Nejvíce citovaný článek - PubMed ID 35371944
Semi-automated detection of cervical spinal cord compression with the Spinal Cord Toolbox
Morphometric measures derived from spinal cord segmentations can serve as diagnostic and prognostic biomarkers in neurological diseases and injuries affecting the spinal cord. For instance, the spinal cord cross-sectional area can be used to monitor cord atrophy in multiple sclerosis and to characterize compression in degenerative cervical myelopathy. While robust, automatic segmentation methods to a wide variety of contrasts and pathologies have been developed over the past few years, whether their predictions are stable as the model is updated using new datasets has not been assessed. This is particularly important for deriving normative values from healthy participants. In this study, we present a spinal cord segmentation model trained on a multisite (n=75) dataset, including 9 different MRI contrasts and several spinal cord pathologies. We also introduce a lifelong learning framework to automatically monitor the morphometric drift as the model is updated using additional datasets. The framework is triggered by an automatic GitHub Actions workflow every time a new model is created, recording the morphometric values derived from the model's predictions over time. As a real-world application of the proposed framework, we employed the spinal cord segmentation model to update a recently-introduced normative database of healthy participants containing commonly used measures of spinal cord morphometry. Results showed that: (i) our model performs well compared to its previous versions and existing pathology-specific models on the lumbar spinal cord, images with severe compression, and in the presence of intramedullary lesions and/or atrophy achieving an average Dice score of 0.95 ± 0.03; (ii) the automatic workflow for monitoring morphometric drift provides a quick feedback loop for developing future segmentation models; and (iii) the scaling factor required to update the database of morphometric measures is nearly constant among slices across the given vertebral levels, showing minimum drift between the current and previous versions of the model monitored by the framework. The model is freely available in Spinal Cord Toolbox v7.0.
- Klíčová slova
- Lifelong Learning, MLOps, MRI, Morphometric Drift, Segmentation, Spinal Cord,
- Publikační typ
- časopisecké články MeSH
- preprinty MeSH
The spinal cord plays a pivotal role in the central nervous system, providing communication between the brain and the body and containing critical motor and sensory networks. Recent advancements in spinal cord MRI data acquisition and image analysis have shown a potential to improve the diagnostics, prognosis, and management of a variety of pathological conditions. In this review, we first discuss the significance of standardized spinal cord MRI acquisition protocol in multi-center and multi-manufacturer studies. Then, we cover open-access spinal cord MRI datasets, which are important for reproducible science and validation of new methods. Finally, we elaborate on the recent advances in spinal cord MRI data analysis techniques implemented in the open-source software package Spinal Cord Toolbox (SCT).
- Klíčová slova
- quantitative magnetic resonance imaging, reproducibility, spinal cord, spinal cord toolbox,
- MeSH
- lidé MeSH
- magnetická rezonanční tomografie * metody MeSH
- mícha * diagnostické zobrazování MeSH
- počítačové zpracování obrazu metody MeSH
- reprodukovatelnost výsledků MeSH
- software * MeSH
- Check Tag
- lidé MeSH
- Publikační typ
- časopisecké články MeSH
- přehledy MeSH
Degenerative cervical myelopathy (DCM) represents the final consequence of a series of degenerative changes in the cervical spine, resulting in cervical spinal canal stenosis and mechanical stress on the cervical spinal cord. This process leads to subsequent pathophysiological processes in the spinal cord tissues. The primary mechanism of injury is degenerative compression of the cervical spinal cord, detectable by magnetic resonance imaging (MRI), serving as a hallmark for diagnosing DCM. However, the relative resilience of the cervical spinal cord to mechanical compression leads to clinical-radiological discordance, i.e., some individuals may exhibit MRI findings of DCC without the clinical signs and symptoms of myelopathy. This degenerative compression of the cervical spinal cord without clinical signs of myelopathy, potentially serving as a precursor to the development of DCM, remains a somewhat controversial topic. In this review article, we elaborate on and provide commentary on the terminology, epidemiology, natural course, diagnosis, predictive value, risks, and practical management of this condition-all of which are subjects of ongoing debate.
Degenerative spinal cord compression is a frequent pathological condition with increasing prevalence throughout aging. Initial non-myelopathic cervical spinal cord compression (NMDC) might progress over time into potentially irreversible degenerative cervical myelopathy (DCM). While quantitative MRI (qMRI) techniques demonstrated the ability to depict intrinsic tissue properties, longitudinal in-vivo biomarkers to identify NMDC patients who will eventually develop DCM are still missing. Thus, we aim to review the ability of qMRI techniques (such as diffusion MRI, diffusion tensor imaging (DTI), magnetization transfer (MT) imaging, and magnetic resonance spectroscopy (1H-MRS)) to serve as prognostic markers in NMDC. While DTI in NMDC patients consistently detected lower fractional anisotropy and higher mean diffusivity at compressed levels, caused by demyelination and axonal injury, MT and 1H-MRS, along with advanced and tract-specific diffusion MRI, recently revealed microstructural alterations, also rostrally pointing to Wallerian degeneration. Recent studies also disclosed a significant relationship between microstructural damage and functional deficits, as assessed by qMRI and electrophysiology, respectively. Thus, tract-specific qMRI, in combination with electrophysiology, critically extends our understanding of the underlying pathophysiology of degenerative spinal cord compression and may provide predictive markers of DCM development for accurate patient management. However, the prognostic value must be validated in longitudinal studies.
