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

This study utilized deep learning to classify osteoporosis and predict bone density using opportunistic CT scans and independently tested the models on data from different hospitals and equipment. Results showed high accuracy and strong correlation with QCT results, showing promise for expanding osteoporosis screening and reducing unnecessary radiation and costs. PURPOSE: 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. METHODS: 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. RESULTS: 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. CONCLUSION: 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.

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

OBJECTIVE: 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. MATERIALS AND METHODS: 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. RESULTS: 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%). CONCLUSION: 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.

Bone Health Screening Prior to Medicare Eligibility-Osteoporosis Screening and Fracture Prevention After Distal Radius Fractures in Patients Aged 50-59.

PURPOSE: Current guidelines recommend bone mineral density (BMD) testing after fragility fractures in patients aged 50 years or older. This study aimed to assess BMD testing and subsequent fragility fractures after low-energy distal radius fractures (DRFs) among patients aged 50-59 years. METHODS: We used the 2010-2020 MarketScan dataset to identify patients with initial DRFs with ages ranging between 50 and 59 years. We assessed the 1-year BMD testing rate and 3-year non-DRF fragility fracture rate. We created Kaplan-Meier plots to depict fragility fracture-free probabilities over time and used log-rank tests to compare the Kaplan-Meier curves. RESULTS: Among 78,389 patients aged 50-59 years with DRFs, 24,589 patients met our inclusion criteria, and most patients were women (N = 17,580, 71.5%). The BMD testing rate within 1 year after the initial DRF was 12.7% (95% CI, 12.3% to 13.2%). In addition, 1-year BMD testing rates for the age groups of 50-54 and 55-59 years were 10.4% (95% CI, 9.9% to 11.0%) and 14.9% (95% CI, 14.2% to 15.6%), respectively. Only 1.8% (95% CI, 1.5% to 2.1%) of men, compared with 17.1% (95% CI, 16.5% to 17.7%) of women, underwent BMD testing within 1 year after the initial fracture. The overall 3-year fragility fracture rate was 6.0% (95% CI, 5.6% to 6.3%). The subsequent fragility fracture rate was lower for those with any BMD testing (4.4%; 95% CI, 3.7% to 5.2%), compared with those without BMD testing (6.2%; 95% CI, 5.9% to 6.6%; P < .05). CONCLUSIONS: We report a low BMD testing rate for patients aged between 50 and 59 years after initial isolated DRFs, especially for men and patients aged between 50 and 54 years. Patients who received BMD testing had a lower rate of subsequent fracture within 3 years. We recommend that providers follow published guidelines and initiate an osteoporosis work-up for patients with low-energy DRFs to ensure early diagnosis. This provides an opportunity to initiate treatment that may prevent subsequent fractures. TYPE OF STUDY/LEVEL OF EVIDENCE: Prognosis II.

CNN-based qualitative detection of bone mineral density via diagnostic CT slices for osteoporosis screening.

The features extracted from diagnostic computed tomography (CT) slices were used to qualitatively detect bone mineral density (BMD) through neural network models, and the evaluation results indicated that it may be a promising approach to perform osteoporosis screening in clinical practice. INTRODUCTION: The purpose of this study is to design a novelty diagnostic method for osteoporosis screening by using the convolutional neural network (CNN), which can be incorporated into the procedure of routine CT diagnostic in medical examination thereby improving the osteoporosis diagnosis and reducing the patient burden. METHODS: The proposed CNN-based method mainly comprises two functional modules to perform qualitative detection of BMD by analyzing the diagnostic 2D CT slice. The first functional module aims to locate and segment the ROI of diagnostic 2D CT slice, called Mark-Segmentation-Network (MS-Net). The second functional module is used to determine the category of BMD by the features of ROI, called BMD-Classification-Network (BMDC-Net). The diagnostic 2D CT slice of pedicle level in lumbar vertebrae (L1) was selected from 3D CT image in our experiments firstly. Then, the trained MS-Net can get the mark image of input original 2D CT slice, thereby obtain the segmentation image. Finally, the trained BMDC-Net can obtain the probability value of normal bone mass, low bone mass, and osteoporosis by inputting the segmentation image. On the basis of network results, the radiologists can provide preliminary qualitative diagnosis results of BMD. RESULTS: Training of the network was performed on diagnostic 2D CT slices of 150 patients. The network was tested on 63 patients. Each patient corresponds to a 2D CT slice. The proposed MS-Net has an excellent segmentation precision on the shape preservation of different lumbar vertebra. The dice index (DI), pixel accuracy (PA), and intersection over union (IOU) of segmentation results are greater than 0.8. The proposed BMDC-Net achieved an accuracy of 76.65% and an area under the receiver operating characteristic curve of 0.9167. CONCLUSIONS: This study proposed a novel method for qualitative detection of BMD via diagnostic CT slices and it has great potential in clinical applications for osteoporosis screening. The method can potentially reduce the manual burden to radiologists and diagnostic cost to patients.

