CONcISE: COmputatioNal Imaging as a training Network for Smart biomedical dEvices

Lead Research Organisation: UNIVERSITY COLLEGE LONDON
Department Name: Computer Science

Abstract

Our vision is to develop novel, unconventional techniques for multi-dimensional biomedical optical imaging for the detection and mapping of absorption, scattering, and fluorescence, in biological tissues using visible and near-infrared light. The possibility of detecting other dimensions like time and wavelength, together with space, dramatically improves the imaging and diagnostic power of biomedical devices. So far, this capability is strongly hampered by the fact that most of the biomedical instrumentation works trying to maximize the number of measurements (pixel, raster scans, ...) regardless of the information content, thus leading to a huge amount of data to manage, transfer and analyze, with consequent bottleneck and gap between measurement and result. CONcISE will overcome these limitations thanks to an outstanding research and training programme based on the vision that (i) a system as a whole includes both hardware and software integrated and working together, (ii) acquisition and detection are piloted by information content derived by the sample under an adaptive, data-driven framework. Under this approach, ESRSs will be capable of
leading and boosting the biomedical imaging industry towards the development of a new generation of devices, with a strong impact in the sector and in general healthcare. The consortium, balanced among EU experts with computational, experimental and industrial competences, will provide ESRs with a unique, advanced, multi-disciplinary training covering all the aspects of the biomedical imaging science: modelling, design, development, data analysis, validation and translation to the application.
 
Description Learned decoders can improve on image reconstruction from undersampled data in the case of hyperspectral imaging with a single pixel camera
Exploitation Route Compressed sensing is an active area of research, especially in the multi-spectral/time-domain data acquisition application.
Sectors Healthcare

Manufacturing

including Industrial Biotechology

 
Description CONcISE network 2nd Topical School 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Postgraduate students
Results and Impact Project updates and management: The meeting kicked off with a Steering and Supervisory Board session to review project progress, discuss deliverables, and plan for upcoming secondments. This was followed by a dedicated DC Board meeting, providing an opportunity for the students to share updates on their individual projects and experiences.
Scientific lectures: Throughout the week, participants benefited from five scientific lectures covering cutting-edge topics in medical imaging and photonics. These included sessions on machine learning for medical imaging, light transport modelling in biological tissues, convolutional neural networks, feature selection, and scientific software development, delivered by experts from the consortium.
DC presentations: A significant portion of the event was dedicated to DC presentations, where each candidate had the chance to showcase the progress in their research with the CONcISE project. These presentations offered valuable insights into the work being done across different partners and facilitate cross-disciplinary dialogue.
Transferable skills workshop: A session focused on entrepreneurship will help DCs develop crucial skills for translating scientific research into valuable commercial and non-commercial applications.
Networking and collaboration: Social activities, including group dinners and informal discussions, will provide ample opportunities for participants to build connections, share ideas, and foster collaboration within the CONcISE network.
Year(s) Of Engagement Activity 2024
URL https://concise-project.eu/2024/09/12/the-concise-network-gathers-in-london-for-the-second-topical-s...