From Instrumentation to Translation
Hyperspectral imaging (HSI) captures rich spatial–spectral signatures of tissue that are often invisible to conventional RGB imaging, offering a non-invasive route to quantify physiology, pathology, and treatment response. At the same time, recent advances in machine learning—particularly deep learning, self-supervised learning, and foundation-model style pretraining—are making it feasible to convert high-dimensional HSI data into clinically actionable decisions. This special session brings together researchers and clinicians working at the intersection of hyperspectral imaging, computational modelling, and AI for diagnosis, with an emphasis on translational impact and deployment in real clinical settings. The session will cover the end-to-end pipeline: (i) imaging hardware and acquisition protocols (surgical, endoscopic, dermatological, and microscopy contexts), (ii) spectral unmixing and physics-informed learning to improve interpretability and robustness, (iii) learning with limited labels through weak supervision, domain adaptation, and uncertainty quantification, (iv) multimodal fusion with histopathology, radiology, or clinical metadata, and (v) validation frameworks, dataset design, and regulatory/ethical considerations for clinical translation. We will also highlight opportunities and pitfalls in generalisation across devices, centres, and patient populations, and discuss practical pathways to prospective trials and integration into clinical workflows. The session will feature invited talks from leaders in biomedical optical imaging and AI-enabled neurosurgical decision support, followed by contributed papers and discussion. We propose an open special session to encourage submissions spanning algorithm development, clinical studies, benchmarks, and deployment-focused work that advances hyperspectral AI toward safe, equitable, and impactful diagnostic tools.
The session gratefully acknowledges acknowledge financial support from DI-VISION project and Hyper-Path project. The project DI-VISION has received funding from the EMPIR programme co-financed by the Participating States and from the European Union’s Horizon 2020 research and innovation programme. The project Hyper-Path has received funding from Cancer Research Wales.
Organiser:
Dr. Deb Roy, Senior Lecturer, Swansea University deb.roy@swansea.ac.uk
Submission format: this special session welcomes both full length papers (12 pages plus up to 2 pages of references) and abstracts (up to 5 pages including references). Click here for detailed submission guidelines and templates.
Deadline: All deadlines, including submission deadline and review timeline are the same as the main conference. Please follow this link to see all the Important Dates.
If you have any questions regarding this Special Session, please contact the organiser.