• 전기학회논문지
• /
• 제59권4호
• /
• 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
• /
• 제49권3호
• /
• 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.

• 문화기술의 융합
• /
• 제6권3호
• /
• pp.457-462
• /
• 2020

골다공증은 주로 노인에서 나타나는 질병으로써 뼈 질량 및 조직의 구조적 악화에 따라 골절의 위험을 증가시킨다. 본 연구의 목적은 영양소 성분과 골다공증과의 연관성을 파악하고, 영양소 성분을 기반으로 골다공증을 예측하는 모델을 생성 및 평가하는 것이다. 실험방법으로 binary logistic regression을 이용하여 연관성분석을 수행하였고, naive Bayes 알고리즘과 variable subset selection 메소드를 이용하여 예측 모델을 생성하였다. 단일 변수들에 대한 분석결과는 남성에서 식품섭취량과 비타민 B2가 골다공증을 예측하는데 가장 높은 the area under the receiver operating characteristic curve (AUC)값을 나타내었다. 여성에서는 단일불포화지방산이 가장 높은 AUC값을 나타내었다. 여성 골다공증 예측모델에서는 Correlation based feature subset 및 wrapper 기반 feature subset 메소드를 이용하여 생성된 모델이 0.662의 AUC 값을 얻었다. 남성에서 전체변수를 이용한 모델은 0.626의 AUC를 얻었고, 그외 남성 모델들에서는 민감도와 1-특이도에서 예측 성능이 매우 낮았다. 이러한 연구결과는 향후 골다공증 치료 및 예방을 위한 기반정보로 활용할수 있을 것으로 기대된다.

• 대한디지털의료영상학회논문지
• /
• 제14권2호
• /
• 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
• /
• 제38권3호
• /
• 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
• /
• 제37권2호
• /
• 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
• /
• 제35권1호
• /
• 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
• /
• 제34권4호
• /
• 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.

• 한국컴퓨터정보학회논문지
• /
• 제26권12호
• /
• pp.45-52
• /
• 2021

본 논문에서는 컴퓨터 단층촬영(CT) 이미지를 이용한 합성곱 신경망(CNN)을 기반의 골감소증 및 골다공증 예측 모델을 제안한다. 기존의 CNN은 단일 CT 이미지에서 예측에 중요한 지역정보를 활용하지 못하다는 문제가 있다. 본 논문에서 이를 해결하고자 CT 이미지를 정규화하여 질감 정보가 다른 두 개의 이미지로 변환하고, 해당 이미지를 활용한 한 쌍의 신경망 네트워크를 제안한다. 동일한 구조를 가진 네트워크 각각의 신경망은 질감 정보가 다른 이미지를 입력으로 사용하고 비유사성 손실함수를 통해 다른 정보를 학습한다. 최종적으로 제안 모델은 중요한 지역정보를 포함한 단일 CT 이미지의 다양한 특징 정보를 학습하며, 이를 앙상블하여 골감소증 및 골다공증 예측 정확도를 높인다. 실험 결과를 통해 제안 모델의 정확도 77.11%를 확인할 수 있으며 Grad-CAM을 이용하여 모델이 바라보는 특징을 확인할 수 있다.

• 대한방사선기술학회지:방사선기술과학
• /
• 제43권6호
• /
• 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.