Search

Study Design: Retrospective observational study., Objective: To demonstrate the clinical usefulness of deep learning by identifying previous spinal implants through application of deep learning., Summary of Background Data: Deep learning has recently been actively applied to medical images. However, despite many attempts to apply deep learning to medical images, the application has rarely been successful. We aimed to demonstrate the effectiveness and usefulness of deep learning in the medical field. The goal of this study was to demonstrate the clinical usefulness of deep learning by identifying previous spinal implants through application of deep learning., Methods: For deep learning algorithm development, radiographs were retrospectively obtained from clinical cases in which the patients had lumbar spine one-segment instrument surgery. A total of 2894 lumbar spine anteroposterior (AP: 1446 cases) and lateral (1448 cases) radiographs were collected. Labeling work was conducted for five different implants. We conducted experiments using three deep learning algorithms. The traditional deep neural network model built by coding the transfer learning algorithm, Google AutoML, and Apple Create ML. Recall (sensitivity) and precision (specificity) were measured after training., Results: Overall, each model performed well in identifying each pedicle screw implant. In conventional transfer learning, AP radiography showed 97.0% precision and 96.7% recall. Lateral radiography showed 98.7% precision and 98.2% recall. In Google AutoML, AP radiography showed 91.4% precision and 87.4% recall; lateral radiography showed 97.9% precision and 98.4% recall. In Apple Create ML, AP radiography showed 76.0% precision and 73.0% recall; lateral radiography showed 89.0% precision and 87.0% recall. In all deep learning algorithms, precision and recall were higher in lateral than in AP radiography., Conclusion: The deep learning application is effective for spinal implant identification. This demonstrates that clinicians can use ML-based deep learning applications to improve clinical practice and patient care.Level of Evidence: 3., (Copyright © 2021 Wolters Kluwer Health, Inc. All rights reserved.)

Study Design: Retrospective study., Objective: The preoperative parameters for predicting the loss of lordosis after cervical laminoplasty were investigated in the present study., Summary of Background Data: Cervical laminoplasty is an effective surgical method to decompress the cervical spinal cord. Maintaining cervical lordosis after laminoplasty is an important factor to ensure the successful surgical treatment. To know the preoperative parameters for predicting loss of lordosis after cervical laminoplasty is important for better outcome after laminoplasty., Methods: In this retrospective study, 106 patients who underwent cervical laminoplasty from 2011 to 2015 were reviewed. The preoperative parameters; T1 slope (TS), Cobb lordotic angle (CLA) and sagittal vertical axis (SVA) at C2-C7, relative cross-sectional area (RCSA), and fatty degeneration of deep extensor muscles (DEMs) were measured. Visual analogue scale (VAS) and modified Japanese Orthopedic Association (mJOA) scores were used for clinical assessment. Correlation analysis was performed between the postoperative CLA change and preoperative parameters. The patients were divided into the decreased- or maintained-lordosis groups based on the difference between postoperative and preoperative CLA. All preoperative parameters were compared between groups., Results: Based on correlation analysis, preoperative TS (P = 0.001), TS-CLA (P = 0.046), RCSA at C7-T1 (P < 0.001), and fatty degeneration of DEMs (P < 0.001) were correlated with loss of lordosis. Among the 106 patients, 68 showed decreased-lordosis and 38 maintained-lordosis. Preoperative TS (P = 0.003), SVA (P = 0.014), TS-CLA (P = 0.015), and RCSA at C7-T1 (P = 0.005) were significantly different between groups. In both correlation and comparative analyses, higher TS and TS-CLA and less RCSA at C7-T1 were associated with loss of lordosis. Neck pain VAS (P < 0.001) and mJOA scores (P < 0.001) were significantly improved in the maintained-lordosis group., Conclusion: Maintaining cervical lordosis is important for clinical outcomes after laminoplasty. Preoperative higher TS, TS-CLA, and less RCSA at C7-T1 were considered as predictors for loss of lordosis. These characteristics should be considered when choosing the surgical method to help maintain cervical lordosis., Level of Evidence: 3.

