A label-free optical imaging technique using autofluorescence lifetime and AI can distinguish colorectal cancer with 85% accuracy.
Key Details
- 1Champalimaud Foundation researchers developed a fiber-optic, label-free optical imaging method for colorectal tissue analysis.
- 2Technique involves autofluorescence lifetime measurements at two wavelengths to capture biochemical differences.
- 3Machine learning (AdaBoost) trained on 117 patients' surgical specimens, validated with matched pathology results.
- 4On test data, the AI achieved 85% accuracy, 85% sensitivity, and 85% specificity.
- 5Potential applications include real-time cancer detection during colonoscopy or surgery, reducing the need for biopsies.
- 6Simplified versions of the imaging system delivered strong results, supporting future clinical use.
Why It Matters
Real-time, label-free optical imaging enhanced with AI could support faster, more accurate detection of cancer during endoscopic procedures, leading to earlier intervention and fewer unnecessary biopsies. This advances integration of functional imaging and AI in clinical workflows.
Source
EurekAlert
Related News
•EurekAlert
ML and Multimodal Imaging Power Cerebral Blood Flow Monitoring for Spaceflight
Researchers developed a machine learning model that uses ultrasound and MRI data to predict cerebral blood flow in simulated microgravity for astronaut health.
•EurekAlert
Deep Learning Model Predicts Language Outcomes After Cochlear Implants Using MRI
AI model using deep transfer learning accurately predicts spoken language outcomes in deaf children after cochlear implantation based on pre-implantation brain MRI scans.
•EurekAlert
AI Model Accurately Predicts Blood Loss Risk in Liposuction
A machine learning model predicts blood loss during high-volume liposuction with 94% accuracy.