This article was published in Dystonia Dialogue, Winter issue 2020 of DMRF (Dystonia Medical Research Foundation in the US), and we are happy to share it with our readers.
The article is about the recently published research using a new diagnostic tool diagnosing dystonia from MRI.
Researchers at Massachusetts Eye and Ear in Boston have developed a unique diagnostic tool that detects dystonia from MRI scans, the first technology of its kind to provide an objective diagnosis of the disorder.
In a newly published study, researchers developed an AI-based deep learning platform called Dystonia-Net to compare brain MRIs of 612 people, including 392 patients with three different forms of isolated focal dystonia and 220 healthy individuals. The platform diagnosed dystonia with an astonishing 98.8% accuracy. During the process, the researchers identified a microstructural neural network bio-marker for dystonia. With further testing and validation, it may be possible for DystoniaNet to be implemented by movement disorder clinics to make high probability diagnosis of dystonia by MRI. In such cases a physician will be able to use this information to more confidently and quickly confirm the diagnosis and recommend treatment without delay.
“There is currently no biomarker of dystonia and no ‘gold standard’ test for its diagnosis. Because of this, many patients have to undergo unnecessary procedures and see different specialists until other diseases are ruled out and the diagnosis of dystonia is established,” said senior study author Kristina Simonyan, MD, PhD, Dr med, Director of Laryngology Research at Mass Eye and Ear, Associate Neuroscientist at Massachusetts General Hospital, and Associate Professor of Otolaryngology–Head and Neck Surgery at Harvard Medical School. “There is a critical need to develop, validate, and incorporate objective testing tools for the diagnosis of this neurological condition, and our results show that DystoniaNet may fill this gap.” Dr. Simonyan is a former member of the DMRF Medical & Scientific Advisory Council.
The study included three of the most common types of focal dystonia: laryngeal dystonia, characterized by involuntary movements of the vocal cords that can cause difficulties with speech (also called spasmodic dysphonia); cervical dystonia, which causes the neck muscles to spasm and abnormal movements and postures in the neck; and blepharospasm, a focal dystonia of the eyelids that causes involuntary blinking and/or forceful eye closure.
Traditionally, a dystonia diagnosis is made based on tedious clinical observations. Previous studies have found that about 50% of cases go misdiagnosed or underdiagnosed at a first patient visit.
DystoniaNet utilizes deep learning, a particular type of AI algorithm, to analyze data from individual MRI and identify subtler differences in brain structure. The platform simultaneously detects clusters of abnormal structures in several regions of the brain that are known to control processing and motor commands. These small changes cannot be seen by a naked eye in MRI, and the patterns are only evident through the platform’s ability to take 3D brain images and zoom into their microstructural details.
DystoniaNet is a patent-pending proprietary platform trained using Amazon Web Services computational cloud platform. The technology interprets an MRI scan for microstructural biomarker in 0.36 seconds.
Future studies are needed to examine additional types of dystonia and will require trials at multiple clinics and hospitals to further validate the DystonaNet platform in a larger number of patients.
Valeriani D, Simonyan K. A microstructural neural network biomarker for dystonia diagnosis identified by a Dystonia-Net deep learning platform. Proc Natl Acad Sci U S A. 2020 Oct 20;117(42):26398-26405.
