Automated Segmentation of Spinal Muscles From Upright Open MRI Using a Multiscale Pyramid 2D Convolutional Neural Network.

STUDY DESIGN: Randomized trial. OBJECTIVE: To implement an algorithm enabling the automated segmentation of spinal muscles from open magnetic resonance images in healthy volunteers and patients with adult spinal deformity (ASD). SUMMARY OF BACKGROUND DATA: Understanding spinal muscle anatomy is critical to diagnosing and treating spinal deformity.Muscle boundaries can be extrapolated from medical images using segmentation, which is usually done manually by clinical experts and remains complicated and time-consuming. METHODS: Three groups were examined: two healthy volunteer groups (N = 6 for each group) and one ASD group (N = 8 patients) were imaged at the lumbar and thoracic regions of the spine in an upright open magnetic resonance imaging scanner while maintaining different postures (various seated, standing, and supine). For each group and region, a selection of regions of interest (ROIs) was manually segmented. A multiscale pyramid two-dimensional convolutional neural network was implemented to automatically segment all defined ROIs. A five-fold crossvalidation method was applied and distinct models were trained for each resulting set and group and evaluated using Dice coefficients calculated between the model output and the manually segmented target. RESULTS: Good to excellent results were found across all ROIs for the ASD (Dice coefficient >0.76) and healthy (dice coefficient > 0.86) groups. CONCLUSION: This study represents a fundamental step toward the development of an automated spinal muscle properties extraction pipeline, which will ultimately allow clinicians to have easier access to patient-specific simulations, diagnosis, and treatment.

Estimation and assessment of sagittal spinal curvature and thoracic muscle morphometry in different postures.

Spine models are typically developed from supine clinical imaging data, and hence clearly do not fully reflect postures that replicate subjects' clinical symptoms. Our objectives were to develop a method to: (i) estimate the subject-specific sagittal curvature of the whole spine in different postures from limited imaging data, (ii) obtain muscle lines-of-action in different postures and analyze the effect of posture on muscle fascicle length, and (iii) correct for cosine between the magnetic resonance imaging (MRI) scan plane and dominant fiber line-of-action for muscle parameters (cross-sectional area (CSA) and position). The thoracic spines of six healthy volunteers were scanned in four postures (supine, standing, flexion, and sitting) in an upright MRI. Geometry of the sagittal spine was approximated with a circular spline. A pipeline was developed to estimate spine geometry in different postures and was validated. The lines-of-action for two muscles, erector spinae (ES) and transversospinalis (TS) were obtained for every posture and hence muscle fascicle lengths were computed. A correction factor based on published literature was then computed and applied to the muscle parameters. The maximum registration error between the estimated spine geometry and MRI data was small (average RMSE∼1.2%). The muscle fascicle length increased (up to 20%) in flexion when compared to erect postures. The correction factor reduced muscle parameters (∼5% for ES and ∼25% for TS) when compared to raw MRI data. The proposed pipeline is a preliminary step in subject-specific modeling. Direction cosines of muscles could be used while improving the inputs of spine models.

Preliminary investigation of spinal level and postural effects on thoracic muscle morphology with upright open MRI.

OBJECTIVE: Spinal-muscle morphological differences between weight-bearing and supine postures have potential diagnostic, prognostic, and therapeutic applications. While the focus to date has been on cervical and lumbar regions, recent findings have associated spinal deformity with smaller paraspinal musculature in the thoracic region. We aim to quantitatively investigate the morphology of trapezius (TZ), erector spinae (ES) and transversospinalis (TS) muscles in upright postures with open upright MRI and also determine the effect of level and posture on the morphological measures. METHODS: Six healthy volunteers (age 26 ± 6 years) were imaged (0.5 T MROpen, Paramed, Genoa, Italy) in four postures (supine, standing, standing with 30° flexion, and sitting). Two regions of the thorax, middle (T4-T5), and lower (T8-T9), were scanned separately for each posture. 2D muscle parameters such as cross-sectional area (CSA) and position (radius and angle) with respect to the vertebral body centroid were measured for the three muscles. Effect of spinal level and posture on muscle parameters was examined using 2-way repeated measures ANOVA separately for T4-T5 and T8-T9 regions. RESULTS: The TZ CSA was smaller (40%, P = .0027) at T9 than at T8. The ES CSA was larger at T5 than at T4 (12%, P = .0048) and at T9 than at T8 (10%, P = .0018). TS CSA showed opposite trends at the two spinal regions with it being smaller (16%, P = .0047) at T5 than at T4 and larger (11%, P = .0009) at T9 than at T8. At T4-T5, the TZ CSA increased (up to 23%), and the ES and TS CSA decreased (up to 10%) in upright postures compared to supine. CONCLUSION: Geometrical parameters that describe muscle morphology in the thorax change with level and posture. The increase in TZ CSA in upright postures could result from greater activation while upright. The decrease in ES CSA in flexed positions likely represents passive stretching compared to neutral posture.

Quantitative identification and segmentation repeatability of thoracic spinal muscle morphology.

OBJECTIVE: MRI derived spinal-muscle morphology measurements have potential diagnostic, prognostic, and therapeutic applications in spinal health. Muscle morphology in the thoracic spine is an important determinant of kyphosis severity in older adults. However, the literature on quantification of spinal muscles to date has been limited to cervical and lumbar regions. Hence, we aim to propose a method to quantitatively identify regions of interest of thoracic spinal muscle in axial MR images and investigate the repeatability of their measurements. METHODS: Middle (T4-T5) and lower (T8-T9) thoracic levels of six healthy volunteers (age 26 ± 6 years) were imaged in an upright open scanner (0.5T MROpen, Paramed, Genoa, Italy). A descriptive methodology for defining the regions of interest of trapezius, erector spinae, and transversospinalis in axial MR images was developed. The guidelines for segmentation are laid out based on the points of origin and insertion, probable size, shape, and the position of the muscle groups relative to other recognizable anatomical landmarks as seen from typical axial MR images. 2D parameters such as muscle cross-sectional area (CSA) and muscle position (radius and angle) with respect to the vertebral body centroid were computed and 3D muscle geometries were generated. Intra and inter-rater segmentation repeatability was assessed with intraclass correlation coefficient (ICC (3,1)) for 2D parameters and with dice coefficient (DC) for 3D parameters. RESULTS: Intra and inter-rater repeatability for 2D and 3D parameters for all muscles was generally good/excellent (average ICC (3,1) = 0.9 with ranges of 0.56-0.98; average DC = 0.92 with ranges from 0.85-0.95). CONCLUSION: The guidelines proposed are important for reliable MRI-based measurements and allow meaningful comparisons of muscle morphometry in the thoracic spine across different studies globally. Good segmentation repeatability suggests we can further investigate the effect of posture and spinal curvature on muscle morphology in the thoracic spine.