Center for Bio-Image Informatics

Center for Bio-Image Informatics works with Marine Science Institute at UCSB, NOAA and Greenpeace to analyze large collection of underwater videos

A collaborative project between Center for Bio-Image Informatics, Marine Science Institute at UCSB, NOAA and Greenpeace has acquired and analyzed 23 hours of HD underwater video by identifying all species present in the videos and producing co-occurrence statistics. A complete dataset of annotated sampled frames is published by the Center on our Bisque server. A paper have been published in PLoS ONE about this effort: "Structure-Forming Corals and Sponges and Their Use as Fish Habitat in Bering Sea Submarine Canyons"

Media reaction

Washington Post reports about this project: "Fishery managers could call for a review of massive underwater canyons"

Mission blue writes: "Canyons in the Deep"

UCSB Press release: "UCSB Teams With Greenpeace and NOAA to Study World's Largest Undersea Canyons"

New Bisque version: 0.5.1

A new version of Bisque 0.5.1 has been released! You can check the live demo from our main image repository. This release includes many new features and testing, among many others are:

Parallel execution of datasets
Rich interfaces for autogenerated module UI
Abstracted storage system for local, irods, etc..

Bisque at BioImage Informatics II, HHMI

Bisque team presents the new version 0.5 at the BioImage Informatics II conference in Janelia farm, HHMI. Take a look at the poster.

Papers selected at ICIP, MICCAI and PERHAPS (ICCV Workshop)!

[1] S. Karthikeyan Mehmet Emre Sargin, Swapna Joshi, B.S. Manjunath, Scott Grafton "Generalized subspace based high dimensional density estimation" IEEE International Conference on Image Processing(ICIP), Brussels, Belgium, 2011.

[2] V Jagadeesh, N Vu, B.S. Manjunath, "Multiple Structure Tracing in 3D Electron Micrographs". MICCAI 2011, Toronto, Canada, Sep. 2011.

[3] S. Karthikeyan, Utkarsh Gaur, B.S. Manjunath, Scott Grafton "Probabilistic subspace-based learning of shape dynamics modes for multi-view action recognition" IEEE International Conference on Computer Vision (ICCV) workshop, PERHAPS 2011, Barcelona, Spain, 2011.

New features in Bisque: Feb 2011

Tiled image viewer for very large 5D images
Google-like image sharing
Statistics service for summarization of textual and graphical objects

See the presentation slides of new features

2010-09-16: 4D image visualization

New "BioView3D" visualizes 3D/4D/5D images.

* Visualization video of the laser scanning confocal image of cell mitosis stages Metaphase-Anaphase by fluorescent tagging of mitotic spindles, courtesy of Alphan Altinok, Caltech.

2011 Summer Internship

We just concluded 8 week long summer internships for 2011! Check out the project abstracts and photos:

iPlant-PhytoBisque Code Sprint

Bisque team attended a 'code-sprint' organized by iPlant at Tucson, Arizona. The aim of the 3 day meet (June 14-16) was to work closely with image analysis researchers and integrate new algorithms into Bisque.

For more information, please visit:
http://www.iplantcollaborative.org/learn/news/leaflet/aug-22-2011

Paper published in the Journal of Neuroscience

"Silencing of CDK5 Reduces Neurofibrillary Tangles in Transgenic Alzheimer's Mice"

Paper published in the Journal of Neuroscience, Oct 2010, utilizes automated image analysis techniques for corroboration of visually observable trends. See abstract for details.

All the image and analysis data is web accessible through our Bique system: http://bisque.ece.ucsb.edu/client_service/browser?tag_query=*CDK5*&wpublic=true

Bisque - Bio-Image Semantic Query User Environment

Bisque (Bio-Image Semantic Query User Environment) was developed for the exchange and exploration of biological images. The Bisque system supports several areas useful for imaging researchers from image capture to image analsysis and querying. The bisque system is centered around a database of images and metadata. Search and comparison of datasets by image data and content is supported. Novel semantic analyses are integrated into the system allowing high level semantic queries and comparison of image content.

NSF Award on Uncertainty Management in Working with Scientific Images

The Center for Bio-Image Informatics faculty have been awarded a new 5 year NSF project that would explore new, fundamental problems in uncertainty analysis while working with image data. The principal investigators on the project include Professors Hollerer, Manjunath, Rose and Singh on the Engineering side and Professors Feinstein, Fisher and Wilson from the biology division.

Center for Bio-Image Informatics