Vertebral fractures (VFs) cause serious problems, such as substantial functional loss and a high mortality rate, and a delayed diagnosis may further worsen the prognosis. Plain thoracolumbar radiography (PTLR) is an essential method for the evaluation of VFs. Therefore, minimizing the diagnostic errors of VFs on PTLR is crucial. Image identification based on a deep convolutional neural network (DCNN) has been recognized to be potentially effective as a diagnostic strategy; however, the accuracy for detecting VFs has not been fully investigated. A DCNN was trained with PTLR images of 300 patients (150 patients with and 150 without VFs). The accuracy, sensitivity, and specificity of diagnosis of the model were calculated and compared with those of orthopedic residents, orthopedic surgeons, and spine surgeons. The DCNN achieved accuracy, sensitivity, and specificity rates of 86.0% [95% confidence interval (CI) 82.0–90.0%], 84.7% (95% CI 78.8–90.5%), and 87.3% (95% CI 81.9–92.7%), respectively. Both the accuracy and sensitivity of the model were suggested to be noninferior to those of orthopedic surgeons. The DCNN can assist clinicians in the early identification of VFs and in managing patients, to prevent further invasive interventions and a decreased quality of life.

Introduction: Most people in modern societies spend the majority of their time sitting. However, sagittal spinal alignment is usually analyzed in the standing position. For understanding the symptoms associated with postural changes, this alignment is better to be analyzed in various positions. The purpose of this study was to investigate lumbo-pelvic relationships between standing up and sitting (sit-to-stand) motion. Methods: The study subjects were 25 healthy young adult volunteers without any spinal symptoms. The following parameters were measured, namely, intervertebral range of motion (IV ROM), lumbar lordotic angle (L1L5), sacral slope (SS), pelvic tilt (PT), and pelvic incidence (PI), on lateral whole-spine radiographs while sitting upright, sitting anterior flexed (anteflexed), standing anteflexed, and standing upright. Results: The measurements of spinopelvic parameters during sit-to-stand motion (sitting upright, sitting anteflexed, standing anteflexed, standing upright, respectively) were as follows:

No abstract

1Background: Preoperative cervico-thoracic kyphosis and cervical regional positive

BACKGROUND As the proportion of elderly people continues to increase, the number of patients with dropped head syndrome (DHS) also grows. However, the relationship between onset and clinical course of DHS has hardly been studied, particularly, that of sudden-onset DHS has not been reported and remains unclear. OBSERVATIONS Sudden-onset DHS was defined as presenting with chin on chest deformity within 3 days from the time of awareness of cervical weakness. Sixty-six patients with DHS visited our facility. Among them, 8 of the total cases (12.1%) had experienced sudden onset DHS (6 females and 2 males; average age: 71.9 ± 10.9 years). Six of 8 cases showed recovery by conservative treatment, whose first interventions were from 0.1 to 12 months, but 3 experienced recurrence. Diffuse spinal kyphotic-type DHS was seen in 2 cases, and both had recurring horizontal gaze disturbance after initial recovery. Two unimproved cases underwent surgery of combined anterior and posterior cervical fixation, and their first interventions were at 5 and 24 months. After surgery, cervical sagittal alignment was improved, and they could walk maintaining horizontal gaze. LESSONS Sudden-onset DHS can be expected to have a better outcome, but recurrence is possible in global imbalanced-type DHS.