Conversion of T2-Weighted Magnetic Resonance Images of Cervical Spine Trauma to Short T1 Inversion Recovery (STIR) Images by Generative Adversarial Network.

INTRODUCTION: The short T1 inversion recovery (STIR) sequence is advantageous for visualizing ligamentous injuries, but the STIR sequence may be missing in some cases. The purpose of this study was to generate synthetic STIR images from MRI T2-weighted images (T2WI) of patients with cervical spine trauma using a generative adversarial network (GAN).  Methods: A total of 969 pairs of T2WI and STIR images were extracted from 79 patients with cervical spine trauma. The synthetic model was trained 100 times, and the performance of the model was evaluated with five-fold cross-validation.  Results: As for quantitative validation, the structural similarity score was 0.519±0.1 and the peak signal-to-noise ratio score was 19.37±1.9 dB. As for qualitative validation, the incorporation of synthetic STIR images generated by a GAN alongside T2WI substantially enhances sensitivity in the detection of interspinous ligament injuries, outperforming assessments reliant solely on T2WI. CONCLUSION: The GAN model can generate synthetic STIRs from T2 images of cervical spine trauma using image-to-image conversion techniques. The use of a combination of synthetic STIR images generated by a GAN and T2WI improves sensitivity in detecting interspinous ligament injuries compared to assessments that use only T2WI.

Differences in Risk Factors for Decreased Cervical Lordosis after Multiple-Segment Laminoplasty for Cervical Spondylotic Myelopathy and Ossification of the Posterior Longitudinal Ligament: A Pilot Study.

STUDY DESIGN: Retrospective study. PURPOSE: To compare the radiographic risk factors for decreased cervical lordosis (CL) after laminoplasty, focusing on the difference between cervical spondylotic myelopathy (CSM) and cervical ossification of the posterior longitudinal ligament (C-OPLL). OVERVIEW OF LITERATURE: A few reports compared the risk factors for decreased CL between CSM and C-OPLL although these two pathologies have their characteristics. METHODS: This study included 50 patients with CSM and 39 with C-OPLL who underwent multi-segment laminoplasty. Decreased CL was defined as the difference between preoperative and 2-year postoperative neutral C2-7 Cobb angles. Radiographic parameters included preoperative neutral C2-7 Cobb angles, C2-7 sagittal vertical axis (SVA), T1 slope (T1S), dynamic extension reserve (DER), and range of motion. The radiographic risk factors were investigated for decreased CL in CSM and C-OPLL. Additionally, the Japanese Orthopedic Association (JOA) score was assessed preoperatively and 2 years postoperatively. RESULTS: C2-7 SVA (p =0.018) and DER (p =0.002) were significantly correlated with decreased CL in CSM, while C2-7 Cobb angle (p =0.012) and C2-7 SVA (p =0.028) were correlated with decreased CL in C-OPLL. Multiple linear regression analysis revealed that greater C2-7 SVA (B =0.22, p =0.026) and small DER (B =-0.53, p =0.002) were significantly associated with decreased CL in CSM. By contrast, greater C2-7 SVA (B =0.36, p =0.031) was significantly associated with decreased CL in C-OPLL. The JOA score significantly improved in both CSM and C-OPLL (p <0.001). CONCLUSIONS: C2-7 SVA was associated with a postoperative decreased CL in both CSM and C-OPLL, but DER was only associated with decreased CL in CSM. Risk factors for decreased CL slightly differed depending on the etiology of the condition.

Magnetic resonance image segmentation of the compressed spinal cord in patients with degenerative cervical myelopathy using convolutional neural networks.

