SELECTING A REGION OF INTEREST FOR EXTRACTING PHYSIOLOGICAL PARAMETERS FROM A VIDEO OF A SUBJECT

• US 20160198965A1
• Filed: 01/09/2015
• Published: 07/14/2016
• Est. Priority Date: 01/09/2015
• Status: Active Grant

• Current Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Original Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Inventors: MESTHA, Lalit Keshav, HOOVER, Martin Edward, KYAL, Survi
• Granted Patent: US 9,986,923 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: A61B 2576/00 Medical imaging apparatus involving image processing or analysis A61B1/00009, A61B6/52 and A61B8/52 take precedence; image processing per se G06T; details of algorithms for analysing medical images G06T7/0012
• CPC Class Codes: A61B 5/0013 Medical image data A61B1/00011, A61B6/56, A61B8/56 take precedence
• CPC Class Codes: A61B 5/02433 for infrared radiation
• CPC Class Codes: A61B 5/7203 for noise prevention, reduction or removal
• CPC Class Codes: A61B 5/7225 Details of analog processing, e.g. isolation amplifier, gain or sensitivity adjustment, filtering, baseline or drift compensation A61B5/30, A61B5/316 take precedence; transformers for specific applications H01F38/00; amplifiers H03F
• CPC Class Codes: A61B 5/725 using specific filters therefor, e.g. Kalman or adaptive filters A61B5/316 take precedence
• CPC Class Codes: A61B 5/748 Selection of a region of interest, e.g. using a graphics tablet
• CPC Class Codes: G16H 30/40 for processing medical images, e.g. editing

Abstract

What is disclosed is a system and method for selecting a region of interest for extracting physiological parameters from a video of a subject. In one embodiment the present method involves performing the following. First, time-series signals are received which have been generated by having processing image frames of a video of a subject captured using a single band video camera with a bandpass filter with a pass band in a wavelength range of 495-565 nm and/or 800-1000 nm. The regions of interest are areas where a plethysmographic signal can be detected by the camera. Each time-series signal is associated with a different region of interest. A signal strength is then calculated for each of the time-series signals. The region associated with the time-series signal having a highest signal strength is selected. The time-series signal associated with the selected region can be processed to extract a videoplethysmographic (VPG) signal containing physiological parameters.

Claims

1. A method for selecting a region of interest for extracting physiological parameters from a video of a subject, the method comprising:

receiving a plurality of time-series signals each associated with a different region of interest of a subject where a plethysmographic signal can be detected, said time-series signals obtained by having processed pixels in batches of image frame of a video of each respective region of interest of said subject, said video having been captured by a single band video camera with a bandpass filter with a pass band in a wavelength range of one of;

495-565 nm, and 800-1000 nm;

calculating a signal strength of each of said time-series signals; and

selecting one of said regions of interest which is associated with a time-series signal having a highest signal strength.

2. The method of claim 1, further comprising:

identifying a dominant frequency f₀ in any of said time-series signals;

identifying harmonics frequencies 2f₀, 3f₀, 4f₀, . . . , ; and

defining a window of frequencies about said dominant frequency, frequencies within said window collectively defining a band of interest, said signal strength being calculated over said band of interest.

3. The method of claim 2, wherein said dominant frequency f₀ is identified by having computed a power spectral density of said time-series signal by any combination of:

a non-parametric spectral density estimation on a filtered time-series signal, and a parametric spectral density estimation on a filtered time-series signal.

4. The method claim 2, wherein said signal strength comprises one of:

a pulse harmonic strength (PHS), and a signal-to-noise ratio (SNR).

5. The method of claim 4, wherein said pulse harmonic strength (PHS) at least comprises:

6. The method of claim 4, wherein said signal-to-noise ratio (SNR) at least comprises:

7. The method in claim 1, further comprising detrending any of said time-series signal to remove non-stationary components.

8. The method of claim 1, further comprising processing said time-series signal associated with said selected region of interest to extract a VPG signal containing at least one physiological parameter of said subject.

9. A system for selecting a region of interest for extracting physiological parameters from a video of a subject, the system comprising:

a memory; and

a processor in communication with said memory, said processor executing machine readable instructions for performing;

receiving a plurality of time-series signals each associated with a different region of interest of a subject where a plethysmographic signal can be detected, said time-series signals obtained by having processed pixels in batches of image frame of a video of each respective region of interest of said subject, said video having been captured by a single band video camera with a bandpass filter with a pass band in a wavelength range of one of;

495-565 nm and 800-1000 nm;

calculating a signal strength of each of said time-series signals; and

selecting one of said regions of interest which is associated with a time-series signal having a highest signal strength.

10. The system of claim 9, further comprising:

identifying a dominant frequency f₀ in any of said time-series signals;

identifying harmonics frequencies 2f₀, 3f₀, 4f₀, . . . , ; and

defining a window of frequencies about said dominant frequency, frequencies within said window collectively defining a band of interest, said signal strength being calculated over said band of interest.

11. The system of claim 10, wherein said dominant frequency f₀ is identified by having computed a power spectral density of said time-series signal by any combination of:

a non-parametric spectral density estimation on a filtered time-series signal, and a parametric spectral density estimation on a filtered time-series signal.

12. The system of claim 10, wherein said signal strength comprises one of:

a pulse harmonic strength (PHS), and a signal-to-noise ratio (SNR).

13. The system of claim 12, wherein said pulse harmonic strength (PHS) at least comprises:

14. The system of claim 12, wherein said signal-to-noise ratio (SNR) at least comprises:

15. The system of claim 9, further comprising detrending any of said time-series signal to remove non-stationary components.

16. The system of claim 9, further comprising processing said time-series signal associated with said selected region of interest to extract a VPG signal containing at least one physiological parameter of said subject.

17. A computer implemented method for selecting a region of interest for extracting physiological parameters from a video of a subject, the method comprising:

receiving a plurality of time-series signals each associated with a different region of interest of a subject where a plethysmographic signal can be detected, said time-series signals obtained by having processed pixels in batches of image frame of a video of each respective region of interest of said subject, said video having been captured by a single band video camera with a bandpass filter with a pass band in a wavelength range of one of;

495-565 nm and 800-1000 nm;

calculating a signal strength of each of said time-series signals; and

selecting one of said regions of interest which is associated with a time-series signal having a highest signal strength.

18. The computer implemented method of claim 17, further comprising:

identifying a dominant frequency f₀ in any of said time-series signals;

identifying harmonics frequencies 2f₀, 3f₀, 4f₀, . . . , ; and

defining a window of frequencies about said dominant frequency, frequencies within said window collectively defining a band of interest, said signal strength being calculated over said band of interest.

19. The computer implemented method of claim 18, wherein said dominant frequency f₀ is identified by having computed a power spectral density of said time-series signal by any combination of:

a non-parametric spectral density estimation on a filtered time-series signal, and a parametric spectral density estimation on a filtered time-series signal.

20. The computer implemented method of claim 19, wherein said signal strength comprises one of:

a pulse harmonic strength (PHS), and a signal-to-noise ratio (SNR).

21. The computer implemented method of claim 20, wherein said pulse harmonic strength (PHS) at least comprises:

22. The computer implemented method of claim 20, wherein said signal-to-noise ratio (SNR) at least comprises:

23. The computer implemented method of claim 17, further comprising detrending any of said time-series signal to remove non-stationary components.

24. The computer implemented method of claim 17, further comprising processing said time-series signal associated with said selected region of interest to extract a VPG signal containing at least one physiological parameter of said subject.