• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.59 no.4
• /
• pp.823-830
• /
• 2010

This study was designed to examine the morphological measurement and characteristics of trabecullae based on femoral radiographic image for prediction of osteoporosis. Study subjects were 34 females (average age of 62.1 years) and 6 males (average age of 60.1 years), they were categorized into normal group and osteoporosis group in accordance with the T-score value. Measurement of the bone density of femoral bone was measured with DEXA(Dual Energy X-ray absorptiometry). ROI(Region of interests) was selected on femoral neck and trochanter. Characteristics of trabecullae was analyzed by using the skeletonization analysis of trabecular image. Morphological measurement was analyzed through femoral radiographic image in order to examine the correlation with osteoporosis. The result demonstrated statistically significant correlation between neck cortical thickness, shaft width, shaft cortical thickness, periphery, mean gray level and trabeculae area with BMD average (T-score) of femoral part. The results show that morphological measurement and characteristics of trabecullae based on femoral radiographic images for osteoporosis prediction could be effective.

• Journal of the Korean Association of Oral and Maxillofacial Surgeons
• /
• v.49 no.3
• /
• pp.135-141
• /
• 2023

Objectives: This study aimed to develop and validate machine learning (ML) models using H₂O-AutoML, an automated ML program, for predicting medication-related osteonecrosis of the jaw (MRONJ) in patients with osteoporosis undergoing tooth extraction or implantation. Patients and Methods: We conducted a retrospective chart review of 340 patients who visited Dankook University Dental Hospital between January 2019 and June 2022 who met the following inclusion criteria: female, age ≥55 years, osteoporosis treated with antiresorptive therapy, and recent dental extraction or implantation. We considered medication administration and duration, demographics, and systemic factors (age and medical history). Local factors, such as surgical method, number of operated teeth, and operation area, were also included. Six algorithms were used to generate the MRONJ prediction model. Results: Gradient boosting demonstrated the best diagnostic accuracy, with an area under the receiver operating characteristic curve (AUC) of 0.8283. Validation with the test dataset yielded a stable AUC of 0.7526. Variable importance analysis identified duration of medication as the most important variable, followed by age, number of teeth operated, and operation site. Conclusion: ML models can help predict MRONJ occurrence in patients with osteoporosis undergoing tooth extraction or implantation based on questionnaire data acquired at the first visit.

• The Journal of the Convergence on Culture Technology
• /
• v.6 no.3
• /
• pp.457-462
• /
• 2020

Osteoporosis is a disease that occurs mainly in the elderly and increases the risk of fractures due to structural deterioration of bone mass and tissues. The purpose of this study are to assess the relationship between nutritional components and osteoporosis and to evaluate models for predicting osteoporosis based on nutrient components. In experimental method, association was performed using binary logistic regression, and predictive models were generated using the naive Bayes algorithm and variable subset selection methods. The analysis results for single variables indicated that food intake and vitamin B2 showed the highest value of the area under the receiver operating characteristic curve (AUC) for predicting osteoporosis in men. In women, monounsaturated fatty acids showed the highest AUC value. In prediction model of female osteoporosis, the models generated by the correlation based feature subset and wrapper based variable subset methods showed an AUC value of 0.662. In men, the model by the full variable obtained an AUC of 0.626, and in other male models, the predictive performance was very low in sensitivity and 1-specificity. The results of these studies are expected to be used as the basic information for the treatment and prevention of osteoporosis.

• Korean Journal of Digital Imaging in Medicine
• /
• v.14 no.2
• /
• pp.63-67
• /
• 2012

Calcium density in human bones decreases as people are getting older due to the interior or exterior environmental factors. Bone aging forms osteoporosis. And this can bring out various spine fractures which develops a complications. Thus the prediction of seniliy is one of the important factors in spine diseases. Once spine aged, diverse fractures occur such as compression fracture and micro fracture. Side images of the spine by the digital radiography (DR) were prepared, and pixel arbitrary unit with Image J was measured from one spot in the lumbar bone part. By calculating pixel arbitrary unit of the simple contrast, it was obtained that the value of pixel arbitrary unit decreased as seniliy of bones increased. By simply applying Image J to the seniliy of patient's spine, the seniliy of bones predicts the level of danger with only digital radiography(2D) image. consequently we show that Image J value of pixel arbitrary unit index for predicts the level of precaution of osteoporosis patient.

• Imaging Science in Dentistry
• /
• v.38 no.3
• /
• pp.147-151
• /
• 2008

Purpose : The purpose of this study was to investigate whether fractal analysis of periapical and panoramic radiographs was useful in predicting osteoporosis risk. Materials and Methods : 37 postmenoposal women between the age of 42 and 79 were classified as normal and osteoporosis group according to the bone mineral density of lumbar vertebrae and periapical and panoramic radio-graphs were taken. Fractal dimensions at periapical areas of mandibular first molars were calculated to differentiate the two groups. Results : The mean fractal dimensions of normal group on periapical and panoramic radiographs were $1.413{\pm}0.079$, $1.517{\pm}0.071$ each. The mean fractal dimensions of osteoporotic group on periapical and panoramic radiographs were $1.498{\pm}0.086$, $1.388{\pm}0.083$ each. The mean fractal dimension from peripaical radiographs of osteoporotic group was statistically significantly higher than that of normal group. The mean fractal dimension from panoramic radiographs of osteoporotic group was statistically significantly lower than that of normal group. Conclusion : Fractal analysis using periapical and panoramic radiographs was useful in predicting osteoporosis.

