Researchers from Saint-Étienne University Hospital and Paris-Saclay University, in collaboration with Damae Medical, have developed a compact imaging system that combines line-field confocal optical coherence tomography (LC-OCT) with confocal Raman microspectroscopy. This dual-mode approach enables noninvasive diagnosis of skin cancer by capturing both structural and chemical data.
LC-OCT provides high-resolution cellular images of skin tissue, while Raman microspectroscopy analyzes molecular composition. Over a year-long clinical study, the system was tested on 330 nonmelanoma skin cancer samples, including basal cell carcinoma and squamous cell carcinoma. Researchers collected over 1,300 Raman spectra and trained an AI model to classify cancerous structures.
The AI achieved 95% accuracy for basal cell carcinoma and 92% across both cancer types. It identified distinct chemical signatures that differentiate cancer subtypes, offering insights into tumor behavior and progression. This method could reduce reliance on biopsies and improve treatment planning by providing real-time, in situ diagnostics.
The system’s compact design and integration of AI make it suitable for clinical use. By merging structural and molecular data, it offers a powerful tool for dermatologists and oncologists seeking faster, more precise skin cancer assessments.
Article in SPIE: Dual-mode optical imaging system offers new noninvasive approach to skin cancer diagnosis
Abstract in the Journal of Biomedical Optics: AI-assisted identification of nonmelanoma skin cancer structures based on combined line-field confocal optical coherence tomography and confocal Raman microspectroscopy
