Optimizing experimental conditions of femtosecond laser-induced breakdown spectroscopy for differentiating melanoma from the normal dermis in Republic of Korea: an experimental study

Janghee Choi

doi:10.25289/ML.24.030

Med Lasers

Optimizing experimental conditions of femtosecond laser-induced breakdown spectroscopy for differentiating melanoma from the normal dermis in Republic of Korea: an experimental study

Janghee Choi

Department of Industrial Transformation Technology, Korea Institute of Industrial Technology, Cheonan, Republic of Korea

Correspondence to: Janghee Choi
E-mail: cjh@kitech.re.kr
ORCID: https://orcid.org/0009-0009-5017-2381

Received: October 16, 2024; Accepted: November 11, 2024; Published online: November 19, 2024.

This is an open access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/4.0) which permits unrestricted noncommercial use, distribution, and reproduction in any medium, provided the original work is properly cited.

Abstract: Background: Femtosecond laser-induced breakdown spectroscopy (fs-LIBS) is a powerful tool for biomedical diagnostics because it provides real-time, in situ elemental analysis with high spatial resolution. This study used fs-LIBS to distinguish melanoma from normal dermis tissue.
Methods: A crater size of approximately 20 μm and an enhanced signal-to-background ratio of critical emission lines were achieved by optimizing the key experimental parameters, such as laser energy, gate delay, and spectral normalization.
Results: Principal component analysis and support vector machine algorithms were applied to the normalized spectra, resulting in 96.4% classification accuracy.
Conclusion: fs-LIBS, under the appropriate experimental conditions and data processing, provides precise tissue analysis and has significant potential for advancing bio-imaging and early cancer detection.; Keywords: Laser-induced breakdown spectroscopy; Spectrum analysis; Melanoma; Classification; Support vector machine