Opportunistic Osteoporosis Screening Research Articles

Opportunistic screening for osteoporosis using routine clinical care computed tomography brain studies.

Osteoporosis and falls are both prevalent in the elderly, and CT brain (CTB) is frequently performed post head-strike. We aim to validate the relationship between frontal bone density (Hounsfield unit) from routine CTB and bone mineral density from dual-energy X-ray absorptiometry (DEXA) scan for opportunistic osteoporosis screening. Patients who had a non-contrast CTB followed by a DEXA scan in the subsequent year were included in this multi-center retrospective study. The relationship between frontal bone density on CT and femoral neck T-score on DEXA was examined using ANOVA, Pearson's correlation, and receiver operating curve (ROC) analysis. Sensitivity, specificity, negative and positive predictive values, and area under the curve (AUC) were calculated. Three hundred twenty-six patients (205 females and 121 males) were analyzed. ANOVA analysis showed that frontal bone density was lower in patients with DEXA-defined osteoporosis (p < 0.001), while Pearson's correlation analysis demonstrated a fair correlation with femoral neck T-score (r = 0.3, p < 0.001). On subgroup analysis, these were true in females but not in males. On ROC analysis, frontal bone density weakly predicted osteoporosis (AUC 0.6, 95% CI 0.5-0.7) with no optimal threshold identified. HU < 610 was highly specific (87.5%) but poorly sensitive (18.9%). HU > 1200 in females had a strong negative predictive value for osteoporosis (92.6%, 95% CI 87.1-98.1%). Frontal bone density from routine CTB is significantly different between females with and without osteoporosis, but not between males. However, frontal bone density was a weak predictor for DEXA-defined osteoporosis. Further research is required to determine the role of CTB in opportunistic osteoporosis screening.

End-to-End Semi-Supervised Opportunistic Osteoporosis Screening Using Computed Tomography.

Osteoporosis is the most common metabolic bone disease and can cause fragility fractures. Despite this, screening utilization rates for osteoporosis remain low among populations at risk. Automated bone mineral density (BMD) estimation using computed tomography (CT) can help bridge this gap and serve as an alternative screening method to dual-energy X-ray absorptiometry (DXA). The feasibility of an opportunistic and population agnostic screening method for osteoporosis using abdominal CT scans without bone densitometry phantom-based calibration was investigated in this retrospective study. A total of 268 abdominal CT-DXA pairs and 99 abdominal CT studies without DXA scores were obtained from an oncology specialty clinic in the Republic of Korea. The center axial CT slices from the L1, L2, L3, and L4 lumbar vertebrae were annotated with the CT slice level and spine segmentation labels for each subject. Deep learning models were trained to localize the center axial slice from the CT scan of the torso, segment the vertebral bone, and estimate BMD for the top four lumbar vertebrae. Automated vertebra-level DXA measurements showed a mean absolute error (MAE) of 0.079, Pearson's r of 0.852 (P<0.001), and R2 of 0.714. Subject-level predictions on the held-out test set had a MAE of 0.066, Pearson's r of 0.907 (P<0.001), and R2 of 0.781. CT scans collected during routine examinations without bone densitometry calibration can be used to generate DXA BMD predictions.

Improving Osteoporosis Prediction Using Vertebral Bone Quality Score and Paravertebral Muscle Measurements From Lumbar MRI Scans.

Retrospective cohort. This study aims to use a novel method of combining vertebral bone quality score with paravertebral cross-sectional area measurements to improve the accuracy of predicting individuals with total hip T-scores <-2.5. Osteoporosis is a prevalent skeletal condition associated with decreased bone density and increased fracture risk. Dual-energy x-ray absorptiometry (DXA) is the conventional method for diagnosing osteoporosis, but it has limitations. Opportunistic osteoporosis screening techniques using lumbar magnetic resonance imaging (MRI), particularly the vertebral bone quality (VBQ) score, have shown promise. This study aims to improve the accuracy of predicting individuals with low total hip T-scores using a novel method that combines VBQ scores with paravertebral cross-sectional area (CSA) measurements. A retrospective cohort of 98 patients with DXA and lumbar MRI scans was analyzed. VBQ scores were calculated based on lumbar MRI images, and CSA measurements of paravertebral and psoas muscles were obtained. Threshold-based logistic regression was used to identify optimal thresholds for predicting total hip T-scores <-2.5. The combined model incorporating the VBQ score and paravertebral muscle percent achieved an accuracy of 96.9% for predicting total hip T-scores <-2.5, compared to 81.6% when using the VBQ score alone. Incorporating paravertebral muscle measurements significantly improved the accuracy of identifying osteoporotic individuals. The combination of VBQ score and paravertebral muscle measurements enhances the accuracy of predicting individuals with low total hip T-scores. Lumbar MRI scans provide valuable information beyond opportunistic osteoporosis screening, and the inclusion of paravertebral muscle measurements could aid in identifying at-risk individuals more accurately.