PURPOSE: Spinal cord segmentation is the first step in atlas-based spinal cord image analysis, but segmentation of compressed spinal cords from patients with degenerative cervical myelopathy is challenging. We applied convolutional neural network models to segment the spinal cord from T2-weighted axial magnetic resonance images of DCM patients. Furthermore, we assessed the correlation between the cross-sectional area segmented by this network and the neurological symptoms of the patients. METHODS: The CNN architecture was built using U-Net and DeepLabv3 + and PyTorch. The CNN was trained on 2762 axial slices from 174 patients, and an additional 517 axial slices from 33 patients were held out for validation and 777 axial slices from 46 patients for testing. The performance of the CNN was evaluated on a test dataset with Dice coefficients as the outcome measure. The ratio of CSA at the maximum compression level to CSA at the C2 level, as segmented by the CNN, was calculated. The correlation between the spinal cord CSA ratio and the Japanese Orthopaedic Association score in DCM patients from the test dataset was investigated using Spearman's rank correlation coefficient. RESULTS: The best Dice coefficient was achieved when U-Net was used as the architecture and EfficientNet-b7 as the model for transfer learning. Spearman's rs between the spinal cord CSA ratio and the JOA score of DCM patients was 0.38 (p = 0.007), showing a weak correlation. CONCLUSION: Using deep learning with magnetic resonance images of deformed spinal cords as training data, we were able to segment compressed spinal cords of DCM patients with a high concordance with expert manual segmentation. In addition, the spinal cord CSA ratio was weakly, but significantly, correlated with neurological symptoms. Our study demonstrated the first steps needed to implement automated atlas-based analysis of DCM patients.

Automated fracture screening using an object detection algorithm on whole-body trauma computed tomography.

The emergency department is an environment with a potential risk for diagnostic errors during trauma care, particularly for fractures. Convolutional neural network (CNN) deep learning methods are now widely used in medicine because they improve diagnostic accuracy, decrease misinterpretation, and improve efficiency. In this study, we investigated whether automatic localization and classification using CNN could be applied to pelvic, rib, and spine fractures. We also examined whether this fracture detection algorithm could help physicians in fracture diagnosis. A total of 7664 whole-body CT axial slices (chest, abdomen, pelvis) from 200 patients were used. Sensitivity, precision, and F1-score were calculated to evaluate the performance of the CNN model. For the grouped mean values for pelvic, spine, or rib fractures, the sensitivity was 0.786, precision was 0.648, and F1-score was 0.711. Moreover, with CNN model assistance, surgeons showed improved sensitivity for detecting fractures and the time of reading and interpreting CT scans was reduced, especially for less experienced orthopedic surgeons. Application of the CNN model may lead to reductions in missed fractures from whole-body CT images and to faster workflows and improved patient care through efficient diagnosis in polytrauma patients.

Early decompression promotes motor recovery after cervical spinal cord injury in rats with chronic cervical spinal cord compression.

The number of elderly patients with spinal cord injury without radiographic abnormalities (SCIWORA) has been increasing in recent years and common of most cervical spinal cord injuries. Basic research has shown the effectiveness of early decompression after spinal cord injury on the spinal cord without stenosis; no studies have reported the efficacy of decompression in models with spinal cord compressive lesions. The purpose of this study was to evaluate the effects of decompression surgery after acute spinal cord injury in rats with chronic spinal cord compressive lesions, mimicking SCIWORA. A water-absorbent polymer sheet (Aquaprene DX, Sanyo Chemical Industries) was inserted dorsally into the 4-5th cervical sublaminar space in 8-week-old Sprague Dawley rats to create a rat model with a chronic spinal compressive lesion. At the age of 16 weeks, 30 mildly myelopathic or asymptomatic rats with a Basso, Beattie, and Bresnahan score (BBB score) of 19 or higher were subjected to spinal cord compression injuries. The rats were divided into three groups: an immediate decompression group (decompress immediately after injury), a sub-acute decompression group (decompress 1 week after injury), and a non-decompression group. Behavioral and histological evaluations were performed 4 weeks after the injury. At 20 weeks of age, the BBB score and FLS (Forelimb Locomotor Scale) of both the immediate and the sub-acute decompression groups were significantly higher than those of the non-decompression group. There was no significant difference between the immediate decompression group and the sub-acute decompression group. TUNEL (transferase-mediated dUTP nick end labeling) staining showed significantly fewer positive cells in both decompression groups compared to the non-decompression group. LFB (Luxol fast blue) staining showed significantly more demyelination, and GAP-43 (growth associated protein-43) staining tended to show fewer positive cells in the non-decompression group. Decompression surgery in the acute or sub-acute phase of injury is effective after mild spinal cord injury in rats with chronic compressive lesions. There was no significant difference between the immediate decompression and sub-acute decompression groups.

