Chemometric histopathology via coherent Raman imaging for precision medicine

Projektinformationen

CHARM

ID Finanzhilfevereinbarung: 101058004

DOI

10.3030/101058004

Projekt abgeschlossen

EK-Unterschriftsdatum 22 März 2022

Startdatum 1 Mai 2022

Enddatum 31 Oktober 2025

Finanziert unter

• The European Innovation Council (EIC)

Gesamtkosten

€ 2 441 980,00

EU-Beitrag

€ 2 441 979,00

Koordiniert durch

CAMBRIDGE RAMAN IMAGING SRL
Italy

Periodic Reporting for period 3 - CHARM (Chemometric histopathology via coherent Raman imaging for precision medicine)

Berichtszeitraum: 2024-08-01 bis 2025-10-31

Zusammenfassung vom Kontext und den Gesamtzielen des Projekts

CHARM aimed to develop a medical device based on high-speed, low-cost Raman digital imaging technology and artificial intelligence to transform cancer diagnosis and treatment.
CHARM addresses two limitations of digital pathology: first, the need for tissue staining, which is time-consuming and introduces variability between samples, and the inability to measure the tissue molecular composition which can further enhance the diagnostic process. Our approach reduces the pathologist’s workload by avoiding staining and by including a prescreening performed by the AI agent. The pathologist is provided with a diagnostic report that supports the differentiation between normal and tumor tissue.

Our aim is to develop a Class C (In-Vitro Diagnostic Regulation) medical device consisting of 1) a turnkey low-cost broadband Coherent Raman Scattering microscope (enabled by our patented graphene-based fiber laser technology); 2) an Artificial Intelligence model based on deep learning, statistics, and machine learning. The instrument will offer histopathologists a reliable, fast, and low-cost Clinical Decision Support System for cancer diagnosis and personalized cancer therapy.

Arbeit, die ab Beginn des Projekts bis zum Ende des durch den Bericht erfassten Berichtszeitraums geleistet wurde, und die wichtigsten bis dahin erzielten Ergebnisse

The CHARM project has successfully developed a new imaging platform to support faster and more reliable cancer diagnostics in clinical environments. By combining advanced laser technology, innovative microscopy, and artificial intelligence, CHARM delivers a label-free approach that can provide detailed tissue information without the need for traditional staining.

The project achieved the development of compact, cost-effective laser sources covering the key molecular regions needed for biomedical imaging. Multiple laser architectures were designed and realised, including dual-wavelength and fully coherent Raman sources, supported by innovative saturable absorber designs enabling passive synchronisation and high stability. These laser solutions meet key performance and cost targets. These lasers were integrated into a broadband microscope system, which was installed and tested at Jena University Hospital. Clinical users actively worked with the system and provided feedback, confirming its usability and relevance for real-world clinical workflows. The microscope achieved high spatial and spectral resolution, adequate signal-to-noise performance, and clinically relevant imaging speeds in both spectral regions.
The project successfully developed AI pipelines for automated tumour identification and Raman-based virtual H&E staining. Tumour segmentation achieved high accuracy and robustness, while virtual staining was demonstrated using state-of-the-art deep learning architectures, producing histologically meaningful images. Explainable AI approaches were also explored to ensure clinical interpretability and trust.

Fortschritte, die über den aktuellen Stand der Technik hinausgehen und voraussichtliche potenzielle Auswirkungen (einschließlich der bis dato erzielten sozioökonomischen Auswirkungen und weiter gefassten gesellschaftlichen Auswirkungen des Projekts)

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.

CORAL microscope