Opportunistic screening for osteoporosis using computed tomography scans and its comparison with DXA findings: a two-center cross-sectional study

BackgroundOsteoporosis is a prevalent condition leading to an increased risk of bone fractures. Osteoporosis poses a worldwide public health concern, impacting over 200 million individuals and resulting in a staggering 1.66 million hip fractures each year. Opportunistic osteoporosis screening can be employed during CT scans to assess bone mineral density (BMD) through Hounsfield units (HU) without the need for additional imaging, radiation exposure, or appointments. This study aimed to investigate a CT scan's diagnostic value in the opportunistic osteoporosis screening through L1 vertebra densitometry and compare it with dual-energy x-ray absorptiometry (DXA) findings.ResultsOne hundred forty-nine patients with an average age of 67.70 ± 10.94 years were included in the study. The age of osteoporotic patients was significantly higher than osteopenic (p = 0.001) and normal individuals (p < 0.001). The HU of osteoporotic patients was found to be significantly lower compared to both osteopenic (p = 0.023) and normal individuals (p < 0.001). According to the ROC curve for osteoporosis prediction using the HU (AUC = 0.793 and p < 0.001), with a cut-off of 103 HU, the CT scan had a sensitivity of 69% and a specificity of 74% for the diagnosis of osteoporosis.ConclusionIndividuals with osteoporosis exhibit a significantly lower average HU compared to both osteopenic and healthy individuals. A CT scan can serve as an effective predictor of osteoporosis in patients. The CT images obtained for reasons unrelated to osteoporosis diagnosis can be employed to discern patients with osteoporosis without incurring the added cost or radiation exposure.

Fully automated deep learning system for osteoporosis screening using chest computed tomography images.

Osteoporosis, a disease stemming from bone metabolism irregularities, affects approximately 200 million people worldwide. Timely detection of osteoporosis is pivotal in grappling with this public health challenge. Deep learning (DL), emerging as a promising methodology in the field of medical imaging, holds considerable potential for the assessment of bone mineral density (BMD). This study aimed to propose an automated DL framework for BMD assessment that integrates localization, segmentation, and ternary classification using various dominant convolutional neural networks (CNNs). In this retrospective study, a cohort of 2,274 patients underwent chest computed tomography (CT) was enrolled from January 2022 to June 2023 for the development of the integrated DL system. The study unfolded in 2 phases. Initially, 1,025 patients were selected based on specific criteria to develop an automated segmentation model, utilizing 2 VB-Net networks. Subsequently, a distinct cohort of 902 patients was employed for the development and testing of classification models for BMD assessment. Then, 3 distinct DL network architectures, specifically DenseNet, ResNet-18, and ResNet-50, were applied to formulate the 3-classification BMD assessment model. The performance of both phases was evaluated using an independent test set consisting of 347 individuals. Segmentation performance was evaluated using the Dice similarity coefficient; classification performance was appraised using the receiver operating characteristic (ROC) curve. Furthermore, metrics such as the area under the curve (AUC), accuracy, and precision were meticulously calculated. In the first stage, the automatic segmentation model demonstrated excellent segmentation performance, with mean Dice surpassing 0.93 in the independent test set. In the second stage, both the DenseNet and ResNet-18 demonstrated excellent diagnostic performance in detecting bone status. For osteoporosis, and osteopenia, the AUCs were as follows: DenseNet achieved 0.94 [95% confidence interval (CI): 0.91-0.97], and 0.91 (95% CI: 0.87-0.94), respectively; ResNet-18 attained 0.96 (95% CI: 0.92-0.98), and 0.91 (95% CI: 0.87-0.94), respectively. However, the ResNet-50 model exhibited suboptimal diagnostic performance for osteopenia, with an AUC value of only 0.76 (95% CI: 0.69-0.80). Alterations in tube voltage had a more pronounced impact on the performance of the DenseNet. In the independent test set with tube voltage at 100 kVp images, the accuracy and precision of DenseNet decreased on average by approximately 14.29% and 18.82%, respectively, whereas the accuracy and precision of ResNet-18 decreased by about 8.33% and 7.14%, respectively. The state-of-the-art DL framework model offers an effective and efficient approach for opportunistic osteoporosis screening using chest CT, without incurring additional costs or radiation exposure.