Feasibility of opportunistic osteoporosis screening in routine contrast-enhanced multi detector computed tomography (MDCT) using texture analysis.

This study investigated the feasibility of opportunistic osteoporosis screening in routine contrast-enhanced MDCT exams using texture analysis. The results showed an acceptable reproducibility of texture features, and these features could discriminate healthy/osteoporotic fracture cohort with an accuracy of 83%. INTRODUCTION: This aim of this study is to investigate the feasibility of opportunistic osteoporosis screening in routine contrast-enhanced MDCT exams using texture analysis. METHODS: We performed texture analysis at the spine in routine MDCT exams and investigated the effect of intravenous contrast medium (IVCM) (n = 7), slice thickness (n = 7), the long-term reproducibility (n = 9), and the ability to differentiate healthy/osteoporotic fracture cohort (n = 9 age and gender matched pairs). Eight texture features were extracted using gray level co-occurrence matrix (GLCM). The independent sample t test was used to rank the features of healthy/fracture cohort and classification was performed using support vector machine (SVM). RESULTS: The results revealed significant correlations between texture parameters derived from MDCT scans with and without IVCM (r up to 0.91) slice thickness of 1 mm versus 2 and 3 mm (r up to 0.96) and scan-rescan (r up to 0.59). The performance of the SVM classifier was evaluated using 10-fold cross-validation and revealed an average classification accuracy of 83%. CONCLUSIONS: Opportunistic osteoporosis screening at the spine using specific texture parameters (energy, entropy, and homogeneity) and SVM can be performed in routine contrast-enhanced MDCT exams.

Predicting Future Hip Fractures on Routine Abdominal CT Using Opportunistic Osteoporosis Screening Measures: A Matched Case-Control Study.

OBJECTIVE: Hip fracture is a major consequence of low bone mineral density, which is treatable but underdiagnosed. The purpose of this case-control study is to determine whether lumbar vertebral trabecular attenuation, vertebral compression fractures, and femoral neck T scores readily derived from abdominopelvic CT scans obtained for various indications are associated with future hip fragility fracture. MATERIALS AND METHODS: A cohort of 204 patients with hip fracture (130 women and 74 men; mean age, 74.3 years) who had undergone abdominopelvic CT before fracture occurred (mean interval, 24.8 months) was compared with an age- and sex-matched control cohort without hip fracture. L1 trabecular attenuation, vertebral compression fractures of grades 2 and 3, and femoral neck T scores derived from asynchronous quantitative CT were recorded. The presence of one or more clinical risk factor for fracture was also recorded. Multivariate logistic regression models were used to determine the association of each measurement with the occurrence of hip fracture. RESULTS: The mean L1 trabecular attenuation value, the presence of one or more vertebral compression fracture, and CT-derived femoral neck T scores were all significantly different in patients with hip fracture versus control subjects (p < 0.01). Logistic regression models showed a significant association of all measurements with hip fracture outcome after adjustments were made for age, sex, and the presence of one or more clinical risk factor. L1 trabecular attenuation and CT-derived femoral neck T scores showed moderate accuracy in differentiating case and control patients (AUC, 0.70 and 0.78, respectively). CONCLUSION: L1 trabecular attenuation, CT-derived femoral neck T scores, and the presence of at least one vertebral compression fracture on CT are all associated with future hip fragility fracture in adults undergoing routine abdominopelvic CT for a variety of conditions.

Effect of IV contrast on lumbar trabecular attenuation at routine abdominal CT: correlation with DXA and implications for opportunistic osteoporosis screening.

