Automatic spinal cord localization, robust to MRI contrasts using global curve optimization

Attention-gated U-Net networks for simultaneous axial/sagittal planes segmentation of injured spinal cords

Magnetic resonance imaging is currently the gold standard for the evaluation of spinal cord injuries. Automatic analysis of these injuries is however challenging, as MRI resolutions vary for different planes of analysis and physiological features are often distorted around these injuries. This study proposes a new CNN-based segmentation method in which information is exchanged between two networks analyzing the scans from different planes. Our aim was to develop a robust method for automatic segmentation of the spinal cord in patients having suffered traumatic injuries. The database consisted of 106 sagittal MRI scans from 94 patients with traumatic spinal cord injuries. Our method used an innovative approach where the scans were analyzed in series under the axial and sagittal plane by two different convolutional networks. The results were compared with those of Deepseg 2D from the Spinal Cord Toolbox (SCT), which was taken as state-of-the-art. Comparisons were evaluated using K-Fold cross-validation combined with statistical t-test results on separate test data. Our method achieved significantly better results than Deepseg 2D, with an average Dice coefficient of 0.95 against 0.88 for Deepseg 2D (p <0.001). Other metrics were also used to compare the segmentations, all of which showed significantly better results for our approach. In this study, we introduce a robust method for spinal cord segmentation which is capable of adequately segmenting spinal cords affected by traumatic injuries, improving upon the methods contained in SCT.

Intelligent Chinese Medicine: A New Direction Approach for Integrative Medicine in Diagnosis and Treatment of Cardiovascular Diseases

High mortality rates from cardiovascular diseases (CVDs) persist worldwide. Older people are at a higher risk of developing these diseases. Given the current high treatment cost for CVDs, there is a need to prevent CVDs and or develop treatment alternatives. Western and Chinese medicines have been used to treat CVDs. However, several factors, such as inaccurate diagnoses, non-standard prescriptions, and poor adherence behavior, lower the benefits of the treatments by Chinese medicine (CM). Artificial intelligence (AI) is increasingly used in clinical diagnosis and treatment, especially in assessing efficacy of CM in clinical decision support systems, health management, new drug research and development, and drug efficacy evaluation. In this study, we explored the role of AI in CM in the diagnosis and treatment of CVDs, and discussed application of AI in assessing the effect of CM on CVDs.

Role of artificial intelligence in oncologic emergencies: a narrative review

Oncologic emergencies are a wide spectrum of oncologic conditions caused directly by malignancies or their treatment. Oncologic emergencies may be classified according to the underlying physiopathology in metabolic, hematologic, and structural conditions. In the latter, radiologists have a pivotal role, through an accurate diagnosis useful to provide optimal patient care. Structural conditions may involve the central nervous system, thorax, or abdomen, and emergency radiologists have to know the characteristics imaging findings of each one of them. The number of oncologic emergencies is growing due to the increased incidence of malignancies in the general population and also to the improved survival of these patients thanks to the advances in cancer treatment. Artificial intelligence (AI) could be a solution to assist emergency radiologists with this rapidly increasing workload. To our knowledge, AI applications in the setting of the oncologic emergency are mostly underexplored, probably due to the relatively low number of oncologic emergencies and the difficulty in training algorithms. However, cancer emergencies are defined by the cause and not by a specific pattern of radiological symptoms and signs. Therefore, it can be expected that AI algorithms developed for the detection of these emergencies in the non-oncological field can be transferred to the clinical setting of oncologic emergency. In this review, a craniocaudal approach was followed and central nervous system, thoracic, and abdominal oncologic emergencies have been addressed regarding the AI applications reported in literature. Among the central nervous system emergencies, AI applications have been reported for brain herniation and spinal cord compression. In the thoracic district the addressed emergencies were pulmonary embolism, cardiac tamponade and pneumothorax. Pneumothorax was the most frequently described application for AI, to improve sensibility and to reduce the time-to-diagnosis. Finally, regarding abdominal emergencies, AI applications for abdominal hemorrhage, intestinal obstruction, intestinal perforation, and intestinal intussusception have been described.

