Objective: To develop and evaluate a technique using convolutional neural networks (CNNs) for the computer-assisted diagnosis of cervical spine fractures from radiographic x-ray images. By leveraging deep learning techniques, the study might potentially lead to improved patient outcomes and clinical decision-making. Methods: This study obtained 500 lateral radiographic cervical spine x-ray images from standard open-source dataset repositories to develop a classification model using CNNs. All the images contained diagnostic information, including normal cervical radiographic images (n=250) and fracture images of the cervical spine fracture (n=250). The model would classify whether the patient had a cervical spine fracture or not. Seventy percent of the images were training data sets used for model training, and 30% were for testing. Konstanz Information Miner (KNIME)’s graphic user interface-based programming enabled class label annotation, data preprocessing, CNNs model training, and performance evaluation. Results: The performance evaluation of a model for detecting cervical spine fractures presents compelling results across various metrics. This model exhibits high sensitivity (recall) values of 0.886 for fractures and 0.957 for normal cases, indicating its proficiency in identifying true positives. Precision values of 0.954 for fractures and 0.893 for normal cases highlight the model’s ability to minimize false positives. With specificity values of 0.957 for fractures and 0.886 for normal cases, the model effectively identifies true negatives. The overall accuracy of 92.14% highlights its reliability in correctly classifying cases by the area under the receiver operating characteristic curve. Conclusion We successfully used deep learning models for computer-assisted diagnosis of cervical spine fractures from radiographic x-ray images. This approach can assist the radiologist in screening, detecting, and diagnosing cervical spine fractures.

Objective: To develop and evaluate a technique using convolutional neural networks (CNNs) for the computer-assisted diagnosis of cervical spine fractures from radiographic x-ray images. By leveraging deep learning techniques, the study might potentially lead to improved patient outcomes and clinical decision-making. Methods: This study obtained 500 lateral radiographic cervical spine x-ray images from standard open-source dataset repositories to develop a classification model using CNNs. All the images contained diagnostic information, including normal cervical radiographic images (n=250) and fracture images of the cervical spine fracture (n=250). The model would classify whether the patient had a cervical spine fracture or not. Seventy percent of the images were training data sets used for model training, and 30% were for testing. Konstanz Information Miner (KNIME)’s graphic user interface-based programming enabled class label annotation, data preprocessing, CNNs model training, and performance evaluation. Results: The performance evaluation of a model for detecting cervical spine fractures presents compelling results across various metrics. This model exhibits high sensitivity (recall) values of 0.886 for fractures and 0.957 for normal cases, indicating its proficiency in identifying true positives. Precision values of 0.954 for fractures and 0.893 for normal cases highlight the model’s ability to minimize false positives. With specificity values of 0.957 for fractures and 0.886 for normal cases, the model effectively identifies true negatives. The overall accuracy of 92.14% highlights its reliability in correctly classifying cases by the area under the receiver operating characteristic curve. Conclusion We successfully used deep learning models for computer-assisted diagnosis of cervical spine fractures from radiographic x-ray images. This approach can assist the radiologist in screening, detecting, and diagnosing cervical spine fractures.

Objective: To develop and evaluate a technique using convolutional neural networks (CNNs) for the computer-assisted diagnosis of cervical spine fractures from radiographic x-ray images. By leveraging deep learning techniques, the study might potentially lead to improved patient outcomes and clinical decision-making. Methods: This study obtained 500 lateral radiographic cervical spine x-ray images from standard open-source dataset repositories to develop a classification model using CNNs. All the images contained diagnostic information, including normal cervical radiographic images (n=250) and fracture images of the cervical spine fracture (n=250). The model would classify whether the patient had a cervical spine fracture or not. Seventy percent of the images were training data sets used for model training, and 30% were for testing. Konstanz Information Miner (KNIME)’s graphic user interface-based programming enabled class label annotation, data preprocessing, CNNs model training, and performance evaluation. Results: The performance evaluation of a model for detecting cervical spine fractures presents compelling results across various metrics. This model exhibits high sensitivity (recall) values of 0.886 for fractures and 0.957 for normal cases, indicating its proficiency in identifying true positives. Precision values of 0.954 for fractures and 0.893 for normal cases highlight the model’s ability to minimize false positives. With specificity values of 0.957 for fractures and 0.886 for normal cases, the model effectively identifies true negatives. The overall accuracy of 92.14% highlights its reliability in correctly classifying cases by the area under the receiver operating characteristic curve. Conclusion We successfully used deep learning models for computer-assisted diagnosis of cervical spine fractures from radiographic x-ray images. This approach can assist the radiologist in screening, detecting, and diagnosing cervical spine fractures.

