Malignant Vertebral Compression Fractures Research Articles

Machine learning models based on CT radiomics features for distinguishing benign and malignant vertebral compression fractures in patients with malignant tumors.

Radiomics has become an important tool for distinguishing benign and malignant vertebral compression fractures (VCFs). It is more clinically significant to concentrate on patients who have malignant tumors and differentiate between benign and malignant VCFs. To explore the value of multiple machine learning (ML) models based on CT radiomics features for differentiating benign and malignant VCFs in patients with malignant tumors. This study retrospectively analyzed 78 patients with malignant tumors accompanied by VCFs, 45 patients with benign VCFs, and 33 patients with malignant VCFs. A total of 140 lesions (86 benign lesions, 54 malignant lesions) were ultimately included in this study. All patients were divided into training sets (n = 98) and validation sets (n = 42) according to the 7:3 ratio. The radiomics features were screened and dimensioned, and multiple radiomics ML models were constructed. The receiver operating characteristic (ROC) curve was performed to assess the diagnostic performance. Five radiomics features were included in the model. All the ML models built have good diagnostic efficiency, among which the support vector machine (SVM) model performs better. The area under the curve (AUC), sensitivity, specificity, and accuracy in the training set were 0.908, 0.816, 0.883, and 0.857, respectively, while those in the validation set were 0.911, 0.647, 0.92, and 0.81, respectively. A variety of ML models built based on CT radiomics features have good value for differentiating benign and malignant VCFs in malignant tumor patients, and the SVM model has a better performance.

Differential diagnostic value of radiomics models in benign versus malignant vertebral compression fractures: A systematic review and meta-analysis

PurposeEarly diagnosis of benign and malignant vertebral compression fractures by analyzing imaging data is crucial to guide treatment and assess prognosis, and the development of radiomics made it an alternative option to biopsy examination. This systematic review and meta-analysis was conducted with the purpose of quantifying the diagnostic efficacy of radiomics models in distinguishing between benign and malignant vertebral compression fractures. MethodsSearching on PubMed, Embase, Web of Science and Cochrane Library was conducted to identify eligible studies published before September 23, 2023. After evaluating for methodological quality and risk of bias using the Radiomics Quality Score (RQS) and the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2), we selected studies providing confusion matrix results to be included in random-effects meta-analysis. ResultsA total of sixteen articles, involving 1,519 vertebrae with pathological-diagnosed tumor infiltration, were included in our meta-analysis. The combined sensitivity and specificity of the top-performing models were 0.92 (95 % CI: 0.87–0.96) and 0.93 (95 % CI: 0.88–0.96), respectively. Their AUC was 0.97 (95 % CI: 0.96–0.99). By contrast, radiologists’ combined sensitivity was 0.90 (95 %CI: 0.75–0.97) and specificity was 0.92 (95 %CI: 0.67–0.98). The AUC was 0.96 (95 %CI: 0.94–0.97). Subsequent subgroup analysis and sensitivity test suggested that part of the heterogeneity might be explained by differences in imaging modality, segmentation, deep learning and cross-validation. ConclusionWe found remarkable diagnosis potential in correctly distinguishing vertebral compression fractures in complex clinical contexts. However, the published radiomics models still have a great heterogeneity, and more large-scale clinical trials are essential to validate their generalizability.

Radiomics Based on Multimodal magnetic resonance imaging for the Differential Diagnosis of Benign and Malignant Vertebral Compression Fractures.

Recent studies have indicated that radiomics may have excellent performance and clinical application prospects in the differential diagnosis of benign and malignant vertebral compression fractures (VCFs). However, multimodal magnetic resonance imaging (MRI)-based radiomics model is rarely used in the differential diagnosis of benign and malignant VCFs, and is limited to lumbar. Herein, this study intends to develop and validate MRI radiomics models for differential diagnoses of benign and malignant VCFs in patients. This cross-sectional study involved 151 adult patients diagnosed with VCF in The First Affiliated Hospital of Soochow University in 2016-2021. The study was conducted in three steps: (i) the original MRI images were segmented, and the region of interest (ROI) was marked out; (ii) among the extracted features, those features with Pearson's correlation coefficient lower than 0.9 and the top 15 with the highest variance and Lasso regression coefficient less than and more than 0 were selected; (iii) MRI images and combined data were studied by logistic regression, decision tree, random forest and extreme gradient boosting (XGBoost) models in training set and the test set (ratio of 8:2), respectively; and the models were further verified and evaluated for the differential diagnosis performance. The evaluated indexes included area under receiver (AUC) of operating characteristic curve, accuracy, sensitivity, specificity, negative predictive value (NPV), positive predictive value (PPV), and 95% confidence intervals (CIs). The AUCs were used to assess the predictive performance of different machine learning modes for benign and malignant VCFs. A total of 1144 radiomics features, and 14 clinical features were extracted. Finally, 12 radiomics features were included in the radiomics model, and 12 radiomics features with 14 clinical features were included in the combined model. In the radiomics model, the differential diagnosis performance in the logistic regression model with the AUC of 0.905 ± 0.026, accuracy of 0.817 ± 0.057, sensitivity of 0.831 ± 0.065, and negative predictive value of 0.813 ± 0.042, was superior to the other three. In the combined model, XGBoost model had the superior differential diagnosis performance with specificity (0.979 ± 0.026) and positive predictive value (0.971 ± 0.035). The multimodal MRI-based radiomics model performed well in the differential diagnosis of benign and malignant VCFs, which may provide a tool for clinicians to differentially diagnose VCFs.

