Multi-view information fusion using multi-view variational autoencoder to predict proximal femoral fracture load.

Background: Hip fracture occurs when an applied force exceeds the force that the proximal femur can support (the fracture load or "strength") and can have devastating consequences with poor functional outcomes. Proximal femoral strengths for specific loading conditions can be computed by subject-specific finite element analysis (FEA) using quantitative computerized tomography (QCT) images. However, the radiation and availability of QCT limit its clinical usability. Alternative low-dose and widely available measurements, such as dual energy X-ray absorptiometry (DXA) and genetic factors, would be preferable for bone strength assessment. The aim of this paper is to design a deep learning-based model to predict proximal femoral strength using multi-view information fusion. Results: We developed new models using multi-view variational autoencoder (MVAE) for feature representation learning and a product of expert (PoE) model for multi-view information fusion. We applied the proposed models to an in-house Louisiana Osteoporosis Study (LOS) cohort with 931 male subjects, including 345 African Americans and 586 Caucasians. We performed genome-wide association studies (GWAS) to select 256 genetic variants with the lowest p-values for each proximal femoral strength and integrated whole genome sequence (WGS) features and DXA-derived imaging features to predict proximal femoral strength. The best prediction model for fall fracture load was acquired by integrating WGS features and DXA-derived imaging features. The designed models achieved the mean absolute percentage error of 18.04%, 6.84% and 7.95% for predicting proximal femoral fracture loads using linear models of fall loading, nonlinear models of fall loading, and nonlinear models of stance loading, respectively. Conclusion: The proposed models are capable of predicting proximal femoral strength using WGS features and DXA-derived imaging features. Though this tool is not a substitute for predicting FEA using QCT images, it would make improved assessment of hip fracture risk more widely available while avoiding the increased radiation exposure from QCT.

ST-V-Net: incorporating shape prior into convolutional neural networks for proximal femur segmentation.

We aim to develop a deep-learning-based method for automatic proximal femur segmentation in quantitative computed tomography (QCT) images. We proposed a spatial transformation V-Net (ST-V-Net), which contains a V-Net and a spatial transform network (STN) to extract the proximal femur from QCT images. The STN incorporates a shape prior into the segmentation network as a constraint and guidance for model training, which improves model performance and accelerates model convergence. Meanwhile, a multi-stage training strategy is adopted to fine-tune the weights of the ST-V-Net. We performed experiments using a QCT dataset which included 397 QCT subjects. During the experiments for the entire cohort and then for male and female subjects separately, 90% of the subjects were used in ten-fold stratified cross-validation for training and the rest of the subjects were used to evaluate the performance of models. In the entire cohort, the proposed model achieved a Dice similarity coefficient (DSC) of 0.9888, a sensitivity of 0.9966 and a specificity of 0.9988. Compared with V-Net, the Hausdorff distance was reduced from 9.144 to 5.917 mm, and the average surface distance was reduced from 0.012 to 0.009 mm using the proposed ST-V-Net. Quantitative evaluation demonstrated excellent performance of the proposed ST-V-Net for automatic proximal femur segmentation in QCT images. In addition, the proposed ST-V-Net sheds light on incorporating shape prior to segmentation to further improve the model performance.

Predictive factors of radioiodine therapy failure in Graves' Disease: A meta-analysis.

BACKGROUND: I-131 therapy is a common treatment modality for adults with Graves' Disease (GD). Utilizing meta-analysis, we examined patient specific factors that predict I-131 therapy failure. METHODS: Literature search followed PRISMA. Comprehensive Meta-analysis (version 3.0) was used. Mantel-Haenszel test with accompanying risk ratio and confidence intervals evaluated categorical variables. Continuous data was analyzed using inverse variance testing yielding mean difference or standardized mean difference. Decision tree algorithms identified variables of high discriminative performance. RESULTS: 4822 collective patients across 18 studies were included. Male sex (RR = 1.23, 95%CI = 1.08-1.41, p = 0.002), I-131 therapy 6 months after GD diagnosis (RR = 2.10, 95%CI = 1.45-3.04, p < 0.001) and history of anti-thyroid drugs (RR = 2.05, 95%CI = 1.49-2.81, p < 0.001) increased the risk of I-131 therapy failure. Elevated free thyroxine, 24-h radioactive iodine uptake scan ≥60.26% and thyroid volume ≥35.77 mL were also associated with failure. CONCLUSION: Patient characteristics can predict the likelihood of I-131 therapy failure in GD. Definitive surgical treatment may be a reasonable option for those patients.

An Elderly Man with a Swollen Knee,Significant Ecchymosis, and Minimal Knee Pain.

A 72-year-old man presents with left knee pain and swelling over several days. The pain and swelling started after he felt a "pop" when bending to pick up an object off the floor. His past medical history is significant for type 2 diabetes mellitus. Physical exam revealed significant ecchymosis on the anterolateral aspect of the thigh. There was a minimal amount pain upon knee flexion.

Radiology Case of the Month: Persistent Lateral Foot Pain.

A 33-year-old female presents with persistent lateral foot pain. Patient does not recall prior trauma that may have led to injury. Symptoms are significantly improved with rest and nonsteroidal anti-inflammatory medications.

Odontogenic keratocysts in nevoid basal cell carcinoma (Gorlin's) syndrome: CT and MRI evaluation.

We describe the imaging findings in a 13-year-old boy with nevoid basal cell carcinoma syndrome (NBCCS). The initial imaging work-up included plain radiographs and computed tomography (CT) of the facial area and mandible. CT detected large expansile cystic changes on both sides of the body and angle of the mandible. When the patient's condition worsened, magnetic resonance imaging (MRI) was performed to further characterize the nature of the lesions and to rule out intracranial anomalies. We agree with others who have published previous reports that although CT is valuable in elucidating osseous craniofacial anomalies associated with NBCCS, MRI is superior in demonstrating the internal composition and structure of the odontogenic keratocysts that are commonly seen in this syndrome.