echocardiography
PulseAugur coverage of echocardiography — every cluster mentioning echocardiography across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New AI method links radar heart sounds to cardiac dysfunction phenotypes
Researchers have developed a new method using radar heart sounds to analyze cardiac mechanical activity and pair it with echocardiographic data. This approach, detailed in a new paper, aims to better understand ventricu…
-
New method estimates uncertainty in echocardiography clinical metrics
Researchers have developed a new method for estimating uncertainty in echocardiography clinical metrics by focusing on contour sampling rather than traditional segmentation. This approach explicitly predicts contour loc…
-
New CardioFAD framework synthesizes cardiac dynamics from sparse data
Researchers have developed CardioFAD, a novel framework for synthesizing cardiac dynamic information from extremely sparse observational data. This method addresses the challenge of recovering full cardiac dynamics by r…
-
Withdrawn research paper explored integrating multiomics and cardiovascular imaging
A research paper, now withdrawn, explored integrating various multiomics data with cardiovascular imaging techniques. The study aimed to link imaging phenotypes from echocardiography, MRI, and CT scans with molecular da…
-
New AI model LAMAE integrates multimodal medical data for improved patient representation
Researchers have developed a new multimodal AI model called Latent-Attention Masked Autoencoder (LAMAE) designed to learn patient-level representations from diverse medical data. Unlike previous models that often proces…
-
New ECG Foundation Model Leverages Multi-Source Clinical Data for Enhanced Health Monitoring
Researchers have developed a new foundation model for electrocardiogram (ECG) analysis called MS-ECG-FM. Unlike previous models that relied solely on ECG interpretation reports, MS-ECG-FM is trained using contrastive al…
-
Ultrasound pretraining for TB screening shows limited domain advantage
Researchers have investigated the effectiveness of transferring pretraining from echocardiography to lung ultrasound for tuberculosis screening. Despite sharing similar imaging physics, a latent-predictive video encoder…
-
Deep learning framework corrects myocardial strain drift in ultrasound tracking
Researchers have developed a deep learning framework to correct temporal drift in myocardial strain tracking from echocardiography. This new method incorporates persistent memory tokens to share information across slidi…
-
Hybrid Quantum-Classical Model Enhances Cardiac Ultrasound Accuracy
Researchers have developed QuantumBoostNet, a novel hybrid classical-quantum architecture designed to improve the accuracy of cardiac ultrasound view identification. This model combines a classical backbone with both cl…
-
New SPARC pipeline automates fetal cardiac MRI reconstruction
Researchers have developed a new pipeline called SPARC for reconstructing 3D+time fetal cardiac MRI (fCMR) from 2D+time acquired slices. This pipeline combines physics-informed slice-to-volume reconstruction with deep l…
-
Vision Transformer Detects Heart Condition from ECGs with High Accuracy
Researchers have developed a vision transformer model capable of detecting reduced left ventricular ejection fraction (LVEF) from standard electrocardiograms (ECGs). The model, trained on over 10,000 patients across mul…
-
Samsung AI models enable real-time smartwatch cardiac diagnostics
Samsung Research America has introduced two new AI models, xMAE and HiMAE, designed for on-device interpretation of electrocardiogram (ECG) and photoplethysmogram (PPG) data. These models enable advanced cardiac diagnos…
-
AI identifies new EKG marker for cardiac death risk
Researchers, including Dr. Ziad Obermeyer, have developed an artificial intelligence system capable of identifying patients at high risk for sudden cardiac death using electrocardiogram (EKG) data. This AI model analyze…
-
New research questions interpretability of AI models in healthcare
Researchers have developed a new method to evaluate the interpretability of concept bottleneck models, particularly in clinical applications like echocardiography. They found that simply predicting an outcome accurately…
-
New methods quantify domain shift in echocardiography segmentation
Researchers have developed methods to quantify and predict domain shift in echocardiographic left ventricular segmentation, a key challenge for clinical deployment. Their study found that geometric inconsistencies, rath…
-
ECG-LLM: Foundation Model for Cardiac Reasoning from ECG Data
Researchers have developed ECG-LLM, a novel large language model designed for cardiac reasoning using electrocardiogram (ECG) data. Trained on over 679,000 ECG studies from 186,000 patients, the model utilizes a multimo…
-
New AI framework fuses motion and vision for heart attack localization
Researchers have developed MCF-Net, a novel framework for localizing myocardial infarction using echocardiography. This system fuses visual features from the EchoPrime foundation model with cardiac motion cues, addressi…
-
AI models for heart health are spatially accurate but temporally blind
A new research paper published on arXiv investigates the attribution methods used to explain the decisions of deep learning models in echocardiography. The study found that while these models can accurately estimate lef…
-
AI applications in cardiac amyloidosis diagnosis reviewed
A new review paper details the application of artificial intelligence across the diagnostic pathway for cardiac amyloidosis. The paper categorizes AI models by clinical tasks such as screening, detection, quantification…
-
Fitbit Air heart rate accuracy tested against EKG monitor
A user tested the accuracy of the Fitbit Air's heart rate monitoring against a device described as 'EKG-accurate.' The results of this comparison reportedly led to a surprise. The test aimed to evaluate the precision of…