New AI tool could expedite treatment decisions for glioblastoma patients
A team of experts at the University of Virginia School of Medicine has developed an artificial intelligence-enabled imaging solution that could improve the treatment of aggressive brain cancers.
The method utilizes findings from PET/MR imaging to differentiate between changes in tissue owed to treatment versus tumor progression. Experts involved in its development are hopeful their method could improve outcomes by enabling providers to adjust treatment plans sooner.
“Early distinction would enable earlier treatment modifications for tumor recurrence in brain cancer patients,” David Schiff, MD, part of UVA’s Departments of Neurology, Neurosurgery and Medicine, said in a statement.
Glioblastoma is an extremely aggressive form of brain cancer that progresses quickly. It is treated with a myriad of methods, including surgery, radiation therapy and chemotherapy. Given its ability to grow rapidly, it is critical for providers to make timely treatment decisions. However, current methods of monitoring treatment effectiveness require a waiting period of three or more months.
This latest method uses deep learning techniques to analyze PET/MR data in detail humans are incapable of visualizing themselves. Researchers put their model to the test recently during an analysis of 26 patients who had been diagnosed with glioblastoma. The team’s AI correctly distinguished between brain changes owed to treatment responses versus cancer progression in 74% of cases, outperforming the current standard of care.
The next step is to train the tool on more patient data, with the goal of increasing its accuracy to 80%, Bijoy Kundu, PhD, of UVA Health’s Department of Radiology and Medical Imaging, noted.
“We hope this work helps patients and families get answers faster. If our AI can give doctors more confidence earlier, it could mean quicker treatment decisions and better outcomes,” Kundu said. “Our goal is to give doctors better tools, so they can focus less on guesswork and more on care. We’re still in the early stages, but even now, our approach is showing real promise. We’re working toward a future where patients get clarity sooner, and where that clarity helps save lives.”
In addition to her background in journalism, Hannah also has patient-facing experience in clinical settings, having spent more than 12 years working as a registered rad tech. She began covering the medical imaging industry for Innovate Healthcare in 2021.