Natural Sciences, Stomotology, 2026
ISSN: 1829-006X
AI INTEGRATED WITH LASERS TO DISTINGUISH BETWEEN HEALTHY AND DISEASED TISSUE FOR MINIMALLY INVASIVE PROCEDURES
This is an open access article distributed under the
Creative Commons Attribution License, which permits unrestricted use, distribution,
and reproduction in any medium, provided the original work is properly cited.
Submitted: 2026-04-08
© 2026 by author(s) and The Gufo Inc.
This work is licensed under Creative Commons Attribution–NonCommercial International License
(CC BY-NC 4.0).
Abstract
Objective:To evaluate the efficacy of an artificial intelligence (AI)-integrated laser system in distinguishing between healthy and diseased oral soft tissues during minimally invasive surgical procedures. Methods:This prospective in vitro study involved 60 soft tissue biopsy specimens (30 healthy, 30 diseased, including hyperplasia and dysplasia). Near-infrared (NIR) diode laser was paired with a deep learning algorithm trained on spectral and thermal feedback data. The AI model was assessed for sensitivity, specificity, and real-time classification accuracy in differentiating tissues during laser ablation. Results:The AI-laser system assured an overall classification accuracy of 92.1%. Sensitivity and specificity of the diseased tissue detection was 93.3% and 90.8%, respectively. Thermal feedback self-regulation of power output, minimizing collateral damage was (<50 µm peripheral necrosis) compared to standard diode lasers (>100 µm). Conclusion:AI-integrated laser enabled real-time, selective ablation with high precision, reducing tissue trauma surgical complications.