ImageXD 2019

Images Across Domains


September 11, 2019 to September 13, 2019
9:00am to 5:30pm
Berkeley, CA


BIDS hosted the third annual ImageXD Conference on September 11–13, 2019, which showcased recent advances in image processing algorithms and tools, which, together with an increased accessibility to modern imaging equipment, have made image data ubiquitous across many fields, with applications ranging from microscopy to radio astronomy. ImageXD (Images Across Domains) brings together researchers from a variety of fields, who share an interest in applications of, as well as algorithms and software for, image analysis.

This three-day event featured tutorials, talks, and collaborative work sessions:

  • Tutorials on image processing software tools such as NumPy, SciPy, scikit-image, Keras, TensorFlow, ITK and ITKwidgets.
  • Presentations about algorithms & solutions utilized by practitioners of computer vision.
  • Collaborative work sessions with time to build software, explore new methods, develop educational material, or solve an existing research problem with a technique from another domain.


PROGRAM SUMMARY with links to the video presentations:

  1. Spatiotemporally adaptive imaging with smart microscopy -- Loic Royer    
  2. Neural network-controlled microscopy and image registration as optimization -- Henry Pinkard, BIDS, UCSF Bakar Computational Health Sciences Institute
  3. Napari: multi-dimensional image visualization in Python -- Kira Evans    
  4. Global scale observation using satellite imagery and machine learning -- Esther Rolf    
  5. Assessing the distribution of recombination proteins during C. elegans meiotic progression using maching learning -- Cedric EspenelCell Science Imaging Facility, Stanford University
  6. Lights! Camera! Extraction! ML methods for when your data is ready for prime time -- Pablo Damasceno, Department of Radiology, UCSF    
  7. Working with multidimensional microscopy images in Julia -- Tamas Nagy, UCSF    
  8. National Center for X-ray Tomography: Soft X-ray Tomography (SXT) -- Carolyn Larabell, UCSF
  9. DASK: Performance at scale -- Matthew Rocklin
  10. Slideslicer: a package for manipulation of whole slide imaging and annotations -- Dima Lituiev, UCSF Bakar Computational Health Sciences Institute
  11. Analyzing motions of molecular machines using cryo-electron microscopy -- Iris Young, UCSF
  12. Data-driven design for computational microscopy -- Michael Kellman, UC Berkeley
  13. Convolutional Neural Networks of Fiber Detection models -- Silvia Miramontes, Berkeley Lab, UC Berkeley 
  14. Recognizing the Impossible Image: How 3D Imaging Can Lead to Optical Character Recognition for Cuneiform Tablets -- Adam Anderson, Digital Humanities, UC Berkeley

Organizing Committee
Daniela Ushizima, LBNL / UC Berkeley
Maryana Alegro, UCSF / UC Berkeley
Kevin Keys, UCSF / UC Berkeley
Henry Pinkard, UC Berkeley
Stéfan van der Walt, UC Berkeley


Stéfan van der Walt

Senior Research Data Scientist

Stéfan van der Walt is a researcher at BIDS. He is the founder of scikit-image and co-author of Elegant SciPy.  Stéfan has been developing scientific open source software for more than a decade, focusing mainly on Python packages such as NumPy & SciPy. Outside work, he enjoys traveling, running, and the great outdoors.

Daniela Ushizima

Staff Scientist, Applied Mathematics and Computational Research Division, Berkeley Lab

BIDS Faculty Affiliate Dani Ushizima is a Staff Scientist in the Machine Learning and Analytics Group in the Computational Research Division at Berkeley Lab, where she leads the Image Processing/Machine Vision team at CAMERA, and an Affiliate Faculty of the Bakar Computational Health Sciences Institute (BCHSI) at the University of California, San Francisco. She also leads the Center for Recognition and Inspection of Cells (CRIC), where her research focuses on imaging cancer cells for early-stage disease diagnosis. With 20 years of research and development experience in Computer Vision, Dani has focused primarily on quantitative microscopy and microstructure classification, from materials science to biomedical imaging.

Maryana Alegro

BIDS Alum – BIDS-BCHSI Data Science Fellow

Computer Scientist Maryana Alegro is a former BIDS-BCHIS Data Science Fellow, now an Associate Professional Researcher at UCSF.  At UC Berkeley, she was a post-doc at the UCSF Grinberg Lab, where she investigated and created computational tools to assist researchers in studying human brain and dementia, especially Alzheimer’s disease (AD). Such tools incorporate a combination of machine learning techniques with visualization and computer vision. She was also responsible for the design/construction of prototype imaging equipment at the lab.  She received her MS and PhD in electrical engineering from the University of São Paulo Polytechnic School. Her major experience is in medical imaging, especially in MRI and histological image analysis.

Henry Pinkard

BIDS Alum - Data Science Fellow

Henry Pinkard was a BIDS Data Science Fellow and a PhD student in Computational Biology, and a member of the Computational Imaging Lab advised by Laura Waller. His work focused 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.

Kevin Keys

BIDS Alum – Data Science Fellow

Kevin L. Keys was a BIDS-UCSF Data Science Fellow and postdoctoral scholar in the Burchard Lab at the UCSF School of Medicine. His biological research interests spanned computational genomics, bioinformatics, and statistical genetics, and his mathematical interests spanned scientific computing, high-dimensional statistical inference, and mathematical optimization. At UCSF Kevin studied the genetic basis of pediatric asthma in admixed populations using multilayered data, including genomic, transcriptomic, methylomic, sociodemographic, environmental, and clinical measures. Kevin completed his M.S and Ph.D in Biomathematics from the UCLA School of Medicine, where he developed open-source penalized regression methods for genetic association studies. He holds a B.S in Mathematics and a B.A. in Linguistics from The University of Arizona, where he did human evolution research with Michael F. Hammer and Joseph Watkins. He was a Fulbright visiting scholar in Jaume Bertranpetit’s lab at the Universitat Pompeu Fabra in Barcelona, Spain, where he studied the molecular evolution of metabolic networks in primates.