Details
- 1Study used the IQ-OTH/NCCD dataset with 110 CT cases (55 normal, 15 benign, 40 malignant).
- 2Google AI Studio achieved an accuracy of 75.5% for lung cancer detection.
- 3Sensitivity was 74.5%; specificity was 76.4%; AUC for malignant cases was 0.9 and for benign cases 0.62.
- 4Model missed 14 positive cases and produced 13 false positives.
- 5Consistent use of radiological terminology and structured reporting observed.
- 6Main improvement needs: reduce oversensitivity and misclassification, diversify training data, and emphasize human-AI collaboration.
Why It Matters
The study highlights that while AI tools like Google AI Studio can support radiologists with structured reporting and high accuracy for malignancy, human oversight remains essential to avoid misclassification and ensure safe clinical deployment.
Source
AuntMinnie
Related News
•Radiology Business
Meta Funds Ohio State’s Radiology AI Innovation Projects
Meta will fund Ohio State researchers to explore AI-driven advancements in radiology, including chest X-ray reporting and disease prediction.
•AuntMinnie
ChatGPT-5 Performs Poorly at Detecting Distal Radius Fractures on X-rays
ChatGPT-5 missed about half of distal radius fractures on x-rays, showing limited diagnostic capability in a real-world scenario.
•AuntMinnie
AI Triage Tool Speeds Up ICH Head CT Turnaround in ED
AI-based triage for intracranial hemorrhage on head CT reduced emergency department report turnaround by 13 minutes.