Comparison of spinal magnetic resonance imaging and classical clinical factors in predicting motor capacity in amyotrophic lateral sclerosis

BACKGROUND

Motor capacity is crucial in amyotrophic lateral sclerosis (ALS) clinical trial design and patient care. However, few studies have explored the potential of multimodal MRI to predict motor capacity in ALS. This study aims to evaluate the predictive value of cervical spinal cord MRI parameters for motor capacity in ALS compared to clinical prognostic factors.

METHODS

Spinal multimodal MRI was performed shortly after diagnosis in 41 ALS patients and 12 healthy participants as part of a prospective multicenter cohort study, the PULSE study (NCT00002013-A00969-36). Motor capacity was assessed using ALSFRS-R scores. Multiple stepwise linear regression models were constructed to predict motor capacity at 3 and 6 months from diagnosis, based on clinical variables, structural MRI measurements, including spinal cord cross-sectional area (CSA), anterior-posterior, and left-to-right cross-section diameters at vertebral levels from C1 to T4, and diffusion parameters in the lateral corticospinal tracts (LCSTs) and dorsal columns.

RESULTS

Structural MRI measurements were significantly correlated with the ALSFRS-R score and its sub-scores. And as early as 3 months from diagnosis, structural MRI measurements fit the best multiple linear regression model to predict the total ALSFRS-R (R² = 0.70, p value = 0.0001) and arm sub-score (R² = 0.69, p value = 0.0002), and combined with DTI metric in the LCST and clinical factors fit the best multiple linear regression model to predict leg sub-score (R² = 0.73, p value = 0.0002).

CONCLUSIONS

Spinal multimodal MRI could be promising as a tool to enhance prognostic accuracy and serve as a motor function proxy in ALS.

Automatic measure and normalization of spinal cord cross-sectional area using the pontomedullary junction

Spinal cord cross-sectional area (CSA) is a relevant biomarker to assess spinal cord atrophy in neurodegenerative diseases. However, the considerable inter-subject variability among healthy participants currently limits its usage. Previous studies explored factors contributing to the variability, yet the normalization models required manual intervention and used vertebral levels as a reference, which is an imprecise prediction of the spinal levels. In this study we implemented a method to measure CSA automatically from a spatial reference based on the central nervous system (the pontomedullary junction, PMJ), we investigated factors to explain variability, and developed normalization strategies on a large cohort (N = 804). Following automatic spinal cord segmentation, vertebral labeling and PMJ labeling, the spinal cord CSA was computed on T1w MRI scans from the UK Biobank database. The CSA was computed using two methods. For the first method, the CSA was computed at the level of the C2-C3 intervertebral disc. For the second method, the CSA was computed at 64 mm caudally from the PMJ, this distance corresponding to the average distance between the PMJ and the C2-C3 disc across all participants. The effect of various demographic and anatomical factors was explored, and a stepwise regression found significant predictors; the coefficients of the best fit model were used to normalize CSA. CSA measured at C2-C3 disc and using the PMJ differed significantly (paired t-test, p-value = 0.0002). The best normalization model included thalamus, brain volume, sex and the interaction between brain volume and sex. The coefficient of variation went down for PMJ CSA from 10.09 (without normalization) to 8.59%, a reduction of 14.85%. For CSA at C2-C3, it went down from 9.96 to 8.42%, a reduction of 15.13 %. This study introduces an end-to-end automatic pipeline to measure and normalize cord CSA from a neurological reference. This approach requires further validation to assess atrophy in longitudinal studies. The inter-subject variability of CSA can be partly accounted for by demographics and anatomical factors.

