Recent years have witnessed wider prevalence of vertebral column pathologies due to lifestyle changes, sedentary behaviors, or injuries. Spondylolisthesis and scoliosis are two of the most common ailments with an incidence of 5% and 3% in the United States population, respectively. Both of these abnormalities can affect children at a young age and, if left untreated, can progress into severe pain. Moreover, severe scoliosis can even lead to lung and heart problems. Thus, early diagnosis can make it easier to apply remedies/interventions and prevent further disease progression. Current diagnosis methods are based on visual inspection by physicians of radiographs and/or calculation of certain angles (e.g., Cobb angle). Traditional artificial intelligence-based diagnosis systems utilized these parameters to perform automated classification, which enabled fast and easy diagnosis supporting tools. However, they still require the specialists to perform error-prone tedious measurements. To this end, automated measurement tools were proposed based on processing techniques of X-ray images. In this paper, we utilize advances in deep transfer learning to diagnose spondylolisthesis and scoliosis from X-ray images without the need for any measurements. We collected raw data from real X-ray images of 338 subjects (i.e., 188 scoliosis, 79 spondylolisthesis, and 71 healthy). Deep transfer learning models were developed to perform three-class classification as well as pair-wise binary classifications among the three classes. The highest mean accuracy and maximum accuracy for three-class classification was 96.73% and 98.02%, respectively. Regarding pair-wise binary classification, high accuracy values were achieved for most of the models (i.e., > 98%). These results and other performance metrics reflect a robust ability to diagnose the subjects’ vertebral column disorders from standard X-ray images. The current study provides a supporting tool that can reasonably help the physicians make the correct early diagnosis with less effort and errors, and reduce the need for surgical interventions.

Background: spondylolisthesis is a condition in which a vertebra slips out of the proper position onto the bone below it as a result of pars interarticularis defect. The slipped segment produces abnormal positioning of the vertebrae in relation to each other along the spinal column and causes mechanical back pain and neural breach.Materials and methods: A randomized and double blinded study consisted of 41 patients aged 36-69 years (18 females and 28 males) treated for symptomatic spondylolisthesis between December,2006 and December, 2009. All patients were randomly distributed into two groups I and II. Twenty patients were in Group I; they underwent reduction of the slipped vertebrae by using Reduction-Screw Technique and posterior lumbar interbody fixation (PLIF). Group II consisted of twenty one patients who underwent only surgical fixation (PLIF) without reduction. All patients in this study had same pre and post operative management.Results: only one case had broken rod in group I that required revision. Superficial wound infection was experienced in two patients and one patient, from group II, developed wound hematoma. The outcome in both groups was variable on the short term but was almost the same on the long term follow up.Conclusion: surgical management of symptomatic low grade spondylolisthesis should include neural decompression and surgical fixation. Reduction of slipped vertebral bodies is unnecessary as the ultimate outcome will be likely similar.

Giant cell tumor of bone is a benign tumor with an aggressive behavior. Its typical subarticular location and high recurrence risk can be associated with significant morbidity. Although benign, it can rarely metastasize especially to the lungs. Also, it can be multicentric in less than 1% of patients. Late malignant transformation, although rare, can occur with a very poor prognosis. This series reports on these unusual and challenging features and management considerations of giant cell tumor of bone. This retrospective study included review of the medical records of patients with a confirmed histopathological diagnosis of giant cell tumor of bone. A total of 25 patients (16 females and 9 males) with a mean age of 34.5 years were included; 22 had primary tumors, while 3 were referred with recurrent tumors. Pain was the most common presenting symptom. Most patients had grade III tumors. Tumors around the knee were the most common. Multicentric tumors were detected in three patients. Twenty-three patients (20 primary giant cell tumor of bone and 3 with recurrence) received treatment. Most patients (15/23) were treated with intralesional curettage with or without adjuvants. Seven patients had wide excision. Recurrence was seen in 45% (9/20) of primary giant cell tumor of bone especially with difficult anatomical locations. Most recurrences occurred more than 4 years after treatment. Pulmonary nodules were detected in four patients; two of them showed resolution during follow-up. One patient developed secondary sarcoma transformation with a fatal outcome. Giant cell tumor of bone was more common in females. Long bones were more affected, especially around the knee. Intralesional curettage was the most frequently used treatment. Recurrence was associated with inadequate tumor resection (especially in difficult anatomical location), younger age, male gender, and advanced local tumor grade. Denosumab can be used in the treatment of pulmonary metastasis, multicentric and recurrent giant cell tumor of bone. Due to late recurrence and malignant transformation, a prolonged follow-up is warranted.

Background: Cervical spondylotic myelopathy increases with age, but not all cases are symptomatic. It is usually diagnosed clinically and radiologically (X-ray and magnetic resonance imaging). Surgical treatment is indicated in severe symptomatic cases, while treatment controversy exists in the presence of less severe cases. Anterior and posterior approaches are generally used for decompression with no significant differences in the results of both. Methods: A total of 287 patients of cervical spondylotic myelopathy were treated at our hospital between January 2004 and December 2015. Only 140 patients were eligible for our study. They had at least 5 years of follow-up using full clinical scores and radiological evaluation. They were divided into two groups: group I with 73 patients (aged 23–79 years) underwent posterior decompression, lateral mass instrumentation, and fusion, while group II with 67 patients (aged 33–70 years) underwent anterior decompression, instrumentation, and fusion. Neck Disability Index, local score, and X-ray were used in the evaluation of the patients. Results: Preoperative mean ± standard deviation of Neck Disability Index of both the groups was 32.06 ± 6.33 and 29.88 ± 5.48, which improved in the last visit (>5 years) to 5.81 ± 7.39 and 2.94 ± 5.48 for groups I and II, respectively (p value <0.05). The local score of groups I and II was (P = 1, F = 21, G = 31, E = 19) and (P = 1, F = 12, G = 36, E = 18), which on discharge day improved to (P = 1, F = 4, G = 12, E = 55) and (P = 0, F = 3, G = 6, E = 58) at last follow-up, respectively. Fusion rate was nearly equal for both the groups during all the follow-up intervals and it was 91.1% and 91.7% in the last follow-up. Conclusion: There were no significant differences in the clinical and radiological results between the anterior and posterior approaches used in the surgical treatment of spondylotic cervical myelopathy. However, statistically significant results of Neck Disability Index of anterior approach were not clinically important and may be due to changes in the size and shape of the neck in group II.

This study evaluates the outcome and complications of decompressive cervical Laminectomy and lateral mass screw fixation in 110 cases treated for variable cervical spine pathologies that included; degenerative disease, trauma, neoplasms, metabolic-inflammatory disorders and congenital anomalies.