Neuroscientists used fMRI and AI models to show that infants as young as two months can categorise objects in their brains.
Key Details
- 1Study involved 130 two-month-old infants undergoing awake fMRI scans while viewing visual stimuli.
- 2Functional MRI tracked brain responses to 12 visual categories, including animals and objects.
- 3AI models were used to analyze and compare infant brain activation patterns for visual recognition.
- 4Research opens new opportunities for early neuroimaging and computational diagnosis in infants.
- 5Findings published in Nature Neuroscience highlight the foundation of visual cognition in early infancy.
Why It Matters
This is the largest awake fMRI study in infants to date and demonstrates the potential for imaging AI to investigate brain function and cognitive development at very early ages, with future implications for both clinical diagnostics and improving AI models. The cross-over between neuroimaging and computational models showcases the growing synergy in radiology and AI research.
Source
EurekAlert
Related News
•EurekAlert
AI-Powered OCT Enables Rapid 'Optical Biopsy' for Early Endometrial Cancer Detection
A team at Washington University has developed a catheter-based 3D OCT system with AI to quickly and noninvasively detect early endometrial cancers.
•EurekAlert
AI Clinical Reasoning in Diagnostics and Digital Fatigue in Healthcare
Recent JMIR features explore large language models in clinical diagnostics and digital fatigue among healthcare professionals.
•EurekAlert
KAIST, MIT, Microsoft Develop Efficient AI Image Upsampling for Robotics
KAIST, MIT, and Microsoft have created 'Upsample Anything,' a training-free AI method to restore high-resolution visual data from compressed images with up to 16x improved GPU memory efficiency.