2018 ImageXD Workshop

Image Processing Across Domains


May 16, 2018 to May 18, 2018
9:00am to 5:00pm
190 Doe Library
Get Directions

BIDS hosted the third annual ImageXD Workshop on May 16–18.  ImageXD (Image Processing Across Domains) bringing together researchers from a variety of fields, who share an interest in applications of, as well as algorithms and software for, image analysis.

Date/Time: May 16-18, 2018, 9:00 AM - 5:00 PM
Location: Berkeley Institute for Data Science, 190 Doe Library, UC Berkeley
Registration is now closed; this event has reached full capacity.

Program - 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, and Dask.
  • Presentations and lunchtime panels about algorithms & solutions utilized by practitioners in fields other than your own.
  • 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.

Maxim Ziatdinov — Oak Ridge National Laboratory
Deep learning for atomically resolved imaging techniques: chemical identification and tracking local transformations

Duygu Tosun — UCSF
Neuroimaging biomarkers of neurodegenerative diseases and psychiatric disorders

James Coughlan — Smith-Kettlewell Eye Research Institute
Computer vision for the visually impaired

Amit Kapadia — Planet Labs
Building Global Mosaics

Natalie Larson — UC Santa Barbara
In-situ X-ray computed tomography for defect evolution

John Canny — UC Berkeley
Deep net visualization, interpretable driving

John Kirkham — Howard Hughes Medical Institute
Interactively analyzing larger than memory neural imaging data

Matt McCormick — Kitware, Inc.
Interactive Analysis and Visualization of Large Images in the Web Browser

Suhas Somnath — Oak Ridge National Laboratory
Pycroscopy - a python package for analyzing, storing, and visualizing multidimensional scientific imaging data

Janine Lupo — UCSF
Challenges in Identifying & Translating Quantitative MR Imaging Markers to Evaluate the Effects of Therapy in Patients with Brain Tumors

James Sethian — CAMERA, Lawrence Berkeley National Laboratory
Mathematics for image across domains

Ashish Raj — UCSF
Beyond images: Opportunities for modeling of diseases using image-processed data

Deep Ganguli — Chan Zuckerberg Initiative
Starfish: A Python library for Image Based Transcriptomics


2018 ImageXD Workshop– using images to cross science boundaries and domains
May 22, 2018 | Daniela Ushizima | BIDS Blog: Data Science Insights


Daniela Ushizima

Staff Scientist, Computational Research Division, Lawrence Berkeley National Lab

Dani Ushizima leads the Image Processing team for the Center of Advanced Mathematics for Energy Research Applications (CAMERA) in the Computational Research Division at Lawrence Berkeley National Lab. She is also the Principal Investigator of the U.S. Department of Energy Early Career Research Project called Image across Domains, Algorithms and Learning (IDEAL). Her interests include pattern recognition, computer vision, machine learning, signal processing, quantitative microscopy, and microstructure inspection in materials sciences .