UNLABELLED: Osteoporosis remains under-diagnosed. Routine abdominal CT can provide opportunistic screening, but the effect of IV contrast is largely unknown. The overall performance for predicting osteoporosis was similar between enhanced and unenhanced scans. Therefore, both non-contrast and contrast-enhanced abdominal CT scans can be employed for opportunistic osteoporosis screening. INTRODUCTION: Osteoporosis is an important yet under-diagnosed public health concern. Lumbar attenuation measurement at routine abdominal CT can provide a simple opportunistic initial screen, but the effect of IV contrast has not been fully evaluated. METHODS: Mean trabecular CT attenuation values (in Hounsfield units, HU) at the L1 vertebral level were measured by oval region-of-interest (ROI) on both the unenhanced and IV-contrast-enhanced CT series in 157 adults (mean age, 62.0). All patients underwent correlative central DXA within 6 months of CT. Based on DXA BMD of the lumbar spine, femoral neck, and total proximal femur: osteoporosis, osteopenia, and normal BMD was present in 33, 77, and 47, respectively. Statistical analysis included Bland-Altman plots and receiver operating characteristic (ROC) curves. RESULTS: Mean difference (±SD) in L1 trabecular attenuation between enhanced and unenhanced CT series was +11.2 HU (±19.2) (95 % CI, 8.16-14.22 HU), an 8 % difference. Intra-patient variation was substantial, but no overall trend in the HU difference was seen according to underlying BMD. ROC area under the curve (AUC) for unenhanced and enhanced CT for diagnosing osteoporosis were similar at 0.818 and 0.830, respectively (p = 0.632). Thresholds for maintaining 90 % specificity for osteoporosis were 90 HU for unenhanced and 102 HU for enhanced CT. Thresholds for maintaining 90 % sensitivity for osteoporosis were 139 HU for unenhanced and 144 HU for enhanced CT. Similar diagnostic performance was seen for diagnosing low BMD (osteoporosis or osteopenia) using higher HU cut-offs. CONCLUSION: Contrast-enhanced CT shows an average increase of 11 HU over the unenhanced series for L1 trabecular attenuation. The overall performance for predicting osteoporosis is similar between the enhanced and unenhanced scans, thus either can be employed for initial opportunistic screening.

Hip fractures, preceding distal radius fractures and screening for osteoporosis: should we be screening earlier? A minimum 10-year retrospective cohort study at a single centre.

UNLABELLED: Both men and women who sustain a fracture of the distal forearm run an increased risk of sustaining a subsequent hip fracture. Our study implies that these patients may not necessarily constitute a group in which osteoporosis screening is warranted. INTRODUCTION: People who sustain a distal radius fracture run an increased risk of sustaining a subsequent hip fracture. However, many institutions only screen for osteoporosis at the time of a hip fracture. We aimed to determine the true incidence of preceding distal radius fractures in an Asian population of patients with a hip fracture aged 60 years or older and whether screening for osteoporosis earlier would be beneficial. METHODS: We reviewed 22 parameters of 572 patients aged 60 years or older admitted after sustaining a hip fracture over a 3-year period. This included the occurrence or absence of a distal radius fracture in the 10 years preceding their hip fracture. RESULTS: Twenty-nine patients (5 %) had a fracture of the distal radius in the preceding decade. Univariate analyses suggested that hip fracture patients who had preceding distal radius fractures were older, female, have lower mean haemoglobin levels, and right-sided hip fractures. Of these factors, only age was found to have significant predictive value in a multivariate analysis. CONCLUSIONS: A number of institutions have started to screen for osteoporosis when a patient presents with a fracture of the distal radius because these patients may have an increased risk of a subsequent hip fracture. Our study implies that this may not be warranted. Implementing such a screening service from both cost and resource utilization point of view must be studied prospectively and in greater detail considering earlier screening may only be beneficial to a very small percentage of patients.

Screening and early treatment for osteoporosis: Who are we missing under age 65?

