Search

Aims/Background Sacroiliitis is a challenging condition to diagnose accurately due to the subtle nature of its presentation in imaging studies. This study aims to improve the diagnostic accuracy of sacroiliitis by applying advanced machine learning techniques to computed tomography (CT) images. Methods We employed five convolutional neural network (CNN) models—Visual Geometry Group 16-layer Network (VGG16), ResNet101, DenseNet, Inception-v4, and ResNeXt-50—to analyze a dataset of 830 CT images, including both sacroiliitis and non-sacroiliitis cases. Each model's performance was evaluated using metrics such as accuracy, precision, recall, F1 score, Receiver Operating Characteristic (ROC), and Area Under the Curve (AUC). The interpretability of the models' decisions was enhanced using Gradient-weighted Class Activation Mapping (Grad-CAM) visualization. Results The ResNeXt-50 and Inception-v4 models demonstrated superior performance, achieving the highest accuracy and F1 scores among the tested models. Grad-CAM visualizations offered insights into the decision-making processes, highlighting the models' focus on relevant anatomical features critical for accurate diagnosis. Conclusion The use of CNN models, particularly ResNeXt-50 and Inception-v4, significantly improves the diagnosis of sacroiliitis from CT images. These models not only provide high diagnostic accuracy but also offer transparency in their decision-making processes, aiding clinicians in understanding and trusting Artificial Intelligence (AI)-driven diagnostics. [ABSTRACT FROM AUTHOR]

Objective: To assess a new intradermal locator device for percutaneous placement of lumbar pedicle screws. Material and methods: Patients were alternately assigned to two groups. The locator group underwent lumbar pedicle screw placement using the intradermal locator. The control group was aided by traditional fluoroscopy. Baseline demographics, visual analog scale (VAS) pain scores, operation time, intraoperative fluoroscopy time and guidewire insertion time were recorded. All postoperative CT scans were reviewed by an independent spine surgeon to grade screw placement accuracy. Results: Thirty-six patients (180 screws) were assigned to the locator group and 30 patients (128 screws) to the control group. The locator device could significantly reduce the fluoroscopy time [3.9 sec (SD = 1.9) vs. 9.6 sec (SD = 5.8), p < 0.001] and guidewire insertion time [2.69 min (SD = 0.67) vs. 4.49 min (SD = 1.96), p < 0.001] compared with the conventional method for each pedicle screw. The whole operation time of the locator group was shorter than that of the control group [2-segment: 243.2 min (SD = 16.9) vs. 301.7 min (SD = 14.9), p < 0.001; 1-segment: 154.5 min (SD = 14.3) vs. 194.6 min (SD = 19.3), p < 0.001]. As for the rates of pedicle breaches, postoperative VAS scores, no significant difference was found between the two groups. Conclusion: The intradermal locator device could help reduce the radiation exposure in percutaneous pedicle screw placement while maintaining the accuracy. [ABSTRACT FROM AUTHOR]

Objective: To introduce a new fluoroscopic method for assessing the quality of medial and lateral joint surface reduction during internal fixation of patellar fractures and to summarize the clinical outcomes of patients treated using this method., Methods: A retrospective analysis was conducted on the clinical data of 52 patients with patellar fractures treated between January 2018 and January 2022 who met the inclusion criteria. There were 27 male and 25 female patients, aged 21-75 years, with an average age of 62 years. The types of patellar fractures included 9 transverse fractures, 37 comminuted fractures, and 6 longitudinal fractures. According to the AO/Orthopaedic Trauma Association (AO-OTA)-2018 fracture classification, there were 21 cases of type 34A, 6 cases of type 34B, and 25 cases of type 34C. The time from injury to operation ranged from 1 to 5 days, with an average of 2.3 days. Treatments included internal fixation with hollow screws or hollow screw tension bands, with or without anchor repair. During operation, the medial and lateral joint surfaces of the patella were observed using the tangential fluoroscopic method to assess the smoothness of reduction of the median ridge, lateral joint surface, medial joint surface, and lateral joint edge. Patients were followed up regularly, and X-ray films were taken to observe fracture healing. Knee joint range of motion, Böstman score, and Lysholm score were used to evaluate functional recovery., Results: The tangential fluoroscopic method for the medial and lateral joint surfaces of the patella during operation showed satisfactory reduction of the joint surfaces and good positioning of the implants. All patients were followed up 12-16 months, with an average of 13.4 months. During the follow-up, fracture displacement occurred in 1 case and titanium cable breakage in 1 case. All patella fractures healed successfully, with a healing time of 8-16 weeks (mean, 11.4 weeks). At last follow-up, knee joint range of motion ranged from 120° to 140°, with an average of 136°. The Böstman score ranged from 20 to 30, with an average of 28, yielding excellent results in 45 cases and good results in 7 cases. The Lysholm score ranged from 88 to 100, with an average of 93, yielding excellent results in 40 cases and good results in 12 cases., Conclusion: The intraoperative application of the tangential fluoroscopic method for the medial and lateral joint surfaces of the patella can quickly determine the fluoroscopic plane of the patella, accurately assess the quality of fracture reduction and the position of internal fixator, thereby improving effectiveness.