Objective: To develop and evaluate a technique using convolutional neural networks (CNNs) for the computer-assisted diagnosis of cervical spine fractures from radiographic x-ray images. By leveraging deep learning techniques, the study might potentially lead to improved patient outcomes and clinical decision-making. Methods: This study obtained 500 lateral radiographic cervical spine x-ray images from standard open-source dataset repositories to develop a classification model using CNNs. All the images contained diagnostic information, including normal cervical radiographic images (n=250) and fracture images of the cervical spine fracture (n=250). The model would classify whether the patient had a cervical spine fracture or not. Seventy percent of the images were training data sets used for model training, and 30% were for testing. Konstanz Information Miner (KNIME)’s graphic user interface-based programming enabled class label annotation, data preprocessing, CNNs model training, and performance evaluation. Results: The performance evaluation of a model for detecting cervical spine fractures presents compelling results across various metrics. This model exhibits high sensitivity (recall) values of 0.886 for fractures and 0.957 for normal cases, indicating its proficiency in identifying true positives. Precision values of 0.954 for fractures and 0.893 for normal cases highlight the model’s ability to minimize false positives. With specificity values of 0.957 for fractures and 0.886 for normal cases, the model effectively identifies true negatives. The overall accuracy of 92.14% highlights its reliability in correctly classifying cases by the area under the receiver operating characteristic curve. Conclusion We successfully used deep learning models for computer-assisted diagnosis of cervical spine fractures from radiographic x-ray images. This approach can assist the radiologist in screening, detecting, and diagnosing cervical spine fractures.

Objective: To develop and evaluate a technique using convolutional neural networks (CNNs) for the computer-assisted diagnosis of cervical spine fractures from radiographic x-ray images. By leveraging deep learning techniques, the study might potentially lead to improved patient outcomes and clinical decision-making. Methods: This study obtained 500 lateral radiographic cervical spine x-ray images from standard open-source dataset repositories to develop a classification model using CNNs. All the images contained diagnostic information, including normal cervical radiographic images (n=250) and fracture images of the cervical spine fracture (n=250). The model would classify whether the patient had a cervical spine fracture or not. Seventy percent of the images were training data sets used for model training, and 30% were for testing. Konstanz Information Miner (KNIME)’s graphic user interface-based programming enabled class label annotation, data preprocessing, CNNs model training, and performance evaluation. Results: The performance evaluation of a model for detecting cervical spine fractures presents compelling results across various metrics. This model exhibits high sensitivity (recall) values of 0.886 for fractures and 0.957 for normal cases, indicating its proficiency in identifying true positives. Precision values of 0.954 for fractures and 0.893 for normal cases highlight the model’s ability to minimize false positives. With specificity values of 0.957 for fractures and 0.886 for normal cases, the model effectively identifies true negatives. The overall accuracy of 92.14% highlights its reliability in correctly classifying cases by the area under the receiver operating characteristic curve. Conclusion We successfully used deep learning models for computer-assisted diagnosis of cervical spine fractures from radiographic x-ray images. This approach can assist the radiologist in screening, detecting, and diagnosing cervical spine fractures.

The present systematic review and meta-analysis was conducted to compare the safety and efficacy of the two approaches for primary spinal cord tumors (PSCTs) in adult patients (laminoplasty [LP] vs. laminectomy [LE]). LE is one of the most common procedures for PSCTs. Despite advantages of LP, it is not yet widely used in the neurosurgical community worldwide. The efficacy of LP vs. LE remains controversial. Adult patients over 18 years of age with PSCT at the level of the cervical, thoracic, and lumbar spine were included in the study. A literature search was performed in MEDLINE via PubMed, EMBASE, The Cochrane Library, and Google Scholar up to December 2021. Operation time, hospital stay, complications, and incidence of postoperative spinal deformity (kyphosis or scoliosis were extracted. A total of seven retrospective observational studies with 540 patients were included. There were no significant differences between LP and LE group in operation time (p =0.25) and complications (p =0.48). The LE group showed larger postoperative spinal deformity rate than the LP group (odds ratio, 0.47; 95% confidence interval [CI], 0.27−0.84; p =0.01). The LP group had a shorter hospital stay (standardized mean differences, −0.68; 95% CI, −1.03 to −0.34; p =0.0001) than the LE group. Both LP and LE have comparable operative times and total complications in the treatment of PSCT. LP was superior to LE in hospital stay and postoperative spinal deformity rate. However, these findings are limited by the very low quality of the available evidence. Randomized controlled trials are needed for further comparison.

Methods: We used 1.0-mm interval computed tomographic scan images of 100 patients (50 men and 50 women) and screw trajectory simulation software. The diameter of all screws was set at 3.5 mm, considering its common usage in real surgery. The anatomical feasibility of placing both pedicle and laminar screws on the same side was evaluated. For all feasible sides, the three-dimensional distance between the screw entry points was measured. Results: In 85% of cases, both pedicle and laminar screws could be placed on both sides, allowing for the insertion of 4 screws. In 11% of cases, 2 screws could be placed on one side, while only 1 screw was feasible on the other side, resulting in the placement of 3 screws. In all 181 sides where both types of screws could be inserted, the distance between their entry points exceeded 16.1 mm, which was sufficient to prevent the collision between the screw heads. Conclusions C2 vertebra can accommodate three (11%) or four (85%) screws in 96% of cases.