For women under age 65, varying recommendations and the need to apply clinical risk calculators can lead to underscreening for osteoporosis. The resulting undertreatment may lead to a risk of osteoporotic fractures with significant morbidity and impact on functional status. Factors that must be considered when deciding to screen a woman under age 65 include a history of fragility fractures, race, family history, body mass index, smoking, high alcohol use, and secondary causes of osteoporosis. Secondary causes of osteoporosis are much more common in younger women. These include common conditions such as glucocorticoid use, hyperthyroidism, hypogonadism, chronic kidney disease, diabetes, anticonvulsant use, rheumatoid arthritis, malabsorption, and a history of anorexia nervosa. The reasons why these conditions confer an increased risk of osteoporosis are discussed. Recommendations are provided for the clinician to be aware of when screening women under age 65 for osteoporosis and initiating treatment when indicated.

Osteoporosis Prediction Using Machine-Learned Optical Bone Densitometry Data.

Optical bone densitometry (OBD) has been developed for the early detection of osteoporosis. In recent years, machine learning (ML) techniques have been actively implemented for the areas of medical diagnosis and screening with the goal of improving diagnostic accuracy. The purpose of this study was to verify the feasibility of using the combination of OBD and ML techniques as a screening tool for osteoporosis. Dual energy X-ray absorptiometry (DXA) and OBD measurements were performed on 203 Thai subjects. From the OBD measurements and readily available demographic data, machine learning techniques were used to predict the T-score measured by the DXA. The T-score predicted using the Ridge regressor had a correlation of r = 0.512 with respect to the reference value. The predicted T-score also showed an AUC of 0.853 for discriminating individuals with osteoporosis. The results obtained suggest that the developed model is reliable enough to be used for screening for osteoporosis.

Asynchronous calibration of a CT scanner for bone mineral density estimation: sources of error and correction.

The estimation of BMD with CT scans requires a calibration method, usually based on a phantom. In asynchronous calibration, the phantom is scanned separately from the patient. A standardized acquisition protocol must be used to avoid variations between patient and phantom. However, variations can still be induced, for example, by temporal fluctuations or patient characteristics. Based on the further use of 739 forensic and 111 clinical CT scans, this study uses the proximal femur BMD value ("total hip") to assess asynchronous calibration accuracy, using in-scan calibration as ground truth. It identifies the parameters affecting the calibration accuracy and quantifies their impact. For time interval and table height, the impact was measured by calibrating the CT scan twice (once using the phantom scan with closest acquisition parameters and once using a phantom scan with standard values) and comparing the calibration accuracy. For other parameters such as body weight, the impact was measured by computing a linear regression between parameter values and calibration accuracy. Finally, this study proposes correction methods to reduce the effect of these parameters and improve the calibration accuracy. The BMD error of the asynchronous calibration, using the phantom scan with the closest acquisition parameters, was -1.2 ± 1.7% for the forensic and - 1.6 ± 3.5% for the clinical dataset. Among the parameters studied, time interval and body weight were identified as the main sources of error for asynchronous calibration, followed by table height and reconstruction kernel. Based on these results, a correction method was proposed to improve the calibration accuracy.

Automated Screening of Hip X-rays for Osteoporosis by Singh's Index Using Machine Learning Algorithms.

Introduction: Osteoporosis is a significant and growing global public health problem, projected to increase in the next decade. The Singh Index (SI) is a simple, semi-quantitative evaluation tool for diagnosing osteoporosis with plain hip radiographs based on the visibility of the trabecular pattern in the proximal femur. This work aims to develop an automated tool to diagnose osteoporosis using SI of hip radiograph images with the help of machine learning algorithms. Methods: We used 830 hip X-ray images collected from Indian men and women aged between 20 and 70 which were annotated and labeled for appropriate SI. We employed three state-of-the-art machine learning algorithms-Vision Transformer (ViT), MobileNet-V3, and a Stacked Convolutional Neural Network (CNN)-for image pre-processing, feature extraction, and automation. Each algorithm was evaluated and compared for accuracy, precision, recall, and generalization capabilities to diagnose osteoporosis. Results: The ViT model achieved an overall accuracy of 62.6% with macro-averages of 0.672, 0.597, and 0.622 for precision, recall, and F1 score, respectively. MobileNet-V3 presented a more encouraging accuracy of 69.6% with macro-averages for precision, recall, and F1 score of 0.845, 0.636, and 0.652, respectively. The stacked CNN model demonstrated the strongest performance, achieving an accuracy of 93.6% with well-balanced precision, recall, and F1-score metrics. Conclusion: The superior accuracy, precision-recall balance, and high F1-scores of the stacked CNN model make it the most reliable tool for screening radiographs and diagnosing osteoporosis using the SI.