Automated Cervical Spinal Cord Segmentation in Real-World MRI of Multiple Sclerosis Patients by Optimized Hybrid Residual Attention-Aware Convolutional Neural Networks

Magnetic resonance (MR) imaging is the most sensitive clinical tool in the diagnosis and monitoring of multiple sclerosis (MS) alterations. Spinal cord evaluation has gained interest in this clinical scenario in recent years, but, unlike the brain, there is a more limited choice of algorithms to assist spinal cord segmentation. Our goal was to investigate and develop an automatic MR cervical cord segmentation method, enabling automated and seamless spinal cord atrophy assessment and setting the stage for the development of an aggregated algorithm for the extraction of lesion-related imaging biomarkers. The algorithm was developed using a real-world MR imaging dataset of 121 MS patients (96 cases used as a training dataset and 25 cases as a validation dataset). Transversal, 3D T1-weighted gradient echo MR images (TE/TR/FA = 1.7-2.7 ms/5.6-8.2 ms/12°) were acquired in a 3 T system (Signa HD, GEHC) as standard of care in our clinical practice. Experienced radiologists supervised the manual labelling, which was considered the ground-truth. The 2D convolutional neural network consisted of a hybrid residual attention-aware segmentation method trained to delineate the cervical spinal cord. The training was conducted using a focal loss function, based on the Tversky index to address label imbalance, and an automatic optimal learning rate finder. Our automated model provided an accurate segmentation, achieving a validation DICE coefficient of 0.904 ± 0.101 compared with the manual delineation. An automatic method for cervical spinal cord segmentation on T1-weighted MR images was successfully implemented. It will have direct implications serving as the first step for accelerating the process for MS staging and follow-up through imaging biomarkers.

Artificial Intelligence in Spinal Imaging: Current Status and Future Directions

Spinal maladies are among the most common causes of pain and disability worldwide. Imaging represents an important diagnostic procedure in spinal care. Imaging investigations can provide information and insights that are not visible through ordinary visual inspection. Multiscale in vivo interrogation has the potential to improve the assessment and monitoring of pathologies thanks to the convergence of imaging, artificial intelligence (AI), and radiomic techniques. AI is revolutionizing computer vision, autonomous driving, natural language processing, and speech recognition. These revolutionary technologies are already impacting radiology, diagnostics, and other fields, where automated solutions can increase precision and reproducibility. In the first section of this narrative review, we provide a brief explanation of the many approaches currently being developed, with a particular emphasis on those employed in spinal imaging studies. The previously documented uses of AI for challenges involving spinal imaging, including imaging appropriateness and protocoling, image acquisition and reconstruction, image presentation, image interpretation, and quantitative image analysis, are then detailed. Finally, the future applications of AI to imaging of the spine are discussed. AI has the potential to significantly affect every step in spinal imaging. AI can make images of the spine more useful to patients and doctors by improving image quality, imaging efficiency, and diagnostic accuracy.

Activity-dependent spinal cord neuromodulation rapidly restores trunk and leg motor functions after complete paralysis

Epidural electrical stimulation (EES) targeting the dorsal roots of lumbosacral segments restores walking in people with spinal cord injury (SCI). However, EES is delivered with multielectrode paddle leads that were originally designed to target the dorsal column of the spinal cord. Here, we hypothesized that an arrangement of electrodes targeting the ensemble of dorsal roots involved in leg and trunk movements would result in superior efficacy, restoring more diverse motor activities after the most severe SCI. To test this hypothesis, we established a computational framework that informed the optimal arrangement of electrodes on a new paddle lead and guided its neurosurgical positioning. We also developed software supporting the rapid configuration of activity-specific stimulation programs that reproduced the natural activation of motor neurons underlying each activity. We tested these neurotechnologies in three individuals with complete sensorimotor paralysis as part of an ongoing clinical trial ( www.clinicaltrials.gov identifier NCT02936453). Within a single day, activity-specific stimulation programs enabled these three individuals to stand, walk, cycle, swim and control trunk movements. Neurorehabilitation mediated sufficient improvement to restore these activities in community settings, opening a realistic path to support everyday mobility with EES in people with SCI.