Objectives: To compare disc degeneration between the cervical and lumbar spine and to elucidate the patterns of degeneration according to the corresponding disc levels in the cervical and lumbar spine.Summary of Literature Review: Disc degeneration results from the aging process in the spine. However, the incidence of disc degeneration in the cervical and lumbar spine might differ due to anatomical differences Materials and Methods: We randomly selected 280 patients by age and sex among 6,168 patients who underwent cervical or lumbar spine magnetic resonance imaging combined with whole-spine T2 sagittal images from June 2006 to March 2012. We classified disc degeneration by the modified Matsumoto grading system and the Pfirrmann classification at 11 intervertebral disc levels from C2 to T1 and from L1 to S1. Results: There was no significant difference in disc degeneration between the cervical and lumbar spine in either grading system. No significant difference was found in the degree of disc degeneration between the lower two disc levels of the cervical spine and the lower two disc levels of the lumbar spine in either system (C5-C6, C6-C7, L4-L5, L5-S1). However, both grading systems showed more severe degeneration in upper two disc levels of the cervical spine than in the upper two disc levels of the lumbar spine (C2-C3, C3-C4, L1-L2, L2- L3). Conclusions There was a significant difference in disc degeneration between the upper two disc levels of the cervical and lumbar spine. Adjacent segmental degeneration after fusion surgery might reflect the natural history of the condition, not adjacent segmental problems.

STUDY DESIGN: Retrospective radiographic study. OBJECTIVES: To evaluate the characteristics of concurrent degenerative cervical and lumbar spondylolisthesis. SUMMARY OF LITERATURE REVIEW: Concurrent degenerative cervical and lumbar spondylotic diseases have been reported. Given that severe spondylosis can result in spondylolisthesis, one might expect that concurrent spondylolisthesis of the cervical and lumbar spines might also be prevalent. However, the incidence of spondylolistheses in the lumbar and cervical spines might differ due to anatomical differences between the 2 areas. Nonetheless, there is minimal information in the literature concerning the incidence of concurrent cervical and lumbar spondylolisthesis. MATERIAL AND METHODS: We evaluated standing cervical and lumbar lateral radiographs of 2510 patients with spondylosis. Concurrence, age group, gender, and direction of spondylolisthesis were evaluated. Lumbar spondylolisthesis was defined as at least Meyerding grade I and degenerative cervical spondylolisthesis was defined as over 2 mm of displacement on standing lateral radiographs. RESULTS: Lumbar spondylolisthesis was found in 125 patients (5.0%) and cervical spondylolisthesis was found in 193 patients (7.7%). Seventeen patients had both degenerative cervical and lumbar spondylolistheses (0.7%). Lumbar spondylolisthesis is a risk factor for co-existing cervical spondylolisthesis. Lumbar spondylolisthesis was more common in females than males, independent of advancing age. In contrast, degenerative cervical spondylolisthesis was more common in older patients, independent of gender. Anterolisthesis was more common in the lumbar spine. Retrolisthesis was more common in the cervical spine. CONCLUSIONS: There was a higher prevalence of degenerative cervical spondylolisthesis in patients with degenerative lumbar spondylolisthesis.
Cervical Vertebrae ; Female ; Humans ; Incidence ; Lumbar Vertebrae ; Male ; Prevalence ; Retrospective Studies ; Risk Factors ; Spine ; Spondylolisthesis ; Spondylosis

OBJECTIVES: To evaluate the characteristics of concurrent degenerative cervical and lumbar spondylolisthesis.SUMMARY OF LITERATURE REVIEW: Concurrent degenerative cervical and lumbar spondylotic diseases have been reported. Given that severe spondylosis can result in spondylolisthesis, one might expect that concurrent spondylolisthesis of the cervical and lumbar spines might also be prevalent. However, the incidence of spondylolistheses in the lumbar and cervical spines might differ due to anatomical differences between the 2 areas. Nonetheless, there is minimal information in the literature concerning the incidence of concurrent cervical and lumbar spondylolisthesis.MATERIAL AND METHODS: We evaluated standing cervical and lumbar lateral radiographs of 2510 patients with spondylosis. Concurrence, age group, gender, and direction of spondylolisthesis were evaluated. Lumbar spondylolisthesis was defined as at least Meyerding grade I and degenerative cervical spondylolisthesis was defined as over 2 mm of displacement on standing lateral radiographs. RESULTS: Lumbar spondylolisthesis was found in 125 patients (5.0%) and cervical spondylolisthesis was found in 193 patients (7.7%). Seventeen patients had both degenerative cervical and lumbar spondylolistheses (0.7%). Lumbar spondylolisthesis is a risk factor for co-existing cervical spondylolisthesis. Lumbar spondylolisthesis was more common in females than males, independent of advancing age. In contrast, degenerative cervical spondylolisthesis was more common in older patients, independent of gender. Anterolisthesis was more common in the lumbar spine. Retrolisthesis was more common in the cervical spine. CONCLUSIONS There was a higher prevalence of degenerative cervical spondylolisthesis in patients with degenerative lumbar spondylolisthesis.