Resumen

Objectives: To investigate the diagnostic accuracy and safety of a real-time noninvasive in vivo skin cancer diagnostics utilizing non-discrete molecular LIPS combined with a deep neural network (DNN)-based diagnostic algorithm. Introduction: Although various skin cancer detection devices have been proposed, most of them are not used owing to their insufficient diagnostic accuracies. Laser-induced plasma spectroscopy (LIPS) can noninvasively extract biochemical information of skin lesions using an ultrashort pulsed laser. Materials / method: In vivo LIPS spectra were acquired from 296 skin cancers (186 BCCs, 96 SCCs and 14 melanomas) and 316 benign lesions in a multisite clinical study. The diagnostic performance was validated using 10-fold cross-validations. Results: The sensitivity and specificity for differentiating skin cancers from benign lesions using LIPS and the DNN-based algorithm were 94.3% (95% CI: 91.6 – 96.9%) and 88.6% (95% CI: 85.1 – 92.1%), respectively. No adverse events, including macroscopic or microscopic visible marks or pigmentation due to laser irradiation, were observed. Conclusion: This LIPS system with a DNN-based diagnostic algorithm is a promising tool to distinguish skin cancers from benign lesions with high diagnostic accuracy in real clinical settings.