Novel Use of Fractal Analysis for Quantifying Polymethylmethacrylate Distribution Patterns in Osteoporotic and Malignant Vertebral Compression Fractures Following Vertebroplasty.

Purpose: Fractal analysis is a mathematical tool which allows the evaluation of complex microstructural features within materials that cannot be expressed in traditional geometric terms. The purpose of this study is to quantify the differences in polymethylmethacrylate intravertebral cement spatial distribution patterns following vertebroplasty using fractal analysis through the examination of osteoporotic and malignant compression fractures. Methods: Frontal and lateral post-vertebroplasty radiographs were evaluated from 29 patients with osteoporotic and malignant compression fractures who underwent vertebroplasty. The individually treated vertebra were divided into osteoporotic (n = 35) and malignant groups (n = 41). Images underwent segmentation, thresholding, and binarization prior to fractal analysis. Fractal dimension and lacunarity values were derived from the region of interest in treated vertebrae using the "box-counting" and "gliding-box" techniques respectively using ImageJ. The mean values of both parameters were compared between the 2 groups. Results: The mean fractal dimension was significantly higher in the malignant vertebral compression fracture group (1.53 ± 0.08) compared to the osteoporotic group (1.34 ± 0.17; P < .001). Similarly, mean lacunarity values were significantly higher in the malignant fracture group (0.50 ± 0.09) compared to the osteoporotic group (0.37 ± 0.10; P < .001). Conclusions: Fractal dimension and lacunarity values of cement spatial distribution patterns obtained from the post-vertebroplasty radiographs can differentiate between benign osteoporotic and malignant vertebral compression fractures. This novel technique may be useful for evaluating cement spatial distribution patterns in spine augmentation procedures, although further research is warranted in this area.

Age was a protective factor for unexpected malignant diagnoses in patients with vertebral compression fracture

ObjectiveThe purpose was to investigate the risk factors for unexpected malignant diagnoses in patients with vertebral compression fractures (VCF). MethodsThe clinical data were retrospectively collected from 1396 patients who underwent vertebral augmentation and biopsy between 2012 and 2022. According to the imaging results, the preoperative diagnoses were benign VCF (BVCF) in all these cases. Based on the histological findings, the patients were divided into two groups. In group A, unexpected malignant VCF (MVCF) was identified, while benign VCF (BVCF) was verified in group B. Logistic regression analysis was performed to analyze the risk and protective factors for unexpected malignant diagnoses. ResultsThere were 44 patients in group A and 1352 in group B. The incidence of unexpected MVCF was 3.2 %. Age was significantly lower in group A compared to group B. Additionally, none of the patients in group A were older than 75. Age was associated with unexpected malignant diagnoses, according to the univariate logistic analysis. The multivariate logistic analysis showed that age was a protective factor for unexpected malignant diagnoses (odds ratio = 0.849, 95 % confidence interval: 0.809–0.891, p < 0.01). ConclusionAge was a protective factor for unexpected malignant diagnoses in patients with preoperative diagnosis of BVCF. A routine biopsy is recommended to be performed during vertebral augmentation in young patients without preoperative imaging evidence of MVCF.

MRI-based Texture Analysis in Differentiation of Benign and Malignant Vertebral Compression Fractures.

The diagnosis and characterization of vertebral compression fractures are very important for clinical management. In this evaluation, which is usually performed with diagnostic (conventional) imaging, the findings are not always typical or diagnostic. Therefore, it is important to have new information to support imaging findings. Texture analysis is a method that can evaluate information contained in diagnostic images and is not visually noticeable. This study aimed to evaluate the magnetic resonance images of cases diagnosed with vertebral compression fractures by the texture analysis method, compare them with histopathological data, and investigate the effectiveness of this method in the differentiation of benign and malignant vertebral compression fractures. Fifty-five patients with a total of 56 vertebral compression fractures were included in the study. Magnetic resonance images were examined and segmented using Local Image Feature Extraction (LIFEx) software, which is an open-source program for texture analysis. The results were compared with the histopathological diagnosis. The application of the Decision Tree algorithm to the dataset yielded impressively accurate predictions (≈95% in accuracy, precision, and recall). Interpreting tissue analysis parameters together with conventional magnetic resonance imaging findings can improve the abilities of radiologists, lead to accurate diagnoses, and prevent unnecessary invasive procedures. Further prospective trials in larger populations are needed to verify the role and performance of texture analysis in patients with vertebral compression fractures.

