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

Patent metadata

Field	Value
Publication number	US-9595104-B2
Application number	US-201514876628-A
Country	US
Kind code	B2
Filing date	Oct 6, 2015
Priority date	May 14, 2012
Publication date	Mar 14, 2017
Grant date	Mar 14, 2017

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.

First claim

We claim:

1. A method for assessment of blood within a fluid receiving substrate, comprising:
at a processor, selecting a region of an image of the fluid-receiving substrate upon detection of a reference marker;
at the processor, generating an estimated volume of blood at the fluid-receiving substrate from the region of the image with a volume estimation algorithm;
at the processor, extracting a feature including a redness value in a red component space from a set of pixels of the region of the image;
at the processor, correlating the feature with a concentration of a blood component at the fluid-receiving substrate;
at the processor, estimating a quantity of the blood component at the fluid-receiving substrate based on the estimated volume and the concentration of the blood component at the fluid-receiving substrate; and
at an electronic device in communication with the processor, providing information indicative of the quantity of the blood component at the fluid-receiving substrate.

2. The method of claim 1 , wherein detection of the reference marker comprises implementing machine vision to identify a volume marker at the fluid receiving substrate, wherein selecting the region of the image comprises selecting at least one pixel adjacent a portion of the image corresponding to the volume marker, and wherein generating the estimated volume comprises identifying a fluid meniscus within the at least one pixel and comparing the fluid meniscus to the volume marker.

3. The method of claim 1 , wherein extracting the redness value includes extracting an average redness value of the set of pixels, and wherein correlating the redness value with the concentration of the blood component comprises comparing the average redness value to a reference redness value of a template image of known concentration of the blood component.

4. The method of claim 1 , wherein extracting the feature comprises extracting a color intensity value of at least one of the set of pixels, and wherein correlating the 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.

5. The method of claim 1 , further comprising extracting a second feature from the region of the image, correlating the second feature with a concentration of a non-blood component at the fluid-receiving substrate, and estimating a quantity of the non-blood component at the fluid-receiving substrate based upon the estimated volume and the concentration of the non-blood component at the fluid-receiving substrate.

6. The method of claim 5 , wherein estimating the quantity of the non-blood component comprises estimating the quantity of saline at the fluid-receiving substrate.

7. The method of claim 1 , wherein extracting the feature further includes extracting a blueness value in the blue component space and a greenness value in a green component space.

8. The method of claim 7 , wherein correlating the feature with a concentration of a blood component at the fluid-receiving substrate comprises comparing the redness value, greenness value, and blueness value with a template image of known concentration of the blood component.

9. The method of claim 1 , wherein the fluid-receiving substrate comprises a canister, and wherein selecting the region of the image comprises selecting the region corresponding to an anti-glare region on the canister.

10. The method of claim 1 , wherein estimating the quantity of the blood component at the fluid-receiving substrate comprises estimating at least one of a red blood cell count and a hemoglobin amount at the fluid receiving substrate.

11. A method for assessment of blood at a fluid-receiving substrate, the method comprising:
at a processor, receiving an image dataset of the fluid-receiving substrate generated using an optical sensor;
at the processor, identifying a portion of the image dataset associated with a portion of the fluid-receiving substrate containing fluid;
at the processor, generating an estimated volume of fluid at the fluid-receiving substrate from the portion of the image dataset;
at the processor, extracting a color feature from the portion of the image dataset;
at the processor, determining an amount of a blood component at the fluid-receiving substrate from the color feature and the estimated volume; and
by way of the processor, rendering information derived from the amount of the blood component at a display of a mobile computing device in communication with the processor.

12. The method of claim 11 , wherein receiving the image dataset of the fluid-receiving substrate comprises receiving the image dataset of at least one of a canister, an intravenous fluid bag, and a fluid-bearing container.

13. The method of claim 11 , wherein extracting the color feature from the portion of the image dataset includes extracting at least one of a redness value in a red component space, a blueness value in a blue component space, and a greenness value in a green component space, and wherein determining the amount of the blood component from the color features includes determining the amount from at least one of the redness value, the blueness value, and the greenness value.

14. The method of claim 11 , wherein determining the amount of the blood component comprises: for each of a set of pixel clusters of the portion of the image dataset, generating a local value of concentration of the blood component based upon comparison between color intensity in the pixel cluster and color intensity of at least one of a set of template images, and deriving the concentration of the blood component from the local values of concentration associated with the set of pixel clusters.

15. The method of claim 11 , wherein generating the estimated volume of fluid at the fluid-receiving substrate comprises: at the processor, implementing machine vision to identify a volume marker at the fluid-receiving substrate, selecting a set of pixels adjacent a portion of the image corresponding to the volume marker, identifying a fluid meniscus within the set of pixels, and generating the estimated volume upon comparison of the fluid meniscus to the volume marker.

16. The method of claim 11 , wherein rendering information at the display of the mobile computing device comprises rendering the estimated volume, the amount of the blood component, and time information associated with the estimated volume and the amount of the blood component at the display.

17. A system for assessment of blood of a patient received at a fluid-receiving substrate, the system comprising:
an image data receiving module;
a processor in communication with the image data receiving module;
a software module executing on the processor and instructing the image data capture module to capture an image dataset of the fluid-receiving substrate, the software module further instructing the processor to select a region of the image dataset associated with a portion of the fluid-receiving substrate containing fluid, to generate an estimated volume of fluid at the fluid-receiving substrate based on the region, to extract a color feature from the region, and to estimate an amount of a blood component at the fluid-receiving substrate based on the color feature; and
an output module in communication with the processor and receiving instructions from the software module to output information indicative of the amount of the blood component and the estimated volume of fluid at the fluid-receiving substrate, to an entity.

18. The system of

Assignees

• Gauss Surgical Inc

Inventors

• Satish Siddarth
• Zandifar Ali
• Miller Kevin J

Classifications

• G06T2207/30004

  Biomedical image processing · CPC title

• G06T7/90

  Determination of colour characteristics · CPC title

• G06T7/0012 Primary

  Biomedical image inspection · CPC title

• G01N21/25

  Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands · CPC title

• G01N33/49

  Blood {(chemical methods for determining blood cell populations G01N33/5094; chemical analysis of blood groups or blood types G01N33/80)} · CPC title