NYU Langone’s Department of Neurosurgery Leverages Its Vast Repository of MRI Images to Help Advance the Scientific Understanding of Metastatic Brain Cancer
Metastatic brain cancer is a notorious shape-shifter. “Almost all tumors respond to treatment, but there’s a lot of variability in how they change,” notes neurosurgeon Douglas Kondziolka, MD. The process by which cancer spreads is a dynamic one, he explains, and new mutations can arise randomly or in response to treatments. This natural bias for evasion makes it hard to track brain cancer’s stealthy evolution—clinically, molecularly, and genetically.
Keeping up with it calls for extraordinary vision and speed. In short, it calls for artificial intelligence (AI). NYU Langone Health’s Department of Neurosurgery, ranked No. 1 in the nation, has long been at the forefront of applying AI to solve tough clinical problems. It only made sense for Dr. Kondziolka, vice chair of clinical research in the Department of Neurosurgery, to team up with fellow neurosurgeon Eric K. Oermann, MD, an AI expert and Google alum, to tap the full power of AI to advance the scientific understanding of metastatic brain cancer.
Together, the neurosurgeons have debuted the world’s largest public database of brain tumor images. Along with a suite of AI tools to help scientists mine the images for meaning, the database will help clinicians map disease progression in real time and assess individual responses to treatment. “For the first time,” says Dr. Oermann, “scientists anywhere will be able to apply computational tools developed from this database for clinical purposes.”
The project, called NYUMets for “NYU metastases,” launched publicly last fall, but it began much earlier. Dr. Kondziolka arrived at NYU Langone a decade ago to head the Center for Advanced Radiosurgery, where gamma radiation is used to treat brain tumors, blood vessel malformations, and functional disorders. Soon he started cataloging the brain scans of his patients and the de-identified clinical data that accompanies them. The repository now contains more than 20,000 image sequences, drawn from 8,003 MRI studies of 1,429 patients. Add the power of AI and the database transforms from an image catalog to a think tank for neurosurgeons and brain cancer researchers. For example, Dr. Kondziolka and Dr. Oermann have collaborated with research scientist Katherine Link to develop a state-of-the-art algorithm for detecting small tumors.
“What makes this database so powerful is its size,” explains Dr. Kondziolka. Traditionally, therapeutic regimens are guided in large part by the published results of evidence-based clinical trials. Dr. Kondziolka notes, however, that the findings of such trials may be limited, due to the size or composition of the patient sample, or other factors. “We do our best to assess how tumors grow or shrink over time,” he says. “But we’re left to wonder: Did the tumor shrink by 17 percent or 75 percent? Did drug X make it shrink more than drug Y? Was radiation more effective than drug X? None of these things are very clear.”
NYUMets was built to deliver answers, and along the way close the gap between AI and neurosurgery. “We need to fundamentally rethink how we approach cancer analytics,” says Dr. Oermann. “Our goal is to encourage computational scientists to start thinking about cancer the way clinicians do—not as an independent entity, but as a disease someone lives with over time.”
NYUMets is a collaboration between NYU Langone’s Departments of Neurosurgery, Radiology, and Radiation Oncology; Perlmutter Cancer Center; the NYU Center for Data Science; and the Center for Advanced Imaging Innovation and Research.
About Our Team
NYU Langone’s Department of Neurosurgery is ranked No. 1 in the country on U.S. News & World Report’s influential “Best Hospitals Honor Roll” for 2022–23. Vizient, Inc., the nation’s largest member-driven healthcare performance improvement company, has rated the department No. 1 in the United States for its ability to lead patients who experience clinical complications to a full recovery.