Machine Learning in Bio-Imaging

Berkeley Statistics and Machine Learning Discussion Group

Forum

October 1, 2018
1:30pm to 2:30pm
1011 Evans Hall
Get Directions

Register

This week, BIDS Fellow Henry Pinkard will talk about Machine Learning in Bio-Imaging, followed by an open session to discuss applications in bio-imaging and computational biology. 

Abstract: Modern optical microscopy of biological systems presents ample opportunity for automation using machine learning, both in terms of instrument control and the analysis of the images they produce. I will talk about my work to address both these challenges for two projects: imaging whole living mammalian organs at the resolution of single cells and finding cheaper ways of identifying different cell types using neural networks that learn correspondences between different contrast modalities.

Relevant ML paper: https://arxiv.org/abs/1611.09842

The Berkeley Statistics and Machine Learning Discussion Group meets weekly to discuss current applications across a wide variety of research domains and software methodologies. All interested members of the UC Berkeley and LBL communities are welcome and encouraged to attend. Questions may be directed to BIDS Fellow François Lanusse.

Speaker(s)

Henry Pinkard

Alumni - BIDS-BCHIS Data Science Fellow

Henry Pinkard is a PhD student in Computational Biology and member of the Computational Imaging Lab advised by Laura Waller. His work focuses on combining machine learning and optical microscopy to create computational imaging systems that can diagnose disease and understand biology in new ways. Before coming to Berkeley, he worked in the Vale Lab and the Biological Imaging Development Center at UCSF, where he created open-source tools for controlling microscopes, performing new types of 3D imaging experiments, and handling the large data streams these experiments produce.

François Lanusse

Alumni - BIDS Data Science Fellow

While at UC Berkeley, François Lanusse was a Data Science Fellow at BIDS and a Postdoctoral Scholar with the Berkeley Center for Cosmological Physics and the Foundations of Data Analysis (FODA) Institute, exploring the intersection between cosmology, statistics, and machine learning. His research was focused on measuring and exploiting the gravitational lensing effect (in which distant galaxies appear distorted due to the presence of massive structures along the line of sight) with the development of novel tools and methodologies based on sparse signal representations, convex optimization, and deep learning.

Before joining Berkeley, Dr. Lanusse worked as a postdoctoral researcher within the McWilliams Center for Cosmology at Carnegie Mellon University, after completing a PhD in astrophysics at CEA Saclay near Paris.