Image Sequence Phase Analysis via Feature Portion Tracking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for analyzing periodic physiological activities in image sequences are inefficient and prone to errors due to reliance on additional monitoring devices, manual reference image selection, and high computational loads, which increase complexity and susceptibility to noise and inaccuracies.
Innovation Solution
A computer-implemented method and system that identifies and tracks feature portions responsive to periodic physiological activities within image sequences, determining the phase of each frame based on the motion of these feature portions, reducing the need for pixel-level calculations and minimizing noise interference.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If additional periodic monitoring devices such as ECGs and respiratory monitors are used to record and monitor relevant clinical information, then the accuracy of phase determination is improved, but the device complexity and system integration requirements increase
Solution Approach 1:
The imaging system performs self-monitoring by automatically detecting periodic physiological activities from the image sequences themselves, eliminating the need for external monitoring devices. The system extracts feature portions from images and tracks their motion to determine phases, making the system self-sufficient for phase determination
Solution Approach 2:
The imaging system serves multiple functions: it both captures images for diagnostic purposes and simultaneously monitors periodic physiological activities for phase determination. This multi-functionality eliminates the need for separate dedicated monitoring devices
2Device complexity
If manual identification of the correlation between image frames and their cardiac periodic phases is performed, then the need for additional equipment is reduced, but the time consumption and labor burden increase
Solution Approach 1:
The patent replaces manual mechanical identification processes with automated computational methods. The system automatically detects feature portions, tracks their motion across frames, and determines phases through algorithmic processing, eliminating manual labor and time consumption
Solution Approach 2:
The system introduces an automated feature portion tracking mechanism as an intermediary between raw image sequences and phase determination. This intermediary automatically extracts and analyzes motion patterns, replacing manual identification processes
3Measurement precision
If pixel-level calculations are performed for all images in the sequence to estimate phases, then the measurement precision is improved, but the computational load increases
Solution Approach 1:
The system extracts only the essential feature portions from images that are relevant for phase determination, rather than performing calculations on all pixels. This extraction approach maintains measurement precision by focusing on discriminative features while significantly reducing computational load
Solution Approach 2:
The patent segments the image processing task by identifying and tracking specific feature portions separately from the rest of the image data. This segmentation allows selective analysis of only the moving features that carry phase information, reducing overall computational requirements
4Ease of manufacture
If traditional analysis methods that calculate differences between consecutive frames are used, then the implementation simplicity is maintained, but the susceptibility to background noise increases
Solution Approach 1:
The system introduces feature portion tracking as an intermediary layer between simple frame difference calculation and phase determination. This intermediary selectively identifies and follows specific moving features across frames, filtering out background noise while maintaining implementation feasibility
Solution Approach 2:
The patent replaces the simple but noise-sensitive frame difference mechanism with a feature-based tracking approach. Instead of comparing all pixels between frames, the system identifies feature portions in one frame and tracks their positions in subsequent frames, reducing noise susceptibility
Data Source
AI summary
The disclosure relates to a computer-implemented method for analyzing an image sequence of a periodic physiological activity, a system, and a medium. The method includes receiving the image sequence from an imaging device, and the image sequence has a plurality of images. The method further includes identifying at least one feature portion in a selected image, which moves responsive to the periodic physiological activity. The method also includes detecting, by a processor, the corresponding feature portions in other images of the image sequence and determining, by the processor, a phase of a the selected image in the image sequence based on the motion of the feature portion.