Disparities in Osteoporosis Prevention and Care: Understanding Gender, Racial, and Ethnic Dynamics.

PURPOSE: Osteoporosis, the most prevalent metabolic bone disease, significantly impacts global public health by increasing fracture risks, particularly among post-menopausal women and the elderly. Osteoporosis is characterized by decreased bone mineral density (BMD) and deterioration of bone tissue, which leads to enhanced fragility. The disease is predominantly diagnosed using dual X-ray absorptiometry (DXA) and is significantly influenced by demographic factors such as age and hormonal changes. This chapter delves into the condition's complex nature, emphasizing the pervasive gender and racial disparities in its screening, diagnosis, and treatment. RECENT FINDINGS: Recent findings highlight a substantial gap in the management of osteoporosis, with many individuals remaining under-screened and under-treated. Factors contributing to this include the asymptomatic early stages of the disease, lack of awareness, economic barriers, and inconsistent screening practices, especially in under-resourced areas. These challenges are compounded by disparities that affect different genders and races unevenly, influencing both the prevalence of the disease and the likelihood of receiving adequate healthcare services. The summary of this chapter underscores the urgent need for targeted strategies to overcome these barriers and improve health equity in osteoporosis care. Proposed strategies include enhancing public and healthcare provider awareness of osteoporosis, broadening access to diagnostic screenings, and integrating personalized treatment approaches. These efforts aim to align with global health objectives to mitigate the impacts of osteoporosis and ensure equitable health outcomes across all demographic groups.

A Study on Intelligent Optical Bone Densitometry.

Osteoporosis is a prevalent chronic disease worldwide, particularly affecting the aging population. The gold standard diagnostic tool for osteoporosis is Dual-energy X-ray Absorptiometry (DXA). However, the expensive cost of the DXA machine and the need for skilled professionals to operate it restrict its accessibility to the general public. This paper builds upon previous research and proposes a novel approach for rapidly screening bone density. The method involves utilizing near-infrared light to capture local body information within the human body. Deep learning techniques are employed to analyze the obtained data and extract meaningful insights related to bone density. Our initial prediction, utilizing multi-linear regression, demonstrated a strong correlation (r = 0.98, p-value = 0.003**) with the measured Bone Mineral Density (BMD) obtained from Dual-energy X-ray Absorptiometry (DXA). This indicates a highly significant relationship between the predicted values and the actual BMD measurements. A deep learning-based algorithm is applied to analyze the underlying information further to predict bone density at the wrist, hip, and spine. The prediction of bone densities in the hip and spine holds significant importance due to their status as gold-standard sites for assessing an individual's bone density. Our prediction rate had an error margin below 10% for the wrist and below 20% for the hip and spine bone density.

Screening for osteoporosis based on IQon spectral CT virtual low monoenergetic images: Comparison with conventional 120 kVp images.

Objectives: To explore the differences between low kiloelectron volt (keV) virtual monoenergetic images (VMIs) using IQon spectral CT and conventional CT (120 kVp) in the diagnosis of osteoporosis. Methods: This retrospective study included 317 patients who underwent IQon spectral CT and dual-energy X-ray absorptiometry (DXA) examination. Commercial deep learning-based software was used for the fully automated extraction of the CT values of the first to fourth lumbar vertebrae (L1-L4) from two different low-keV levels (including 40/70 keV) VMIs and conventional 120 kVp images. The DXA examination results served as the standard of reference (normal [T-score ≥ -1], osteopenia [-2.5 < T-score < -1], and osteoporosis [T-score < -2.5]). Osteoporosis diagnosis models were constructed using machine learning classifiers (logistic regression, support vector machine, random forest, XGBoost, and multilayer perceptron) based on the average CT values of L1-L4. The area under the receiver operating characteristic curve (AUC) and DeLong test were performed to compare differences in the performance of the osteoporosis diagnosis model between virtual low-keV VMIs and standard 120 kVp images. Results: Random forest-based prediction model obtained good overall performance among all classifiers, and macro/micro average AUC values of 0.820/840, 0.834/853, and 0.831/852 were obtained based on 40/70 keV and 120 kVp images, respectively. The model presented no significant difference between low-keV VMIs and standard 120 kVp images for the diagnosis of osteoporosis (p > 0.05). Conclusions: The performance of the osteoporosis diagnosis model using IQon spectral CT simulating the low tube voltage scanning condition (less than 120 kVp) was also satisfactory. Bone density screening evaluation can be performed with a combination of low-dose lung scanning CT, greatly reducing the radiation dose without affecting the diagnosis.