Comparisons of Hounsfield units and volumetric bone density in discriminating vertebral fractures on lumbar CT scans.

To compare the performance of areal Hounsfield units (aHUs), volumetric Hounsfield units (vHUs), and volumetric bone mineral density (vBMD) by quantitative CT (QCT) in discriminating vertebral fractures (VFs) risk. We retrospectively included CT scans of the lumbar spine 101 VFs cases (60 women, mean age: 64 ± 4 years; 41 men, mean age: 73 ± 10 years) and sex- and age-matched 101 control subjects (60 women, mean age: 64 ± 4 years; 41 men, mean age: 72 ± 7 years). In order to assess the discriminatory capability of aHU, vHU, and vBMD measurements at the L1 and L2 levels in identifying VFs, we conducted binary logistic regression and receiver operating characteristic (ROC) curve analyses in men and women. Sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were calculated. In both men and women with and without VFs, aHU, vHU, and vBMD were highly correlated with each other (r2 from 0.832 to 0.957, all P < .001). There was a statistically significant difference in aHU, vHU, and vBMD between subjects with and without VFs (P < .001). When age, gender, and BMI were taken into account as covariances and adjusted simultaneously, odds ratios (ORs) for aHU, vHU, and vBMD values, which represent the risk of VFs, were significant (P < .001). Compared with aHU and vHU, vBMD was more strongly associated with VF risk (vBMD: OR, 6.29; 95% CI, 3.83-10.35 vs vHU: OR, 3.64; 95% CI, 2.43-5.46 vs aHU: OR, 2.56; 95% CI, 1.79-3.67). In both men and women, further, vBMD had higher values for AUC, sensitivity, specificity, PPV, and NPV compared to vHU, with vHU in turn surpassing aHU. The area under the receiver operating characteristic curve (AUC) for discriminating VFs using the average aHU, vHU, and vBMD of 2 vertebrae was 0.72, 0.77, and 0.87 in men and 0.76, 0.79, and 0.86 in women. In both men and women, there exist statistically significant differences in the AUC when employing the 3 measurements-namely, aHU, vHU, and vBMD-to discriminate fractures (P < .05). The QCT-measured vBMD is more associated with acute VFs than vHU and aHU values of the lumbar spine. Although the use of vHU and aHU values for the diagnosis of osteoporosis and discriminating fracture risk is limited to scanner- and imaging protocol-specific, they have great potential for opportunistic osteoporosis screening, particularly vHU. The novelty of this study presents a comparison of the VF discriminative capabilities among aHU, vHU, and vBMD. The vHU values introduced in this study demonstrate a greater capacity to discriminate fractures compared to aHU, presenting an improved clinical choice. Although its discriminatory capability is slightly lower than that of vBMD, it is more convenient to measure and does not require specialized software.

Effectiveness of opportunistic osteoporosis screening on chest CT using the DCNN model.

To develop and evaluate a deep learning model based on chest CT that achieves favorable performance on opportunistic osteoporosis screening using the lumbar 1 + lumbar 2 vertebral bodies fusion feature images, and explore the feasibility and effectiveness of the model based on the lumbar 1 vertebral body alone. The chest CT images of 1048 health check subjects from January 2021 to June were retrospectively collected as the internal dataset (the segmentation model: 548 for training, 100 for tuning and 400 for test. The classification model: 530 for training, 100 for validation and 418 for test set). The subjects were divided into three categories according to the quantitative CT measurements, namely, normal, osteopenia and osteoporosis. First, a deep learning-based segmentation model was constructed, and the dice similarity coefficient(DSC) was used to compare the consistency between the model and manual labelling. Then, two classification models were established, namely, (i) model 1 (fusion feature construction of lumbar vertebral bodies 1 and 2) and (ii) model 2 (feature construction of lumbar 1 alone). Receiver operating characteristic curves were used to evaluate the diagnostic efficacy of the models, and the Delong test was used to compare the areas under the curve. When the number of images in the training set was 300, the DSC value was 0.951 ± 0.030 in the test set. The results showed that the model 1 diagnosing normal, osteopenia and osteoporosis achieved an AUC of 0.990, 0.952 and 0.980; the model 2 diagnosing normal, osteopenia and osteoporosis achieved an AUC of 0.983, 0.940 and 0.978. The Delong test showed that there was no significant difference in area under the curve (AUC) values between the osteopenia group and osteoporosis group (P = 0.210, 0.546), while the AUC value of normal model 2 was higher than that of model 1 (0.990 vs. 0.983, P = 0.033). This study proposed a chest CT deep learning model that achieves favorable performance on opportunistic osteoporosis screening using the lumbar 1 + lumbar 2 vertebral bodies fusion feature images. We further constructed the comparable model based on the lumbar 1 vertebra alone which can shorten the scan length, reduce the radiation dose received by patients, and reduce the training cost of technologists.

