Non-invasive non-contact system and method for measuring dyslipidemia condition using thermal imaging
Inventors
Shivpure, Sameer Raghuram • THIRUVENGADAM, Jayanthi • Choda, Anuhya • CHODA, Gayathri
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-11903742-B2
Publication Date
2024-02-20
Expiration Date
Abstract
System and method for measuring dyslipidemia condition of a subject using thermal imaging is disclosed. The disclosed system and method includes thermal sensors for capturing thermal images and/or videos of a body part; and a processing engine to detect a predefined region of the body part in each frame of the captured images and/or videos. The processing engine segments one or more portions from the predefined region in each frame of the captured images and/or videos to identify a ROI comprising arteries in the segmented portions. Based on the identified region of interest, the engine extracts pixel values, representing biosignals, from each frame of the captured images and/or videos to determine parameters associated with a rate of atherosclerotic, levels of lipids and lipoproteins, and hemodynamic factors of the subject. Further a risk score for the dyslipidemia condition based on the determined parameters using computational models is measured.
Core Innovation
The disclosure describes a non-contact, non-invasive thermal-imaging system and method for assessing dyslipidemia. Thermal images or thermal images/videos of an anterior face region are captured, including detection of a predefined facial region such as a forehead, and a processing engine identifies a region of interest (ROI) corresponding to arterial frontal branches near the skin and segments forehead portions to isolate the ROI for further analysis.
Pixel intensity variations within the ROI are extracted per frame as biosignals. The extracted biosignal values are transformed into time-domain and frequency-domain values using signal processing operations, including Fast Fourier Transform (FFT) and frequency filtering within a pulse range. The system determines parameters from the processed biosignals, including average intensity, amplitude, period, entropy, power spectral density, histogram values, and peak count.
The determined parameters are used to determine parameters related to atherosclerotic rate, lipids and lipoproteins, and hemodynamic factors for dyslipidemia assessment. The parameters are compared with reference or healthy subject values and/or provided to computational models such as principal component analysis (PCA) and machine learning models, including clustering, logistic regression, random forest, and neural network, to output a dyslipidemia risk score. The risk score determination may consider demographics and medical history in addition to the determined parameters.
Claims Coverage
Not explicitly described in patent (no independent claims were provided in the relevant claims list).
Not explicitly described in patent.
Stated Advantages
Enables early detection of dyslipidemia-related risk.
Supports monitoring progression.
Evaluates treatment efficacy, including anti-dyslipidemic medication dosage monitoring.
Evaluates lifestyle intervention efficacy.
Provides dyslipidemia assessment without blood sampling via thermal imaging.
Documented Applications
Assessing dyslipidemia risk using non-contact, non-invasive thermal imaging and ROI arterial segmentation.
Monitoring dyslipidemia progression.
Evaluating anti-dyslipidemic medication dosage monitoring.
Evaluating lifestyle intervention efficacy.
Interested in licensing this patent?