Generic acquisition protocol for quantitative MRI of the spinal cord

Quantitative spinal cord (SC) magnetic resonance imaging (MRI) presents many challenges, including a lack of standardized imaging protocols. Here we present a prospectively harmonized quantitative MRI protocol, which we refer to as the spine generic protocol, for users of 3T MRI systems from the three main manufacturers: GE, Philips and Siemens. The protocol provides guidance for assessing SC macrostructural and microstructural integrity: T1-weighted and T2-weighted imaging for SC cross-sectional area computation, multi-echo gradient echo for gray matter cross-sectional area, and magnetization transfer and diffusion weighted imaging for assessing white matter microstructure. In a companion paper from the same authors, the spine generic protocol was used to acquire data across 42 centers in 260 healthy subjects. The key details of the spine generic protocol are also available in an open-access document that can be found at https://github.com/spine-generic/protocols . The protocol will serve as a starting point for researchers and clinicians implementing new SC imaging initiatives so that, in the future, inclusion of the SC in neuroimaging protocols will be more common. The protocol could be implemented by any trained MR technician or by a researcher/clinician familiar with MRI acquisition.

Improved Assessment of Longitudinal Spinal Cord Atrophy in Multiple Sclerosis Using a Registration-Based Approach: Relevance for Clinical Studies

BACKGROUND

Reliable measurements of cervical cord atrophy progression may be useful for monitoring neurodegeneration in multiple sclerosis (MS).

PURPOSE

To compare a new, registration-based (Reg) method with two existing methods (active surface [AS] and propagation segmentation [PropSeg]) to measure cord atrophy changes over time in MS.

STUDY TYPE

Retrospective.

SUBJECTS

Cohort I: Eight healthy controls (HC) and 28 MS patients enrolled at a single institution, and cohort II: 25 HC and 63 MS patients enrolled at three European sites.

FIELD STRENGTH/SEQUENCE

3D T1-weighted gradient echo sequence, acquired at 1.5 T (cohort I) and 3.0 T (cohort II).

ASSESSMENT

Percentage cord area changes (PCACs) between baseline and follow-up (cohort I: 2.34 years [interquartile range = 2.00-2.55 years], cohort II: 1.05 years [interquartile range = 1.01-1.18 years]) were evaluated for all subjects using Reg, AS, and PropSeg. Reg included an accurate registration of baseline and follow-up straightened cord images, followed by AS-based optimized cord segmentation. A subset of studies was analyzed twice by two observers.

STATISTICAL TESTS

Linear regression models were used to estimate annualized PCAC, and effect sizes expressed as the ratio between the estimated differences and HC error term (P < 0.05). Reproducibility was assessed by linear mixed-effect models. Annualized PCACs were used for sample size calculations (significance: α = 0.05, power: 1 - β = 0.80).

RESULTS

Annualized PCACs and related standard errors (SEs) were lower with Reg than with other methods: PCAC in MS patients at 1.5 T was -1.12% (SE = 0.22) with Reg, -1.32% (SE = 0.30) with AS, and -1.40% (SE = 0.33) with PropSeg, while at 3.0 T PCAC was -0.83% (SE = 0.25) with Reg, -0.92% (SE = 0.32) with AS, and -1.18 (SE = 0.53) with PropSeg. This was reflected in larger effect sizes and lower sample sizes. Intra- and inter-observer agreement range was 0.72-0.91 with AS, and it was >0.96 with Reg.

DATA CONCLUSION

The results support the use of the registration method to measure cervical cord atrophy progression in future MS clinical studies.

