Chemometric histopathology via coherent Raman imaging for precision medicine (CHARM)

CHARM项目旨在从根本上改变癌症诊断过程，并将新兴的数字组织病理学领域提升到一个新的水平，引入一种新的组织分析技术，能够测量患者组织样本的分子组成，并以完全无标签/无染色的方式识别和分类肿瘤。该仪器与人工智能（AI）相结合，将为组织病理学家提供可靠、快速、低成本的临床决策支持系统（CDSS），用于癌症诊断和个性化癌症治疗。我们将开发一款C类（IVDR，体外诊断调节）医疗设备，由一个低成本的宽带相干拉曼散射（CRS）显微镜（由我们基于石墨烯的专利光纤激光技术实现）组成，名为化学计量病理学系统（CPS），集成了一个基于深度学习、统计和机器学习的人工智能模块。CPS将能够自动分析未染色组织，提供快速准确的肿瘤识别（区分正常与肿瘤组织），准确率为>98%，最终肿瘤诊断预测（区分和分级组织学亚型），准确率为>90%，从而为组织病理学家提供与现有临床方案兼容的决策树，但具有基于生物分子的客观性和缩短的时间（TRL6）。我们将为该应用程序开发一个强有力的商业案例，并确保项目继续提高trl并最终进入市场。该提案基于ERC POC项目GSYNCOR的结果。没有项目总结。

The CHARM project aims to radically transform the cancer diagnosing process and bring the emerging field of digital histopathology to the next level, introducing a novel technology for tissue analysis, capable to measure the molecular composition of the patient tissue samples and to recognize and classify the tumor in a completely label/stain-free way. The instrument, integrated with artificial intelligence (AI), will offer to histopathologists a reliable, fast and low-cost Clinical Decision Support System (CDSS) for cancer diagnosis and personalized cancer therapy. We will develop a Class C, (IVDR, In-Vitro Diagnostic Regulation) medical device consisting of a turnkey low-cost broadband Coherent Raman Scattering (CRS) microscope (enabled by our patented graphene-based fiber laser technology), named the Chemometric Pathology System (CPS), integrating an AI module based on deep learning, statistics and machine learning. The CPS will be capable of automatically analyzing unstained tissues, providing fast and accurate tumour identification (differentiating normal vs neoplastic tissues) with accuracy >98% and final tumour diagnosis prediction (differentiating and grading histologic subtypes) with accuracy >90%, thus offering to the histopathologist a decision tree compatible with existing clinical protocols but with biomolecularbased objectivity and reduced time to result (TRL6). We will develop a robust business case for the application and ensure the project continuation to higher TRLs and the final market entrance. This proposal builds on the results of the ERC POC project GSYNCOR.no project summary.