CHARM has demonstrated the feasibility of coherent Raman scattering microscopy combined with AI for the automated analysis of unstained tissue samples. The developed technology is capable of rapidly differentiating normal from neoplastic tissue based on intrinsic biomolecular contrast, providing objective and reproducible results without the need for conventional staining. The integration of AI-based tumour identification and virtual H&E staining supports the generation of clinically meaningful outputs from label-free data, representing a significant advancement in digital pathology and optical diagnostics.
CHARM offers a new approach to tissue analysis that is compatible with existing clinical protocols while significantly reducing time to result. By providing fast and accurate tumour identification and supporting final diagnostic decisions through AI-assisted analysis, the technology has the potential to support histopathologists with an objective, biomolecular-based decision pathway. The project demonstrated the applicability of the approach in head and neck cancer, a disease where early diagnosis substantially improves treatment options and patient survival. Importantly, head and neck cancer represents a model for a wider group of cancers characterised by field cancerisation, including oesophageal, gastrointestinal, non-melanoma skin, non-small cell lung, and many breast cancers, indicating strong potential for broader clinical impact.
CHARM delivered concrete industrial results, including advanced prototypes, commercial products, and patent-protected innovations. These outcomes strengthen European leadership in photonics, medical imaging, and AI-enabled diagnostics, while creating opportunities for market expansion into clinical, life science, and research applications. The modular and scalable nature of the CHARM technology supports future adaptation to additional indications and markets.
