Brain Scans Get a New Interpretation

Mathematical tools could help identify and treat mental disorders

By Martha McKenzie

math

Mario Wagner

Ying Guo

What if a brain scan could detect the presence of a mental disorder even before symptoms have emerged? Or predict which depressed patients will respond to a particular medication? Or determine the likely progression rate of Alzheimer’s?

Ying Guo is working to transform such aspirations into reality using math—really, really sophisticated math. Guo is director of Emory’s Center for Biomedical Imaging Statistics (CBIS), which drives research and ultimately clinical practice by developing specialized statistical techniques tailored for data collected through biomedical imaging studies.

The center collaborates with researchers who are trying to find the underlying brain anomalies of mental disorders, drug cravings, and other mysteries of the mind. Guo and the CBIS team provide the mathematical muscle, devising statistical models that can analyze the vast, cacophonous universe of data produced by sophisticated scanning technologies— sMRIs, fMRIs, and DW-MRIs—and distill the meaningful information. The ability to identify biosignatures in the brain could have widespread implications for the diagnosis and treatment of mental disorders.

Depression, schizophrenia, posttraumatic stress disorder, and other mental illnesses are traditionally diagnosed based on self-reporting or clinician-administered rating scales, which mostly rely on behavioral assessment and can result in inaccurate diagnosis. And since behavioral symptoms don’t always show up immediately, the disease can progress unnoticed in the early stages.

“When you scan someone with cancer, you can often see the tumor,” says Guo. “But with brain imaging, the raw data is hard to interpret directly, so we need to use statistical tools to help extract relevant information and translate it into results that can be visualized and interpreted. It’s sort of like a puzzle with millions of little pieces scattered in different locations. The only way we can put those pieces together to make a picture is by developing effective models and algorithms that can do it.”

Email the editor