Quantification of cervical spinal stenosis by automated 3D MRI segmentation of spinal cord and cerebrospinal fluid space

Abstract

Design: Prospective diagnostic study.

Objectives: Anatomical evaluation and graduation of the severity of spinal stenosis is essential in degenerative cervical spine disease. In clinical practice, this is subjectively categorized on cervical MRI lacking an objective and reliable classification. We implemented a fully-automated quantification of spinal canal compromise through 3D T2-weighted MRI segmentation.

Setting: Medical Center - University of Freiburg, Germany.

Methods: Evaluation of 202 participants receiving 3D T2-weighted MRI of the cervical spine. Segments C2/3 to C6/7 were analyzed for spinal cord and cerebrospinal fluid space volume through a fully-automated segmentation based on a trained deep convolutional neural network. Spinal canal narrowing was characterized by relative values, across sever segments as adapted Maximal Canal Compromise (aMCC), and within the index segment as adapted Spinal Cord Occupation Ratio (aSCOR). Additionally, all segments were subjectively categorized by three observers as "no", "relative" or "absolute" stenosis. Computed scores were applied on the subjective categorization.

Results: 798 (79.0%) segments were subjectively categorized as "no" stenosis, 85 (8.4%) as "relative" stenosis, and 127 (12.6%) as "absolute" stenosis. The calculated scores revealed significant differences between each category (p ≤ 0.001). Youden's Index analysis of ROC curves revealed optimal cut-offs to distinguish between "no" and "relative" stenosis for aMCC = 1.18 and aSCOR = 36.9%, and between "relative" and "absolute" stenosis for aMCC = 1.54 and aSCOR = 49.3%.

Conclusion: The presented fully-automated segmentation algorithm provides high diagnostic accuracy and objective classification of cervical spinal stenosis. The calculated cut-offs can be used for convenient radiological quantification of the severity of spinal canal compromise in clinical routine.

Fig. 1. Overview of the fully-automated evaluation procedure of an exemplary patient with cervical stenosis in C5/6.

A High-resolution 3D T2-weighted images. B Segmentation of spinal cord (yellow) and CSF space (green) with determination of the vertebral bodies from C2 to C7. C Calculation of CSF and spinal cord volumes at the middle third of each evaluated segment (white shaded rectangle). Right: Formula for aMCC (CSF space proportion of the index to both surrounding segments) and aSCOR (proportion of spinal cord and CSF space at the index segment) as objective parameters.

Fig. 2. Subjective categorization of cervical spinal stenosis.

Exemplary transverse T2-weighted images at level C5/6 for all three subjective stenosis categories: “no stenosis” = no degenerative elements contacting the spinal cord; “relative stenosis” = focal narrowing of the CSF space with contact to the spinal cord or circumferential narrowing with residual CSF signaling; “absolute stenosis” = absent CSF space with or without spinal cord volume reduction.

Fig. 3. Boxplots for aMCC and aSCOR values.

Comparison using Kruskal–Wallis test for independent samples revealed significant differences between all evaluated groups (p ≤ 0.05). The cut-offs between the groups (rectangle) were determined by ROC analysis and calculation of Youden’s Index.

Fig. 4. Boxplots for aMCC and aSCOR values separated for the different cervical levels: yellow = C3/4, red = C4/5, green = C5/6, blue = C6/7.

Level C2/3 is not depicted for clarity reasons, because of only two patients with a pathological affected segment. Absolute values and significance levels comparing the three subjective categories are added as Supplement 2.