Projects

Glioblastoma progression and pseudoprogression biomarkers

This project develops a biomarker using early magnetic resonance imaging (MRI) to determine if early enhancement is due to tumor progression or treatment effects that mimic tumor progression. An accurate determination of true versus pseudoprogression is critical — effective therapy should continue during treatment, but if the tumor is progressing, second line agents can be beneficial.

Brain tumor change detection

This project focuses on changes in any pair of brain MRIs, allowing for better detection of early tumor progression. An accurate detection of progression permits early institution of therapy, which can improve outcome. According to Dr. Erickson, this algorithm is used routinely in practice and when combined with proper display methods, can improve accuracy.

Aneurysm detection

The purpose of this project is to highlight regions that are suspicious for intracranial aneurysm, which has an incidence of about 1 to 2 percent in the general population. A number of magnetic resonance angiography studies of the brain have been done for other purposes, but detection of unsuspected aneurysms is reported to be as low as 60 percent. Aneurysms that rupture cause death in about one-third of patients and significant morbidity in one-third of patients. Detection of an aneurysm that ruptures can allow for treatment. This disease frequently affects young people, so the economic and social impact is large. Researchers at the lab have developed an algorithm that has shown high sensitivity in aneurysm detection in the laboratory setting (more than 90 percent accuracy). The lab is now doing a clinical trial of its value.

Oligodendroglioma therapy response prediction

This project develops a biomarker using early MRI to predict the most effective way to treat low-grade gliomas such as oligodendroglioma. It is known that there are some visual patterns that tend to correlate with chromosomal abnormalities (for example, 1p19q chromosome deletion), which in turn, predict responsiveness to temozolomide and survival. The lab is in the early development stages of MRI-based tools to better predict chromosomal patterns and therapy responsiveness.

Image-sharing network

This project is part of a multisite National Institutes of Health contract to develop software that allows patients to get images from their health care facility and store them in a personal health record. From there, patients can send a link allowing any physician to view them, or the records can be sent to another hospital. Dr. Erickson and his team hope to demonstrate reduced duplication of imaging exams and more timely access to imaging.

Polycystic kidney disease biomarkers

This project develops efficient, clinically viable tools that allow estimation of prognosis and therapy planning. The efficient characterization of disease can allow for better assessment of disease state and measurement of the benefits of possible therapies. This is in the development stage.

Computer-Aided Lung Informatics for Pathology Evaluation and Rating (CALIPER)

This project quantifies and displays lung disease based on computerized tomography scans and allows objective and early reproducible assessment of lung disease at a single time point and over time. It is currently in the clinical evaluation stage.

Dicom-Enabled Workflow Engine System (DEWEY)

This project develops an infrastructure that enables efficient, reliable and flexible implementation of human and computer analytic tools into imaging departments. Workflows to support modern, multisite imaging departments are complex, and relying on humans to execute this workflow is inefficient and unreliable. Using workflow engines to supplement humans improves efficiency, reliability and quality of imaging departments.