LEVEL OF EVIDENCE

3 TECHNICAL EFFICACY STAGE: 2.

Utility of machine learning algorithms in degenerative cervical and lumbar spine disease: a systematic review

Machine learning is a rapidly evolving field that offers physicians an innovative and comprehensive mechanism to examine various aspects of patient data. Cervical and lumbar degenerative spine disorders are commonly age-related disease processes that can utilize machine learning to improve patient outcomes with careful patient selection and intervention. The aim of this study is to examine the current applications of machine learning in cervical and lumbar degenerative spine disease. A systematic review was conducted using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. A search of PubMed, Embase, Medline, and Cochrane was conducted through May 31st, 2020, using the following terms: "artificial intelligence" OR "machine learning" AND "neurosurgery" AND "spine." Studies were included if original research on machine learning was utilized in patient care for degenerative spine disease, including radiographic machine learning applications. Studies focusing on robotic applications in neurosurgery, navigation, or stereotactic radiosurgery were excluded. The literature search identified 296 papers, with 35 articles meeting inclusion criteria. There were nine studies involving cervical degenerative spine disease and 26 studies on lumbar degenerative spine disease. The majority of studies for both cervical and lumbar spines utilized machine learning for the prediction of postoperative outcomes, with 5 (55.6%) and 15 (61.5%) studies, respectively. Machine learning applications focusing on degenerative lumbar spine greatly outnumber the current volume of cervical spine studies. The current research in lumbar spine also demonstrates more advanced clinical applications of radiographic, diagnostic, and predictive machine learning models.

Automatic multiclass intramedullary spinal cord tumor segmentation on MRI with deep learning

•

Automatic spinal cord tumor segmentation with deep learning.

•

Multi-class model for tumor, edema, and cavity.

•

Model trained to recognize astrocytoma, ependymoma, and hemangioblastoma.

•

Multi-contrast input for more robustness: Gd-T1w and T2w.

•

Method and model are available in open-source Spinal Cord Toolbox (SCT).

Spinal cord tumors lead to neurological morbidity and mortality. Being able to obtain morphometric quantification (size, location, growth rate) of the tumor, edema, and cavity can result in improved monitoring and treatment planning. Such quantification requires the segmentation of these structures into three separate classes. However, manual segmentation of three-dimensional structures is time consuming, tedious and prone to intra- and inter-rater variability, motivating the development of automated methods. Here, we tailor a model adapted to the spinal cord tumor segmentation task. Data were obtained from 343 patients using gadolinium-enhanced T1-weighted and T2-weighted MRI scans with cervical, thoracic, and/or lumbar coverage. The dataset includes the three most common intramedullary spinal cord tumor types: astrocytomas, ependymomas, and hemangioblastomas. The proposed approach is a cascaded architecture with U-Net-based models that segments tumors in a two-stage process: locate and label. The model first finds the spinal cord and generates bounding box coordinates. The images are cropped according to this output, leading to a reduced field of view, which mitigates class imbalance. The tumor is then segmented. The segmentation of the tumor, cavity, and edema (as a single class) reached 76.7 ± 1.5% of Dice score and the segmentation of tumors alone reached 61.8 ± 4.0% Dice score. The true positive detection rate was above 87% for tumor, edema, and cavity. To the best of our knowledge, this is the first fully automatic deep learning model for spinal cord tumor segmentation. The multiclass segmentation pipeline is available in the Spinal Cord Toolbox (https://spinalcordtoolbox.com/). It can be run with custom data on a regular computer within seconds.

