Method for Automatic Detection of Anatomical Landmarks and Device

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

This invention presents a fully automated method and device for detecting anatomical landmarks in hollow organs, such as the heart, using medical imaging data (e.g., CT or MRI). The method generates a 3D surface mesh of the organ, determines a central axis (centerline) using skeletization, extracts features from points along this axis, and applies a machine-learning classifier to identify potential anatomical landmarks. The process is completed without the need for manual user input, and includes logic for confirming or rejecting landmark candidates based on organ anatomy, making the detection fast, consistent, and highly accurate.

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

• Automatic identification of pulmonary vein ostia in the left atrium for planning atrial fibrillation ablation procedures.
• Automated detection of anatomical entry and exit points for stent or catheter placement in cardiovascular interventions.
• Aid in preoperative planning for structural heart disease interventions (e.g., valve replacement) by identifying relevant anatomical landmarks.
• Detection of stenoses, aneurysms, or abnormal changes in diameter in blood vessels or airways.
• Integration with imaging-guided navigation systems for real-time surgical guidance.
• Automated landmark detection for training or assisting less experienced clinicians in complex procedures.

BenefitsContent extracted from patent full text and abstract with AI.

• Reduces or eliminates the need for manual landmark marking, saving time and minimizing user errors.
• Provides fast and consistent detection, thereby improving workflow efficiency in clinical settings.
• Improves the accuracy and reliability of anatomical landmark identification, supporting better patient outcomes.
• Is compatible with various imaging modalities and mesh formats, increasing versatility in medical environments.
• Can offer procedure or device recommendations based on detected landmarks, further assisting clinicians in decision-making.
• Enables large-scale or batch processing of imaging data for research or quality assurance.
• Supports live visualization by overlaying anatomical landmarks on real-time imaging for enhanced procedural safety.

Technical Classifications (CPCs)

Inventors & Applicants

Patent Abstract

A method for automatic recognition of at least one anatomical landmark in a hollow organ of a patient is provided. The method includes providing an image dataset of the hollow organ, establishing or providing a three-dimensional mesh of a surface of the hollow organ from the image dataset, and determining a centerline of the mesh by skeletization. At least one feature is determined for each of a plurality of points on the centerline. A classifier pre-trained on the at least one feature is used for detecting candidates for the at least one anatomical landmark from the plurality of points. The candidates are grouped together with a distance from one another below a threshold. At least one specification determined from the anatomy of the hollow organ is used for confirming or rejecting the candidates for the at least one anatomical landmark. One or more candidates are defined as an anatomical landmark.