31 papers
This study develops and validates a computationally efficient ultra-high frequency ultrasound imaging pipeline using interframe subtraction with motion compensation to effectively quantify microvascular flow and assess treatment response in avian chorioallantoic membrane xenograft renal cell carcinoma models.
The paper introduces AIRT, an end-to-end deep-learning framework that generates high-quality, deliverable single-arc VMAT prostate treatment plans in under one second directly from CT images and contours, demonstrating non-inferiority to standard clinical planning systems while significantly accelerating workflow efficiency.
The paper introduces ICHOR, a self-supervised masked autoencoder framework pretrained on a large, multi-site dataset of 11,405 ASL CBF maps, which outperforms existing methods in learning robust, transferable representations for downstream diagnostic and quality prediction tasks.
This study demonstrates that Transformer-based neural networks equipped with evidential output layers outperform LSTM and GRU models in predicting blood glucose and identifying adverse glycemic events for Type 1 diabetes by providing superior accuracy and well-calibrated uncertainty estimates validated on the HUPA-UCM dataset.
This paper proposes sFRC, a novel method that performs Fourier Ring Correlation analysis over small patches to robustly detect and quantify hallucinations in deep learning-based medical image restoration across various undersampled imaging problems.
This study challenges the prevailing hypothesis that rotational acceleration is the primary cause of concussion by demonstrating through direct in vivo measurements that linear acceleration is a significantly more precise predictor of injury, leading to the development of a liquid shock-absorbing helmet technology that could reduce concussion risk by up to 73%.
This paper presents a real-time 3D CMR-MOTUS method that enables continuous, beat-to-beat volumetric quantification of cardiac function in patients with arrhythmias, successfully overcoming motion artifacts to reveal functional heterogeneity and bimodal ejection fraction distributions obscured by conventional imaging techniques.
This review advocates for integrating biomechanical principles into hernia management by framing abdominal hernias as mechanical failures, thereby guiding the selection of surgical techniques and implants—such as lightweight retrorectus meshes and small-bite suturing—to better mimic native tissue properties and improve patient outcomes.
This paper introduces a Fourier Neural Operator-based surrogate model that rapidly and accurately predicts angle- and energy-resolved proton transport and neutron production in proton therapy, achieving Monte Carlo-level accuracy within seconds to enable real-time adaptive range verification and neutron dose estimation.
This study assesses the implementation of radiation protection systems in four Ethiopian hospitals, revealing that while background and idle radiation levels are safe, poor operational practices and a lack of monitoring equipment lead to dangerously high exposure for staff during active X-ray procedures, necessitating immediate training, modern equipment, and dedicated radiation protection oversight.
This paper presents a physics-informed neural network framework that accurately reconstructs three-dimensional cardiac activation dynamics, active tension, deformation, and pressure from measurable deformation data by integrating nonlinear constitutive modeling and physical constraints, offering a promising pathway for non-invasive, patient-specific arrhythmia assessment.