The role of diffusion-weighted MRI in the accurate diagnosis of vertebral compression fractures: A comparative study

IntroductionAccurately distinguishing between benign and malignant vertebral compression fractures is crucial for clinical management. This study evaluated the predictive accuracy of diffusion-weighted imaging (DWI) in differentiating the cause of vertebral fractures using MRI. MethodsA longitudinal cross-over study was conducted at Jinnah Postgraduate Medical Centre (JPMC) Karachi from July 2018 to January 2021. Patients with vertebral compression fractures underwent T1-weighted, T2-weighted, and DWI imaging with ADC mapping on a 1.5 T MRI scanner. Imaging findings were compared with histopathologic results and clinical follow-up. Sensitivity, specificity, and ROC curve analyses were performed. ResultsThe study enrolled 303 patients with a mean age of 43.6 ± 10.9 years, of whom 118 were male. DWI demonstrated high accuracy in predicting the cause of vertebral compression fractures, with a sensitivity of 96.2 %, a specificity of 76.2 %, and an area under the ROC curve of 0.857. The optimal ADC cut-off value was 0.82 × 10˄-3 mm˄2/s, which yielded a positive predictive value of 79.7 % and a negative predictive value of 95.4 %. ConclusionsDWI is a safe and non-invasive imaging modality with excellent predictive accuracy in differentiating between benign and malignant vertebral compression fractures. Iso- or hypointensity of collapsed vertebral bodies on DWI suggests a benign lesion, while T2-weighted hyperintensity is highly indicative of malignancy. Low signal on ADC is also highly indicative of malignant vertebral fractures. Incorporating DWI improves accuracy in assessing vertebral lesions, especially when standard sequences are inconclusive. Implications for practiceDWI revolutionizes vertebral compression fracture diagnosis, distinguishing between benign and malignant cases. This precision guides treatment decisions, minimizing the necessity for invasive procedures like biopsy. As a safe and reliable imaging method, DWI elevates patient care, ensuring accurate diagnostics and improved outcomes.

An MRI-Based Radiomics Nomogram for Differentiation of Benign and Malignant Vertebral Compression Fracture

This study aimed to develop and validate a magnetic resonance imaging (MRI)-based radiomics nomogram combining radiomics signatures and clinical factors to differentiate between benign and malignant vertebral compression fractures (VCFs). A total of 189 patients with benign VCFs (n=112) or malignant VCFs (n=77) were divided into training (n=133) and validation (n=56) cohorts. Radiomics features were extracted from MRI T1-weighted images and short-TI inversion recovery images to develop the radiomics signature, and the Rad score was constructed using least absolute shrinkage and selection operator regression. Demographic and MRI morphological characteristics were assessed to build a clinical factor model using multivariate logistic regression analysis. A radiomics nomogram was constructed based on the Rad score and independent clinical factors. Finally, the diagnostic performance of the radiomics nomogram, clinical model, and radiomics signature was validated using receiver operating characteristic and decision curve analysis (DCA). Six features were used to build a combined radiomics model (combined-RS). Pedicle or posterior element involvement, paraspinal mass, and fluid sign were identified as the most important morphological factors for building the clinical factor model. The radiomics signature was superior to the clinical model in terms of the area under the curve (AUC), accuracy, and specificity. The radiomics nomogram integrating the combined-RS, pedicle or posterior element involvement, paraspinal mass, and fluid sign achieved favorable predictive efficacy, generating AUCs of 0.92 and 0.90 in the training and validation cohorts, respectively. The DCA indicated good clinical usefulness of the radiomics nomogram. The MRI-based radiomics nomogram, combining the radiomics signature and clinical factors, showed favorable predictive efficacy for differentiating benign from malignant VCFs.

