AI Cardiac Motion Classification via Myocardium Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for classifying cardiac motion based on Cardiac Magnetic Resonance (CMR) cine imaging are highly subjective and time-consuming, requiring a significant amount of time for human operators to complete, typically ranging from 30-60 minutes.
Innovation Solution
A computer-implemented method using trained neural networks to classify cardiac motion by segmenting myocardium, extracting movement features, and classifying them into predetermined classes, significantly reducing the time required for global and segmental classification.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional manual methods are used for cardiac motion classification, then measurement precision can be maintained through expert analysis, but productivity is significantly reduced due to the 30-60 minute evaluation time required
Solution Approach 1:
The patent replaces the manual mechanical analysis process with an automated computer-based system that processes CMR image data through defined algorithms. The system automatically segments the myocardium, tracks motion across frames, and classifies wall motion patterns without requiring manual frame-by-frame analysis, thereby maintaining measurement precision while dramatically improving productivity
Solution Approach 2:
The system enables self-service by allowing the computer to autonomously perform the complete classification workflow. The automated processing pipeline independently executes image segmentation, motion tracking, and classification tasks without human intervention, transforming a manual expert-dependent process into an autonomous system that delivers consistent results rapidly
2Reliability
If comprehensive manual analysis is performed to ensure reliable classification, then reliability is improved, but loss of time increases due to the extensive evaluation period
Solution Approach 1:
The system performs preliminary automated processing of CMR images before final classification, pre-segmenting the myocardium and pre-tracking motion patterns. This preliminary action prepares the data in advance, allowing the classification algorithm to operate on pre-processed information, thereby maintaining reliability through thorough analysis while reducing the time required for the actual classification decision
3Measurement precision
If detailed segmental classification is performed for all 17 segments, then measurement precision is improved, but device complexity increases due to the comprehensive analysis requirements
Solution Approach 1:
The patent applies segmentation by dividing the myocardium into standardized 17 segments and analyzing motion patterns in each segment independently. This segmentation approach maintains measurement precision by examining each region separately while managing complexity through the use of established anatomical divisions and automated processing algorithms that handle multiple segments systematically
Data Source
AI summary
A method for providing a global cardiac wall motion classification for a patient is disclosed, and includes employing Cardiac Magnetic Resonance (CMR) image data. In some embodiments, the method comprises one or more of a myocardium segmentation step, a slice classification step, a movement feature extraction step, and a global classification or evaluation step, wherein a patient is classified as having normal cardiac wall motion, or as having suspicious or abnormal cardiac wall motion.