Scientists at the University of Virginia Medicine School exploit the power of artificial intelligence to improve and speed up the treatment of glioblastoma, the deadliest brain cancer.
The UVA researcher, Bijoy Kundu, PHD, and colleagues develop an AI imaging approach to distinguish tumor progression and brain changes caused by tumor treatment. This can now take months to make this distinction, leaving uncertain doctors if the tumor develops and blocks significant care decisions.
The KUNDU AI approach already surpasses the standard clinical option in initial tests. Tested in 26 glioblastoma patients immediately after treatment, artificial intelligence was able to distinguish correct 74% of the time.
The objective of the project is to train on additional patient data and increase this precision by more than 80% for clinical use. “”
Bijoy Kundu, PhD, UVA Cancer Center, Uva Health’s Department of Radiology and Medical Imaging and UVA’s Department of Biomedical Engineering
This could have real advantages for patients. “The early distinction would allow previous changes in treatment for tumor recurrence in patients with brain cancer,” said David Schiff, MD, who is part of the departments of neurology, neurosurgery and UVA medicine. Schiff is also co-director of the UVA Health Neuro-Oncology Center.
Best glioblastoma treatments
The glioblastoma is more than half of all primary brain tumors. This is very aggressive and rapid cancer – rapidly diagnosed -typical survival is only 15 months. This makes it extremely important that doctors act quickly. This can prolong the survival time and improve the quality of life of patients.
Now, however, doctors must wait three to four months after treatment to assess the progression of the tumor. They do it using magnetic resonance imaging (MRI) or, in some cases, brain surgery.
Kundu’s approach combines MRI with another form of imaging, Dynamic PET (positrons emission tomography). This produces sophisticated and multidimensional views inside the brain that artificial intelligence can analyze – everything without needing to cut inside the skull.
Kundu and his employees received $ 90,000 from the Ivy Biomedical Innovation fund from UVA to advance and refine their approach. They will use money to improve the accuracy of their in -depth learning algorithms, essentially teaching AI to better distinguish signs of tumor progression and the effects of chemotherapy and radiotherapy.
They hope that their work will ultimately help doctors get the information they need earlier, improving care for glioblastoma patients.
“We hope this work helps patients and families get answers faster. If our AI can give more confidence to doctors earlier, it could mean faster treatment decisions and better results, “Kundu said. “Our goal is to give doctors better tools, so that they can focus less on assumptions and more on care. We are still in the early stages, but even now our approach shows a real promise. We are working on a future where patients become earlier and this clarity helps save lives. »»
UVA Cancer Search
Finding new ways to improve patient care is a central mission of UVA Cancer Center and Paul and Diane Manning Institute of Biotechnology in UVA. UVA Cancer Center is one of the 57 cancer centers in the country designated “complete” by the National Cancer Institute for their exceptional care for patients and research on advanced cancer.
The Manning Institute, on the other hand, has been launched to accelerate the development of new treatments and remedies for the most difficult diseases. This will be supplemented by a network of clinical trials at the level of the State which widens access to new potential treatments as they are developed and tested.
The Department of Biomedical Engineering of UVA is a joint program of the School of Medicine and the Applied Engineering and Sciences School.