ROLE OF PERCUTANEOUS VERTEBROPLASTY IN VERTEBRAL COMPRESSION FRACTURES: EFFICACY AND SAFETY

Background: Percutaneous Vertebroplasty (PVP) is a minimally invasive interventional procedure performed by injecting bone cement or other therapeutic material into a painful osteoporotic or neoplastic compression fracture for pain or disability improvement. There is conflicting evidence regarding the use of vertebroplasty in osteoporotic vertebral compression fractures (VCFs) in the available literature. Objectives: To evaluate the efficacy and safety of Percutaneous Vertebroplasty in painful vertebral compression fractures in terms of pain alleviation and disability improvement, and thereby, study the profile of complications. Study design: Prospective observational study Study Participants: Patients with clinically symptomatic VCFs, who received various forms of treatment (interventional/conservative) were enrolled for the study. Patients who met the inclusion/exclusion criteria were finally selected. Methodology: Out of the selected patients, two groups were made, one who received the Intervention (PVP) and another group who received conservative management (Bed rest, medications, physiotherapy, etc.). Out of 31 patients selected, 11 were treated by PVP and 20 were treated by conservative management. These patients were followed up at 1-month, 3-month and 6-month intervals to record the Visual analog pain scores (VAS), Ronald Morris disability scores (RDQ) and any complication. Results: VAS scores in the vertebroplasty group decreased from (8.09±0.539) to (3.64 ± 0.674) at 1-month to (3.27±1.009) at 3-month to (3.09±0.831) at 6-month. VAS scores also decreased in the conservative group from (7.6±0.598) to (5.95±0.999) at 1-month to (5.1±1.294) at 3-month to (5.15±1.424) at 6-month. Vertebroplasty group showed the steep fall (-4.45) in VAS values as compared to a gradual decrease in VAS (-1.65) in the conservative group at 1 month follow up, concluding that conservative treatment has a slower effect on pain relief compared with the early response after PVP. Disability scores (RDQ) follow a similar trend with early and better improvement in the vertebroplasty group. RDQ scores: Vertebroplasty group (18.45±1.572 at baseline to 12.27±1.421 at 1-month to 11.82±1.079 at 3-month to 11.82±1.471 at 6-month), Conservative group (17.95±1.146 at baseline to 14.3±1.418 at 1-month to 12.9±1.518 at 3-month to 12.85±2.207 at 6-month). Subgroup analysis showed more benefit in malignant VCFs treated by PVP. The procedure was largely uneventful. An immediate complication was noted in one patient with cement extravasation into the venous channels, however, the patient showed pain and disability improvement without any adverse effects. Furthermore, no additional complication was noted during the follow-up period in any other patient. Conclusion: Percutaneous Vertebroplasty provides early and significant pain and disability improvement in vertebral compression fractures to comparison to conservative management. Implication: Minimal invasive technique for pain relief in osteoporotic and malignant vertebral compression fractures.

A 3D Radiomics-Based Artificial Neural Network Model for Benign Versus Malignant Vertebral Compression Fracture Classification in MRI

To train an artificial neural network model using 3D radiomic features to differentiate benign from malignant vertebral compression fractures (VCFs) on MRI. This retrospective study analyzed sagittal T1-weighted lumbar spine MRIs from 91 patients (average age of 64.24 ± 11.75 years) diagnosed with benign or malignant VCFs from 2010 to 2019, of them 47 (51.6%) had benign VCFs and 44 (48.4%) had malignant VCFs. The lumbar fractures were three-dimensionally segmented and had their radiomic features extracted and selected with the wrapper method. The training set consisted of 100 fractured vertebral bodies from 61 patients (average age of 63.2 ± 12.5 years), and the test set was comprised of 30 fractured vertebral bodies from 30 patients (average age of 66.4 ± 9.9 years). Classification was performed with the multilayer perceptron neural network with a back-propagation algorithm. To validate the model, the tenfold cross-validation technique and an independent test set (holdout) were used. The performance of the model was evaluated using the average with a 95% confidence interval for the ROC AUC, accuracy, sensitivity, and specificity (considering the threshold = 0.5). In the internal validation test, the best model reached a ROC AUC of 0.98, an accuracy of 95% (95/100), a sensitivity of 93.5% (43/46), and specificity of 96.3% (52/54). In the validation with independent test set, the model achieved a ROC AUC of 0.97, an accuracy of 93.3% (28/30), a sensitivity of 93.3% (14/15), and a specificity of 93.3% (14/15). The model proposed in this study using radiomic features could differentiate benign from malignant vertebral compression fractures with excellent performance and is promising as an aid to radiologists in the characterization of VCFs.