Evaluation of deep learning-based quantitative computed tomography for opportunistic osteoporosis screening

To evaluate diagnostic efficacy of deep learning (DL)-based automated bone mineral density (BMD) measurement for opportunistic screening of osteoporosis with routine computed tomography (CT) scans. A DL-based automated quantitative computed tomography (DL-QCT) solution was evaluated with 112 routine clinical CT scans from 84 patients who underwent either chest (N:39), lumbar spine (N:34), or abdominal CT (N:39) scan. The automated BMD measurements (DL-BMD) on L1 and L2 vertebral bodies from DL-QCT were validated with manual BMD (m-BMD) measurement from conventional asynchronous QCT using Pearson’s correlation and intraclass correlation. Receiver operating characteristic curve (ROC) analysis identified the diagnostic ability of DL-BMD for low BMD and osteoporosis, determined by dual-energy X-ray absorptiometry (DXA) and m-BMD. Excellent concordance were seen between m-BMD and DL-BMD in total CT scans (r = 0.961/0.979). The ROC-derived AUC of DL-BMD compared to that of central DXA for the low-BMD and osteoporosis patients was 0.847 and 0.770 respectively. The sensitivity, specificity, and accuracy of DL-BMD compared to central DXA for low BMD were 75.0%, 75.0%, and 75.0%, respectively, and those for osteoporosis were 68.0%, 80.5%, and 77.7%. The AUC of DL-BMD compared to the m-BMD for low BMD and osteoporosis diagnosis were 0.990 and 0.943, respectively. The sensitivity, specificity, and accuracy of DL-BMD compared to m-BMD for low BMD were 95.5%, 93.5%, and 94.6%, and those for osteoporosis were 88.2%, 94.5%, and 92.9%, respectively. DL-BMD exhibited excellent agreement with m-BMD on L1 and L2 vertebrae in the various routine clinical CT scans and had comparable diagnostic performance for detecting the low-BMD and osteoporosis on conventional QCT.

Incident fractures of the distal radius: Dual-energy CT-derived metrics for opportunistic risk stratification

BackgroundDual-energy CT (DECT)-derived bone mineral density (BMD) of the distal radius and other CT-derived metrics related to bone health have been suggested for opportunistic osteoporosis screening and risk evaluation for sustaining distal radius fractures (DRFs). MethodsThe distal radius of patients who underwent DECT between 01/2016 and 08/2021 was retrospectively analyzed. Cortical Hounsfield Unit (HU), trabecular HU, cortical thickness, and DECT-based BMD were acquired from a non-fractured, metaphyseal area in all examinations. Receiver-operating characteristic (ROC) analysis was conducted to determine the area under the curve (AUC) values for predicting DRFs based on DECT-derived BMD, HU values, and cortical thickness. Logistic regression models were then employed to assess the associations of these parameters with the occurrence of DRFs. ResultsIn this study, 263 patients (median age: 52 years; interquartile range: 36–64; 132 women; 192 fractures) were included. ROC curve analysis revealed a higher area under the curve (AUC) value for DECT-derived BMD compared to cortical HU, trabecular HU, and cortical thickness (0.91 vs. 0.61, 0.64, and 0.69, respectively; p <.001). Logistic regression models confirmed the association between lower DECT-derived BMD and the occurrence of DRFs (Odds Ratio, 0.83; p <.001); however, no influence was observed for cortical HU, trabecular HU, or cortical thickness. ConclusionsDECT can be used to assess the BMD of the distal radius without dedicated equipment such as calibration phantoms to increase the detection rates of osteoporosis and stratify the individual risk to sustain DRFs. In contrast, assessing HU-based values and cortical thickness does not provide clinical benefit.

Opportunistic screening for osteoporosis using enhanced images based on dual-energy computed tomography material decomposition: a comparison with quantitative computed tomography.

