Previous Page  |  Table of Contents  |  Next Page

Guillermo Sapiro, Principal Investigator

Partial Differential Equation Based Biomedical Imaging in a Windows Environment

Figure 1: Detecting a skin lesion in a hairy image

Figure 2: Automatic removal of text from a digital image.

Research Group

Marcelo Bertalmio, Research Associate
Do Hyun Chung, Research Associate
Uma Ramamurthy, Graduate Student Researcher

This project is concerned with the development of advanced computerized tools to assist in the analysis and visualization of biomedical digital images. This researcher is investigating and using advanced mathematical techniques in the areas of partial differential equations and differential geometry, and together with state-of-the-art numerical algorithms, study and development is being done for image processing and visualization algorithms that are fast, accurate, and reliable. Areas of application include segmentation of magnetic resonance imaging and ultrasound, analysis and visualization of functional magnetic resonance imaging, and analysis of images from electronic microscopy. Part of this research is performed in collaboration with different radiology departments. Many of the algorithms are universal and can be adapted to other imaging modalities like SAR and digital photography.

The family of algorithms being developed were once considered to be too computationally expensive for personal computers. With the incredible improvement in hardware and software, this is not true anymore. All of this projectÕs research is currently being migrated to personal computers. This makes the results more accessible and makes personal computers more digital-imaging oriented. An IBM Intellistation, provided by the Supercomputing Institute through the IBM Shared University Research Award Program, is helping to achieve this goal. In addition, the user interface part of the system is being extended to JAVA. A PC-based JAVA server is supporting this. By putting this system on the Internet, immediate delivery of new developments can be achieved, and the results will be easier to use both by professionals and by consumers that want to apply advanced image processing tools to their digital images.

This information is available in alternative formats upon request by individuals with disabilities. Please send email to alt-format@msi.umn.edu or call 612-624-0528.

HOME | QUESTIONS | FEEDBACK
Employment | Events | Links | People | Programs | Publications | Support | Welcome