Body surface optical imaging for respiratory monitoring
A method for measuring respiratory parameters of a subject using a range imaging sensor, wherein the method includes: receiving from the range imaging sensor at least one raw image of at least one portion of the torso of the subject, wherein each point of the raw image represents the distance between the range imaging sensor and the subject; generating a surface image of at least one portion of a surface of the torso of the subject by surface interpolation of the raw image; estimating a respiratory signal as a function of time calculated as the spatial average, in a given region of interest (ROI) defined on the torso of the subject, of the differences between the depth values of the surface image at a given time and the depth values of a reference surface image; and estimating a lung volume.
1. A computer-implemented method for estimating respiratory parameters of a subject, wherein said method comprises:
receiving a set of acquisitions derived from a range imaging sensor, said set of acquisitions comprising at least one raw image and a reference surface image of at least one portion of a torso of the subject, wherein each point of said at least one raw image represents a distance between the range imaging sensor and the subject; said reference surface image comprising depth values;
generating, for each raw image of said at least one raw image, a surface image of at least one portion of a surface of the torso of the subject by surface interpolation of said at least one raw image;
estimating a respiratory signal as a function of time by;
for each surface image, calculating the differences between depth values comprised in a given region of interest (ROI) defined on the surface image, said region of interest (ROI) comprising at least portion of the torso of the subject, at a given time, and the depth values of said reference surface image, and
calculating the spatial average of the obtained differences;
estimating respiratory parameters including at least a lung volume as a function of time by multiplying the respiratory signal by a surface of the region of interest; and
providing as output said respiratory parameters.
2. The method according to claim 1 , further comprising estimating a tidal volume as the difference between the maximum value and the minimum value in one respiratory cycle of the respiratory signal multiplied by the surface of the region of interest.
3. The method according to claim 1 , further comprising estimating a respiratory rate calculated from the detection of inhalation peaks in the respiratory signal.
4. The method according to claim 1 , wherein surface interpolation of said at least one raw image is obtained using basis spline functions.
5. The method according to claim 1 , further comprising filtering said at least one raw image so as to remove noise originating from other objects in a scene.
6. The method according to claim 1 , wherein said at least one raw image is derived from the range imaging sensor being a time-of-flight camera.
7. The method according to claim 6 , wherein the method further comprises calibrating by applying a rotation matrix to said at least one raw image so as to align the subject torso in said at least one raw image with a xy plane of the time-of-flight camera.
8. The method according to claim 1 , wherein said at least one raw image is derived from the range imaging sensor being placed in front of the torso of the subject.
9. A non-transitory computer readable medium comprising instructions which, when the program is executed by a computer, cause the computer to carry out the method according to claim 1 .
10. A system for estimating respiratory parameters of a subject comprising:
at least one input selected from the group consisting of hardware, software, firmware and combinations thereof, said at least one input being configured to receive a set of acquisitions derived from a range imaging sensor, said set of acquisitions comprising at least one raw image and a reference image of at least one portion of a torso of the subject, wherein each point of the at least one raw image represents a distance between the range imaging sensor and the subject, said reference surface image comprising depth values;
at least one processor configured to:
generate, for each raw image of said at least one raw image, a surface image of at least one portion of a surface of the torso of the subject by surface interpolation of said at least one raw image,
estimate a respiratory signal as a function of time by:
for each surface image, calculating the differences between depth values comprised in a given region of interest (ROI) defined on the surface image, said region of interest (ROI) comprising at least portion of the torso of the subject, at a given time, and the depth values of said reference surface image, and
calculating the spatial average of the obtained differences,
calculate respiratory parameters including at least a lung volume as a function of time by multiplying the respiratory signal by the surface of the region of interest; and
at least one output selected from the group consisting of hardware, software, firmware and combinations thereof, said at least one output being configured to output said respiratory parameters.
11. The system according to claim 10 , wherein the at least one processor is configured to further calculate a respiratory rate calculated from the detection of inhalation peaks in the respiratory signal.
12. The system according to claim 11 , wherein the range imaging sensor is placed in front of the torso of the subject.
13. The system according to claim 10 , wherein the range imaging sensor is a time-of-flight camera and the at least one processor is further configured to apply a rotation matrix to said at least one raw image so as to align the subject torso in said at least one raw image with the xy plane of the range imaging sensor.
14. The system according to claim 10 , wherein the at least one processor is further configured to calculate a tidal volume as the difference between the maximum value and the minimum value in one respiratory cycle of the respiratory signal multiplied by the surface of the region of interest.
15. The system according to claim 10 , wherein the at least one processor is further configured to filter said at least one raw image so as to remove noise originating from other objects in a scene.
16. The system according to claim 10 , wherein surface interpolation of said at least one raw image is obtained using basis spline functions.