Camera-Based Apnoea Detection Through Cardiac–Respiratory Signal Separation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for detecting apnea are obtrusive, uncomfortable for patients, and prone to errors due to superimposed vital sign signals, particularly in cases of respiratory arrest, leading to inaccurate detection.
Innovation Solution
A device and system using remote photoplethysmography and image analysis to extract cardiac and motion signals from a subject's skin and body parts, determining their similarity through correlation or frequency analysis to unobtrusively detect apnea with improved accuracy and reliability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If contact sensors (electrodes, thorax impedance plethysmography) are used to measure vital signs, then measurement precision is improved, but ease of operation deteriorates due to obtrusive body contact and patient discomfort
Solution Approach 1:
The patent replaces mechanical contact-based measurement systems (electrodes, thorax impedance plethysmography) with an optical system using video cameras to capture images of the patient's chest and skin. This substitution eliminates physical contact while enabling non-intrusive extraction of cardiac and respiratory signals through image analysis, thereby improving patient comfort without sacrificing measurement capability
Solution Approach 2:
The patent creates optical copies (images) of the patient's chest and skin surfaces using video cameras. These image copies are then processed to extract vital sign information, replacing the need for direct physical contact with sensors. The copying approach allows measurement of physiological parameters through visual observation and image analysis rather than mechanical or electrical contact
2Ease of operation
If remote photoplethysmography is used to unobtrusively monitor heart rate and respiratory rate, then ease of operation is improved, but reliability deteriorates due to superimposed vital sign signals causing false detection
Solution Approach 1:
The patent segments the superimposed vital sign signals by separating cardiac activity and respiratory motion into distinct components. By extracting and analyzing these separate signals independently, the system can identify when respiratory signal is absent (apnoea) versus when both cardiac and respiratory signals are present, thereby improving detection reliability
Solution Approach 2:
The patent employs feedback mechanisms where the extracted cardiac and respiratory signals are continuously monitored and compared. The system uses the relationship between these signals to validate detection results, providing feedback to distinguish true apnoea events from false positives caused by signal superposition
3Ease of operation
If video camera based remote PPG is used to detect apnoea, then ease of operation is improved, but measurement precision deteriorates due to superposition of cardiac and respiratory signals
Solution Approach 1:
The patent segments the composite signal from video camera based remote PPG into distinct cardiac and respiratory components. By separating these signals through image analysis and processing, the system can accurately measure respiratory rate independent of cardiac activity, improving measurement precision while maintaining non-intrusive operation
Solution Approach 2:
The patent introduces image processing algorithms as intermediaries between the raw video camera data and the vital sign extraction. These intermediary processing steps filter and separate the superimposed signals, enabling precise respiratory rate measurement by eliminating the confounding effect of cardiac signal superposition
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
Enables fully non-intrusive apnea detection with high accuracy by distinguishing cardiac and respiratory signals, reducing false positives and ensuring patient comfort, suitable for hospital and home monitoring applications.
Implementation Method 1
remote photoplethysmographic imaging. Remote photoplethysmographic imaging is, for instance, described in Wim Verkruysse, Lars O. Svaasand, and J. Stuart Nelson, 'Remote plethysmographic imaging using ambient light'
Implementation Method 2
the pulsation of arterial blood causes changes in light absorption. Those changes observed with a photodetector (or an array of photodetectors) form a PPG (photo-plethysmography) signal
Implementation Method 3
A video camera captures the breathing movements of a patient's chest in a stream of images. The breathing movements lead to a temporal modulation of certain image features
Data Source
Figure 1
Figure 2~3B
Figure 4A~4C
AI summary
The present invention relates to device, system and method for unobtrusively and reliably detecting apnoea of a subject (2). The proposed device comprises an input unit (11) for receiving image data of subject, said image data including a sequence of images over time, a cardiac activity extraction unit (12) for extracting from said image data a cardiac activity signal representing the subject's cardiac activity from a skin area of the subject using remote photoplethysmography, a motion signal extraction unit (14) for extracting from said image data a motion signal representing motion of a subject's body part caused by breathing of the subject, an analysis unit (16) for determining the similarity between said cardiac activity signal and said motion signal, and an decision unit (18) for detecting apnoea of the subject based on the determined similarity.