Jiyun Byun | Projects

Current project @ Mayachitra

Mayachitra imago: bioimage management and analysis software

The goal of this STTR phase II effort is to develop a bioimage database analysis and management system that is easy to use and provides sophisticated image processing and computer vision functionalities. The outcome, Mayachitra imago software, has unique features that are not currently available to biologists. It integrates an advance set of image tools with our advanced technologies in image storage and retrieval into a flexible user interface. The creation of such image informatics tools is expected to have a significant impact on the science community and will accelerate the analysis and management of ever-growing image collections.

Projects @ Center for Bio-image informatics

Benchmark For Evaluating Biological Image Analysis Tools

We develop ongoing work on creating a benchmarking and validation dataset for biological image segmentation. The motivation for creating this resource comes from the observation that while there are a large number of effective segmentation methods available in the research literature, it is difficult for the scientists to make an informed choice as to what methods would work for their particular problems. No one single tool exists that is effective on a diverse set of application contexts and different methods have their own strengths and limitations. We describe three different classes of data, ranging in scale from subcellular to cellular to tissue level images, each of which pose their own set of challenges to image analysis.

E. D. Gelasca, J. Byun, B. Obara, and B. S. Manjunath, "Evaluation and benchmark for biological image segmentation," in IEEE International Conference on Image Processing, Oct 2008.

Thesis related projects

The primary motivation is to develop quantitative analysis and modeling methods of bio-molecular images, in particular retinal images, for characterizing patterns of cellular/subcellular protein distribution and changes in such patterns. We provide a quantitative understanding of mechanism behind vision loss and recovery after injury from the images through automated analysis and statistical modeling. These quantitative analyses provide opportunities to test therapeutic agents that may reduce the damaging effects of detachment or improve the outcome of reattachment surgery. Additionally, the detailed understanding leads us to develop new hypotheses.