A Novel Application of Deep Learning (Convolutional Neural Network) for Traumatic Spinal Cord Injury Classification Using Automatically Learned Features of EMG Signal.

In this study, a traumatic spinal cord injury (TSCI) classification system is proposed using a convolutional neural network (CNN) technique with automatically learned features from electromyography (EMG) signals for a non-human primate (NHP) model. A comparison between the proposed classification system and a classical classification method (k-nearest neighbors, kNN) is also presented. Developing such an NHP model with a suitable assessment tool (i.e., classifier) is a crucial step in detecting the effect of TSCI using EMG, which is expected to be essential in the evaluation of the efficacy of new TSCI treatments. Intramuscular EMG data were collected from an agonist/antagonist tail muscle pair for the pre- and post-spinal cord lesion from five Macaca fasicularis monkeys. The proposed classifier is based on a CNN using filtered segmented EMG signals from the pre- and post-lesion periods as inputs, while the kNN is designed using four hand-crafted EMG features. The results suggest that the CNN provides a promising classification technique for TSCI, compared to conventional machine learning classification. The kNN with hand-crafted EMG features classified the pre- and post-lesion EMG data with an F-measure of 89.7% and 92.7% for the left- and right-side muscles, respectively, while the CNN with the EMG segments classified the data with an F-measure of 89.8% and 96.9% for the left- and right-side muscles, respectively. Finally, the proposed deep learning classification model (CNN), with its learning ability of high-level features using EMG segments as inputs, shows high potential and promising results for use as a TSCI classification system. Future studies can confirm this finding by considering more subjects.

Neurophysiological Characterization of a Non-Human Primate Model of Traumatic Spinal Cord Injury Utilizing Fine-Wire EMG Electrodes.

This study aims to characterize traumatic spinal cord injury (TSCI) neurophysiologically using an intramuscular fine-wire electromyography (EMG) electrode pair. EMG data were collected from an agonist-antagonist pair of tail muscles of Macaca fasicularis, pre- and post-lesion, and for a treatment and control group. The EMG signals were decomposed into multi-resolution subsets using wavelet transforms (WT), then the relative power (RP) was calculated for each individual reconstructed EMG sub-band. Linear mixed models were developed to test three hypotheses: (i) asymmetrical volitional activity of left and right side tail muscles (ii) the effect of the experimental TSCI on the frequency content of the EMG signal, (iii) and the effect of an experimental treatment. The results from the electrode pair data suggested that there is asymmetry in the EMG response of the left and right side muscles (p-value < 0.001). This is consistent with the construct of limb dominance. The results also suggest that the lesion resulted in clear changes in the EMG frequency distribution in the post-lesion period with a significant increment in the low-frequency sub-bands (D4, D6, and A6) of the left and right side, also a significant reduction in the high-frequency sub-bands (D1 and D2) of the right side (p-value < 0.001). The preliminary results suggest that using the RP of the EMG data, the fine-wire intramuscular EMG electrode pair are a suitable method of monitoring and measuring treatment effects of experimental treatments for spinal cord injury (SCI).

Model of Traumatic Spinal Cord Injury for Evaluating Pharmacologic Treatments in Cynomolgus Macaques (Macaca fasicularis).

Here we present the results of experiments involving cynomolgus macaques, in which a model of traumatic spinal cord injury (TSCI) was created by using a balloon catheter inserted into the epidural space. Prior to the creation of the lesion, we inserted an EMG recording device to facilitate measurement of tail movement and muscle activity before and after TSCI. This model is unique in that the impairment is limited to the tail: the subjects do not experience limb weakness, bladder impairment, or bowel dysfunction. In addition, 4 of the 6 subjects received a combination treatment comprising thyrotropin releasing hormone, selenium, and vitamin E after induction of experimental TSCI. The subjects tolerated the implantation of the recording device and did not experience adverse effects due the medications administered. The EMG data were transformed into a metric of volitional tail moment, which appeared to be valid measure of initial impairment and subsequent natural or treatment-related recovery. The histopathologic assessment demonstrated widespread axon loss at the site of injury and areas cephalad and caudad. Histopathology revealed evidence of continuing inflammation, with macrophage activation. The EMG data did not demonstrate evidence of a statistically significant treatment effect.

Reduced variability of acetabular cup positioning with use of an imageless navigation system.