Differential diagnosis of benign and malignant vertebral compression fractures: Comparison and correlation of radiomics and deep learning frameworks based on spinal CT and clinical characteristics

PurposeDifferentiating benign from malignant vertebral compression fractures (VCFs) is a diagnostic dilemma in clinical practice. To improve the accuracy and efficiency of diagnosis, we evaluated the performance of deep learning and radiomics methods based on computed tomography (CT) and clinical characteristics in differentiating between Osteoporosis VCFs (OVCFs) and malignant VCFs (MVCFs). MethodsWe enrolled a total of 280 patients (155 with OVCFs and 125 with MVCFs) and randomly divided them into a training set (80%, n = 224) and a validation set (20%, n = 56). We developed three predictive models: a deep learning (DL) model, a radiomics (Rad) model, and a combined DL_Rad model, using CT and clinical characteristics data. The Inception_V3 served as the backbone of the DL model. The input data for the DL_Rad model consisted of the combined features of Rad and DCNN features. We calculated the receiver operating characteristic curve, area under the curve (AUC), and accuracy (ACC) to assess the performance of the models. Additionally, we calculated the correlation between Rad features and DCNN features. ResultsFor the training set, the DL_Rad model achieved the best results, with an AUC of 0.99 and ACC of 0.99, followed by the Rad model (AUC: 0.99, ACC: 0.97) and DL model (AUC: 0.99, ACC: 0.94). For the validation set, the DL_Rad model (with an AUC of 0.97 and ACC of 0.93) outperformed the Rad model (with an AUC: 0.93 and ACC: 0.91) and the DL model (with an AUC: 0.89 and ACC: 0.88). Rad features achieved better classifier performance than the DCNN features, and their general correlations were weak. ConclusionsThe Deep learnig model, Radiomics model, and Deep learning Radiomics model achieved promising results in discriminating MVCFs from OVCFs, and the DL_Rad model performed the best.

Benign vs malignant vertebral compression fractures with MRI: a comparison between automatic deep learning network and radiologist's assessment.

To test the diagnostic performance of a deep-learning Two-Stream Compare and Contrast Network (TSCCN) model for differentiating benign and malignant vertebral compression fractures (VCFs) based on MRI. We tested a deep-learning system in 123 benign and 86 malignant VCFs. The median sagittal T1-weighted images (T1WI), T2-weighted images with fat suppression (T2WI-FS), and a combination of both (thereafter, T1WI/T2WI-FS) were used to validate TSCCN. The receiver operator characteristic (ROC) curve was analyzed to evaluate the performance of TSCCN. The accuracy, sensitivity, and specificity of TSCCN in differentiating benign and malignant VCFs were calculated and compared with radiologists' assessments. Intraclass correlation coefficients (ICCs) were tested to find intra- and inter-observer agreement of radiologists in differentiating malignant from benign VCFs. The AUC of the ROC plots of TSCCN according to T1WI, T2WI-FS, and T1WI/T2WI-FS images were 99.2%, 91.7%, and 98.2%, respectively. The accuracy of T1W, T2WI-FS, and T1W/T2WI-FS based on TSCCN was 95.2%, 90.4%, and 96.2%, respectively, greater than that achieved by radiologists. Further, the specificity of T1W, T2WI-FS, and T1W/T2WI-FS based on TSCCN was higher at 98.4%, 94.3%, and 99.2% than that achieved by radiologists. The intra- and inter-observer agreements of radiologists were 0.79-0.85 and 0.79-0.80 for T1WI, 0.65-0.72 and 0.70-0.74 for T2WI-FS, and 0.83-0.88 and 0.83-0.84 for T1WI/T2WI-FS. The TSCCN model showed better diagnostic performance than radiologists for automatically identifying benign or malignant VCFs, and is a potentially helpful tool for future clinical application. TSCCN-assisted MRI has shown superior performance in distinguishing benign and malignant vertebral compression fractures compared to radiologists. This technology has the value to enhance diagnostic accuracy, sensitivity, and specificity. Further integration into clinical practice is required to optimize patient management. • The Two-Stream Compare and Contrast Network (TSCCN) model showed better diagnostic performance than radiologists for identifying benign vs malignant vertebral compression fractures. • The processing of TSCCN is fast and stable, better than the subjective evaluation by radiologists in diagnosing vertebral compression fractures. • The TSCCN model provides options for developing a fully automated, streamlined artificial intelligence diagnostic tool.

Differentiation of benign versus malignant indistinguishable vertebral compression fractures by different machine learning with MRI-based radiomic features.