7 T imaging reveals a gradient in spinal cord lesion distribution in multiple sclerosis

We used 7 T MRI to: (i) characterize the grey and white matter pathology in the cervical spinal cord of patients with early relapsing-remitting and secondary progressive multiple sclerosis; (ii) assess the spinal cord lesion spatial distribution and the hypothesis of an outside-in pathological process possibly driven by CSF-mediated immune cytotoxic factors; and (iii) evaluate the association of spinal cord pathology with brain burden and its contribution to neurological disability. We prospectively recruited 20 relapsing-remitting, 15 secondary progressive multiple sclerosis participants and 11 age-matched healthy control subjects to undergo 7 T imaging of the cervical spinal cord and brain as well as conventional 3 T brain acquisition. Cervical spinal cord imaging at 7 T was used to segment grey and white matter, including lesions therein. Brain imaging at 7 T was used to segment cortical and white matter lesions and 3 T imaging for cortical thickness estimation. Cervical spinal cord lesions were mapped voxel-wise as a function of distance from the inner central canal CSF pool to the outer subpial surface. Similarly, brain white matter lesions were mapped voxel-wise as a function of distance from the ventricular system. Subjects with relapsing-remitting multiple sclerosis showed a greater predominance of spinal cord lesions nearer the outer subpial surface compared to secondary progressive cases. Inversely, secondary progressive participants presented with more centrally located lesions. Within the brain, there was a strong gradient of lesion formation nearest the ventricular system that was most evident in participants with secondary progressive multiple sclerosis. Lesion fractions within the spinal cord grey and white matter were related to the lesion fraction in cerebral white matter. Cortical thinning was the primary determinant of the Expanded Disability Status Scale, white matter lesion fractions in the spinal cord and brain of the 9-Hole Peg Test and cortical thickness and spinal cord grey matter cross-sectional area of the Timed 25-Foot Walk. Spinal cord lesions were localized nearest the subpial surfaces for those with relapsing-remitting and the central canal CSF surface in progressive disease, possibly implying CSF-mediated pathogenic mechanisms in lesion development that may differ between multiple sclerosis subtypes. These findings show that spinal cord lesions involve both grey and white matter from the early multiple sclerosis stages and occur mostly independent from brain pathology. Despite the prevalence of cervical spinal cord lesions and atrophy, brain pathology seems more strongly related to physical disability as measured by the Expanded Disability Status Scale.

Effect of distortion corrections on the tractography quality in spinal cord diffusion-weighted imaging

PURPOSE

To assess the impact of a different distortion correction (DC) method and patient geometry (sagittal balance) on the quality of spinal cord tractography rendering according to different tractography approaches.

METHODS

Forty-four adults free of spinal cord diseases underwent cervical diffusion-weighted imaging. The phase-encoding direction was head→foot. Sequence with opposed polarities (foot→head) was acquired to perform DC. Eddy-current, motion effects, and susceptibility artifact correction methods were used for DC, and two deterministic and one probabilistic tractography approaches were evaluated using MRtrix and DSI Studio tractography software. Fiber length and number of fibers were extracted to evaluate the quality of the tractography rendering. For each subject, cervical lordosis was measured to assess patient geometry. The angle between the main direction of the spinal cord and the orientation of the acquisition box were computed at each spine level to assess acquisition geometry and define an angle threshold for which a tractography of good quality is no longer possible.

RESULTS

There was a significant improvement in tractography quality after performing DC with susceptibility artifact correction using a deterministic approach based on tensor. Before DC, the angle threshold was defined at C6 (15.2°) compared with C7 (21.9°) after corrections, demonstrating the importance of spinal cord angulation for DC.

CONCLUSION

The impact of DC on tractography quality is greatly impacted by acquisition geometry. To obtain a good-quality tractography, we propose as a future perspective to adapt the acquisition geometry to that of the patient by automatically adjusting the acquisition box.

Minimum detectable spinal cord atrophy with automatic segmentation: Investigations using an open-access dataset of healthy participants

•

Evaluate the robustness of an automated analysis pipeline for detecting SC atrophy.

•

Simulate spinal cord atrophy and scan-rescan variability.

•

Fully automated analysis method available on an open access database.

•

Evaluation of sample size and inter/intra-subject variability for T1w and T2w images.

Spinal cord atrophy is a well-known biomarker in multiple sclerosis (MS) and other diseases. It is measured by segmenting the spinal cord on an MRI image and computing the average cross-sectional area (CSA) over a few slices. Introduced about 25 years ago, this procedure is highly sensitive to the quality of the segmentation and is prone to rater-bias. Recently, fully-automated spinal cord segmentation methods, which remove the rater-bias and enable the automated analysis of large populations, have been introduced. A lingering question related to these automated methods is: How reliable are they at detecting atrophy? In this study, we evaluated the precision and accuracy of automated atrophy measurements by simulating scan-rescan experiments.