Background: We aimed to elucidate the causal relationship between plasma metabolites and the vulnerability to Osteoarthritis (OA), encompassing both hip OA and knee OA., Methods: We conducted a two-way two-sample Mendelian randomization (MR) analysis to investigate the association of 1,400 plasma metabolites with OA. The Inverse Variance Weighted (IVW) model served as the primary two-sample MR Analysis method, with supplementary analysis using the Weighted Median (WM) and MR Egger methods. To ensure the robustness of our findings, sensitivity analyses were performed, incorporating Cochran's Q test, MR-Egger intercept test, MR-PRESSO, and Leave-One-Out analyses. To validate the identified metabolites, we utilized the Steiger test and linkage disequilibrium score regression., Results: A total of 94 plasma metabolites were associated with osteoarthritis, with 60 associated with hip OA and 106 associated with knee OA. IVW analysis revealed that tryptophan levels showed the strongest positive association with hip OA (OR [95% CI]: 1.119 [1.024, 1.223]), while X-24757 levels exhibited the highest positive association with knee osteoarthritis (OR [95% CI]: 1.095 [1.032, 1.162]). Ethylparaben sulfate levels were found to have the greatest positive association with hip OA (OR [95% CI]: 1.118 [1.015, 1.231]). Notably, the plasma metabolite X-2475 showed a strong robust random effect across all three types of osteoarthritis. Metabolic pathway analysis revealed that the pathogenesis of osteoarthritis in the hip was mediated by acetylarginine, specifically in four important metabolic pathways: ethanol degradation ( p  = 0.044), amino sugar metabolism ( p  = 0.090), fatty acid biosynthesis ( p  = 0.095), and aspartate metabolism ( p  = 0.097816)., Conclusion: There is a significant association between tryptophan levels and the risk of hip OA, as well as X-24757 levels and the risk of knee osteoarthritis. Additionally, X-24757 levels are also linked to the risk of hip OA. Moreover, this study has identified four crucial metabolic pathways in hip osteoarthritis, which are all regulated by acetylarginine. These findings provide valuable insights into potential biomarkers for OA and highlight potential pathways for its prevention and clinical intervention., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2024 Fu, Yuan, Wang, Han, Zhang, Wu and Wang.)

Aim: Spinal fractures, particularly vertebral compression fractures, pose a significant challenge in medical imaging due to their small-scale nature and blurred boundaries in Computed Tomography (CT) scans. However, advanced deep learning models, such as the integration of the You Only Look Once (YOLO) V7 model with Efficient Layer Aggregation Networks (ELAN) and Max-Pooling Convolution (MPConv) architectures, can substantially reduce the loss of small-scale information during computational processing, thus improving detection accuracy. The purpose of this study is to develop an innovative deep learning approach for detecting spinal fractures, particularly vertebral compression fractures, in CT images., Methods: We proposed a novel method to precisely identify spinal injury using the YOLO V7 model as a classifier. This model was enhanced by integrating ELAN and MPConv architectures, which were influenced by the Receptive Field Learning and Aggregation (RFLA) small object recognition framework. Standard normalization techniques were utilized to preprocess the CT images. The YOLO V7 model, integrated with ELAN and MPConv architectures, was trained using a dataset containing annotated spinal fractures. Additionally, to mitigate boundary ambiguities in compressive fractures, a Theoretical Receptive Field (TRF) based on Gaussian distribution and an Effective Receptive Field (ERF) were used to capture multi-scale features better. Furthermore, the Wasserstein distance was employed to optimize the model's learning process. A total of 240 CT images from patients diagnosed with spinal fractures were included in this study, sourced from Ningbo No.2 Hospital, ensuring a robust dataset for training the deep learning model., Results: Our method demonstrated superior performance over conventional object detection networks like YOLO V7 and YOLO V3. Specifically, with a dataset of 200 pathological images and 40 normal spinal images, our method achieved a 3% increase in accuracy compared to YOLO V7., Conclusions: The proposed method offers an innovative and more effective approach for identifying vertebral compression fractures in CT scans. These promising findings suggest the method's potential for practical clinical applications, highlighting the significance of deep learning in enhancing patient care and treatment in medical imaging. Future research should incorporate cross-validation and independent validation and test sets to assess the model's robustness and generalizability. Additionally, exploring other deep learning models and methods could further enhance detection accuracy and reliability, contributing to the development of more effective diagnostic tools in medical imaging.

Aim: We conducted a novel classification system of degenerative lumbar spinal stenosis (DLSS) based on clinical manifestations and imaging (computed tomography and magnetic resonance imaging) features. We chose different minimally invasive surgical procedures according to our system. Clinical parameters and radiological findings will be assessed in the article., Material and Methods: A retrospective study was conducted on 96 patients undergoing minimally invasive surgery for DLSS. We chose different surgical procedures according to our novel classification system based on clinical manifestations, imaging features, and concurrence with other spinal diseases. Clinical parameters and radiological findings were assessed pre- and postoperatively., Results: The mean follow up period was 24 months (range, 15~36 months). There was a statistically significant improvement in the Visual Analogue Scale (VAS) score of low back pain and leg pain after surgery (p < 0.05). According to the Japanese Orthopaedic Association (JOA) scores, the operation efficacy was excellent in 57 cases, good in 36 cases, and fair in 3 cases. According to Bridwell's criterion, the fusion rate was 96% (48/50) in patients who underwent fusion surgery. There were no cages or pedicle screws related complications., Conclusion: Minimally invasive surgical treatment of DLSS has satisfactory outcomes according to the novel classification, but further long-term, prospective, randomized controlled studies involving a larger study group are needed to validate the long-term efficacy.