To explore an optimal machine learning (ML) model trained on MRI-based radiomic features to differentiate benign from malignant indistinguishable vertebral compression fractures (VCFs). This retrospective study included patients within 6weeks of back pain (non-traumatic) who underwent MRI and were diagnosed with benign and malignant indistinguishable VCFs. The two cohorts were retrospectively recruited from the Affiliated Hospital of Qingdao University (QUH) and Qinghai Red Cross Hospital (QRCH). Three hundred seventy-six participants from QUH were divided into the training (n = 263) and validation (n = 113) cohort based on the date of MRI examination. One hundred three participants from QRCH were used to evaluate the external generalizability of our prediction models. A total of 1045 radiomic features were extracted from each region of interest (ROI) and used to establish the models. The prediction models were established based on 7 different classifiers. These models showed favorable efficacy in differentiating benign from malignant indistinguishable VCFs. However, our Gaussian naïve Bayes (GNB) model attained higher AUC and accuracy (0.86, 87.61%) than the other classifiers in validation cohort. It also remains the high accuracy and sensitivity for the external test cohort. Our GNB model performed better than the other models in the present study, suggesting that it may be more useful for differentiating indistinguishable benign form malignant VCFs. • The differential diagnosis of benign and malignant indistinguishable VCFs based on MRI is rather difficult for spine surgeons or radiologists. • Our ML models facilitate the differential diagnosis of benign and malignant indistinguishable VCFs with improved diagnostic efficacy. • Our GNB model had the high accuracy and sensitivity for clinical application.

Automated Differentiation Between Osteoporotic Vertebral Fracture and Malignant Vertebral Fracture on MRI Using a Deep Convolutional Neural Network.

Retrospective study of magnetic resonance imaging (MRI). To assess the ability of a convolutional neural network (CNN) model to differentiate osteoporotic vertebral fractures (OVFs) and malignant vertebral compression fractures (MVFs) using short-TI inversion recovery (STIR) and T1-weighted images (T1WI) and to compare it to the performance of three spine surgeons. Differentiating between OVFs and MVFs is crucial for appropriate clinical staging and treatment planning. However, an accurate diagnosis is sometimes difficult. Recently, CNN modeling-an artificial intelligence technique-has gained popularity in the radiology field. We enrolled 50 patients with OVFs and 47 patients with MVFs who underwent thoracolumbar MRI. Sagittal STIR images and sagittal T1WI were used to train and validate the CNN models. To assess the performance of the CNN, the receiver operating characteristic curve was plotted and the area under the curve was calculated. We also compared the accuracy, sensitivity, and specificity of the diagnosis made by the CNN and three spine surgeons. The area under the curve of receiver operating characteristic curves of the CNN based on STIR images and T1WI were 0.967 and 0.984, respectively. The CNN model based on STIR images showed a performance of 93.8% accuracy, 92.5% sensitivity, and 94.9% specificity. On the other hand, the CNN model based on T1WI showed a performance of 96.4% accuracy, 98.1% sensitivity, and 94.9% specificity. The accuracy and specificity of the CNN using both STIR and T1WI were statistically equal to or better than that of three spine surgeons. There were no significant differences in sensitivity based on both STIR images and T1WI between the CNN and spine surgeons. We successfully differentiated OVFs and MVFs based on MRI with high accuracy using the CNN model, which was statistically equal or superior to that of the spine surgeons.Level of Evidence: 4.

Differentiation between benign and malignant vertebral compression fractures using qualitative and quantitative analysis of a single fast spin echo T2-weighted Dixon sequence

ObjectivesTo determine and compare the qualitative and quantitative diagnostic performance of a single sagittal fast spin echo (FSE) T2-weighted Dixon sequence in differentiating benign and malignant vertebral compression fractures (VCF), using multiple readers and different quantitative methods.MethodsFrom July 2014 to June 2020, 95 consecutive patients with spine MRI performed prior to cementoplasty for acute VCFs were retrospectively included. VCFs were categorized as benign (n = 63, mean age = 76 ± 12 years) or malignant (n = 32, mean age = 63 ± 12 years) with a best valuable comparator as a reference. Qualitative analysis was independently performed by four radiologists by categorizing each VCF as either benign or malignant using only the image sets provided by FSE T2-weighted Dixon sequences. Quantitative analysis was performed using two different regions of interest (ROI1-2) and three methods (signal drop, fat fraction (FF) from ROIs, FF maps). Diagnostic performance was compared using ROC curves analyses. Interobserver agreement was assessed using kappa statistics and intraclass correlation coefficients (ICC).ResultsThe qualitative diagnostic performance ranged from area under the curve (AUC) = 0.97 (95% CI: 0.91–1.00) to AUC = 0.99 (95% CI: 0.95–1.0). The quantitative diagnostic performance ranged from AUC = 0.82 (95% CI: 0.73–0.89) to AUC = 0.97 (95% CI: 0.91–0.99). Pairwise comparisons showed no statistical difference in diagnostic performance (all p > 0.0013, Bonferroni-corrected p < 0.0011). All five cases with disagreement among the readers were correctly diagnosed at quantitative analysis using ROI2. Interobserver agreement was excellent for both qualitative and quantitative analyses.ConclusionsA single FSE T2-weighted Dixon sequence can be used to differentiate benign and malignant VCF with high diagnostic performance using both qualitative and quantitative analyses, which can provide complementary information.Key Points• Qualitative analysis of a single FSE T2-weighted Dixon sequence yields high diagnostic performance and excellent observer agreement for differentiating benign and malignant compression fractures.• The same FSE T2-weighted Dixon sequence allows quantitative assessment with high diagnostic performance.• Quantitative data can readily be extracted from the FSE T2-weighted Dixon sequence and may provide complementary information to the qualitative analysis, which may be useful in doubtful cases.

