DeepGlioma: A Revolutionary AI-Based Diagnostic Screening System for Rapid Molecular Characterization of Gliomas
A team of neurosurgeons and engineers at Michigan Medicine at the University of Michigan, in collaboration with investigators from New York University, University of California, San Francisco and others, have developed an AI-based diagnostic screening system called DeepGlioma that uses rapid imaging to analyze tumor specimens taken during an operation and detect genetic mutations more rapidly.[0] The system was tested on a group of more than 150 patients with diffuse glioma—the most common and deadly brain tumor—and was able to define the molecular subgroups of the patients as defined by the World Health Organization.[1] DeepGlioma achieved an accuracy rate of over 90% in this context.[1]
The genetic composition of brain tumor patients plays a significant role in determining the advantages and disadvantages of surgical procedures, making molecular classification crucial for the diagnosis and management of gliomas. Patients diagnosed with astrocytomas, a particular form of diffuse glioma, can extend their lifespan by five years on average if they undergo complete removal of the tumor when compared to other subtypes of diffuse glioma.[2]
The researchers noted that molecular testing for brain tumors isn’t widely available and may also take days or weeks to return results. In contrast, the DeepGlioma system aims to churn out molecular analyses in less than two minutes, helping medical care providers to be more accurate in identifying the type of brain tumor.[0]
Lead author and creator of DeepGlioma Todd Hollon, MD, a neurosurgeon at University of Michigan Health and assistant professor of neurosurgery at U-M Medical School, said, “DeepGlioma creates an avenue for accurate and more timely identification that would give providers a better chance to define treatments and predict patient prognosis.”[2] At present, there are limited choices to identify the category of brain tumor.
Patients diagnosed with diffuse glioma have limited treatment options despite receiving the best standard-of-care treatment available.[3] Patients diagnosed with malignant diffuse gliomas have a median survival time of merely 18 months.[0] According to Hollon, hindrances in molecular diagnosis may lead to inadequate treatment for individuals with brain tumors, making surgical decision-making and the choice of chemoradiation regimens more complex.
The research team hopes that DeepGlioma can become a tool to advance the treatment of the deadly disease, noting that even patients who receive standard of care have few treatment options. Although the creation of drugs to cure tumors is crucial, only a meager percentage of glioma patients, less than 10%, join clinical trials, which frequently restrict participation based on molecular subcategories.[3] The researchers aspire for DeepGlioma to serve as a driving force for timely enrollment in clinical trials.
“Progress in the treatment of the most deadly brain tumors has been limited in the past decades. In part because it has been hard to identify the patients who would benefit most from targeted therapies,” said senior author Daniel Orringer, MD, an associate professor of neurosurgery and pathology at NYU Grossman School of Medicine, who developed stimulated Raman histology. The potential of swift techniques in molecular classification is enormous as it can revolutionize the design of clinical trials and introduce innovative treatments to patients.[3]
In conclusion, the development of a fast method to molecularly characterize gliomas is gaining in importance as it allows surgeons to identify the risks and benefits of surgery for each patient depending on their genetic makeup. The DeepGlioma may serve as a solution to the problem of limited availability of molecular testing for diffuse gliomas in certain cancer centers, and the time-consuming nature of current testing which can take weeks for the results to be obtained. The hope is that DeepGlioma can be a catalyst for early trial enrollment and bring new therapies to patients.
0. “DeepGlioma AI classifies brain tumors within 90 seconds: study” FierceBiotech, 27 Mar. 2023, https://www.fiercebiotech.com/medtech/deepglioma-ai-classifies-brain-tumors-within-90-seconds-and-93-accuracy-study-finds
1. “Rapid Imaging Plus AI Detect Brain Cancer Mutations in under 90 Seconds” Inside Precision Medicine, 24 Mar. 2023, https://www.insideprecisionmedicine.com/topics/oncology/brain-cancer/rapid-imaging-plus-ai-detect-brain-cancer-mutations-in-under-90-seconds
2. “Scientists Develop AI to Predict Genetics of Cancerous Brain Tumors | HealthNews” Healthnews.com, 27 Mar. 2023, https://healthnews.com/news/scientists-develop-ai-to-predict-genetics-of-cancerous-brain-tumors/
3. “Artificial intelligence predicts genetics of cancerous brain tumors in under 90 seconds” Medical Xpress, 23 Mar. 2023, https://medicalxpress.com/news/2023-03-artificial-intelligence-genetics-cancerous-brain.html