Spinal cord MRI data from the open-access spine-generic project were used. The dataset aggregates 42 sites worldwide and consists of 260 healthy subjects and includes T1w and T2w contrasts. To simulate atrophy, each volume was globally rescaled at various scaling factors. Moreover, to simulate patient repositioning, random rigid transformations were applied. Using the DeepSeg algorithm from the Spinal Cord Toolbox, the spinal cord was segmented and vertebral levels were identified. Then, the average CSA between C3-C5 vertebral levels was computed for each Monte Carlo sample, allowing us to derive measures of atrophy, intra/inter-subject variability, and sample-size calculations.

The minimum sample size required to detect an atrophy of 2% between unpaired study arms, commonly seen in MS studies, was 467 +/− 13.9 using T1w and 467 +/− 3.2 using T2w images. The minimum sample size to detect a longitudinal atrophy (between paired study arms) of 0.8% was 60 +/− 25.1 using T1w and 10 +/− 1.2 using T2w images. At the intra-subject level, the estimated CSA, observed in this study, showed good precision compared to other studies with COVs (across Monte Carlo transformations) of 0.8% for T1w and 0.6% for T2w images.

While these sample sizes seem small, we would like to stress that these results correspond to a “best case” scenario, in that the dataset used here was of particularly good quality and the model for simulating atrophy does not encompass all the variability met in real-life datasets. The simulated atrophy and scan-rescan variability may over-simplify the biological reality. The proposed framework is open-source and available at https://csa-atrophy.readthedocs.io/.

Spatial distribution of multiple sclerosis lesions in the cervical spinal cord

Spinal cord lesions detected on MRI hold important diagnostic and prognostic value for multiple sclerosis. Previous attempts to correlate lesion burden with clinical status have had limited success, however, suggesting that lesion location may be a contributor. Our aim was to explore the spatial distribution of multiple sclerosis lesions in the cervical spinal cord, with respect to clinical status. We included 642 suspected or confirmed multiple sclerosis patients (31 clinically isolated syndrome, and 416 relapsing-remitting, 84 secondary progressive, and 73 primary progressive multiple sclerosis) from 13 clinical sites. Cervical spine lesions were manually delineated on T2- and T2*-weighted axial and sagittal MRI scans acquired at 3 or 7 T. With an automatic publicly-available analysis pipeline we produced voxelwise lesion frequency maps to identify predilection sites in various patient groups characterized by clinical subtype, Expanded Disability Status Scale score and disease duration. We also measured absolute and normalized lesion volumes in several regions of interest using an atlas-based approach, and evaluated differences within and between groups. The lateral funiculi were more frequently affected by lesions in progressive subtypes than in relapsing in voxelwise analysis (P < 0.001), which was further confirmed by absolute and normalized lesion volumes (P < 0.01). The central cord area was more often affected by lesions in primary progressive than relapse-remitting patients (P < 0.001). Between white and grey matter, the absolute lesion volume in the white matter was greater than in the grey matter in all phenotypes (P < 0.001); however when normalizing by each region, normalized lesion volumes were comparable between white and grey matter in primary progressive patients. Lesions appearing in the lateral funiculi and central cord area were significantly correlated with Expanded Disability Status Scale score (P < 0.001). High lesion frequencies were observed in patients with a more aggressive disease course, rather than long disease duration. Lesions located in the lateral funiculi and central cord area of the cervical spine may influence clinical status in multiple sclerosis. This work shows the added value of cervical spine lesions, and provides an avenue for evaluating the distribution of spinal cord lesions in various patient groups.

Convolutional Neural Network-Based Automated Segmentation of the Spinal Cord and Contusion Injury: Deep Learning Biomarker Correlates of Motor Impairment in Acute Spinal Cord Injury

BACKGROUND AND PURPOSE

Our aim was to use 2D convolutional neural networks for automatic segmentation of the spinal cord and traumatic contusion injury from axial T2-weighted MR imaging in a cohort of patients with acute spinal cord injury.

