Artificial intelligence predicts genetics of brain tumors in 90 seconds. « Medicine in the Library

Can Artificial Intelligence (AI) be used to predict brain tumors? Yes. AI can be trained using medical imaging data, such as magnetic resonance images, to identify any abnormalities in the structure of the brain that may indicate the presence of a tumor.

Furthermore, AI can also be used to analyze the genetic and molecular data associated with brain tumors, in order to identify any risk factors or biological markers that may suggest the presence of a tumor.

Now Michigan Medicine researchers, in collaboration with researchers at New York University, the University of California, San Francisco, have discovered how to screen for genetic mutations in cancerous brain tumors in less than 90 seconds with the potential to simplify diagnosis and treatment of gliomas.

The AI-based diagnostic screening system called DeepGlioma which uses rapid imaging to analyze tumor samples taken during an operation and detect genetic mutations faster.

“DeepGlioma creates an avenue for more timely and accurate identification that would give providers a better chance to define treatments and predict patient prognosis“, said Prof. Hollon.

Read abstract of the article:
Artificial-intelligence-based molecular classification of diffuse gliomas using rapid, label-free optical imaging.
Hollon , T. , Jiang , C. , Chowdury , A. et al.
Night With (2023).