Funded Research Projects
-
Scalable Automated Brain Tumor Segmentation:
Brain tumor segmentation in Magnetic Resonance Imaging is an
important task for neurosurgeons, oncologists, and radiologists
to assess disease burden and measure tumor response to
treatment. In 2008, over 237,000 individuals worldwide are
estimated to have been diagnosed with malignant brain and
central nervous system tumors with over 174,000 deaths.
Detection of brain tumors with the exact location and
orientation is extremely important for effective diagnosis,
treatment planning, and analysis of treatment effectiveness;
however, manual delineation of the tumor takes considerable time
and is prone to error and wide variability. The overall goal of
this proposal is to develop a scalable and automated approach
for the segmentation of brain tumors based on Hidden Markov
Models (HMMs). The objectives of the project are: 1) Develop a
tumor segmentation approach based on a novel utilization of HMMs
for automated segmentation of multi-sequence brain MRI data for
accurate and robust determination of tumor volume; 2) Design a
MapReduce model for the HMM-based brain tumor segmentation
approach to enable scalable development of the segmentation
processes in a cluster environment; 3) Evaluate the HMM-based
brain tumor segmentation framework in terms of accuracy,
robustness, and performance in the context of multi-sequence MRI
data.
-
Data Mining Software for Large-Scale Analyses of Infections Caused by Hepatitis Viruses:
The goal of this project is to develop data mining software that
extracts, transforms, and loads structured data relating to
infection with hepatitis viruses from diverse sources into a
warehouse appropriate for mainframe, client/server, and PC
platforms. This data will include but may not be limited to
demographic, clinical, epidemiological, laboratory and
phylogenetic information. The software will store and manage the
data in a data warehouse system with a web-based interface to provide data access to the scientific community and analysis of relationships in the stored data using end-user defined queries to discover disease patterns and trends. It is expected that the software will generate associations between epidemiological and laboratory data leading to the discovery of new disease patterns, epidemiological trends and proteomic associations. Such discoveries are expected to lead to new strategies for public health interventions, surveillance, prophylaxis and the development of antivirals and vaccines. This software tool will be applicable not only to hepatitis viruses but other pathogens in the areas of epidemiology, laboratory research and public health.
-
Information Integration of Heterogeneous Data Sources: Development of an information
integration solution to provide a common interaction environment
to query data and knowledge from multiple heterogeneous sources.
Based on the latest Semantic Web technologies, it utilizes ontologies to address the integrated querying of sources of
knowledge and information relevant to investigations of
genotype-phenotype associations and to the identification of
genes responsible for human diseases and conditions. [NIH
RePORTER]
-
Semantic Data Integration for Integrative Cancer Biology Research: Development of a mechanism to
formulate a coherent ontological view of caBIG semantics in
order to perform ontology-based queries using the SPARQL query
language over distributed caBIG-compatible data services. [NIH
RePORTER]
-
Automated Development of Electronic Data Capture for Clinical Trials: Development of a set of
graphical tools and automated software applications to simplify,
automate, standardize, and reduce the cost of creating and
reporting clinical research instruments used in substance abuse
trials. [NIH
RePORTER]
-
Administration and Management of Portable Electronic Forms in Clinical Environments (eForms): Development of a
next-generation system for the development, administration and
exchange of portable electronic clinical forms using XML and
highly mobile platforms such as laptops and tablet computers.
The product that resulted from this project is currently
marketed under the name Aspect.
-
Integrated and Distributed Clinical Trials:
Development and implementation of an electronic
clinical trials system, an integrated clinical trial development
and distributed administration framework to reduce the cost and
increase the efficiency of creating and administering clinical
trials. This system has recently been launched in the market
with the name Aspect Trials.
-
A Mobile Clinical Trials Data Collection System:
Development of mechanisms for the efficient and timely
electronic capture of cancer clinical trials’ data using mobile
handheld devices at the point of participant contact. The Mobile
Clinical Trials Data Collection System interfaces directly with
a clinical trial data management system (CDMS), and supports the
CDISC ODM standard.
|
|