Congenital heart disease (CHD) is the most common birth defect. Fetal screening ultrasound provides five views of the heart that together can detect 90% of complex CHD, but in practice, sensitivity is as low as 30%. Here, using 107,823 images from 1,326 retrospective echocardiograms and screening ultrasounds from 18- to 24-week fetuses, we trained an ensemble of neural networks to identify recommended cardiac views and distinguish between normal hearts and complex CHD. We also used segmentation models to calculate standard fetal cardiothoracic measurements. In an internal test set of 4,108 fetal surveys (0.9% CHD, >4.4 million images), the model achieved an area under the curve (AUC) of 0.99, 95% sensitivity (95% confidence interval (CI), 84-99%), 96% specificity (95% CI, 95-97%) and 100% negative predictive value in distinguishing normal from abnormal hearts. Model sensitivity was comparable to that of clinicians and remained robust on outside-hospital and lower-quality images. The model's decisions were based on clinically relevant features. Cardiac measurements correlated with reported measures for normal and abnormal hearts. Applied to guideline-recommended imaging, ensemble learning models could significantly improve detection of fetal CHD, a critical and global diagnostic challenge.
Download full-text PDF |
Source |
---|---|
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8380434 | PMC |
http://dx.doi.org/10.1038/s41591-021-01342-5 | DOI Listing |
Vision Res
January 2025
Laboratoire Cognition Langage et Développement, Université Libre de Bruxelles, Belgium.
Animals and humans possess an adaptive ability to rapidly estimate approximate numerosity, yet the visual mechanisms underlying this process remain poorly understood. Evidence suggests that approximate numerosity relies on segmented perceptual units modulated by grouping cues, with perceived numerosity decreasing when objects are connected by irrelevant lines, independent of low-level features. However, most studies have focused on physical objects.
View Article and Find Full Text PDFNeural Netw
January 2025
School of Computer Science, University of Birmingham, Edgbaston, Birmingham, B15 2TT, United Kingdom.
Learning from data streams that emerge from nonstationary environments has many real-world applications and poses various challenges. A key characteristic of such a task is the varying nature of the underlying data distributions over time (concept drifts). However, the most common type of data stream learning approach are ensemble approaches, which involve the training of multiple base learners.
View Article and Find Full Text PDFPLoS Comput Biol
January 2025
Kavli Institute for Systems Neuroscience and Centre for Algorithms in the Cortex, Faculty of Medicine and Health Sciences, Norwegian University of Science and Technology, Trondheim, Norway.
Persistent homology applied to the activity of grid cells in the Medial Entorhinal Cortex suggests that this activity lies on a toroidal manifold. By analyzing real data and a simple model, we show that neural oscillations play a key role in the appearance of this toroidal topology. To quantitatively monitor how changes in spike trains influence the topology of the data, we first define a robust measure for the degree of toroidality of a dataset.
View Article and Find Full Text PDFThe hippocampus forms memories of our experiences by registering processed sensory information in coactive populations of excitatory principal cells or ensembles. Fast-spiking parvalbumin-expressing inhibitory neurons (PV INs) in the dentate gyrus (DG)-CA3/CA2 circuit contribute to memory encoding by exerting precise temporal control of excitatory principal cell activity through mossy fiber-dependent feed-forward inhibition. PV INs respond to input-specific information by coordinating changes in their intrinsic excitability, input-output synaptic-connectivity, synaptic-physiology and synaptic-plasticity, referred to here as experience-dependent PV IN plasticity, to influence hippocampal functions.
View Article and Find Full Text PDFBackground: Coronary heart disease (CHD) and depression frequently co-occur, significantly impacting patient outcomes. However, comprehensive health status assessment tools for this complex population are lacking. This study aimed to develop and validate an explainable machine learning model to evaluate overall health status in patients with comorbid CHD and depression.
View Article and Find Full Text PDFEnter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!