Background To determine the related imaging findings and risk factors to refracture of the cemented vertebrae after percutaneous vertebroplasty (PVP) treatment. Methods Patients who were treated with PVP for single vertebral compression fractures (VCFs) and met this study’s inclusion criteria were retrospectively reviewed from January 2012 to January 2019. The follow-up period was at least 2 years. Forty-eight patients with refracture of the cemented vertebrae and 45 non-refractured patients were included. The following variates were reviewed: age, sex, fracture location, bone mineral density (BMD), intravertebral cleft (IVC), kyphotic angle (KA), wedge angle, endplate cortical disruption, cement volume, surgical approach, non-PMMA-endplate-contact (NPEC), cement leakage, other vertebral fractures, reduction rate (RR), and reduction angle (RA). Multiple logistic regression modeling was used to identify the independent risk factors of refracture. Results Refracture was found in 48 (51.6%) patients. Four risk factors, including IVC (P = 0.005), endplate cortical disruption (P = 0.037), larger RR (P = 0.007), and NPEC (P = 0.006) were found to be significant independent risk factors for refracture. Conclusions Patients with IVC or larger RR, NPEC, or endplate cortical disruption have a high risk of refracture in the cemented vertebrae after PVP.

ObjectiveTo develop and validate an artificial intelligence diagnostic system based on X-ray imaging data for diagnosing vertebral compression fractures (VCFs)MethodsIn total, 1904 patients who underwent X-ray at four independent hospitals were retrospectively (n=1847) and prospectively (n=57) enrolled. The participants were separated into a development cohort, a prospective test cohort and three external test cohorts. The proposed model used a transfer learning method based on the ResNet-18 architecture. The diagnostic performance of the model was evaluated using receiver operating characteristic curve (ROC) analysis and validated using a prospective validation set and three external sets. The performance of the model was compared with three degrees of musculoskeletal expertise: expert, competent, and trainee.ResultsThe diagnostic accuracy for identifying compression fractures was 0.850 in the testing set, 0.829 in the prospective set, and ranged from 0.757 to 0.832 in the three external validation sets. In the human and deep learning (DL) collaboration dataset, the area under the ROC curves(AUCs) in acute, chronic, and pathological compression fractures were as follows: 0.780, 0.809, 0.734 for the DL model; 0.573, 0.618, 0.541 for the trainee radiologist; 0.701, 0.782, 0.665 for the competent radiologist; 0.707,0.732, 0.667 for the expert radiologist; 0.722, 0.744, 0.610 for the DL and trainee; 0.767, 0.779, 0.729 for the DL and competent; 0.801, 0.825, 0.751 for the DL and expert radiologist. ConclusionsOur study offers a high-accuracy multi-class deep learning model which could assist community-based hospitals in improving the diagnostic accuracy of VCFs.

ObjectivesTo assess the diagnostic accuracy of diffusion-weighted imaging (DWI) in predicting the malignant potential in patients with intraductal papillary mucinous neoplasms (IPMNs) of the pancreas.MethodsA systematic search of articles investigating the diagnostic performance of DWI for prediction of malignant potential in IPMNs was conducted from PubMed, Embase, and Web of Science from January 1997 to 10 February 2020. QUADAS-2 tool was used to evaluate the study quality. Pooled sensitivity, specificity, diagnostic odds ratio (DOR), positive likelihood ratios (PLR), negative likelihood ratios (NLR), and their 95% confidence intervals (CIs) were calculated. The summary receiver operating characteristic (SROC) curve was then plotted, and meta-regression was also performed to explore the heterogeneity.ResultsFive articles with 307 patients were included. The pooled sensitivity and specificity of DWI were 0.74 (95% CI: 0.65, 0.82) and 0.94 (95% CI: 0.78, 0.99), in evaluating the malignant potential of IPMNs. The PLR was 13.5 (95% CI: 3.1, 58.7), the NLR was 0.27 (95% CI: 0.20, 0.37), and DOR was 50.0 (95% CI: 11.0, 224.0). The area under the curve (AUC) of SROC curve was 0.84 (95% CI: 0.80, 0.87). The meta-regression showed that the slice thickness of DWI (p = 0.02) and DWI parameter (p= 0.01) were significant factors affecting the heterogeneity.ConclusionsDWI is an effective modality for the differential diagnosis between benign and malignant IPMNs. The slice thickness of DWI and DWI parameter were the main factors influencing diagnostic specificity.

No abstract

Objective To develop and validate a deep learning (DL) model based on CT for differentiating bone islands and osteoblastic bone metastases. Materials and methods The patients with sclerosing bone lesions (SBLs) were retrospectively included in three hospitals. The images from site 1 were randomly assigned to the training (70%) and intrinsic verification (10%) datasets for developing the two-dimensional (2D) DL model (single-slice input) and “2.5-dimensional” (2.5D) DL model (three-slice input) and to the internal validation dataset (20%) for evaluating the performance of both models. The diagnostic performance was evaluated using the internal validation set from site 1 and additional external validation datasets from site 2 and site 3. And statistically analyze the performance of 2D and 2.5D DL models. Results In total, 1918 SBLs in 728 patients in site 1, 122 SBLs in 71 patients in site 2, and 71 SBLs in 47 patients in site 3 were used to develop and test the 2D and 2.5D DL models. The best performance was obtained using the 2.5D DL model, which achieved an AUC of 0.996 (95% confidence interval [CI], 0.995–0.996), 0.958 (95% CI, 0.958–0.960), and 0.952 (95% CI, 0.951–0.953) and accuracies of 0.950, 0.902, and 0.863 for the internal validation set, the external validation set from site 2 and site 3, respectively. Conclusion A DL model based on a three-slice CT image input (2.5D DL model) can improve the prediction of osteoblastic bone metastases, which can facilitate clinical decision-making. Key Points • This study investigated the value of deep learning models in identifying bone islands and osteoblastic bone metastases. • Three-slice CT image input (2.5D DL model) outweighed the 2D model in the classification of sclerosing bone lesions. • The 2.5D deep learning model showed excellent performance using the internal (AUC, 0.996) and two external (AUC, 0.958; AUC, 0.952) validation sets.