Positioning the acetabular component is one of the most important steps in total hip arthroplasty; malpositioned components can result in dislocations, impingement, limited range of motion, and increased polyethylene wear. Conventional surgery makes use of specialized alignment guides provided by the manufacturers of the implants. The use of mechanical guides has been shown to result in large variations of cup inclination and version. We investigated acetabular cup alignment with the nonimage-based hip navigation system compared with a conventional mechanically guided procedure in 12 human cadavers. Postoperative cup position relative to the pelvic reference plane was assessed in both groups with the use of a three-dimensional digitizing arm. In the navigated group, a median inclination of 45.5 degrees and a median anteversion of 21.9 degrees (goals, 45 degrees and 20 degrees) were reached. In the control group, the median inclination was 41.8 degrees and the median anteversion was 24.6 degrees. The ninetieth percentile showed a much wider range for the control group (36.1 degrees-51.8 degrees inclination, 15 degrees-33.5 degrees anteversion) than for the navigated group (43.9 degrees-48.2 degrees inclination, 18.3 degrees-25.4 degrees anteversion). This cadaver study shows that computer-assisted cup positioning using a nonimage-based hip navigation system allowed for more consistent placement of the acetabular component.

Similarities and differences in the treatment of spine trauma between surgical specialties and location of practice.

STUDY DESIGN: Questionnaires administered to practicing orthopedic and neurosurgical spine surgeons from various regions of the United States and abroad. OBJECTIVES: To determine similarities and differences in the treatment of spinal trauma. SUMMARY OF BACKGROUND DATA: Spinal trauma is generally referred to subspecialists of orthopedic or neurosurgical training. Prior studies have suggested that there is significant variability in the management of such injuries. METHODS: Questionnaires based on eight clinical scenarios of commonly encountered cervical, thoracic, and lumbar injuries were administered to 35 experienced spinal surgeons. Surgeons completed profile information and answered approximately one dozen questions for each case. Data were analyzed with SPSS software to determine the levels of agreement and characteristics of respondents that might account for a lack of agreement on particular aspects of management. RESULTS: Of the 35 surgeons completing the questionnaire, 63% were orthopedists, 37% were neurosurgeons, and 80% had been in practice for more than 5 years. Considerable agreement was found in the majority of clinical decisions, including whether or not to operate and the timing of surgery. Of the differences noted, neurosurgeons were more likely to obtain a MRI, and orthopedists were more likely to use autograft as a sole graft material. Physicians from abroad were, in general, more likely to operate and to use an anterior approach during surgery than physicians from the northeastern United States. CONCLUSIONS: More commonalities were identified in the management of spinal trauma than previously reported. When found, variability in opinion was related to professional and regional differences.

Traumatic labral avulsion from the stable rim: a constant pathology in displaced transverse acetabular fractures.

INTRODUCTION: During the treatment of a malunited transverse acetabular fracture, a hitherto undescribed extended avulsion of the labrum from the stable acetabular fragment was found. Based on the labral pathomorphology present in this case, the hypothesis was put forward that traumatic acetabular labral avulsions are a constant phenomenon in transverse acetabular fractures. PATIENTS AND METHODS: Fourteen patients underwent capsulotomy and/or surgical dislocation of the involved hip to facilitate open reduction and internal fixation of transverse acetabular fractures. RESULTS: In all cases, the labrum was partially or completely detached from the superior acetabular rim. In eight cases with bucket-handle tears of the labrum from the stable superior fragment, the injured portion was resected back to normal margins. In one case the labrum was avulsed with an attached piece of bone and was repaired by screw fixation. Small separations of the labrum from the underlying acetabular rim occurred at the level of the fractures in five cases with minor displacement and received no treatment. CONCLUSION: With displaced transverse acetabular fractures, consideration should be given to opening the joint at the time of open reduction and internal fixation to look for associated intracapsular injuries. An avulsed portion of the labrum should be left if stable and undamaged. If unstable and damaged, it is probably better resected and if unstable but intact and/or attached to a bony fragment, it should be repaired.

An algorithm for the treatment of Vancouver type B2 periprosthetic proximal femoral fractures.

The number of individuals with periprosthetic fractures of the proximal part of the femur is increasing. Multiple treatment methods have been described but none that correlate to fracture type and few with mostly good-to-excellent results. This article describes an algorithmic reconstruction tactic for treating patients with periprosthetic fractures associated with a loose femoral component. The stem is approached through the fracture fragments. Reconstructing the tube of the proximal part of the femur with 18G cerclage wires allows for canal preparation and implantation of the new stem. Application of the allograft struts and cables maximizes the biomechanical integrity of the proximal part of the femur to promote fracture repair and implant fixation. No treatment failures have occurred as of this date.