Two-Stream Compare and Contrast Network for Vertebral Compression Fracture Diagnosis.

Differentiating Vertebral Compression Fractures (VCFs) associated with trauma and osteoporosis (benign VCFs) or those caused by metastatic cancer (malignant VCFs) is critically important for treatment decisions. So far, automatic VCFs diagnosis is solved in a two-step manner, i.e., first identify VCFs and then classify them into benign or malignant. In this paper, we explore to model VCFs diagnosis as a three-class classification problem, i.e., normal vertebrae, benign VCFs, and malignant VCFs. However, VCFs recognition and classification require very different features, and both tasks are characterized by high intra-class variation and high inter-class similarity. Moreover, the dataset is extremely class-imbalanced. To address the above challenges, we propose a novel Two-Stream Compare and Contrast Network (TSCCN) for VCFs diagnosis. This network consists of two streams, a recognition stream which learns to identify VCFs through comparing and contrasting between adjacent vertebrae, and a classification stream which compares and contrasts between intra-class and inter-class to learn features for fine-grained classification. The two streams are integrated via a learnable weight control module which adaptively sets their contribution. TSCCN is evaluated on a dataset consisting of 239 VCFs patients and achieves the average sensitivity and specificity of 92.56% and 96.29%, respectively.

Combined radiomics-clinical model to predict malignancy of vertebral compression fractures on CT.

To develop and validate a combined radiomics-clinical model to predict malignancy of vertebral compression fractures on CT. One hundred sixty-five patients with vertebral compression fractures were allocated to training (n = 110 [62 acute benign and 48 malignant fractures]) and validation (n = 55 [30 acute benign and 25 malignant fractures]) cohorts. Radiomics features (n = 144) were extracted from non-contrast-enhanced CT images. Radiomics score was constructed by applying least absolute shrinkage and selection operator regression to reproducible features. A combined radiomics-clinical model was constructed by integrating significant clinical parameters with radiomics score using multivariate logistic regression analysis. Model performance was quantified in terms of discrimination and calibration. The model was internally validated on the independent data set. The combined radiomics-clinical model, composed of two significant clinical predictors (age and history of malignancy) and the radiomics score, showed good calibration (Hosmer-Lemeshow test, p > 0.05) and discrimination in both training (AUC, 0.970) and validation (AUC, 0.948) cohorts. Discrimination performance of the combined model was higher than that of either the radiomics score (AUC, 0.941 in training cohort and 0.852 in validation cohort) or the clinical predictor model (AUC, 0.924 in training cohort and 0.849 in validation cohort). The model stratified patients into groups with low and high risk of malignant fracture with an accuracy of 98.2% in the training cohort and 90.9% in the validation cohort. The combined radiomics-clinical model integrating clinical parameters with radiomics score could predict malignancy in vertebral compression fractures on CT with high discriminatory ability. • A combined radiomics-clinical model was constructed to predict malignancy of vertebral compression fractures on CT by combining clinical parameters and radiomics features. • The model showed good calibration and discrimination in both training and validation cohorts. • The model showed high accuracy in the stratification of patients into groups with low and high risk of malignant vertebral compression fractures.

Differentiation of usual vertebral compression fractures using CT histogram analysis as quantitative biomarkers: A proof-of-principle study

PurposeTo investigate the utility of CT histogram analysis (CTHA) for discrimination of traumatic, osteoporotic and malignant fractures in patients with vertebral compression fractures (VCFs). To evaluate the feasibility and accuracy of CTHA in differentiating non-malignant (traumatic and osteoporotic) from malignant VCFs. Materials and methodsTotally, 235 patients with VCFs were enrolled in the current experimental study. There were 132 patients with traumatic VCFs, 51 with osteoporotic VCFs and 52 with malignant VCFs, with MRI and histology as the standard references. All the patients underwent unenhanced CT scans. Nineteen histogram-based parameters were derived using Omni-Kinetics software (Omni-Kinetics, GE Healthcare). The reproducibility of those parameters was evaluated using two independent delineations conducted by two observers. These histogram parameters were compared among the three different VCFs using Kruskal-Wallis H test. Traumatic VCFs and osteoporotic VCFs were combined as non-malignant VCFs and compared with malignant VCFs using Mann-Whitney U test Multivariable logistic regression analysis was performed on the significantly different features and built a diagnosis model. Receiver operating characteristic (ROC) curve was carried out to observe the difference of diagnostic performance between the single positive parameter and the combination of parameters. ResultsAll the 19 parameters presented excellent reproducibility, with intraclass correlation coefficient values from 0.789 to 0.997. At quantitative evaluation, the best predictive histogram parameters in discrimination of the three different types of VCFs were relative min intensity (p = 0.022), relative entropy (p = 0.043), and relative frequency size (p < 0.001). Relative frequency size (p < 0.001) and relative quantile5 (p = 0.012) resulted in statistically significant difference between non-malignant and malignant VCFs. The area under ROC curve indicated that relative frequency size combined with relative quantile5 (0.754; 95 % confidence intervals: 0.661∼0.829; p < 0.001) was of best performance in differentiating malignant from non-malignant VCFs. ConclusionsOur results are encouraging and suggest that histogram parameters derived from unenhanced CT could be reliable quantitative biomarkers for diff ;erential diagnosis of usual VCFs.

