A knowledge -based framework for high-content screening of multi-modality biological imaging data
In recent years there has been a tremendous growth in the volume of biological imaging data owing to rapid advances in optical instrumentation, high-speed cameras, and fluorescent probes. Powerful semantic analysis tools are required to exploit the full potential of the information content of these data. Semantic analysis of multi-modality imaging data, however, poses unique challenges. Firstly, the analysis of these data sets requires flexible and extensible knowledge-based tools that can extract objective and quantitative semantic knowledge. Secondly, semantic interoperability requires knowledge representation formalisms that can be used for representation of the extracted semantic information. Thirdly, the high volume of such data requires a powerful computing infrastructure to meet the high-throughput analysis requirements of high-content screening data sets. None of the existing tools provides an integrated solution to these three requirements. ^ In this research we present an integrated framework for addressing all three dimensions of this problem. This framework provides a multi-layered architecture and spatio-temporal models for analysis of biological images. The analysis is divided into low-level and high-level processing. At the lower level, issues like segmentation, tracking, and object recognition are addressed, and at the higher level, finite state machine- and Petri net-based models are used for spatio-temporal event recognition. The proposed system provides high throughput through the use of grid technologies. The grid-enabled implementation comprises two levels of knowledge-based services. The first level provides tools for extracting spatio-temporal knowledge from image sets and the second level provides high-level knowledge management and reasoning services. Moreover, an XML-based language named cellular imaging markup language (CIML) has been developed for modeling of biological images and representation of spatio-temporal knowledge in a standard format. A research prototype of this framework has been developed and these tools have been applied to different biological problems. ^
Arif Ghafoor, Purdue University, Joseph P. Robinson, Purdue University.
Engineering, Electronics and Electrical
Off-Campus Purdue Users:
To access this dissertation, please log in to our