Kaixiang Yang

Background: Osteoporotic vertebral compression fractures (OVCFs) are a common spinal disease. Differentiating acute and chronic fractures is the key to determining the treatment plan. To develop and evaluate a deep learning model capable of differentiating acute and chronic OVCFs on CT images. Methods: The internal dataset comprised CT images of 624 fractured vertebrae from 400 patients with OVCF treated at Hospital 1 between January 1, 2020, and November 1, 2023. The patients were randomly divided into a training set (340 patients, 532 fractured vertebrae, 85.0%) and an internal testing set (60 patients, 92 fractured vertebrae, 15.0%). An external testing set included CT images of 86 fractured vertebrae from 70 patients with OVCF treated at Hospital 2 from January 1, 2023, to November 1, 2023, using identical inclusion criteria. Three radiologists manually delineated regions of interest (ROIs) in CT images of diseased vertebrae using Anaconda Prompt software with rectangular bounding boxes. The trained YOLO v7 model’s performance was evaluated on both the internal and external testing sets and compared with that of the three radiologists using metrics with accuracy, sensitivity, specificity, and AUC. Results: The internal testing set revealed the following: AUC, 0.937 (95%CI: 0.932–0.991); accuracy, 0.961 (0.930–0.977); sensitivity, 0.973 (95%CI: 0.958–0.994); specificity, 0.761 (95%CI: 0.728–0.784); precision, 0.936 (95%CI: 0.920–0.966), and F1 score; 0.954 (95%CI: 0.913–0.975). The external testing set revealed the following: AUC, 0.882 (95%CI: 0.839–0.894); accuracy, 0.852 (95%CI: 0.827–0.886); sensitivity, 0.895 (95%CI: 0.840–0.913); specificity, 0.780 (95%CI: 0.730–0.812); precision, 0.874 (95%CI: 0.839–0.892); and F1 score, 0.884 (95%CI: 0.846–0.903). Conclusion: The YOLO v7 model achieved good performance for CT-based differentiation of acute versus chronic OVCFs in patients and showed better performance compared to radiologists in both testing sets, which may serve as a decision-support tool for CT-equivocal cases.

Background Currently, the primary treatment for ulnar neuropathy at the elbow is open in-situ decompression surgery. The effectiveness of ultrasound localization therapy, especially small-incision surgery using ultrasound combined with SWE, remains unclear. Objectives To evaluate the effect of small-incision ulnar nerve release in treating ulnar neuropathy at the elbow by ultrasound combined with shear wave elastography (SWE). Methods A retrospective analysis of 98 patients treated in our hospital for ulnar neuropathy at the elbow was conducted from June 2023 to March 2025. According to the treatment style, these patients were divided into a traditional open in-situ decompression surgery group (n = 51) and an ultrasound combined with SWE small-incision surgery group (n = 47). The maximum proximal Cross-sectional Area (CSA), Sensory Conduction Velocity (SCV), Motor Conduction Velocity (MCV), modified Bishop score, Quick-DASH score, and Visual Analogue Scale(VAS) score were compared between the two groups. Additionally, the amount of intraoperative blood loss, operation duration, hospital stay, patients' satisfaction with postoperative incision aesthetics, the postoperative complications of different operation methods, and the degree of damage to the medial cutaneous nerve of the forearm were studied. Results All patients underwent surgical treatment, with preoperative ultrasonography confirming no ulnar nerve subluxation. No statistically significant differences in age, preoperative SCV, MCV, CSA, Quick-DASH score, or VAS score were found between the two groups. The postoperative and the last follow-up SCV, MCV, and CSA were similar in the two groups. In addition, the improved Bishop score, Quick-DASH score, VAS score, postoperative hematoma rate, elbow stiffness rate, and postoperative protection of the medial cutaneous nerve of the forearm in the ultrasound combined with SWE surgery group were better than those in the traditional open surgery group. What’s more, compared with the traditional open surgery group, the ultrasound combined with SWE surgery reduced the amount of intraoperative blood loss, shortened the operation duration and hospital stay, and the patients were more satisfied with the scar of the incision. Conclusions For patients with ulnar neuropathy at the elbow who are amenable to in situ decompression, this study highlights the potential of preoperative ultrasound combined with SWE to guide a targeted, minimally invasive surgical approach.

Pedicle screw fixation is a well-established technique for thoracolumbar fracture. A large number of studies have shown that the bending angle of the connecting rod has a significant correlation with the postoperative spinal stability. However, no studies have confirmed an objective indicator to guide the bending angle of the connecting rod during the operation. Our study aims to define a sagittal Cobb* angle to guide the bending angle of the connecting rod during surgery. The frontal and lateral X-ray films in 150 cases of normal thoracolumbar spine were included to measure the normal spinal sagittal Cobb* angle in each segment. The patients who underwent single segment thoracolumbar fractures and pedicle screw internal fixation surgery were included. The radiological parameters included lumbar lordosis (LL), thoracic kyphosis (TK), pelvic tilt (PT), pelvic incidence (PI), sagittal vertical axis (SVA), and sacral slope (SS) were measured. The incidence of adjacent segment degeneration (ASD) 2 years after surgery was measured. The average values of normal sagittal Cobb* angle in each segment were − 5.196 ± 3.318° (T12), 2.279 ± 3.324° (L1), 7.222 ± 2.798° (L2), and 12.417 ± 11.962° (L3), respectively. The LL in the three groups was 35.20 ± 9.12°, 46.26 ± 9.68°, and 54.24 ± 15.31°, respectively. Compared with the normal group, there were significant differences in group A and group C, respectively (p < 0.05). The results were similar in the parameters of TL, PT, and SS. The incidences of SVA > 50 mm in group A, group B, and group C were 23.33%, 12.50%, and 19.23%, respectively. The parameter of PI in three groups was 41.36 ± 12.69, 44.53 ± 15.27, and 43.38 ± 9.85°, respectively. The incidences of ASD in group A, group B, and group C 2 years after surgery were 21.67%, 13.75%, and 17.95%, respectively. The study confirmed that the sagittal Cobb* angle can be used as a reference angle for bending rods. When the bending angle of the connecting rod is 4 to 8° greater than the corresponding segment sagittal Cobb* angle, the patient’s spinal sagittal stability is the best 2 years after the operation.