Smart data-driven imaging (SDDI) technology builds upon the ability to monitor image data on-the-fly and computationally control the acquisition system to create automatic and adaptive imaging setups. For this session, we welcome topics that lie in the intersection between photonics, life sciences, artificial intelligence, microscopy, and computer vision and are tailored for SDDI.(Show details)
Some potential topics, and related ones, are good candidates for the session: Imaging approaches empowered with data-driven algorithms.
The session will cover:
- Software:Developments for the connection between the data analysis and the microscopy components.
- Image processing: pipelines to enable adaptive imaging setups.
- Quantifying imaged processes: quantification to support data-driven approaches.
Dr. Pontus Nordenfelt
The Quantitative Immunobiology Lab, Lund University, Sweden
Data-Driven microscopy as an approach for high-fidelity context-specific acquisition
Light microscopy is a powerful single-cell technique that allows for quantitative spatial information at subcellular resolution. However, unlike flow cytometry and single-cell sequencing techniques, microscopy has issues achieving high-quality population-wide sample characterization while maintaining high resolution resulting in a compromise between resolution and population context. It is especially challenging to know the contextual relevance of data being acquired for high-resolution live imaging applications where the field of view limits cell population analysis. I will present a general framework, data-driven microscopy (DDM), that uses real-time population-wide object characterization to enable data-driven high-fidelity imaging of relevant phenotypes based on the population context. DDM combines data-independent and data-dependent steps to synergistically enhance data acquired using different imaging modalities. We have developed plugins for improved high-content screening and live adaptive microscopy for cell migration and infection studies that capture events of interest, rare or common, with high precision and resolution. We believe DDM will be a valuable approach for reducing human bias, increasing reproducibility, and placing single-cell characteristics in the context of the sample population when interpreting microscopy data, leading to an overall increase in data fidelity.
Yiwen Zhang, University of Southern California, United States, “Label-free deep imaging inside scattering media through virtual spatiotemporal wavefront shaping.”
Philipp Del Hougne, University of Rennes, France, “Experimentally realized physical-model-based wave control in massively parametrized complex media.”
Hao Wang, Boston University, United States, “Advancing Large-Scale Computational Imaging by Local Conditional Neural Fields.”
Estibaliz Gómez-de-Mariscal, Instituto Gulbenkian de Ciência, Oeiras, Portugal
Hannah S. Heil, Instituto Gulbenkian de Ciência, Oeiras, Portugal
Catherine Bouchard, CERVO Brain Research Center, Universitè Laval, Canada
Erick Moen, California Institute of Technology, United States