Many patients with malignant tumors require chemotherapy and radiation therapy, which can result in a decline in physical function and potentially influence bone mineral density (BMD). Furthermore, these treatments necessitate enhanced computed tomography (CT) scans for determining disease staging or treatment outcomes, and opportunistic screening with available imaging data is beneficial for patients at high risk for osteoporosis if existing imaging data can be used. The study aimed to investigate the feasibility of opportunistic screening for osteoporosis using enhanced CT based on a dual-energy CT (DECT) material decomposition technique. We prospectively enrolled 346 consecutive patients who underwent abdominal unenhanced and triphasic contrast-enhanced CT (arterial, portal venous, and delayed phases) between June 2021 and June 2022. The BMD, and the density of hydroxyapatite (HAP) on HAP-iodine images and calcium (Ca) on Ca-iodine images were measured on the L1-L3 vertebral bodies. The iodine intake was recorded. Pearson analysis was conducted to assess the correlation between iodine intake and the density values in three phases and the correlation between BMD and the densities of HAP and Ca. Furthermore, linear regression was employed for quantitative evaluation. Bland-Altman analysis was used to evaluate the agreement between calculated BMD derived from DECT (BMD-DECT) and reference BMD derived from quantitative CT (BMD-QCT). Receiver operating characteristic (ROC) analysis was applied to assess the diagnostic efficacy. The HAP and Ca density of the L1-L3 vertebral bodies did not differ significantly among the three phases of contrast-enhanced CT (F=0.001-0.049; P>0.05). Significant positive correlations were found between HAP, Ca densities, and BMD (HAP-BMD: r=0.9472, R2=0.8973; Ca-BMD: r=0.9470, R2=0.8968; all P<0.001). Bland-Altman plots showed high agreement between BMD-DECT and BMD-QCT. The area under the curve (AUC) using HAP and Ca measurements was 0.963 [95% confidence interval (CI): 0.937-0.980] and 0.964 (95% CI: 0.939-0.981), respectively, for diagnosing osteoporosis and was 0.951 (95% CI: 0.917-0.973) and 0.950 (95% CI: 0.916-0.973), respectively, for diagnosing osteopenia. The HAP and Ca density measurements generated through the material decomposition technique in DECT have good diagnostic performances in assessing BMD, which offers a new perspective for opportunistic screening of osteoporosis on contrast-enhanced CT.

Automated osteoporosis classification and T-score prediction using hip radiographs via deep learning algorithm.

Despite being the gold standard for diagnosing osteoporosis, dual-energy X-ray absorptiometry (DXA) is an underutilized screening tool for osteoporosis. This study proposed and validated a controllable feature layer of a convolutional neural network (CNN) model with a preprocessing image algorithm to classify osteoporosis and predict T-score on the proximal hip region via simple hip radiographs. This was a single-center, retrospective study. An image dataset of 3460 unilateral hip images from 1730 patients (age ⩾50 years) was retrospectively collected with matched DXA assessment for T-score for the targeted proximal hip regions to train (2473 unilateral hip images from 1430 patients) and test (497 unilateral hip images from 300 patients) the proposed CNN model. All images were processed with a fully automated CNN model, X1AI-Osteo. The proposed screening tool illustrated a better performance (sensitivity: 97.2%; specificity: 95.6%; positive predictive value: 95.7%; negative predictive value: 97.1%; area under the curve: 0.96) than the open-sourced CNN models in predicting osteoporosis. Moreover, when combining variables, including age, body mass index, and sex as features in the training metric, there was high consistency in the T-score on the targeted hip regions between the proposed CNN model and the DXA (r = 0.996, p < 0.001). The proposed CNN model may identify osteoporosis and predict T-scores on the targeted hip regions from simple hip radiographs with high accuracy, highlighting the future application for population-based opportunistic osteoporosis screening with low cost and high adaptability for a broader population at risk. TMU-JIRB N201909036.

Applying Machine Learning Analysis Based on Proximal Femur of Abdominal Computed Tomography to Screen for Abnormal Bone Mass in Femur

To evaluate the performance of machine learninganalysis based on proximal femur of abdominal computed tomography (CT) scans in screening for abnormal bone mass in femur. 222 patients aged 50 years or older who underwent abdominal CT and dual-energy X-ray absorptiometryscans within 14 dayswere retrospectively enrolled. The patients were randomly assigned to a training cohort (n=155) and a testing cohort (n=67) in a ratio of 7:3. A total of 2288 candidate radiomic features were extracted from the volume region of interest- the left proximal femur of the abdominal CT scans. The most valuable radiomic features were selected using minimum-Redundancy Maximum-Relevancyand the least absolute shrinkage and selection operatorto construct the radiomics model. The predictive performance was assessed with receiver operating characteristiccurve. 13 features were chosen to establish the radiomics model. The radiomics model using logistic regressiondisplayed excellent prediction performance in distinguishing normal bone mass and abnormal bone mass, with the area under the curve (AUC), accuracy, sensitivity and specificity of 0.917 (95% CI, 0.867-0.967), 0.826, 0.935 and 0.780 in the training cohort. The testing cohort indicated a better performance with AUC, accuracy, sensitivity and specificity of 0.963 (95% CI, 0.919-0.999), 0.851, 0.923 and 0.889. The radiomics model based on proximal femur of abdominal CT scans had a high predictive performance to identify abnormal bone mass in femur, which can be used as a tool for opportunistic osteoporosis screening.

