REVEAL Imaging
REVEAL Imaging

Scale up high-content screening as well as creating phenotypes from image data.

Agile support for complex imaging formats like mass-spec, FLIM, FISH.

REVEAL Imaging delivers:

  • Agility: Streamline exploration, image analysis, and machine-learning on cellular and imaging study datasets. Efficient, intuitive data management for MRI, mass-spec, FLIM, FISH, and other datasets.
  • Scalability: Automated parallel processing of image processing scales across thousands of cores with Burst Mode™ computing.
  • Extensibility: Deploy any R, Python, C++ image processing libraries.
  • Cost-effectiveness: Significantly reduced the time and human resources required to analyze experimental imaging data sets and assess the effect of different parameters and methods.
  • Reproducibility: Version raw, QA’d, and processed data. Guaranteed data integrity and security in a transaction safe and secure multi-user environment.
  • Scientific Results: Develop robust phenotyping of high content cellular images for chemical biology. Machine-learning on FISH images to characterize bioproduction cell lines.

“Our image volumes are going from “small to scary”. Analyzing 32K images took person months. We have to automate this.”

Lead Imaging Technologies, Process Analytical Engineer, Top 15 Pharma

 

“The greatest advantage that truly sets SciDB apart from other Big Data analysis technologies is the optimized communication protocol that Paradigm 4 implemented to support efficient multimodal parallelization; that is, beyond embarrassingly parallel processing. This protocol empowers SciDB users to leverage its functions and operators with exceptional performance for a wider range of analyses on arrays.”

NASA climatologist

Relevant Publications and Posters
02.08.2021 | STARE into the future of GeoData integrative analysis Michael L. Rilee, Kwo-Sen Kuo, James Frew, James Gallagher, Niklas Griessbaum, Kodi Neumiller, Robert E. Wolfe » FULL ARTICLE
12.11.2017 | Visual analytics with unparalleled variety scaling for big earth data Yu, et al. » FULL ARTICLE
07.20.2017 | Deep Learning for Robust Phenotyping of High Content Cellular Images High Content Analysis; Roohani Y, Hoffman A, Musso R, Richmond N.  » FULL ARTICLE
09.24.2016 | Benchmarking SciDB data import on HPC systems. IEEE High Performance

Extreme Computing Conference Samsi S, Brattain L, Arcand W, Bestor D, Bergeron B, Byun C, et al.

 » FULL ARTICLE
07.20.2015 | Analysis of Metabolomics Datasets with High-Performance Computing and Metabolite Atlases

Metabolites Yao Y, Sun T, Wang T, Ruebel O, Northen T, Bowen BP.

 » FULL ARTICLE