Biophotonics has transformed our ability to investigate biological and biomedical systems by leveraging the interactions between light and matter. Modern biphotonic techniques offer high-resolution insights into molecular structures, cellular dynamics, and tissue organization. Among the many tools in biophotonics, molecular spectroscopy (e.g. fluorescence, IR or spontaneous and coherent Raman spectroscopy) stands out as particularly powerful and versatile methods, enabling both morphological and chemical characterization of a broad variety of biomedical samples.
This lecture will explore how the integration of multimodal spectroscopy in combination with AI is revolutionizing biomedical and clinical diagnostics. We will focus on two primary domains: intraoperative spectral histopathology and infectious disease management, while also addressing further emerging applications across healthcare, environmental science, and bioanalytics.
One of the most impactful clinical applications lies in surgical oncology. A key challenge during tumor resections is the real-time identification of cancerous versus healthy tissue to ensure complete removal while preserving surrounding structures. Traditional histopathological analysis is limited by its post-operative nature and time requirements. Coherent Raman spectroscopy, integrated into multimodal imaging systems, offers real-time, in situ chemical and morphological contrast that supports more accurate intraoperative decision-making. When augmented with AI, these systems can automatically interpret complex spectral data and provide immediate diagnostic feedback to surgeons. The fusion of advanced optical imaging - such as coherent anti-Stokes Raman scattering (CARS), two-photon excited fluorescence (TPEF), and second harmonic generation (SHG) - with AI-assisted image analysis paves the way toward precision-guided surgery. Importantly, the addition of laser ablation capabilities enables a "seek-and-treat" workflow where identified malignant tissues can be directly removed, bringing diagnostics and therapy into a single, efficient process.
Beyond oncology, molecular spectroscopy has shown great promise in the field of infectious disease diagnostics. The rapid identification of pathogens, including antibiotic-resistant strains, remains a major global health challenge. Raman-spectroscopy based approaches provide a rapid alternative to culture-based or PCR-based diagnostics and are well-suited for point-of-care and on-site applications. Our work focuses on the development of compact, portable instruments that can acquire and analyze patient samples in minutes. With the support of AI, these tools enable robust identification of microbial species, resistance profiling, and even monitoring of host immune responses, all critical for timely and personalized therapeutic interventions.
Importantly, our approach spans the entire diagnostic workflow - from sample collection and spectral acquisition to real-time data analysis and clinical decision-making. AI models trained on extensive spectral datasets can perform complex classification and pattern recognition tasks, transforming raw data into actionable insights. This accelerates the diagnostic process and reduces dependence on specialized expertise, making high-end diagnostics more accessible and scalable.
In addition to cancer and infectious diseases, advanced (micro-)spectroscopic methods - including Raman, IR, and fluorescence techniques allow to address challenges in biology, and life sciences. A major focus lies in investigating biological processes at the molecular level, such as the uptake and localization of active molecules in cells, also using intelligent Raman tags.
The technique’s broad adaptability is further enhanced by advances in miniaturized, robust hardware and cloud-connected AI systems, which allow for remote operation and centralized data processing.
The success of the aforementioned applications depends not only on technological innovation but also on strategic translational infrastructure. To ensure the clinical viability we are developing pathways that bridge the divide between laboratory research and clinical translation.
Overall, this lecture will showcase how advanced multimodal (micro-)spectroscopic methods, empowered by AI, is poised to redefine medical diagnostics—making them faster, more accurate, and more accessible. Whether guiding surgeons in real time, identifying life-threatening infections, or providing molecular-level insights into complex biological systems, this powerful synergy is laying the foundation for a new era of intelligent, personalized medicine.
Acknowledgment: Financial support of the EU, the ”Thüringer Ministerium für Wirtschaft, Wissenschaft und Digitale Gesellschaft”, the ”Thüringer Aufbaubank”, the Federal Ministry of Education and Research, Germany (BMBF), the German Science Foundation, and the Carl-Zeiss Foundation are greatly acknowledged.