Addressing gaps in osteoporosis screening in kuwait using opportunistic quantitative computer tomography (QCT): a retrospective study.

Osteoporosis is a common skeletal disorder which is underdiagnosed and undertreated. Consequent fragility fractures are associated with high morbidity and mortality. Prevention of these fractures is possible by timely osteoporosis screening followed by timely therapeutic interventions when needed. Utilizing all available modalities such as bone density measurements on preexisting CT scans could help narrow the diagnostic gap. PURPOSE: To demonstrate the feasibility and clinical utility of opportunistic osteoporosis screening in Kuwait using QCT, aiming to increase screening rates in a country with a relatively high prevalence of osteoporosis and an alarming trend of increasing incidence of fractures. METHODS: At a tertiary referral center, all abdominal CT scans performed on females ≥60 years old between 12/2020 and 12/2021 were retrospectively utilized for asynchronous QCT acquisition. The average volumetric bone mineral density (vBMD) was calculated, and rates of osteoporosis (vBMD < 80 mg/cm3 calcium hydroxyapatite) and osteopenia (80-120 mg/cm3) were determined. CT images were reviewed to assess for the presence of vertebral fractures. For each patient, the electronic health record was reviewed for any previous DXA scans. RESULTS: vBMD was calculated in 305 females ≥60 years old (mean [SD] 71 [8.7], range 60-93). Low bone mass was detected in 258 patients (84.6%); 148 (48.5%) met criteria for osteopenia and 110 (36.1%) for osteoporosis. Osteoporotic vertebral fractures were observed in 64 (21.0%) study participants. Only 73 patients (23.9% of total) had a previous DXA documented in the reviewed health records. For 231 patients who were ≥65 years old, who would routinely qualify for a screening DXA, only 63 (27.3%) had a documented DXA available. CONCLUSION: vBMD measurements obtained by opportunistic QCT had comparable rates of osteopenia and osteoporosis detection to those previously reported using DXA in a similar population in Kuwait. These findings suggest that opportunistic QCT on preexisting CT scans can be effectively utilized to narrow gaps in osteoporosis screening.

Assessing Bone Mineral Density in Weight-Bearing Regions of the Body through Texture Analysis of Abdomen and Pelvis CT Hounsfield Unit.

Objective: This study aimed to develop a novel method for opportunistically screening osteoporosis by measuring bone mineral density (BMD) from CT images. We addressed the limitations of commercially available software and introduced texture analysis using Hounsfield units (HU) as an alternative approach. Methods: A total of 458 samples (296 patients) were selected from a dataset of 1320 cases (782 patients) between 1 March 2013, and 30 August 2022. BMD measurements were obtained from the ilium, femoral neck, intertrochanteric region of both femurs, and L1-L5 and sacrum spine body. The region of interest (ROI) for each patient's CT scan was defined as the maximum trabecular area of the spine body, ilium, femoral neck, and femur intertrochanter. Using gray-level co-occurrence matrices, we extracted 45 texture features from each ROI. Linear regression analysis was employed to predict BMD, and the top five influential texture features were identified. Results: The linear regression (LR) model yielded correlation coefficients (R-squared values) for total lumbar BMD, total lumbar BMC, total femur BMD, total femur BMC, femur neck BMD, femur neck BMC, femur intertrochanter BMD, and femur intertrochanter BMC as follows: 0.643, 0.667, 0.63, 0.635, 0.631, 0.636, 0.68, and 0.68, respectively. Among the 45 texture features considered, the top five influential factors for BMD prediction were Entropy, autocorrelate_32, autocorrelate_32_volume, autocorrelate_64, and autocorrelate_64_volume.

Evaluation of Transfer Learning with Deep Convolutional Neural Networks for Screening Osteoporosis in Dental Panoramic Radiographs.

