System and method for estimating a quantity of a blood component in a fluid canister

• US 8,983,167 B2
• Filed: 01/10/2013
• Issued: 03/17/2015
• Est. Priority Date: 05/14/2012
• Status: Active Grant

• Current Assignee: Gauss Surgical, Gauss Surgical, Inc. (Stryker Corporation)
• Original Assignee: Gauss Surgical
• Inventors: Satish, Siddarth, Zandifar, Ali, Miller, Kevin J
• Primary Examiner(s): Tabatabai, Abolfazl
• Application Number:
  US13/738,919
• Publication Number:
  US 20130301901A1
• Time in Patent Office: 796 Days
• Field of Search: 382128-134, 600/302, 600/322, 600/326, 600/369, 600/407, 600/424, 600/500, 600/558, 604/358, 604/362, 604/503, 356/39, 356/40, 356/244
• US Class Current: 382/134
• CPC Class Codes: A61B 5/02042 Determining blood loss or bleeding, e.g. during a surgical procedure
• CPC Class Codes: G01F 22/00 Methods or apparatus for measuring volume of fluids or fluent solid material, not otherwise provided for
• CPC Class Codes: G01F 23/292 Light , e.g. infrared or ultraviolet
• CPC Class Codes: G01N 21/25 Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
• CPC Class Codes: G01N 21/84 Systems specially adapted for particular applications
• CPC Class Codes: G01N 21/90 in a container or its contents G01N21/91 takes precedence
• CPC Class Codes: G01N 33/49 Blood chemical methods for determining blood cell populations G01N33/5094; chemical analysis of blood groups or blood types G01N33/80
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 2207/30004 Biomedical image processing
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G06T 7/70 Determining position or orientation of objects or cameras camera calibration G06T7/80
• CPC Class Codes: G06T 7/90 Determination of colour characteristics

Abstract

A variation of a method for estimating a quantity of a blood component in a fluid canister includes: within an image of a canister, identifying a reference marker on the canister; selecting an area of the image based on the reference marker; correlating a portion of the selected area with a fluid level within the canister; estimating a volume of fluid within the canister based on the fluid level; extracting a feature from the selected area; correlating the extracted featured with a concentration of a blood component within the canister; and estimating a quantity of the blood component within the canister based on the estimated volume and the concentration of the blood component within the canister.

Claims

1. A method comprising:

within an image of a canister, identifying a reference marker on the canister;

selecting an area of the image based on the reference marker;

correlating a portion of the selected area with a fluid level within the canister;

estimating a volume of fluid within the canister based on the fluid level;

extracting a redness value from the selected area;

correlating the redness value with a concentration of red blood cells within the canister; and

estimating a quantity of red blood cells within the canister based on the estimated volume and the concentration of red blood cells within the canister.

2. The method of claim 1, wherein identifying the reference marker on the canister comprises identifying a surgical fluid canister within the image and removing a background, neighboring the canister, from the image.

3. The method of claim 1, wherein identifying the reference marker on the canister comprises implementing machine vision to identify the reference marker arranged at a standardized position on the canister, and wherein selecting the area of the image comprises selecting the area according to a standardized distance between the reference marker and a region of interest on the canister, the selected area of the image corresponding to the region of interest on the canister.

4. The method of claim 3, wherein selecting the area of the image comprises selecting the area corresponding to the region of interest comprising an anti-glare surface on the canister.

5. The method of claim 1, wherein identifying the reference marker on the canister comprises implementing machine vision to identify a volume marker on the canister, wherein selecting the area of the image comprises selecting a set of pixels adjacent a portion of the image corresponding to the volume marker, and wherein correlating the portion of the selected area with the fluid level comprises identifying a fluid meniscus within the set of pixels and comparing the fluid meniscus to the volume marker.

6. The method of claim 1, wherein extracting the feature from the selected area comprises extracting an average redness value of a set of pixels within the selected area, and wherein correlating the redness value with the concentration of red blood cells comprises comparing the average redness value to a redness value of a template image of known concentration of the red blood cells.

7. The method of claim 1, wherein extracting the feature from the selected area comprises extracting a color intensity value of a set of pixels within the selected area, and wherein correlating the redness value with the concentration of red blood cells comprises transforming the color intensity value into the concentration of red blood cells according to a parametric model.

8. The method of claim 1, wherein estimating the quantity of red blood cells within the canister comprises estimating a red blood cell count within the canister.

9. The method of claim 1, further comprising extracting a second feature from the selected area, correlating the second redness value with a concentration of a non-blood component within the canister, and estimating a quantity of the non-blood component within the canister based on the estimated volume and the concentration of the non-blood component within the canister.

10. The method of claim 9, wherein estimating the quantity of the non-blood component comprises estimating the quantity of saline within the canister.

11. The method of claim 1, wherein estimating the quantity of red blood cells within the canister comprises estimating the volume of blood in the canister, and further comprising estimating total patient blood loss based on the estimated volume of blood in the canister.

12. The method of claim 1, further comprising implementing template matching to determine a type of the canister, wherein estimating the volume of fluid within the canister comprises estimating the volume of fluid based on the type of the canister.

13. The method of claim 1, wherein extracting the redness value from the selected area comprises extracting at least one of a color intensity, a luminosity, a hue, a saturation value, a brightness value, and a gloss value from the selected area.

14. A method comprising:

receiving an image of a canister, the canister comprising one of a surgical suction canister, a blood salvage canister, and an intravenous fluid bag;

removing a background from the image;

correlating a segment of the image with a portion of the canister containing fluid;

estimating a volume of fluid within the canister based on the segment;

extracting a color feature from a pixel within the segment;

correlating the color feature with a concentration of a blood component within the canister; and

estimating a content of the blood component within the canister based on the estimated volume of fluid and the concentration of the blood component within the fluid canister.

15. The method of claim 14, wherein estimating a content of the blood component within the canister comprises estimating a hemoglobin content within the canister.

16. The method of claim 14, wherein extracting the color feature from the pixel within the segment comprises extracting a redness value in a red component space, a blueness value in the a component space, and a greenness value in a green component space, wherein correlating the color feature with the concentration of the blood component comprises comparing the redness value, greenness value, and blueness value with a template image of known concentration of the blood component.

17. The method of claim 14, wherein extracting the color feature from a pixel within the segment comprises extracting a color intensity value of a set of pixels within the selected area, and wherein correlating the extracted feature with the concentration of the blood component comprises transforming the color intensity value into the concentration of the blood component according to a parametric model.

18. The method of claim 14, wherein extracting the color feature from the a pixel within the segment comprises extracting at least one of a color intensity, a luminosity, a hue, a saturation value, a brightness value, and a gloss value from the pixel.

19. A system comprising:

an optical sensor;

a processor coupled to the optical sensor;

a data storage module storing a library of template images of known concentrations of a blood component;

a software module executing on the processor, instructing the optical sensor to capture an image of a canister, and instructing the processor to select an area of the image correlated with a portion of the canister containing fluid, to estimate a volume of fluid within the canister based on the selected area, to extract a feature from the selected area, to correlate the extracted feature with a concentration of the blood component by comparing the extracted feature with a template image in the library of template images, and to estimate a quantity of the blood component within the canister based on the concentration of the blood component; and

a display coupled to the processor and receiving instruction from the software module to display the quantity of the blood component within the canister.

20. The system of claim 19, wherein the optical sensor comprises a camera configured to be mounted adjacent the canister.