A new metasurface spectral AI chip enables rapid, accurate diagnosis of meibomian gland dysfunction (MGD) from tissue samples, achieving 96.22% accuracy.
Key Details
- 1Researchers from Peking Union Medical College Hospital and Tsinghua University developed a compact optical AI chip for MGD diagnosis.
- 2The AI chip integrates a spectral convolutional neural network (SCNN) directly onto a CMOS imaging sensor.
- 3Pathological tissue sections from MGD patients and controls were rapidly analyzed, producing spectral feature maps in tens of milliseconds.
- 4The chip identifies MGD with 96.22% accuracy, outperforming conventional RGB image analysis (84%) and matching hyperspectral imaging.
- 5Distinct spectral signatures corresponded with disease severity and biochemical changes in gland tissue.
- 6The device is CMOS-fabricated, enabling potential clinical integration for real-time, objective ocular assessment.
Why It Matters
This innovation demonstrates the power of combining metasurface optics and AI for rapid, objective tissue diagnostics—reducing reliance on subjective clinical assessment and paving the way for real-time, in-sensor medical AI applications.
Source
EurekAlert
Related News
•EurekAlert
AI Analyzes 66,000 MRI Scans to Map Body Composition Risks
Researchers used AI to analyze over 66,000 whole-body MRI scans, creating a detailed body composition reference map linked to health risks.
•EurekAlert
Brain-Inspired Training Enhances AI Reliability and Uncertainty Recognition
KAIST researchers developed a brain-inspired AI training method that reduces overconfidence and improves the recognition of unfamiliar data.
•EurekAlert
AI and PS-OCT Enhance Early Keratoconus Detection
AI combined with polarization-sensitive OCT enables earlier and more accurate detection of subclinical keratoconus compared to standard tomography.