Back to all news
HKU Develops AI-Enabled Optical Device for Rapid, Non-Invasive Cancer Risk Assessment
The University of Hong Kong has introduced a portable AI-enabled optical device for rapid, non-invasive cancer risk detection using saliva samples.
Key Details
- 1Device detects cancer risk through advanced chemical sensing and AI analysis of saliva samples.
- 2Detection process requires under 10 minutes and is designed for ease of use without medical personnel.
- 3Awarded a Gold Medal at the 51st International Exhibition of Inventions of Geneva (2026).
- 4Uses novel luminescent metal complexes that respond to DNA damage, signalling cancer-associated changes.
- 5Preliminary studies showed strong differentiation between healthy and cancer patients (breast and nasopharyngeal carcinoma).
- 6Large-scale clinical validations are underway in collaboration with multiple hospitals.
Why It Matters
This innovation represents a potential shift toward accessible, user-friendly cancer risk screening tools that leverage AI and advanced optical sensing, complementing traditional radiology and pathology workflows. Early, non-invasive detection could enhance monitoring, especially for high-risk populations, and advance integration between molecular diagnostics and digital health.
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.