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
•AuntMinnie
AI Model Uses Ultrasound to Assess Fetal Lung Maturity
Researchers demonstrated an AI model's strong accuracy in measuring fetal lung maturity from ultrasound images.
•AuntMinnie
AI Model Predicts Dosimetry for Lu-177 PSMA Therapy Using PET/CT
A machine learning PET/CT model shows promise for predicting radiation dose prior to Lu-177 PSMA therapy in prostate cancer patients.
•Radiology Business
AI Concerns Influence Medical Students' Interest in Radiology
AI is deterring a significant portion of medical students from choosing radiology as a career, though most remain optimistic about AI's benefits for the field.