Researchers demonstrated AI could detect early laryngeal cancer from voice recordings, distinguishing it from benign conditions.
Key Details
- 1Laryngeal cancer affects over 1 million people worldwide, with high mortality rates.
- 2Diagnosis currently requires invasive endoscopy and biopsy; voice-based screening could simplify detection.
- 3The study analyzed 12,523 voice samples from 306 participants using the Bridge2AI-Voice dataset.
- 4Significant differences in acoustic features, especially harmonic-to-noise ratio, identified laryngeal cancer in men.
- 5Findings suggest voice could serve as a practical biomarker for cancer risk assessment, pending further validation.
Why It Matters
A non-invasive, AI-based screening tool for laryngeal cancer could enable earlier detection, reducing diagnostic delays and easing burden on specialists. This advances the potential of digital biomarkers and broadens the scope of imaging AI in oncology.
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.