UK Biobank
PulseAugur coverage of UK Biobank — every cluster mentioning UK Biobank across labs, papers, and developer communities, ranked by signal.
5 day(s) with sentiment data
-
New framework synthesizes multi-shell dMRI from single-shell data
Researchers have developed DTI-SHNet, a novel framework designed to synthesize multi-shell diffusion MRI (dMRI) data from single-shell inputs. This method operates in the spherical harmonics (SH) coefficient domain and …
-
New ePID method offers scalable analysis of symptom network information
Researchers have developed a new method called embedding-based partial information decomposition (ePID) to analyze complex relationships within symptom networks. This technique addresses the computational limitations of…
-
AI framework improves brain sulci labeling with geometric and semantic learning
Researchers have developed a new framework called Geometric-to-Semantic Spherical Transfer Learning to address the challenge of labeling cortical sulci in brain scans. This method utilizes a large dataset from the UK Bi…
-
New method attributes disease effects in age biomarkers to training data
Researchers have developed a new method called pyinfluence to attribute the disease-related effects in normative age biomarkers to individual training samples. This technique, validated against leave-one-out retraining,…
-
AI model uses cardiac imaging to boost ECG-based Chagas disease detection
Researchers have developed a novel method to improve the detection of Chagas disease using electrocardiography (ECG) by leveraging cardiac magnetic resonance (CMR) imaging data. The approach involves pre-training an ECG…
-
SleepFM-2 model learns transferable human physiology from 2M hours of sleep data
Researchers have developed SleepFM-2, a novel sleep foundation model trained on over two million hours of multimodal physiological data from nearly 300,000 sleep recordings. This model demonstrates significant improveme…
-
Google Research explores transfer learning for genomic prediction
Google Research has explored transfer learning techniques to improve genomic prediction accuracy in underrepresented populations. Their study found that while transferring knowledge from large European cohorts can enhan…
-
Retinal biometrics system enhances patient identity verification across studies
Researchers have developed a novel retinal biometric system designed to enhance the accuracy of patient identity verification and retrieval within longitudinal medical records. This system utilizes a ConvNeXtV2 backbone…
-
New method uses metadata to guide synthetic cardiac MRI generation
Researchers have developed a new method for generating synthetic cardiac magnetic resonance imaging (CMR) using a pre-trained latent diffusion model. This approach conditions the model on structured clinical metadata an…
-
Google Research uses smartphone photos to estimate metabolic risk
Google Research has developed PhotoScan, a deep learning framework that estimates body composition metrics like body fat percentage, Android-to-Gynoid fat ratio, and Visceral-to-Subcutaneous fat ratio using standard sma…
-
New method improves whole-body MRI registration for UK Biobank data
Researchers have developed a new method for registering whole-body MRI images from the UK Biobank, a large-scale health data study. This technique utilizes tissue masks, specifically subcutaneous adipose tissue and musc…
-
New CAN-FLOW framework generates realistic cardiac anatomy for virtual cohorts
Researchers have developed CAN-FLOW, a novel framework for generating realistic cardiac anatomy data for virtual cohorts. This method utilizes conditional normalizing flows to model anatomical variability based on facto…
-
AI model for brain atrophy detection shows cross-population transferability
Researchers have investigated the transferability of a Stochastic Cortical Self-Reconstruction (SCSR) model, originally trained on UK Biobank data, to an independent Chinese population dataset. The study evaluated SCSR'…
-
Coffee consumption linked to reduced risk of liver and heart disease
New research suggests that moderate coffee consumption, defined as up to five cups daily, is linked to significant health benefits for both the liver and the cardiovascular system. A large UK Biobank study found that re…
-
AI model LeDXA extracts disease risk and biological age from X-ray scans
Researchers have developed LeDXA, a self-supervised learning model that extracts health insights from dual-energy X-ray absorptiometry (DXA) scans. Trained on unlabeled DXA images, LeDXA predicts disease risk, biologica…
-
New AI models cardiac function from 2D MRI scans
Researchers have developed NISF++, an advanced neural implicit representation system designed to model cardiac function from 2D cardiac magnetic resonance (CMR) imaging views. This system integrates information from var…
-
New deep-learning framework Eddeep speeds up MRI distortion correction
Researchers have developed Eddeep, a novel deep-learning framework designed to rapidly correct geometric distortions in diffusion MRI (dMRI) data. These distortions, caused by eddy currents, can significantly impact the…
-
New AI model screens aortic valve disease using PPG signals
Researchers have developed a novel Physiology-Guided Self-Supervised Learning (PG-SSL) method to screen for aortic valve disease (AVD) using photoplethysmography (PPG) signals. This approach leverages approximately 170,…
-
Deep learning model enables population-scale penile MRI segmentation
Researchers have developed a deep learning framework to automatically segment penile tissue from DIXON MRI scans, enabling population-scale quantitative phenotyping for male reproductive health studies. The model, optim…
-
New methods improve cardiac motion estimation with implicit neural representations
Researchers have explored four distinct strategies for learning cardiac motion priors to enhance the efficiency and accuracy of implicit neural representations (INRs) in cardiac motion estimation. These strategies, incl…