Researchers have developed an AI-based diagnostic screening system called DeepGlioma that uses rapid imaging to analyze tumor samples taken during surgery and detect genetic mutations more quickly. In a study of more than 150 patients with diffuse glioma, the most common and deadly primary brain tumor, the newly developed system identified mutations used by the World Health Organization to define molecular subgroups of the disease with an average accuracy of over 90 percent.
The study was published in the journal “Nature Medicine” “This AI-based tool has the potential to improve the access and speed of diagnosis and care for patients with deadly brain tumors,” said lead author and creator of DeepGlioma Todd Hollon, M.D., a neurosurgeon at University of Michigan Health and an assistant professor. neurosurgery at the UM School of Medicine.
Brain Tumor Patients
Molecular classification is increasingly important for the diagnosis and treatment of gliomas, as the benefits and risks of surgery vary among brain tumor patients depending on their genetic make-up. In fact, patients with a specific type of diffuse glioma called astrocytomas can get an average of five years after the tumor is completely removed compared to other subtypes of diffuse gliomas.
However, access to molecular testing for diffuse glioma is limited and not uniformly available in centers that treat patients with brain tumors. When available, Hollon says, “the turnaround time for results can take days, even weeks, barriers to molecular diagnosis can lead to suboptimal care for patients with brain tumors, complicating surgical decision-making and selection of chemoradiation regimens”.
Before DeepGlioma, surgeons had no method to differentiate diffuse gliomas during surgery. An idea that began in 2019, the system combines deep neural networks with an optical imaging method known as stimulated Raman histology, also developed at UM, to image brain tumor tissue in real time.
He also says “DeepGlioma creates a pathway for accurate and timely identification that would give providers a better chance to define treatment and predict patient prognosis”.
Even with optimal standard treatment, patients with diffuse glioma have limited treatment options. The median survival time for patients with malignant diffuse gliomas is only 18 months. While the development of drugs to treat tumors is essential, less than 10% of glioma patients are enrolled in clinical trials, often limiting the participation of molecular subgroups. The researchers hope that DeepGlioma can be a catalyst for early enrollment in trials.
“Progress in the treatment of the deadliest brain tumors has been limited in recent decades in part because it has been difficult to identify patients who would benefit most from targeted therapy,” said lead author Daniel Orringer, M.D., associate professor of Neurosurgery and Pathology at the NYU Grossman School of Medicine, who developed stimulated Raman histology. “Rapid methods for molecular classification hold great promise for rethinking clinical trial design and bringing new therapies to patients.”
Read Now :<strong>All types of hormonal contraception can increase the risk of breast cancer</strong>