Method and Device for Determining a Cardiac Phase in Magnet Resonance Imaging

Simple SummaryContent extracted from patent full text and abstract with AI.

This invention introduces a method and device employing a deep learning network to automatically determine the cardiac phase (such as R-wave or other ECG phases) in magnetic resonance imaging (MRI) data. Instead of relying on external ECG signals or complex manual post-processing, the trained neural network analyzes MRI data directly to label or assign probabilities to specific cardiac phases. The solution integrates seamlessly with MRI systems and can also be implemented in cloud-based computing environments.

Use CasesContent extracted from patent full text and abstract with AI.

• Automatic cardiac phase detection in MRI scans for cardiac imaging workflows
• Retrospective cardiac binning of MRI data without external ECG equipment
• Acceleration and automation of dynamic cardiac MRI reconstruction
• Enhancing MRI analysis in patients with irregular heart rhythms (arrhythmias)
• Integration with MRI scanner software or cloud-based medical imaging platforms for workflow optimization
• Research studies in cardiac motion analysis and imaging
• Development and deployment of ECG-free cardiac MRI in clinical settings
• Reducing setup time in MRI examinations by removing the need for electrocardiographic electrodes or sensors

BenefitsContent extracted from patent full text and abstract with AI.

• Eliminates the need for external ECG signal acquisition during MRI scans
• Reduces reliance on hand-crafted signal processing and prior frequency knowledge
• Speeds up the process of cardiac phase identification (real-time or near real-time operation)
• Increases robustness of cardiac phase detection, especially in challenging cases (e.g., arrhythmias, noisy data)
• Simplifies MRI workflow and setup, as no additional sensors are needed
• Facilitates easier and more automated retrospective cardiac binning in MRI data
• Enables cardiac MRI for a wider range of patients, including those where ECG placement is difficult
• Improves accuracy and adaptability over traditional principal or independent component analysis methods
• Can be deployed and updated via software, including in cloud or distributed computing settings

Technical Classifications (CPCs)

Inventors & Applicants

Patent Abstract

The invention describes a trained deep learning network (22) for determining a cardiac phase in magnet resonance imaging, comprising an input layer (E), an output layer (S) and a number of hidden layers (CR, MP) between input layer (E) and output layer (S), the layers processing input data (ID) entered into the input layer (E), wherein the deep learning network (22) is designed and trained to output a probability or some other label of a certain cardiac phase at a certain time from entered input data (ID).The invention further describes a method determining a cardiac phase in magnet resonance imaging, a related device, a training method for the deep learning network, a control device and a related magnetic resonance imaging system.