Differences in the expression of myelopathy in a rat model of chronic spinal cord compression.

CONTEXT/OBJECTIVE: The degree of spinal cord compression does not always parallel neurological symptoms. We considered that some compensatory neuroprotective mechanism underlies the expression of this neurological phenotype. Oxygen-regulated-protein 150 (ORP150) is neuroprotective and expressed in neurons in response to neuronal ischemia. We sought to elucidate whether ORP150 expression is associated with the severity and variation of neurological recovery in our rat model of chronic spinal cord compression. METHODS: We made a rat model of chronic spinal cord compression inserting an expandable water-absorbing polyurethane sheet. A neurological behavioral assessment of the severity of paralysis was performed for 10 weeks postoperatively. The rat model was defined as two groups: a myelopathy group with decreased locomotor function and an asymptomatic group. At 10 weeks postoperatively, the spinal cord of the cervical segment was resected for histology and qPCR. RESULTS: Slowly progressive paralysis appeared at 5-10 weeks postoperatively in 53% of the rats with spinal cord compression. The asymptomatic group had no histological changes indicative of myelopathy. Histology and qPCR showed increased expression of ORP150 in the asymptomatic group, but the ratio of ORP150-positive neuron in the two groups was not significantly different. CONCLUSION: The expression of ORP150 in neurons associated with spinal cord compression suggested that the spinal cord was under ischemic stress due to compression, but relation to the development of myelopathy was unclear. The results suggested that some other compensatory mechanisms may exist in response to spinal cord compression in asymptomatic rats.

Determining the short-term neurological prognosis for acute cervical spinal cord injury using machine learning.

It is challenging to predict neurological outcomes of acute spinal cord injury (SCI) considering issues such as spinal shock and injury heterogeneity. Deep learning-based radiomics (DLR) were developed to quantify the radiographic characteristics automatically using a convolutional neural network (CNN), and to potentially allow the prognostic stratification of patients. We aimed to determine the functional prognosis of patients with cervical SCI using machine learning approach based on MRI and to assess the ability to predict the neurological outcomes. We retrospectively analyzed the medical records of SCI patients (n=215) who had undergone MRI and had an American Spinal cord Injury Association Impairment Scale (AIS) assessment at 1 month after injury, enrolled with a total of 294 MR images. Sagittal T2-weighted MR images were used for the CNN training and validation. The deep learning framework TensorFlow was used to construct the CNN architecture. After we calculated the probability of the AIS grade using the DLR, we built the identification model based upon the random forest using 3 features: the probability of each AIS grade obtained by the DLR method, age, and the initial AIS grade at admission. We performed a statistical evaluation between the actual and predicted AIS. The accuracy, precision, recall and f1 score of the ensemble model based on the DLR and RF were 0.714, 0.590, 0.565 and 0.567, respectively. The present study demonstrates that prediction of the short-term neurological outcomes for acute cervical spinal cord injury based on MRI using machine learning is feasible.

Automated Differentiation Between Osteoporotic Vertebral Fracture and Malignant Vertebral Fracture on MRI Using a Deep Convolutional Neural Network.

