Discover Community Create You

Loading publication...

Noodle always counts identifier-free feature events for service operation. With your permission, Google Analytics can also estimate audience and engagement. Search text, publication identifiers, cookies, IP addresses and browser fingerprints are never included in Noodle's first-party event counters.

Privacy details

Article

EF-Gated 3D Capsule Networks with Spatially Decoupled Routing for Clinical Phenotyping of Heart Failure Subtypes in Cardiac MRI.

Journal of imaging informatics in medicine - 1 Aug 2026

Zhang YiMing, Hao XiaoBo, Ma JiYing

Abstract excerpt

Addressing the challenge of geometric feature modeling for heart failure subtype classification in cardiac magnetic resonance imaging (MRI), this study proposes an Ejection Fraction (EF) Gated 3D Capsule Network (EG3D-CapsNet). Traditional 3D convolutional neural networks (e.g., Res3DNet-50) achieve only 46.00% (±9.75%) classification accuracy on the Automated Cardiac Diagnosis Challenge (ACDC) dataset due to...

Read the complete abstract on PubMed

Topics

Share this publication in a Topic to start or enrich a Post.

Share to Heart Failure
Share to Image Interpretation, Computer-Assisted

Methodology Data sources Editorial policy Privacy Delete account & data About Contact Helena Bioinformatics

Share to Imaging, Three-Dimensional

Share to Magnetic Resonance Imaging

Share to Phenotype

Share to Stroke Volume

Source

Open in PubMed Open full text

Identifiers

PMID: 41083839
DOI: 10.1007/s10278-025-01702-4
PMCID: PMC13481972

Provenance

PubMed metadata and Literature Corpus relationships. Corpus snapshot updated 9 Sept 2026.

Related research

Semantic proximity does not establish scientific evidence.

Research trail→

Click a neighbor to travelStep 1 · 12 closest

EF-Gated 3D Capsule Networks with Spatially Decoupled Routing for Clinical Phenotyping of Heart Failure Subtypes in Cardiac MRI.PMID 41083839Read ↗

Advances in Deep Learning for Medical Imaging: Foundations, Evolution, and ImpactSemantic proximity Read ↗

Fully automated 4D cardiac modelling from 2D echocardiography for clinical applicationsSemantic proximity Read ↗

Deep learning enhanced magnetocardiography enables multi-task detection of coronary, ventricular, and rhythm disordersSemantic proximity Read ↗

ADG-Net: A Lightweight Adaptive Deformable Convolution Network with Gradient-Optimized Pooling for Medical Image SegmentationSemantic proximity Read ↗

Deep Learning-Based Multi-View Echocardiographic Framework for Comprehensive Diagnosis of Pericardial DiseaseSemantic proximity Read ↗

Design of U-Net Architectures for Medical Image Segmentation using AI/ML ModelSemantic proximity Read ↗

Development and multi-dataset evaluation of a unified single-view deep-learning model for the right heart: four-chamber segmentation, biventricular ejection fraction, deformation, and pulmonary-hypertension prediction from the apical four-chamber echocardiogramSemantic proximity Read ↗

CardiacField: Computational Echocardiography for Universal ScreeningSemantic proximity Read ↗

Multimodal Deep Learning Integrating Electrocardiography and Chest Radiography Enhances Prediction of Incident Regurgitant Valvular Heart DiseaseSemantic proximity Read ↗

SLIViT: a general AI framework for clinical-feature diagnosis from limited 3D biomedical-imaging dataSemantic proximity Read ↗

DeepStrain: A Deep Learning Workflow for the Automated Characterization of Cardiac MechanicsSemantic proximity Read ↗

CorSeg-CineSAX: An Open-Source Deep Learning Framework for Fully Automatic Segmentation of Short-Axis Cine Cardiac MRI Across Multiple Cardiac DiseasesSemantic proximity Read ↗

⌁Select a neighboring publication to make it the new centre.