• Imaging Science in Dentistry
• /
• v.37 no.2
• /
• pp.79-82
• /
• 2007

Purpose: The purpose of this study was to investigate whether panoramic radiographs were useful in predicting osteoporosis. Materials and Methods: 50 postmenoposal women between the age of 41.8 and 78.5 were classified as normal and osteoporosis groups according to the bone mineral density of lumbar vertebrae. Panoramic radiographs were taken. Age, body mass index, remaining mandibular teeth, mandibular cortical thickness and morphology, and fractal dimensions at periapical areas of mandibular first molars were evaluated to differentiate the two groups. Results: The age of osteoporotic group was statistically significantly higher than that of normal group (p<0.05), but not the body mass index or number of remaining mandibular teeth. The mean fractal dimension of osteoporotic group was $1.391{\pm}0.085$, and was significantly lower than that of the normal group, which was $1.523{\pm}0.725$ (p<0.01). Thick mandibular cortical thickness was common in normal group, whereas thin or very thin mandibular cortical thickness was common in osteoporotic group and the difference was significant (p < 0.05). C2 pattern was common in normal group followed by C1, whereas C2 was common in osteoporotic group followed by C3. The difference was statistically significant (p< 0.0 1). Conclusion: Age, mandibular cortical thickness and shape, fractal dimension on panoramic radiographs were useful in predicting osteoporosis.

• Imaging Science in Dentistry
• /
• v.35 no.1
• /
• pp.41-46
• /
• 2005

Purpose : The purpose of this study was to investigate whether the fractal dimension and radiographic image brightness of periapical radiograph were useful in predicting osteoporosis. Materials and Methods : Ninety-two postmenopausal women were classified as normal, osteopenia and osteoporosis group according to the bone mineral density of lumbar vertebrae and periapical radiographs of both mandibular molar areas were taken. The ROIs of 358 areas were selected at periapical and interdental areas and fractal dimension and radiographic image brightness were measured. Results : The fractal dimension in normal group was significantly higher than that in osteoporosis group at periapical ROI (P < 0.05). The radiographic image brightness in normal group was higher than that in osteopenia and osteoporosis group. There was significant difference not only between normal and osteopenia group (P < 0.05) but also within osteopenia and osteoporosis group (P< 0.01) at periapical ROI. Significant difference was observed not only between normal and osteopenia group but also between normal and osteoporosis group at interdental ROI (P< 0.01). Positive linear relationship was weakly shown at Pearson correlation analysis between fractal dimension and radiographic image brightness. BMD significantly correlated with fractal dimension at periapical ROI (P< 0.01), and BMD and radiographic image brightness significantly correlated at both periapical and interdental ROIs (P< 0.01). Conclusion : This study suggests that the fractal dimension and radiographic image brightness of periapical ROI may predict BMD. (Korean J Oral Maxillofac Radiol 2005: 35 : 41-6)

• Journal of Preventive Medicine and Public Health
• /
• v.34 no.4
• /
• pp.408-416
• /
• 2001

Objectives : To evaluate the diagnostic value of quantitative ultrasound (QUS) in the prediction of osteoporosis as defined by dual energy x-ray absorptiometry (DEXA) in postmenopausal women. Methods : Questionnaires and height and weight measurements were used in the investigation of 176 postmenopausal women. QUS measurements were taken on the right calcaneus while bone mineral density (BMD) measurements of the lumbar spine and femoral neck were made with DEXA. The areas under the curves (AUC) of the speed of sound (SOS) for osteoporosis in the lumbar spine and femoral neck were obtained through receiver operating characteristic (ROC) analysis and evaluated. A comparison was made, for osteoporosis in the lumbar spine and femoral neck, between the AUCs of the logistic model with clinical risk factors and SOS. Results : Pearson's correlation coefficients of SOS and lumbar spine BMD, and of SOS and femoral neck BMD were 0.26 and 0.37. The AUC for the logistic model in its discrimination for lumbar spine osteoporosis was 0.764, and for SOS 0.605. The AUCs for the logistic model in its discrimination for femoral neck osteoporosis and for SOS were 0.890 and 0.892, respectively. Conclusions : These results suggest that the diagnostic value of QUS as a screening tool for osteoporosis is moderate for the femoral neck, but merely low for the lumbar spine and that the predictability provided by SOS is no better than that by the sole use of clinical risk factors in postmenopausal women.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.12
• /
• pp.45-52
• /
• 2021

In this paper, we propose a prediction model for osteopenia and osteoporosis based on a convolutional neural network(CNN) using computed tomography(CT) images. In a single CT image, CNN had a limitation in utilizing important local features for diagnosis. So we propose a compound model which has two identical structures. As an input, two different texture images are used, which are converted from a single normalized CT image. The two networks train different information by using dissimilarity loss function. As a result, our model trains various features in a single CT image which includes important local features, then we ensemble them to improve the accuracy of predicting osteopenia and osteoporosis. In experiment results, our method shows an accuracy of 77.11% and the feature visualize of this model is confirmed by using Grad-CAM.

• Journal of radiological science and technology
• /
• v.43 no.6
• /
• pp.495-502
• /
• 2020

In this study, the prevalence of osteoporosis was predicted based on 10 independent variables such as age, weight, and alcohol consumption and 4 tree-based machine-learning models, and the performance of each model was compared. Also the model with the highest performance was used to check the performance by clearing the independent variable, and Area Under Curve(ACU) was utilized to evaluate the performance of the model. The ACU for each model was Decision tree 0.663, Random forest 0.704, GBM 0.702, and XGBoost 0.710 and the importance of the variable was shown in the order of age, weight, and family history. As a result of using XGBoost, the highest performance model and clearing independent variables, the ACU shows the best performance of 0.750 with 7 independent variables. This data suggests that this method be applied to predict osteoporosis, but also other various diseases. In addition, it is expected to be used as basic data for big data research in the health care field.