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 BrainPFN Network Predicts Behavior from MRI Data
Researchers have developed BrainPFN, a novel Prior Data Fitted Network designed for predicting behavioral phenotypes from functional MRI data. Unlike traditional Kernel Ridge Regression (KRR) methods that require separa…
-
CardioDrift framework automates cardiac motion tracking in 3D CMR scans
Researchers have developed CardioDrift, a novel automated framework for tracking cardiac motion in 3D cine cardiac magnetic resonance (CMR) images. This method utilizes a shape-aware Coherent Point Drift approach with s…
-
Hawkes processes match neural TPPs on event timing, study finds
A new research paper re-evaluates the performance of Hawkes processes and neural temporal point processes (TPPs) on event sequence data. The study found that the performance gap between classical Hawkes processes and mo…
-
Deep Regression Method Extracts Medical Data from UK Biobank MRIs
Researchers have developed a novel methodology using targeted deep regression to extract numerical properties from whole-body water-fat MRI scans. This approach employs a ResNet50-style network on collages representing …
-
AI, cybersecurity, and open-source developments detailed in UK Biobank digest
This news digest covers a range of topics including AI advancements, cybersecurity threats, and open-source software developments. Notable AI news includes former Intel CEO Pat Gelsinger's investment in Nagare Labs for …
-
AI model accurately classifies retinal development across OCT devices
Researchers have developed and validated an unsupervised domain adaptation model to accurately classify normal versus abnormal retinal development from optical coherence tomography (OCT) scans. This model, based on a Re…
-
Biomedical imaging AI progress stalled by data silos, not model limitations
The primary challenge in advancing biomedical imaging AI is not the development of more sophisticated models, but rather the accessibility and usability of the data itself. Imaging data is often siloed within hospital s…
-
JEPA-Anything framework unifies world model creation across 7 domains
Researchers have introduced JEPA-Anything, a novel domain-agnostic framework designed to build world models. This framework extends joint-embedding predictive architectures (JEPAs) by incorporating Orthogonal Predictive…
-
AI activity recognition models show performance gap for older adults
A new study published on arXiv highlights a significant performance gap in human activity recognition (HAR) models when applied to older adults, despite advancements in deep learning. Researchers found that models train…
-
LLM-guided study reveals pathways linking physical activity to dementia risk
A new study published on arXiv utilized large language models and causal discovery techniques to analyze data from the UK Biobank, involving over 42,000 older adults. The research aimed to understand the mechanisms link…
-
New AI framework enhances brain MRI analysis for genetic discovery
Researchers have developed a novel self-supervised learning framework called MEVA (Mesh-Enhanced Volumetric Autoencoder) for analyzing brain MRI scans. This framework integrates both volumetric data and cortical surface…
-
New CASE framework enhances AI's longitudinal medical reasoning capabilities
Researchers have developed a new framework called CASE, which stands for Clinical Agents for Seeking Evidence, designed to improve longitudinal medical reasoning in foundation models. This framework includes a tool-use …
-
New AI framework CASE enhances medical reasoning with autonomous evidence-seeking
Researchers have developed a new framework called CASE (Clinical Agents for Seeking Evidence) to improve AI's ability to reason with longitudinal medical data. This framework includes a multimodal benchmark built on UK …
-
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…