Respiratory Phase Detection in Radiographic Image Processing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional radiographic image processing methods struggle to accurately display differences between respiratory moving images taken at different time points during respiration, as they require patients to hold their breath, making it difficult to specify a respiratory phase and complicating the radiography process.
Innovation Solution
A radiographic image processing method and apparatus that input and analyze respiratory moving images from two different time points, determine a reference image with a respiration phase approximate to the other time point's phase, and perform difference computation to cancel out phase differences, allowing for accurate difference processing and improved diagnostic performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If patients hold their breath during radiography to specify a respiratory phase, then the radiographic phase can be controlled, but the radiography process becomes complicated and diagnostic accuracy for dynamic changes deteriorates
Solution Approach 1:
The system automatically detects respiratory phase using image processing without requiring patient cooperation or external sensors. The respiratory phase detection is performed self-service by the radiographic system itself, analyzing the captured images to determine phase information, thereby simplifying the radiography process while maintaining phase specification accuracy
Solution Approach 2:
The patent replaces the mechanical/manual method of breath-holding instruction with an automated image-based detection system. Instead of relying on patient compliance with breath-holding commands, the system uses computational analysis of radiographic images to automatically determine respiratory phase, substituting a mechanical control approach with an information-processing approach
2Ease of manufacture
If conventional difference processing is applied to still images radiographed while holding breath, then the processing is simple, but it cannot capture dynamic changes during respiration and diagnostic accuracy deteriorates
Solution Approach 1:
The patent transitions from static difference processing of breath-held images to dynamic difference processing of respiratory moving images. By capturing and processing a sequence of images throughout the respiratory cycle, the system maintains processing feasibility while enabling the detection of dynamic changes in morbid portions that occur during respiration, thereby improving diagnostic accuracy
Solution Approach 2:
The system performs preliminary classification of respiratory phases from the captured moving images before conducting difference processing. By pre-identifying corresponding phases across different time points, the system prepares the data in advance to enable accurate dynamic comparison, maintaining processing simplicity while capturing temporal changes
3Measurement precision
If respiratory moving images are captured without breath-holding to improve diagnostic performance, then dynamic changes can be observed, but the respiratory cycles vary greatly and phase matching becomes difficult
Solution Approach 1:
The system implements feedback by using the captured respiratory moving images themselves to detect and identify phase information. The image data provides feedback about the actual respiratory state, which is then used to select corresponding phases for difference processing, compensating for variations in respiratory cycle stability without requiring external monitoring devices
Solution Approach 2:
The patent changes the approach from assuming stable respiratory cycles to adapting to variable cycles by using image-based phase detection. Instead of relying on the stability parameter of respiratory rhythm, the system extracts phase information directly from the visual characteristics of the images, allowing accurate matching despite variations in respiratory timing and depth
4Measurement precision
If external sensors are added to detect respiratory phase, then phase specification is accurate, but the radiography process becomes complicated and patient comfort deteriorates
Solution Approach 1:
The radiographic system performs self-service by using its own captured images to detect respiratory phase information. No external sensors or additional monitoring equipment are required; the system extracts phase data from the radiographic images themselves, maintaining detection accuracy while avoiding the complexity and patient discomfort associated with external attachments
Solution Approach 2:
The captured radiographic images serve multiple functions: they provide both the diagnostic image data and the information needed for respiratory phase detection. This multi-functionality eliminates the need for separate sensing systems, reducing overall system complexity while maintaining accurate phase specification through the dual-use of the image data
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach enables accurate difference processing of chest respiratory moving images, improving diagnostic performance by canceling out phase differences and allowing for more precise observation of changes over time, thereby enhancing diagnostic accuracy.
Implementation Method 1
the semiconductor image sensor reads X-rays in an extremely wide dynamic range as electrical signals by using a photoelectric conversion means
Data Source
AI summary
N images in a respiratory cycle which are radiographed in year P are input, and binary lung field images are extracted from the respective front chest images. Lung field areas S and lung field heights are then calculated. In forming area and height variation waveforms, regions of the N input images are obtained and plotted. Each image is determined as an image belonging to the inspiration mode or expiration mode. The respective images are sorted and stored. Similar processing is performed for N images in a respiratory cycle which are radiographed in year P+1, and the resultant images are stored. Difference images are obtained from the basic images radiographed in year P+1 and the reference images radiographed in year P for each mode by image analysis, thereby extracting changes over time.