: Dental panoramic radiographs (DPRs) provide information required to potentially evaluate bone density changes through a textural and morphological feature analysis on a mandible. This study aims to evaluate the discriminating performance of deep convolutional neural networks (CNNs), employed with various transfer learning strategies, on the classification of specific features of osteoporosis in DPRs. For objective labeling, we collected a dataset containing 680 images from different patients who underwent both skeletal bone mineral density and digital panoramic radiographic examinations at the Korea University Ansan Hospital between 2009 and 2018. Four study groups were used to evaluate the impact of various transfer learning strategies on deep CNN models as follows: a basic CNN model with three convolutional layers (CNN3), visual geometry group deep CNN model (VGG-16), transfer learning model from VGG-16 (VGG-16_TF), and fine-tuning with the transfer learning model (VGG-16_TF_FT). The best performing model achieved an overall area under the receiver operating characteristic of 0.858. In this study, transfer learning and fine-tuning improved the performance of a deep CNN for screening osteoporosis in DPR images. In addition, using the gradient-weighted class activation mapping technique, a visual interpretation of the best performing deep CNN model indicated that the model relied on image features in the lower left and right border of the mandibular. This result suggests that deep learning-based assessment of DPR images could be useful and reliable in the automated screening of osteoporosis patients.

Utility of an index metacarpal cortical thickness application as an osteoporosis screen in distal radius fracture patients aged over 50.

BACKGROUND: Following wrist fracture, it is desirable to identify patients with osteoporosis. A smartphone-based application (BoneGauge) that uses second metacarpal cortical thickness ratio (2MCP) measured on X-ray has been proposed. This study aims to validate this application using dual-energy X-ray absorptiometry scan in a cohort of patients with distal radius fractures. METHODS: Thirty subjects aged 50 and over who sustained low-energy fractures of the radius were recruited and measurements were completed by two independent observers using the application. RESULTS: The interrater reliability as a screening tool was insufficient (κ = 0.61). Using the 2MCP threshold of 60% for detection of osteopaenia or osteoporosis, we found insufficient correlation between the dual-energy X-ray absorptiometry scan and the two sets of readings using the application (κ = 0.28 and 0.35, respectively). CONCLUSION: On the basis of these results, 2MCP of 60% is not sensitive enough to be used as a screening tool via a smartphone application for assessment of osteoporosis risk.

Management of Fragility Hip Fractures: Our Institutional Experience.

INTRODUCTION: Approximately 320 000 fragility hip fractures are sustained in the United States annually, resulting in substantial morbidity and mortality as well as significant economic burden on the health-care system. Nevertheless, a majority of these patients are not screened and do not receive treatment for osteoporosis. The objective of this study was to evaluate rates of osteoporosis screening and treatment in our institution and compare them to those reported in the literature. METHODS: This was a retrospective cohort study of 191 patients ages 50 and older who sustained osteoporotic hip fractures. Primary outcome measures were percentage of patients who (1) underwent bone health laboratory workup during admission, (2) were started on vitamin D, calcium, and/or a bisphosphonate, (3) received bone mineral density testing, and (4) followed up with a primary care doctor or endocrinologist. Secondary outcomes measures were (1) whether gender, race, or age influenced our primary outcomes and (2) whether obtaining in-hospital laboratory workup led to increased rates of further screening and treatment. RESULTS: Fifty-six (29.3%) patients received full laboratory workup, 48 (25.1%) were prescribed vitamin D and calcium, 11 (5.7%) were prescribed a bisphosphonate, 13 (6.8%) underwent bone mineral density testing, and 41 (21.5%) followed up with primary care or endocrinology. DISCUSSION: Women were more likely to be treated with vitamin D and calcium. Outcomes were similar regardless of race. Younger patients were more likely to undergo laboratory testing, bisphosphonate therapy, and bone mineral density testing. Initiating workup during admission did not lead to increased rates of outpatient treatment. CONCLUSION: Despite nationwide efforts to improve, rates of osteoporosis screening and treatment following hip fracture are suboptimal. Rates at our institution are similar to those reported in previous studies. There were disparities between gender and age groups. Future studies are needed to evaluate whether more recently implemented policies lead to better osteoporosis screening and management.