Back to all news
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.
Key Details
- 1Researchers combined optical coherence tomography (OCT) with machine learning for endometrial tissue analysis.
- 2Custom catheter probe imaged the entire endometrial cavity in less than 3 seconds.
- 3Study involved 57 post-hysterectomy uteri, 34 with precancerous or cancerous lesions.
- 4AI model classified tissue with 94% sensitivity and 87% specificity using 26 imaging features.
- 5Current standard biopsy has ≈10% false negatives, but the OCT+AI approach showed potential for higher sensitivity.
- 6Plan to evaluate in live patients for clinical translation.
Why It Matters
This pioneering work offers a fast, noninvasive alternative to traditional biopsies, potentially improving sensitivity and early detection of endometrial cancer. Adoption of such technologies could significantly enhance gynecologic cancer screening and outcome prediction in clinical practice.
Source
EurekAlert
Related News
•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.
•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
AI Method Protects Sensitive Data in ECGs While Retaining Clinical Value
Researchers developed an AI model (PP-VAE) that safeguards sensitive personal data in electrocardiograms without sacrificing clinical utility.