Automatic Motion Detection in Medical Image-series

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

This invention provides a method and system for automatically detecting motion in a series of medical images, particularly for applications like cardiac imaging. It uses advanced image analysis (including deep learning algorithms) to automatically identify and track the location and movement of anatomical targets—such as parts of the heart—in time-resolved imaging data (like MRI, CT, or ultrasound). The system determines the periods when the target is at rest, enabling optimal image acquisition with reduced motion artifacts, without the need for manual inspection by medical professionals.

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

• Automated detection of resting phases in cardiac magnetic resonance imaging (MRI) for improved whole-heart imaging.
• Motion correction or artifact reduction in other medical imaging modalities such as CT, ultrasound, and fluoroscopy for moving organs.
• Optimized image acquisition timing in dynamic imaging studies of other body parts affected by periodic or involuntary movements, like lungs during breathing.
• Integration into medical imaging workflow to replace or assist manual resting phase detection, saving time and improving accuracy in clinical practice.
• Cloud-based analysis and remote collaboration, allowing hospitals to process imaging studies with enhanced motion detection without local advanced computational resources.
• Facilitating automated diagnosis or monitoring of arrhythmia and other movement-related abnormalities by providing quantitative motion curves in target organs.

BenefitsContent extracted from patent full text and abstract with AI.

• Eliminates the need for manual frame-by-frame inspection by medical experts, saving time and reducing user-dependent variability.
• Enhances image quality by enabling acquisition during optimal resting phases, thus reducing motion artifacts and improving diagnostic accuracy.
• Supports a wide range of imaging systems (MRI, CT, ultrasound, fluoroscopy), making it broadly applicable in medical imaging.
• Enables region-specific or organ-specific motion detection, allowing tailored imaging strategies for different anatomical structures.
• Leverages advanced machine learning (deep neural networks), which increases detection robustness and adapts to variable anatomy or motion patterns.
• Can be integrated into cloud-based or networked environments, making it easily upgradable and scalable for healthcare systems.

Technical Classifications (CPCs)

Inventors & Applicants

Patent Abstract

The invention describes a method for automatic motion detection in medical image-series, comprising the steps:- providing a dataset (D) of a series of images (I1, I2, I3), wherein images (I1, I2, I3) of a similar region of interest are recorded at consecutive points of time,- calculating localization data (LD) of a target (T) by localizing the target (T) in the images (I1, I2, I3) of the dataset (D) and calculating the position of this target (T) in these images (I1, I2, I3),- calculating movement data (MD) of the movement of the target (T) on the basis of temporal adjacent images (I1, I2, I3) based on the localization data (LD).The invention further describes a related system, a related control device and a related medical imaging system.