Cost-Benefit Analysis of Routine Bone Biopsy During Augmentation of Osteoporotic Vertebral Compression Fractures

Multi-center prospective study. To analyze the cost of routine biopsy during augmentation of osteoporotic vertebral compression fractures (VCF) and the affect it has on further treatment. Vertebroplasty (VP) and Balloon Kyphoplasty (BKP) are accepted treatments for VCF. Bone biopsy is routinely performed during every VCF surgery in many centers around the world to exclude an incidental finding of malignancy as the cause of the pathological VCF. The incidence been reported as 0.7% to 7.3%, however the published cohorts are small and do not discuss cost-benefit aspects. From 2008 to 2016 we performed 122 vertebral biopsies routinely on 116 patients in three hospitals. Twenty-three patients had history of malignancy (26 biopsies) and four were suspected of having malignancy based on imaging findings. The remaining 86 patients (99 biopsies) were presumed osteoporotic VCF. Out of 99 biopsies in the VCF cohort group only one yielded an unsuspected malignancy (1.16%), positive for multiple myeloma (MM). The ability of clinical assessment and imaging alone to diagnose malignancy was found to be 91.7% sensitive and 84.2% specific in our cohort. Routine bone biopsy during vertebral augmentation procedure is a safe option for evaluating the cause of the VCF but has significant cost to the health system. The cost of one diagnosed case of unsuspected malignancy was $31,000 in our study. The most common pathology was MM, which has not been proven to benefit from early diagnosis. When comparing clinical diagnosis with imaging, a previous history of malignancy was found in only 40.7% of VCF patients, while imaging was 100% accurate in predicting presence of malignancy on biopsy. This study reassures spine surgeons in their ability to diagnose malignant VCFs and does not support the significant cost of routine bone biopsies. 3.

Diagnostic Performance of F-18 Fluorodeoxyglucose Positron Emission Tomography or Positron Emission Tomography/Computed Tomography for Differentiation of Benign and Malignant Vertebral Compression Fractures: A Meta-Analysis

The purpose of the present study was to investigate the diagnostic performance of F-18 fluorodeoxyglucose (FDG) positron emission tomography/computed tomography (PET/CT) for the differentiation of benign and malignant vertebral compression fractures (VCFxs) through a systematic review and meta-analysis. MEDLINE via PubMed, Cochrane, Scopus, and Embase database, from the earliest available date of indexing through September 30, 2019, were searched for studies evaluating the diagnostic performance of F-18 FDG PET or PET/CT for the differentiation of malignant VCFxs. We determined the sensitivities and specificities across the studies, calculated the positive and negative likelihood ratios (LR+ and LR-, respectively), and constructed summary receiver operating characteristic curves. For the 5 studies (274 patients), the pooled sensitivity was 0.96 (95% confidence interval [CI], 0.82-0.99) without heterogeneity (I2, 50.6) and 0.77 (95% CI, 0.56-0.89) with heterogeneity (I2, 76.1). LR syntheses gave an overall LR+ of 4.1 (95% CI, 2.1-8.0) and LR- of 0.05 (95% CI, 0.01-0.23). The pooled diagnostic odds ratio (DOR) was 78 (95% CI, 19-316). The hierarchical summary receiver operating characteristic curve indicates that the areas under the curve was 0.94 (95% CI, 0.92-0.96). The results of the present meta-analysis have shown high sensitivity and moderate specificity for F-18 FDG PET and PET/CT for differentiation of malignant VCFxs. At present, the reported data regarding the use of F-18 FDG PET for differentiation of malignant VCFxs remain limited; thus, further large multicenter studies are necessary to substantiate the diagnostic accuracy of F-18 FDG PET for the differentiation of malignant VCFxs.