Researchers developed a dual-modality imaging system that combines high-resolution structural and chemical analysis with AI to improve skin cancer diagnosis.
Key Details
- 1The system merges line-field confocal optical coherence tomography (LC-OCT) with confocal Raman microspectroscopy.
- 2Over 330 nonmelanoma skin cancer samples were examined in a year-long clinical study.
- 3AI models trained on chemical spectra achieved classification accuracy of 0.95 for basal cell carcinoma and 0.92 for both basal and squamous cell carcinoma.
- 4The approach allows targeted, noninvasive analysis of suspicious skin structures at cellular and molecular levels.
Why It Matters
This innovation promises less invasive, more accurate skin cancer diagnosis by combining structural and biochemical imaging with AI classification, potentially reducing reliance on biopsies and improving patient outcomes.
Source
EurekAlert
Related News
•EurekAlert
UVA's $4M NIH Grant Backs AI to Optimize Cardiac MRI Therapies
UVA secures $4 million NIH funding to develop GenStrain, an AI model using MRI data to personalize cardiac pacing therapies.
•EurekAlert
Machine Learning Models Predict Cancer Risk with Routine Health Data
Researchers developed machine learning models using routinely collected health data to predict individual risk for 20 common cancers, outperforming traditional methods for several cancer types.
•EurekAlert
Duke Receives $25M to Lead National Trustworthy AI Hub for Dementia and Aging
Duke University has launched a $25 million national center to make AI for aging and dementia clinically robust and trustworthy.