Diffusion basis spectrum imaging identifies clinically relevant disease phenotypes of cervical spondylotic myelopathy

This study uses an advanced imaging technique called diffusion basis spectrum imaging (DBSI) to examine the spinal cords of patients with cervical spondylotic myelopathy (CSM). DBSI can provide detailed measurements of white matter injury. The study applied a machine learning algorithm (k-means clustering) to the DBSI data to identify different types of CSM patients based on their imaging characteristics. The goal was to see if imaging could help differentiate patients with varying degrees of disease. The researchers found three distinct groups of CSM patients based on their DBSI data. These groups differed in terms of clinical symptoms, quality of life, and specific imaging markers related to spinal cord damage and swelling.

• 1
  The study identified three distinct clusters of CSM patients based on DBSI metrics using k-means clustering.
• 2
  Cluster 3, characterized by worse neurofunctional status and quality-of-life, also possessed significantly higher intra-axonal axial diffusivity and extra-axonal fraction values, indicative of vasogenic edema.
• 3
  Inclusion of control patients in the k-means clustering revealed that a significant portion of mild CSM patients clustered with healthy controls, suggesting potentially less severe or reversible spinal cord damage in this subgroup.