Paper 11970-23
Paper 11970-23
CANCELED: From phase imaging to CNN-based quantitative representation
23 January 2022 • 9:40 AM - 10:00 AM PST | Room 202 (Level 2 South)
Abstract
We present a CNN-based quantification pipeline for the imaging and analysis of adherent cell cultures. The imaging part features two CNNs dedicated to lens-free microscopy performing accelerated holographic reconstruction and phase unwrapping. The analysis part features CNNs estimating several cellular metrics. These CNNs maps phase image into 2D quantitative representations of cell positions and measurements. The outputs images are processed by a local maxima algorithm to obtain a list of cell measurements. Here, we discuss the performance and limitations of this CNN-based quantification pipeline. The advantage is the fast processing time, i.e. the analysis of ~10.000 cells in 10 seconds.
Presenter
Cédric P. Allier
CEA-LETI (France)
Cédric ALLIER, born in 1972, received his Ph.D in Nuclear Physics from the University of the TU Delft (NL) in May 2000. From 2001 to 2009, he worked for the company Cyberstar (industrial and scientific instrumentation). Since May 2009 he is a principal investigator at the CEA-Leti LSIV laboratory working on innovative bio-imaging solutions. Since 2009, he has conducted several studies that led to the filling of >20 patents, the publication of several papers (co-author of 22 peer-reviewed papers, more than 30 proceedings) and important milestones (detection of bacteria and viruses by lensfree microscopy, Nature Photonics 2013). Overall, his work is supporting a coherent project, which is to embrace biology with simple and cheap imaging methods. He also manages several collaborative academic projects such as REVEAL (H2020) and Smart Microscopy (Plan Cancer).