STUDY DESIGN: Retrospective study of magnetic resonance imaging (MRI). OBJECTIVES: To assess the ability of a convolutional neural network (CNN) model to differentiate osteoporotic vertebral fractures (OVFs) and malignant vertebral compression fractures (MVFs) using short-TI inversion recovery (STIR) and T1-weighted images (T1WI) and to compare it to the performance of three spine surgeons. SUMMARY OF BACKGROUND DATA: Differentiating between OVFs and MVFs is crucial for appropriate clinical staging and treatment planning. However, an accurate diagnosis is sometimes difficult. Recently, CNN modeling-an artificial intelligence technique-has gained popularity in the radiology field. METHODS: We enrolled 50 patients with OVFs and 47 patients with MVFs who underwent thoracolumbar MRI. Sagittal STIR images and sagittal T1WI were used to train and validate the CNN models. To assess the performance of the CNN, the receiver operating characteristic curve was plotted and the area under the curve was calculated. We also compared the accuracy, sensitivity, and specificity of the diagnosis made by the CNN and three spine surgeons. RESULTS: The area under the curve of receiver operating characteristic curves of the CNN based on STIR images and T1WI were 0.967 and 0.984, respectively. The CNN model based on STIR images showed a performance of 93.8% accuracy, 92.5% sensitivity, and 94.9% specificity. On the other hand, the CNN model based on T1WI showed a performance of 96.4% accuracy, 98.1% sensitivity, and 94.9% specificity. The accuracy and specificity of the CNN using both STIR and T1WI were statistically equal to or better than that of three spine surgeons. There were no significant differences in sensitivity based on both STIR images and T1WI between the CNN and spine surgeons. CONCLUSION: We successfully differentiated OVFs and MVFs based on MRI with high accuracy using the CNN model, which was statistically equal or superior to that of the spine surgeons.Level of Evidence: 4.

Minimally displaced unilateral facet fracture of cervical spine can lead to spinal cord injury: a report of two cases.

BACKGROUND: According to most of the commonly used classification systems for subaxial spine injuries, unilateral and minimally displaced facet fractures without any sign of a spinal cord injury would be directed to non-operative management. However, the failure rate of non-operative treatment varies from 20 to 80%, and no consensus exists with regard to predictors of failure after non-operative management. CASE PRESENTATION: Case 1 is a patient with a unilateral facet fracture. The patient had only numbness in the right C6 dermatome but failed non-operative treatment, which resulted in severe spinal cord injury. Case 2 is a patient who had a similar injury pattern as case 1 but presented with immediate instability and underwent fusion surgery. Both patients had a minimally displaced unilateral facet fracture accompanied by disc injury and blunt vertebral artery injury, which are possible signs indicating significant instability. CONCLUSIONS: This is the first report of an isolated unilateral facet fracture that resulted in catastrophic spinal cord injury. These two cases illustrate that an isolated minimally displaced unilateral facet fracture with disc injury and vertebral artery injury were associated with significant instability that can lead to spinal cord injury.

Mid-term Surgical Outcome of Posterior Decompression With Instrumented Fusion in Patients With K-line (-) Type Cervical Ossification of the Posterior Longitudinal Ligament With a 5-Year Minimum Follow-up.

