Researchers are exploring the use of radiologists' eye gaze data to enhance AI models for medical imaging.
Key Details
- 1Jeremy Wolfe, MD, of Harvard Medical School, highlights integrating eye gaze data from radiologists into AI algorithms.
- 2This approach shows early success in mammography and x-ray imaging AI models.
- 3The technique may help decrease perceptual errors and improve image labeling.
- 4Incorporating human visual attention patterns could make AI a better collaborative partner for radiologists.
- 5No imminent threat of AI replacing radiologists is foreseen, according to Wolfe.
Why It Matters
Integrating human visual attention patterns into AI could lead to more accurate and human-like diagnostic support systems. This approach may improve workflow and error reduction in radiology, helping create more effective clinician-AI partnerships.
Source
AuntMinnie
Related News
•AI in Healthcare
FDA Seeks Real-World Performance Insights on AI Medical Devices
FDA calls for healthcare worker feedback to enhance monitoring of AI-enabled medical devices in real-world settings.
•Radiology Business
AI Triage Cuts CT Report Turnaround for Pulmonary Embolism—Daytime Only
FDA-backed study finds AI triage tools reduce radiology CT report turnaround times for pulmonary embolism during peak hours.
•Radiology Business
AI Tool Detects Elusive Epilepsy Lesions Missed by Radiologists
Researchers developed an AI tool that identifies focal cortical dysplasia on imaging, aiding diagnosis and surgical planning for epilepsy.