Cervical spondylotic myelopathy (CSM) is a chronic disorder of the spinal cord. ROI-based features on diffusion tensor imaging (DTI) provide additional information about spinal cord status, which would benefit the diagnosis and prognosis of CSM. However, the manual extraction of the DTI-related features on multiple ROIs is time-consuming and laborious. In total, 1159 slices at cervical levels from 89 CSM patients were analyzed, and corresponding fractional anisotropy (FA) maps were calculated. Eight ROIs were drawn, covering both sides of lateral, dorsal, ventral, and gray matter. The UNet model was trained with the proposed heatmap distance loss for auto-segmentation. Mean Dice coefficients on the test dataset for dorsal, lateral, and ventral column and gray matter were 0.69, 0.67, 0.57, 0.54 on the left side and 0.68, 0.67, 0.59, 0.55 on the right side. The ROI-based mean FA value based on segmentation model strongly correlated with the value based on manual drawing. The percentages of the mean absolute error between the two values of multiple ROIs were 0.07, 0.07, 0.11, and 0.08 on the left side and 0.07, 0.1, 0.1, 0.11, and 0.07 on the right side. The proposed segmentation model has the potential to offer a more detailed spinal cord segmentation and would be beneficial for quantifying a more detailed status of the cervical spinal cord.

The progression and remission of cervical spondylotic myelopathy (CSM) are quite unpredictable due to the ambiguous pathomechanisms. Spontaneous functional recovery (SFR) has been commonly implicated in the natural course of incomplete acute spinal cord injury (SCI), while the evidence and underlying pathomechanisms of neurovascular unit (NVU) compensation involved in SFR remains poorly understood in CSM. In this study, we investigate whether compensatory change of NVU, in particular in the adjacent level of the compressive epicenter, is involved in the natural course of SFR, using an established experimental CSM model. Chronic compression was created by an expandable water-absorbing polyurethane polymer at C5 level. Neurological function was dynamically assessed by BBB scoring and somatosensory evoked potential (SEP) up to 2 months. (Ultra)pathological features of NVUs were presented by histopathological and TEM examination. Quantitative analysis of regional vascular profile area/number (RVPA/RVPN) and neuroglial cells numbers were based on the specific EBA immunoreactivity and neuroglial biomarkers, respectively. Functional integrity of blood spinal cord barrier (BSCB) was detected by Evan blue extravasation test. Although destruction of the NVU, including disruption of the BSCB, neuronal degeneration and axon demyelination, as well as dramatic neuroglia reaction, were found in the compressive epicenter and spontaneous locomotor and sensory function recovery were verified in the modeling rats. In particular, restoration of BSCB permeability and an evident increase in RVPA with wrapping proliferated astrocytic endfeet in gray matter and neuron survival and synaptic plasticity were confirmed in the adjacent level. TEM findings also proved ultrastructural restoration of the NVU. Thus, NVU compensation changes in the adjacent level may be one of the essential pathomechanisms of SFR in CSM, which could be a promising endogenous target for neurorestoration.