A study on whether deep learning models based on CT images for bone density classification and prediction can be used for opportunistic osteoporosis screening.

To explore the feasibility of using deep learning to establish a model for osteoporosis classification and bone density value prediction based on opportunistic CT scans and to verify its generalization and diagnostic ability using an independent test set. A total of 1219 cases of opportunistic CT scans were included in this study, with QCT results as the reference standard. The training set: test set: independent test set ratio was 703: 176: 340, and the independent test set data of 340 cases were from 3 different hospitals and 4 different CT scanners. The VB-Net structure automatic segmentation model was used to segment the trabecular bone, and DenseNet was used to establish a three-classification model and bone density value prediction regression model. The performance parameters of the models were calculated and evaluated. The ROC curves showed that the mean AUCs of the three-category classification model for categorizing cases into "normal," "osteopenia," and "osteoporosis" for the training set, test set, and independent test set were 0.999, 0.970, and 0.933, respectively. The F1 score, accuracy, precision, recall, precision, and specificity of the test set were 0.903, 0.909, 0.899, 0.908, and 0.956, respectively, and those of the independent test set were 0.798, 0.815, 0.792, 0.81, and 0.899, respectively. The MAEs of the bone density prediction regression model in the training set, test set, and independent test set were 3.15, 6.303, and 10.257, respectively, and the RMSEs were 4.127, 8.561, and 13.507, respectively. The R-squared values were 0.991, 0.962, and 0.878, respectively. The Pearson correlation coefficients were 0.996, 0.981, and 0.94, respectively, and the p values were all < 0.001. The predicted values and bone density values were highly positively correlated, and there was a significant linear relationship. Using deep learning neural networks to process opportunistic CT scan images of the body can accurately predict bone density values and perform bone density three-classification diagnosis, which can reduce the radiation risk, economic consumption, and time consumption brought by specialized bone density measurement, expand the scope of osteoporosis screening, and have broad application prospects.

Vertebral bone quality score for opportunistic osteoporosis screening: a correlation and optimal threshold analysis.

This study investigated the vertebral bone quality (VBQ) score as a potential tool for opportunistic osteoporosis screening and its correlation with dual-energy X-ray absorptiometry (DXA) values. In a single-center retrospective cohort of 130 patients, VBQ and DXA measures were compared using various statistical analyses. The optimal VBQ threshold for predicting osteoporosis was determined using receiver operating characteristic (ROC) analysis. VBQ exhibited a significant negative association with DXA values, suggesting that higher VBQ scores are indicative of lower bone density. Age and VBQ were significant predictors of osteoporosis, with both increasing the log-odds of the condition. An optimal VBQ threshold of 2.7 was determined, demonstrating fair discriminatory power and high negative predictive value. The study highlighted the potential of VBQ as a diagnostic tool for osteoporosis with high intra- and inter-observer reliability. The optimal VBQ threshold of 2.7 can aid in ruling out osteoporosis and identifying individuals for further evaluation.

Development and validation of a fully automated system using deep learning for opportunistic osteoporosis screening using low-dose computed tomography scans.

Bone density measurement is an important examination for the diagnosis and screening of osteoporosis. The aim of this study was to develop a deep learning (DL) system for automatic measurement of bone mineral density (BMD) for osteoporosis screening using low-dose computed tomography (LDCT) images. This retrospective study included 500 individuals who underwent LDCT scanning from April 2018 to July 2021. All images were manually annotated by a radiologist for the cancellous bone of target vertebrae and post-processed using quantitative computed tomography (QCT) software to identify osteoporosis. Patients were divided into the training, validation, and testing sets in a ratio of 6:2:2 using a 4-fold cross validation method. A localization model using faster region-based convolutional neural network (R-CNN) was trained to identify and locate the target vertebrae (T12-L2), then a 3-dimensional (3D) AnatomyNet was trained to finely segment the cancellous bone of target vertebrae in the localized image. A 3D DenseNet was applied for calculating BMD. The Dice coefficient was used to evaluate segmentation performance. Linear regression and Bland-Altman (BA) analyses were performed to compare the calculated BMD values using the proposed system with QCT. The diagnostic performance of the system for osteoporosis and osteopenia was evaluated with receiver operating characteristic (ROC) curve analysis. Our segmentation model achieved a mean Dice coefficient of 0.95, with Dice coefficients greater than 0.9 accounting for 96.6%. The correlation coefficient (R2) and mean errors between the proposed system and QCT in the testing set were 0.967 and 2.21 mg/cm3, respectively. The area under the curve (AUC) of the ROC was 0.984 for detecting osteoporosis and 0.993 for distinguishing abnormal BMD (osteopenia and osteoporosis). The fully automated DL-based system is able to perform automatic BMD calculation for opportunistic osteoporosis screening with high accuracy using LDCT scans.

