Brain cancer is a misleading term for what turns out to be a group of more than 120 distinct types of tumors. A glioblastoma, a type of glioma tumor, can double in size within two weeks: it’s the deadliest form of brain cancer. The life expectancy of those with such tumors is just eight months.

To formulate the best treatment plan and maximize the potential for a positive outcome, neurosurgeons need to identify which genetic mutations are present in a tumor. But that analysis, currently done by testing a tumor biopsy for biomarkers, can take a month or longer, delaying surgery and other forms of treatment.

“It really is hard for clinicians and patients to wrap our heads around that waiting period,” Daniel A. Orringer, MD, associate professor in the Departments of Neurosurgery and Pathology, tells NBC News Now. Dr. Orringer is also a member of the neurosurgery program at NYU Langone’s Brain and Spine Tumor Center, part of the Laura and Isaac Perlmutter Cancer Center.

To expedite diagnosis, Dr. Orringer has developed a device that uses advanced imaging techniques and artificial intelligence to predict a tumor’s genetic makeup. The process takes just three minutes. So far, his research has found the results to be 93 percent as accurate as the current methodology.

The device, called DeepGlioma, is currently in clinical trials. If it receives U.S. Food and Drug Administration (FDA) approval, it could one day be broadly adopted to help diagnose brain cancer and other types of cancer faster—a potential game changer.

“Time is so meaningful in the face of a terminal diagnosis,” says Dr. Orringer.

Watch more on NBC News Now.