STUDY DESIGN: A retrospective case-control study. OBJECTIVE: The objective of this study was to assess mid-term surgical outcomes after posterior decompression with instrumented fusion (PDF) in patients with K-line (-) type cervical ossification of the posterior longitudinal ligament (OPLL). SUMMARY OF BACKGROUND DATA: The poor surgical outcome for K-line (-) type cervical OPLL can result from posterior decompression alone. MATERIALS AND METHODS: We reviewed cases of K-line (-) type cervical OPLL in 24 patients who underwent PDF in our institute from 2002 to 2014. As a control, we used K-line (-) type cervical OPLL in 9 patients who underwent laminoplasty before 2002 (LMP group). The neurological status and radiographic findings were evaluated retrospectively. RESULTS: The preoperative Japanese Orthopedic Association score was 7.9±2.4 points in the PDF group and 7.4±2.3 points in the LMP group (P=0.584). The postoperative Japanese Orthopedic Association score was 11.7±2.6 points in the PDF group and 9.2±2.0 points in the LMP group at a 5-year follow-up (P=0.008). The recovery rate on average was 39.0% in the PDF group and 14.9% in the LMP group at a 5-year follow-up (P=0.037). The range of motion postoperatively at the maximal spinal cord compression level decreased significantly in the PDF group. The C2-C7 angle was 2.7 degrees of kyphosis in the PDF group, whereas 5.5 degrees of kyphosis was found in the LMP group at a 5-year follow-up (P=0.303). The center of gravity of the head-C7 sagittal vertical axis was 40 mm in the PDF group and 43 mm in the LMP group (P=0.936). CONCLUSIONS: The relatively good surgical outcome could be obtained by PDF for patients with K-line (-)-type cervical OPLL. The addition of posterior instrumented fusion eliminated the dynamic factor at the level of maximal spinal cord compression. LEVEL OF EVIDENCE: Level IV.

A Deep Convolutional Neural Network With Performance Comparable to Radiologists for Differentiating Between Spinal Schwannoma and Meningioma.

STUDY DESIGN: Retrospective analysis of magnetic resonance imaging (MRI). OBJECTIVE: The aim of this study was to evaluate the performance of our convolutional neural network (CNN) in differentiating between spinal schwannoma and meningioma on MRI. We compared the performance of the CNN and that of two expert radiologists. SUMMARY OF BACKGROUND DATA: Preoperative discrimination between spinal schwannomas and meningiomas is crucial because different surgical procedures are required for their treatment. A deep-learning approach based on CNNs is gaining interest in the medical imaging field. METHODS: We retrospectively reviewed data from patients with spinal schwannoma and meningioma who had undergone MRI and tumor resection. There were 50 patients with schwannoma and 34 patients with meningioma. Sagittal T2-weighted magnetic resonance imaging (T2WI) and sagittal contrast-enhanced T1-weighted magnetic resonance imaging (T1WI) were used for the CNN training and validation. The deep learning framework Tensorflow was used to construct the CNN architecture. To evaluate the performance of the CNN, we plotted the receiver-operating characteristic (ROC) curve and calculated the area under the curve (AUC). We calculated and compared the sensitivity, specificity, and accuracy of the diagnosis by the CNN and two board-certified radiologists. RESULTS: . The AUC of ROC curves of the CNN based on T2WI and contrast-enhanced T1WI were 0.876 and 0.870, respectively. The sensitivity of the CNN based on T2WI was 78%; 100% for radiologist 1; and 95% for radiologist 2. The specificity was 82%, 26%, and 42%, respectively. The accuracy was 80%, 69%, and 73%, respectively. By contrast, the sensitivity of the CNN based on contrast-enhanced T1WI was 85%; 100% for radiologist 1; and 96% for radiologist 2. The specificity was 75%, 56, and 58%, respectively. The accuracy was 81%, 82%, and 81%, respectively. CONCLUSION: We have successfully differentiated spinal schwannomas and meningiomas using the CNN with high diagnostic accuracy comparable to that of experienced radiologists. LEVEL OF EVIDENCE: 4.

Effectiveness of Clavicula Pro Humero Reconstruction for Elderly Patients: Report of Two Cases.

Clavicula pro humero (CPH) reconstruction is a method that is used after proximal humeral excision. During CPH reconstruction, the ipsilateral clavicle is rotated downward and connected to the preserved distal humerus by using plates and screws. This method is frequently used for reconstruction surgeries involving young patients and has positive outcomes. In this study, we describe two cases of CPH reconstruction that were performed on elderly individuals after wide resection of the proximal humerus; postoperative results from these surgeries were satisfactory. The average Musculoskeletal Tumor Society (MSTS) functional score after surgery was 68.5%, indicating that CPH reconstruction is suitable for not only younger but also elderly patients, particularly those over the age of 65 years.