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

Background@#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). @*Methods@#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. @*Results@#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. @*Conclusion@#CT scans collected during routine examinations without bone densitometry calibration can be used to generate DXA BMD predictions.

Unsupervised Deformable Image Registration Using Polyphase UNet for 3D Brain MRI Volumes

Purpose@#Image registration is a fundamental task in various medical imaging studies and clinical image analyses, such as comparison of patient data with anatomical structures. In order to solve the problems of conventional image registration approaches, such as long computational time, recent deep-learning supervised and unsupervised methods have been extensively studied because of their excellent performance and fast computational time. In this study, we propose a deep-learningbased network for deformable medical image registration using unsupervised learning. @*Materials and Methods@#In this paper, we solve the image-registration optimization problem by modelling a function using a convolutional neural network with polyphase decomposition to learn the spatial transformable parameters based on the input images and to generate the registration field. A spatial transformer is used to reconstruct the output warped image while imposing smoothness constraints on the registration field. With polyphase decomposition, our proposed method learns more features based on the input image pairs without the need for any ground-truth registration field. @*Results@#Experimental results using 3D T1 brain MRI volume scans and compared with state-of-the-art image-registration methods demonstrated that our method provides better 3D-image registration. @*Conclusion@#Our proposed method uses less computational time in registering unseen pairs of input images during inference and can be applied for other unimodal image registration tasks, and the hyper-parameters can be adjusted for the specific task.

Unsupervised Deformable Image Registration Using Polyphase UNet for 3D Brain MRI Volumes

Purpose@#Image registration is a fundamental task in various medical imaging studies and clinical image analyses, such as comparison of patient data with anatomical structures. In order to solve the problems of conventional image registration approaches, such as long computational time, recent deep-learning supervised and unsupervised methods have been extensively studied because of their excellent performance and fast computational time. In this study, we propose a deep-learningbased network for deformable medical image registration using unsupervised learning. @*Materials and Methods@#In this paper, we solve the image-registration optimization problem by modelling a function using a convolutional neural network with polyphase decomposition to learn the spatial transformable parameters based on the input images and to generate the registration field. A spatial transformer is used to reconstruct the output warped image while imposing smoothness constraints on the registration field. With polyphase decomposition, our proposed method learns more features based on the input image pairs without the need for any ground-truth registration field. @*Results@#Experimental results using 3D T1 brain MRI volume scans and compared with state-of-the-art image-registration methods demonstrated that our method provides better 3D-image registration. @*Conclusion@#Our proposed method uses less computational time in registering unseen pairs of input images during inference and can be applied for other unimodal image registration tasks, and the hyper-parameters can be adjusted for the specific task.

Effects of Continuity of Care on Diabetes-Related Avoidable Hospitalizations among Middle- and Old-Aged Patients: Analysis of National Health Insurance Claims Data / 보건행정학회지

BACKGROUND: Diabetes is known as one of the most important ambulatory care sensitive conditions. This study purposed to assess the status of continuity of care (COC) and diabetes-related avoidable hospitalizations (DRAHs) of a group of middle- and old-aged patients and to observe the relationship of the two elements by the two age groups. METHODS: This study utilized the National Health Insurance Service's National Sample Cohort data and the subjects are diabetes patients of 45 and over, classified into two groups of ‘middle-aged’(45–64 years) and ‘old-aged’(≥65 years) patients. The dependent variable was DRAHs, which was defined in accordance with the definition of the Organization for Economic Cooperation and Development “Health Care Quality Indicators” project. COC, as an independent variable, is measured by the COC index in this study. Two-part model (multi-variate and multi-level analyses) was utilized. RESULTS: Factors associated with the status and the number of DRAHs differed by each age group. Meanwhile, the two-part model showed that higher COC was associated with a lower risk of preventable hospitalizations in both middle- and old-aged groups. CONCLUSION: Study findings can provide health policy insights and implications in order to strengthen the primary care system for further improvement of diabetes management, especially for middle- and old-aged groups.

The Role of Job Stress and Brain-Derived Neurotrophic Factor Gene Polymorphism on the Severity of Alcohol Drinking in Korean Office Workers in Their Twenties

OBJECTIVES: The aim of this study was to examine the effects of brain-derived neurotrophic factor (BDNF) genetic polymorphism and job stress on the severity of alcohol drinking. It was hypothesized that individuals with the Met/Met BDNF genotype would be more vulnerable than those carrying the Val allele. METHODS: Participants were 133 healthy Korean adults (mean age 28.2 +/- 1.1). Job stress and the severity index of drinking were investigated through self-reported questionnaires. BDNF (rs6265) gene was genotyped. RESULTS: There was no significant association between job stress and the severity of alcohol drinking. Although the severity of alcohol drinking was not associated with BDNF genetic polymorphism, there was a significant difference in men according to genotype and job stress. Men with homozygous BDNF Met allele were more severe in alcohol drinking when job stress was high, less severe in alcohol drinking when job stress was low than those carrying the Val allele (F = 4.47, p = 0.038). Also higher level of job stress was correlated with higher severity of alcohol drinking in men homozygous for BDNF Met allele (rs = 0.620, p = 0.005). CONCLUSIONS: These findings suggest the possibility that Met allele could have differential susceptibility, with men homozygous for BDNF Met allele being more susceptible to both more adverse and less adverse environmental influences.