We conducted a retrospective study to compare the clinical and radiological results of anterior cervical discectomy and fusion (ACDF) and posterior laminoplasty for two-level localized ossification of the posterior longitudinal ligament (OPLL).ACDF and posterior laminoplasty are performed for localized OPLL at the disc and vertebral body levels, respectively.Eighty six patients with two-level localized OPLL who underwent surgery from January 2011 to December 2016 were retrospectively investigated (41, ACDF group; 45, laminoplasty group). Clinical outcomes were reviewed, and radiologic results such as occupying ratio (OR), space available in the spinal cord, cranial and caudal OPLL-to-disc distance (ODD)/posterior body height (PBH) ratios, segmental angle, C2-C7 Cobb angle, T1 slope, C2-C7 sagittal vertical axis (SVA), and range of motion were investigated.Patients were followed-up for an average of 42.7 ± 10.5 months. Clinical outcomes, postoperative OR, and space available in the spinal cord were significantly improved at the final follow-up in both groups. Preoperatively, the OR and cranial and caudal ODD/PBH ratios were not significantly different between the groups. Compared to pre-operative values, differences in the segmental and C2-C7 Cobb angles at the final follow-up were statistically significant for the ACDF group (P < .05). The mean operative time, bleeding volume, and the duration of hospitalization were significantly lower in the ACDF group than in the laminoplasty group (P < .05). Complications occurred in 1 ACDF case and in 5 laminoplasty cases.Both ACDF and laminoplasty provided satisfactory clinical and radiologic outcomes for two-level localized OPLL. However, ACDF was associated with a lower operation time, bleeding loss, duration of hospitalization, and complications.

Study Design: A retrospective investigation of clinical and radiologic outcomes after surgical treatment for 2-level cervical spondylotic myelopathy (CSM)., Objective: The study was undertaken to compare the outcomes of 2 different anterior approach types for 2-level CSM. Specifically, 2-level anterior cervical discectomy and fusion (ACDF) was compared with 1-level anterior cervical corpectomy and fusion (ACCF)., Summary of Background Data: The optimal surgical approach for 2-level CSM has not been defined, and thus, the relative merits of 2-level ACDF and 1-level ACCF remain controversial. However, few comparative studies have been conducted on these 2 surgical approaches., Methods: The authors reviewed the case histories of 31 patients that underwent surgical treatment for 2-level CSM from 2002 to 2006. Cases of myelopathy because of cervical ossification of posterior longitudinal ligament were excluded. Thirty-one patients (16 men and 15 women) of mean age 54.45 +/- 11.6 years (28 approximately 77) were included. The average follow-up period was 26.23 +/- 15.0 months (12 approximately 63). The authors compared perioperative parameters (hospital stays, bleeding amounts, operation times, complications), clinical parameters (Japanese Orthopedic Association scores, Visual Analog Scale scores for neck and arm pain), and radiologic parameters (total cervical range of motion, segmental range of motion, segmental height, cervical lordosis, fusion rate)., Results: Of these above parameters, operation time (P = 0.001) and bleeding amount (P = 0.001) were significantly greater in the ACCF group, whereas segmental height (P = 0.018) and postoperative cervical lordosis (P = 0.009) were significantly lower in the ACCF group. However, other parameters were not significantly different in the 2 groups., Conclusion: Surgical managements of 2-level CSM using ACDF or ACCF were found to be similar in terms of clinical outcomes. However, 2-level ACDF was found to be superior to 1-level ACCF in terms of operation times, bleeding amounts, and radiologic results.

Study Design: A retrospective investigation of patients who underwent decompressive surgery for cervical ossification of the posterior longitudinal ligament (OPLL)., Objective: In this study, we would like to introduce a new terminology for the phenomena of coexisting paraspinal ligament ossification in 2 adjacent spinal regions as "tandem ossification." The purpose of this study is to evaluate the incidence and features of tandem ossification in patients with cervical OPLL., Summary of Background Data: Sometimes, OPLL and ossification of the ligamentum flavum (OLF) may coexist in the cervical and thoracic spine on the account of similar pathogenesis. However, there has been only a few previous reports concerning about the incidence of concurrent thoracic ligament ossification in the patients with cervical OPLL., Methods: We reviewed the cervicothoracic magnetic resonance imaging (MRI) and computed tomography (CT) images of patients who underwent decompressive surgery for cervical OPLL in our institute during the last 5 years. Total 68 cases of cervical OPLL patients were included. All patients underwent surgical decompression due to cervical myelopathy or myeloradiculopathy. We focus, however, on the presence of thoracic tandem ossification found in 23 of these cases (33.8%); 21 had thoracic OLF, 5 had thoracic OPLL and 3 had both combined., Results: Six of the 23 patients (26.1%) with thoracic tandem ossification had myelopathic symptoms, and required secondary thoracic surgery within 3.3 months (1-7 months) of the original cervical procedures. There were no significant differences in age, sex, cervical OPLL type, or length of cervical OPLL between the patients with and without tandem ossification., Conclusion: Patients having cervical surgery for OPLL should also undergo simultaneous studies of the thoracic spine looking for tandem OPLL and/or OLF. The frequency of tandem lesions in this series was 23 of 68, with 6 requiring subsequent surgery for an evolving thoracic myelopathic deficit.