Development and Validation of a Feature-Based Broad-Learning System for Opportunistic Osteoporosis Screening Using Lumbar Spine Radiographs

Osteoporosis is primarily diagnosed using dual-energy X-ray absorptiometry (DXA); yet, DXA is significantly underutilized, causing osteoporosis, an underdiagnosed condition. We aimed to provide an opportunistic approach to screen for osteoporosis using artificial intelligence based on lumbar spine X-ray radiographs. In this institutional review board-approved retrospective study, female patients aged ≥50 years who received both X-ray scans and DXAof the lumbar vertebrae, in three centers, were included. A total of 1180 cases were used for training and 145 cases were used for testing. We proposed a novel broad-learning system (BLS) and then compared the performance of BLS models using radiomic features and deep features as a source of input. The deep features were extracted using ResNet18 and VGG11, respectively. The diagnostic performances of these BLS models were evaluated with the area under the curve (AUC), sensitivity, and specificity. The incidence rate of osteoporosis in the training and test sets was 35.9% and 37.9%, respectively. The radiomic feature-based BLS model achieved higher testing AUC (0.802 vs. 0.654 vs. 0.632, both P=.002), sensitivity (78.2% vs. 56.4% vs. 50.9%), and specificity (82.2% vs. 74,4% vs. 75.6%) than the two deep feature-based BLS models. Our proposed radiomic feature-based BLS model has the potential to expand osteoporosis screening to a broader population by identifying osteoporosis on lumbar spine X-ray radiographs.

Cost-Effectiveness of Osteoporosis Opportunistic Screening Using Computed Tomography in China

ObjectivesUnderutilization and insufficient availability of dual-energy X-ray absorptiometry (DXA) in diagnosing osteoporosis in China could be changed by adopting unindicated quantitative computed tomography. We aimed to assess the cost-effectiveness of quantitative computed tomography (QCT) as a screening tool for osteoporosis in China. MethodsA Markov microsimulation model was developed to assess the long-term costs and quality-adjusted life-years (QALYs) saved associated with 2 examinations as opportunistic screening for osteoporosis in a general population without prior histories of fracture. The diagnostic performance of both examinations was incorporated into the model. In lifetime modeling, opportunistically screened people may face the risk of experiencing hip, vertebral, and wrist fractures depending on their osteoporosis, age, and sex. Model parameters were informed by published literature. ResultsThe base-case result showed that QCT was associated with higher costs ($6054 vs $5883) and higher benefits (10.081 vs 10.071 QALYs) in comparison with DXA, making QCT a cost-effective option for opportunistic screening (incremental cost-effectiveness ratio of US $16 430/QALY). Screening with QCT led to fewer fractures over the lifetime simulation: for every 10 000 people screened, 129 fractures (32 hip, 78 vertebral, and 19 wrist fractures) could be avoided because of the early initiation of antiosteoporotic treatment. ConclusionsUsing QCT to screen people for osteoporosis is more cost-effective than standard practice in China, where access to DXA is minimal. This finding could support opportunistic osteoporosis screening using QCT in other countries with similar status.

Generalizability of Deep Learning Classification of Spinal Osteoporotic Compression Fractures on Radiographs Using an Adaptation of the Modified-2 Algorithm-Based Qualitative Criteria

