South Korean researchers developed an AI model that detects meningiomas on skull x-rays, showing high accuracy in initial tests.
Key Details
- 1Hybrid AI approach combined deep learning (EfficientNetB0) with traditional machine learning methods.
- 2Trained on 632 x-rays from 158 meningioma patients and 804 images from 201 controls.
- 3Internal validation achieved 0.97 accuracy and 0.999 AUC.
- 4External dataset accuracy was lower (0.74; AUC 0.76) on 103 meningioma/103 control cases.
- 5Grad-CAM showed AI focused on cranial regions correlating with MRI findings.
- 6First feasibility study applying AI to skull x-rays for meningioma detection.
Why It Matters
This study suggests that AI can help detect meningiomas on conventional x-rays, potentially offering diagnostic support in settings lacking access to advanced imaging. The approach could aid earlier tumor identification and reduce reliance on expert radiologist interpretation, improving availability in resource-limited environments.
Source
AuntMinnie
Related News
•Radiology Business
New AI Flags Uncertainty in Breast Cancer Imaging Predictions
University of Pittsburgh researchers developed an AI model that quantifies uncertainty in breast cancer diagnostic predictions to enhance trustworthiness.
•AuntMinnie
LLMs Rarely Recommend Unnecessary Imaging, Except for Thyroid Ultrasound
Large language models seldom over-recommend imaging, but thyroid ultrasound guidance shows substantial discrepancies.
•Radiology Business
UC Irvine Implements AI to Find Lung Cancer Screening Candidates
UC Irvine's radiology department developed an NLP tool to identify patients eligible for lung cancer screening from EHR notes.