The Radiological Society of North America (RSNA) recently published a review article, "Emerging Perspectives on MRI Application in Multiple Sclerosis: Moving from Pathophysiology to Clinical Practice", led by the multiple sclerosis research group in Milan and with the collaboration of Arman Eshaghi from Queen Square Institute of Neurology and Queen Square Analytics, discusses the role of Magnetic Resonance Imaging (MRI) in diagnosing and monitoring Multiple Sclerosis (MS), a disease that affects the brain and spinal cord.
Advanced MRI techniques have helped improve the accuracy of MS diagnosis and have provided a deeper understanding of how the disease progresses. These techniques have also led to the discovery of potential MRI markers that could be useful in clinical practice, although their importance and validity still need to be confirmed.
The article highlights five emerging perspectives on the use of MRI in MS:
The possibility of using non-invasive MRI-based methods to measure the function of the glymphatic system (the brain's waste clearance system) and its impairment.
The use of the ratio of T1-weighted to T2-weighted intensity to quantify the content of myelin (a substance that protects nerve fibers) in the brain.
The classification of MS types based on their MRI features rather than their clinical symptoms.AI, particularly machine learning, can be used to analyze large amounts of data and identify patterns that may not be easily discernible to humans. In the context of MS, AI could be used to analyze MRI scans and identify unique patterns or features associated with different disease subtypes. This could lead to more accurate prognostication of outcomes and personalized treatment plans based on the specific subtype of MS a patient has.
The clinical significance of the shrinkage of gray matter (areas of the brain involved in muscle control, sensory perception, and decision making) versus white matter (areas of the brain that transmit signals) in the brain.
The comparison of time-varying versus static resting-state functional connectivity in evaluating the organization of brain function.