Spinal osteoporotic compression fractures (OCFs) can be an early biomarker for osteoporosis but are often subtle, incidental, and underreported. To ensure early diagnosis and treatment of osteoporosis, we aimed to build a deep learning vertebral body classifier for OCFs as a critical component of our future automated opportunistic screening tool. We retrospectively assembled a local dataset, including 1790 subjects and 15,050 vertebral bodies (thoracic and lumbar). Each vertebral body was annotated using an adaption of the modified-2 algorithm-based qualitative criteria. The Osteoporotic Fractures in Men (MrOS) Study dataset provided thoracic and lumbar spine radiographs of 5994 men from six clinical centers. Using both datasets, five deep learning algorithms were trained to classify each individual vertebral body of the spine radiographs. Classification performance was compared for these models using multiple metrics, including the area under the receiver operating characteristic curve (AUC-ROC), sensitivity, specificity, and positive predictive value (PPV). Our best model, built with ensemble averaging, achieved an AUC-ROC of 0.948 and 0.936 on the local dataset's test set and the MrOS dataset's test set, respectively. After setting the cutoff threshold to prioritize PPV, this model achieved a sensitivity of 54.5% and 47.8%, a specificity of 99.7% and 99.6%, and a PPV of 89.8% and 94.8%. Our model achieved an AUC-ROC>0.90 on both datasets. This testing shows some generalizability to real-world clinical datasets and a suitable performance for a future opportunistic osteoporosis screening tool.

Automated Opportunistic Trabecular Volumetric Bone Mineral Density Extraction Outperforms Manual Measurements for the Prediction of Vertebral Fractures in Routine CT

Opportunistic osteoporosis screening using multidetector CT-scans (MDCT) and convolutional neural network (CNN)-derived segmentations of the spine to generate volumetric bone mineral density (vBMD) bears the potential to improve incidental osteoporotic vertebral fracture (VF) prediction. However, the performance compared to the established manual opportunistic vBMD measures remains unclear. Hence, we investigated patients with a routine MDCT of the spine who had developed a new osteoporotic incidental VF and frequency matched to patients without incidental VFs as assessed on follow-up MDCT images after 1.5 years. Automated vBMD was generated using CNN-generated segmentation masks and asynchronous calibration. Additionally, manual vBMD was sampled by two radiologists. Automated vBMD measurements in patients with incidental VFs at 1.5-years follow-up (n = 53) were significantly lower compared to patients without incidental VFs (n = 104) (83.6 ± 29.4 mg/cm3 vs. 102.1 ± 27.7 mg/cm3, p &lt; 0.001). This comparison was not significant for manually assessed vBMD (99.2 ± 37.6 mg/cm3 vs. 107.9 ± 33.9 mg/cm3, p = 0.30). When adjusting for age and sex, both automated and manual vBMD measurements were significantly associated with incidental VFs at 1.5-year follow-up, however, the associations were stronger for automated measurements (β = −0.32; 95% confidence interval (CI): −20.10, 4.35; p &lt; 0.001) compared to manual measurements (β = −0.15; 95% CI: −11.16, 5.16; p &lt; 0.03). In conclusion, automated opportunistic measurements are feasible and can be useful for bone mineral density assessment in clinical routine.

Detecting whether L1 or other lumbar levels would be excluded from DXA bone mineral density analysis during opportunistic CT screening for osteoporosis using machine learning.

One or more vertebrae are sometimes excluded from dual-energy X-ray absorptiometry (DXA) analysis if the bone mineral density (BMD) T-score estimates are not consistent with the other lumbar vertebrae BMD T-score estimates. The goal of this study was to build a machine learning framework to identify which vertebrae would be excluded from DXA analysis based on the computed tomography (CT) attenuation of the vertebrae. Retrospective review of 995 patients (69.0% female) aged 50years or greater with CT scans of the abdomen/pelvis and DXA within 1year of each other. Volumetric semi-automated segmentation of each vertebral body was performed using 3D-Slicer to obtain the CT attenuation of each vertebra. Radiomic features based on the CT attenuation of the lumbar vertebrae were created. The data were randomly split into training/validation (90%) and test datasets (10%). We used two multivariate machine learning models: a support vector machine (SVM) and a neural net (NN) to predict which vertebra(e) were excluded from DXA analysis. L1, L2, L3, and L4 were excluded from DXA in 8.7% (87/995), 9.9% (99/995), 32.3% (321/995), and 42.6% (424/995) patients, respectively. The SVM had a higher area under the curve (AUC = 0.803) than the NN (AUC = 0.589) for predicting whether L1 would be excluded from DXA analysis (P = 0.015) in the test dataset. The SVM was better than the NN for predicting whether L2 (AUC = 0.757 compared to AUC = 0.478), L3 (AUC = 0.699 compared to AUC = 0.555), or L4 (AUC = 0.751 compared to AUC = 0.639) were excluded from DXA analysis. Machine learning algorithms could be used to identify which lumbar vertebrae would be excluded from DXA analysis and should not be used for opportunistic CT screening analysis. The SVM was better than the NN for identifying which lumbar vertebra should not be used for opportunistic CT screening analysis.