MATERIALS AND METHODS

Forty-seven patients who underwent 3T MR imaging within 24 hours of spinal cord injury were included. We developed an image-analysis pipeline integrating 2D convolutional neural networks for whole spinal cord and intramedullary spinal cord lesion segmentation. Linear mixed modeling was used to compare test segmentation results between our spinal cord injury convolutional neural network (Brain and Spinal Cord Injury Center segmentation) and current state-of-the-art methods. Volumes of segmented lesions were then used in a linear regression analysis to determine associations with motor scores.

RESULTS

Compared with manual labeling, the average test set Dice coefficient for the Brain and Spinal Cord Injury Center segmentation model was 0.93 for spinal cord segmentation versus 0.80 for PropSeg and 0.90 for DeepSeg (both components of the Spinal Cord Toolbox). Linear mixed modeling showed a significant difference between Brain and Spinal Cord Injury Center segmentation compared with PropSeg (P < .001) and DeepSeg (P < .05). Brain and Spinal Cord Injury Center segmentation showed significantly better adaptability to damaged areas compared with PropSeg (P < .001) and DeepSeg (P < .02). The contusion injury volumes based on automated segmentation were significantly associated with motor scores at admission (P = .002) and discharge (P = .009).

CONCLUSIONS

Brain and Spinal Cord Injury Center segmentation of the spinal cord compares favorably with available segmentation tools in a population with acute spinal cord injury. Volumes of injury derived from automated lesion segmentation with Brain and Spinal Cord Injury Center segmentation correlate with measures of motor impairment in the acute phase. Targeted convolutional neural network training in acute spinal cord injury enhances algorithm performance for this patient population and provides clinically relevant metrics of cord injury.

Automatic segmentation of the spinal cord and intramedullary multiple sclerosis lesions with convolutional neural networks

The spinal cord is frequently affected by atrophy and/or lesions in multiple sclerosis (MS) patients. Segmentation of the spinal cord and lesions from MRI data provides measures of damage, which are key criteria for the diagnosis, prognosis, and longitudinal monitoring in MS. Automating this operation eliminates inter-rater variability and increases the efficiency of large-throughput analysis pipelines. Robust and reliable segmentation across multi-site spinal cord data is challenging because of the large variability related to acquisition parameters and image artifacts. In particular, a precise delineation of lesions is hindered by a broad heterogeneity of lesion contrast, size, location, and shape. The goal of this study was to develop a fully-automatic framework - robust to variability in both image parameters and clinical condition - for segmentation of the spinal cord and intramedullary MS lesions from conventional MRI data of MS and non-MS cases. Scans of 1042 subjects (459 healthy controls, 471 MS patients, and 112 with other spinal pathologies) were included in this multi-site study (n = 30). Data spanned three contrasts (T1-, T2-, and T2∗-weighted) for a total of 1943 vol and featured large heterogeneity in terms of resolution, orientation, coverage, and clinical conditions. The proposed cord and lesion automatic segmentation approach is based on a sequence of two Convolutional Neural Networks (CNNs). To deal with the very small proportion of spinal cord and/or lesion voxels compared to the rest of the volume, a first CNN with 2D dilated convolutions detects the spinal cord centerline, followed by a second CNN with 3D convolutions that segments the spinal cord and/or lesions. CNNs were trained independently with the Dice loss. When compared against manual segmentation, our CNN-based approach showed a median Dice of 95% vs. 88% for PropSeg (p ≤ 0.05), a state-of-the-art spinal cord segmentation method. Regarding lesion segmentation on MS data, our framework provided a Dice of 60%, a relative volume difference of -15%, and a lesion-wise detection sensitivity and precision of 83% and 77%, respectively. In this study, we introduce a robust method to segment the spinal cord and intramedullary MS lesions on a variety of MRI contrasts. The proposed framework is open-source and readily available in the Spinal Cord Toolbox.