Federated learning-based prediction of depression among adolescents across multiple districts in China.

Depression in adolescents is a serious mental health condition that can affect their emotional and social well-being. Detailed understanding of depression patterns and status of depressive symptoms in adolescents could help identify early intervention targets. Despite the growing use of artificial intelligence for diagnosis and prediction of mental health conditions, the traditional centralized machine learning methods require aggregating adolescents' data; this raises concerns about confidentiality and privacy, which hampers the clinical application of machine learning algorithms. In this study, we use federated learning to solve those problems. We included 583,405 middle and high school adolescents from 20 districts in Chengdu China, and collected from three aspects: individuals, families, and schools, containing 11 psychological phenomena to evaluate the status of depressive symptoms. We compared federated and local training frameworks; the results showed the area under the receiver operating characteristic curve for depression increased by up to 20 % (from 0.7544 with local training to 0.9064 with federated training). Moreover, based on the best-performing model, the XGBoost model, we explore the data heterogeneity in federated learning and found that stress, student burnout, and social connection were the three most important predictors of depression symptoms. We then assessed the impact of each subdimension of depression symptoms, results show that sleep was the most impact one which may provide clues to predict depression symptoms in early stage and improve control and prevention efforts.

Role of Lower Limb Muscle Strength in Knee Osteoarthritis Progression for Patients With Mild and Moderate Knee Osteoarthritis.

OBJECTIVE: We aimed to elucidate the association of lower limb muscle strength with the volume loss of cartilages/menisci for patients with mild and moderate knee osteoarthritis. DESIGN: One hundred seventy individuals with mild and moderate knee osteoarthritis were included from the Osteoarthritis Initiative database. Five muscle strength variables were measured from isometric strength test. The measurement of volume on medial and lateral menisci and seven subregional cartilages from knee magnetic resonance scans were used for assessing 2-yr osteoarthritis progression. RESULTS: Along with the decreased lower limb muscle strength, the volume of patellar cartilage, medial meniscus, and lateral meniscus decreased more than cartilage on tibia and weight-bearing femoral condyle. However, the cartilage volume on the entire medial and lateral femoral condyle increased significantly. The maximum quadricep strength was the most sensitive muscle strength variable, and we found that it was more positively correlated with lateral meniscus volume than with other subregions at baseline and 24-mo follow-up. CONCLUSIONS: This study shows the relationship between lower limb muscle strength and volumes of cartilage and meniscus for patients with mild and moderate knee osteoarthritis. In addition, our study indicates a biomechanical mechanism of quadricep strength and meniscus-related knee dynamic stability in progression of mild-to-moderate knee osteoarthritis.

Palladium-catalyzed regioselective hydroboration of aryl alkenes with B2pin2.

A palladium(ii)-catalyzed hydroboration of aryl alkenes with stable and easy-to-handle (pinacolato)diboron (B2pin2) under mild conditions has been developed. Acetic acid acted as the solvent and the hydrogen source, which has been identified by deuterium experiments. Notably, isomerization-hydroboration of allyl benzene derivatives was observed. As a result, a series of benzyl boronic esters were obtained in moderate to excellent yields with exclusive regioselectivity.

3D Motion Modeling and Reconstruction of Left Ventricle Wall in Cardiac MRI.

The analysis of left ventricle (LV) wall motion is a critical step for understanding cardiac functioning mechanisms and clinical diagnosis of ventricular diseases. We present a novel approach for 3D motion modeling and analysis of LV wall in cardiac magnetic resonance imaging (MRI). First, a fully convolutional network (FCN) is deployed to initialize myocardium contours in 2D MR slices. Then, we propose an image registration algorithm to align MR slices in space and minimize the undesirable motion artifacts from inconsistent respiration. Finally, a 3D deformable model is applied to recover the shape and motion of myocardium wall. Utilizing the proposed approach, we can visually analyze 3D LV wall motion, evaluate cardiac global function, and diagnose ventricular diseases.

Atlas-based liver segmentation and hepatic fat-fraction assessment for clinical trials.

Automated assessment of hepatic fat-fraction is clinically important. A robust and precise segmentation would enable accurate, objective and consistent measurement of hepatic fat-fraction for disease quantification, therapy monitoring and drug development. However, segmenting the liver in clinical trials is a challenging task due to the variability of liver anatomy as well as the diverse sources the images were acquired from. In this paper, we propose an automated and robust framework for liver segmentation and assessment. It uses single statistical atlas registration to initialize a robust deformable model to obtain fine segmentation. Fat-fraction map is computed by using chemical shift based method in the delineated region of liver. This proposed method is validated on 14 abdominal magnetic resonance (MR) volumetric scans. The qualitative and quantitative comparisons show that our proposed method can achieve better segmentation accuracy with less variance comparing with two other atlas-based methods. Experimental results demonstrate the promises of our assessment framework.

Adaptive mesh optimization and nonrigid motion recovery based image registration for wide-field-of-view ultrasound imaging.

Wide field of view (WFOV) imaging mode obtains an ultrasound image over an area much larger than the real time window normally available. As the probe is moved over the region of interest, new image frames are combined with prior frames to form a panorama image. Image registration techniques are used to recover the probe motion, eliminating the need for a position sensor. Speckle patterns, which are inherent in ultrasound imaging, change, or become decorrelated, as the scan plane moves, so we pre-smooth the image to reduce the effects of speckle in registration, as well as reducing effects from thermal noise. Because we wish to track the movement of features such as structural boundaries, we use an adaptive mesh over the entire smoothed image to home in on areas with feature. Motion estimation using blocks centered at the individual mesh nodes generates a field of motion vectors. After angular correction of motion vectors, we model the overall movement between frames as a nonrigid deformation. The polygon filling algorithm for precise, persistence-based spatial compounding constructs the final speckle reduced WFOV image.