Sports Medicine

Addressing Data Scarcity in 3D Trauma Detection through Self-Supervised and Semi-Supervised Learning with Vertex Relative Position Encoding

Accurate detection and localization of traumatic injuries in abdominal CT scans remains a critical challenge in emergency radiology, primarily due to severe scarcity of annotated medical data. This paper presents a label-efficient approach combining self-supervised pre-training with semi-supervised detection for 3D medical image analysis. We employ patch-based Masked Image Modeling (MIM) to pre-tr...

Application of large language models to the annotation of cell lines and mouse strains in genomics data

Accurate, consistent and comprehensive metadata are essential for the reuse of functional genomics data deposited in repositories such as the Gene Expression Omnibus (GEO), however, achieving this often requires careful manual curation that is time-consuming, costly and prone to errors. In this paper, we evaluate the performance of Large Language Models (LLMs), specifically OpenAI's GPT-4o, as an ...

Continuous Estimation of Achilles Tendon Loading in Rupture Patients Using a Single Boot-Mounted Accelerometer

Objective: Achilles tendon ruptures lead to long-term structural and functional deficits. Prior research that sought to identify optimal rehabilitatio...

Efficacy of BodyMirror Clinical MS Multimodal Game-Based Digital Therapeutic for Remote Monitoring and Neurorehabilitation in Multiple Sclerosis: Protocol for a Multisite Randomised Controlled Trial

Multiple sclerosis (MS) is a chronic neurodegenerative disease characterised by progressive neurological disability and heterogeneous symptom trajecto...

Automated machine learning of echocardiographic strain enables identification of early myocardial changes in pre-symptomatic TTR carriers

Objectives: To identify unique echocardiographic signatures associated with TTR+ carrier status preceding onset of cardiac amyloidosis. Background: Ca...

Automated high-throughput fabrication of patient-specific vessel-on-chips enables a generative AI digital twin--Cascade Learner of Thrombosis (CLoT) for personalized thrombosis prediction

We developed an integrated platform combining high-throughput automated biofabrication, systematic patient-derived tissue experiments, and specialized...

Scalable Injury-Risk Screening in Baseball Pitching From Broadcast Video

Injury prediction in pitching depends on precise biomechanical signals, yet gold-standard measurements come from expensive, stadium-installed multi-ca...

MMTA: Multi Membership Temporal Attention for Fine-Grained Stroke Rehabilitation Assessment

To empower the iterative assessments involved during a person's rehabilitation, automated assessment of a person's abilities during daily activities r...

AI-BioMech: Deep Learning Prediction of Mechanical Behavior in Aperiodic Biological Cellular Materials

We introduce AI-BioMech, a deep learning based framework that directly predicts the mechanical response of cellular structures from 2D images, elimina...

How to gain valuable insight from scarce data with Machine Learning: a post-hoc explanation tool to identify biases in biological images classification

Machine learning (ML) models are effective at classifying images across various fields, including biology. However, their performance on biomedical im...

A multi-layered approach to elucidate mechanisms of physical function in response to rehabilitation in heart failure with preserved ejection fraction

Heart failure with preserved ejection fraction (HFpEF) is an increasingly common cause of morbidity and mortality in older adults that is driven by ca...

Explainable Machine-Learning based Detection of Knee Injuries in Runners

Running is a widely practiced activity but shows a high incidence of knee injuries, especially Patellofemoral Pain Syndrome (PFPS) and Iliotibial Band...

Metagenomic strain tracking reveals patterns of bacterial spread and the impact of water chlorination

Bacterial infections are a major cause of morbidity and mortality among children under five in low- and middle-income countries (LMICs). Children in L...

DUCK-Net: Automated deep learning segmentation of Ductular Reaction in murine liver injury captures multicellular niche dynamics from H&E morphology

Ductular Reactions (DRs) are dynamic and complex multicellular responses that occur as a result of various hepatic injuries. Precise identification an...

Beyond Calibration: Confounding Pathology Limits Foundation Model Specificity in Abdominal Trauma CT

Purpose: Translating foundation models into clinical practice requires evaluating their performance under compound distribution shift, where severe cl...

Distributional Impacts of AI-Enhanced Telerehabilitation on Functional Recovery: A Recentered Influence Function Quantile Regression Decomposition Analysis

Background: Conventional evaluations of digital health interventions typically assess mean treatment effects, potentially masking heterogeneous impact...

α-Synuclein Strain Dynamics Correlate with Cognitive Shifts in Parkinson's Disease

-Synuclein (-syn) strains can serve as discriminators between Parkinson's disease (PD) and related -synucleinopathies. The relationship between -syn s...

Targeted saliva multi-omics is a reliable, non-invasive method to capture physiological stress and recovery

Determining physiological stress at high resolution is crucial across diverse settings to enable informed decision-making in the context of health and...

AI quantification of inflammatory and architectural features in ulcerative colitis distinguishes active disease from remission

Background and Aims: Artificial intelligence (AI) is increasingly applied to histological assessment in inflammatory bowel disease (IBD), but most app...

Time-to-Injury Forecasting in Elite Female Football: A DeepHit Survival Approach

Injury occurrence in football poses significant challenges for athletes and teams, carrying personal, competitive, and financial consequences. While m...