Methods and systems for characterizing fluids from a patient

Patent metadata

Field	Value
Publication number	US-12002211-B2
Application number	US-202318211819-A
Country	US
Kind code	B2
Filing date	Jun 20, 2023
Priority date	May 15, 2015
Publication date	Jun 4, 2024
Grant date	Jun 4, 2024

Abstract

Methods for characterizing fluids from a patient. A time series of images of a conduit are received, and a conduit image region in the images is identified. A flow type of the fluids passing through the conduit may be classified as one of air, laminar liquid, and turbulent liquid by evaluating an air-liquid boundary of the fluid. A volumetric flow rate of the fluids in the conduit is estimated. The volumetric flow rate may be based on the classified flow type. A concentration of a blood component of the fluids passing through the conduit may be estimated based on the images. A proportion of the fluid that is blood may also be determined, and a volume of blood that has passed through the conduit within a predetermined period of time may be estimated based on the estimated total volumetric flow rate and the determined proportion.

First claim

The invention claimed is:

1. A computer-implemented method for characterizing fluids from a patient, the method comprising:
receiving a time series of images of a conduit configured to receive the fluids from the patient;
receiving conduit-related information associated with the conduit;
identifying a conduit image region in the time series of images;
classifying a flow type of the fluids passing through the conduit;
estimating a volumetric flow rate of the fluids in the conduit based on the classified flow type and the conduit-related information;
estimating a concentration of a blood component of the fluids passing through the conduit;
estimating a volume of blood passing through the conduit based on the estimated concentration of the blood component and the estimated volumetric flow rate; and
displaying, on a display, the estimated volume of blood.

2. The method of claim 1 , wherein at least one of the time series of images includes an optical fiducial, wherein the method further comprises determining the conduit-related information based on information associated with the optical fiducial.

3. The method of claim 2 , wherein the optical fiducial includes at least one of a QR code, a barcode, a symbolic marker, and a color fiducial.

4. The method of claim 2 , wherein the optical fiducial is coupled to or integral with the conduit or a packaging of the conduit.

5. The method of claim 1 , further comprising:
receiving an input from a user; and
determining the conduit-related information based on the input.

6. The method of claim 1 , wherein the conduit-related information includes at least one of a type or classification of the conduit, a geometry, dimensions of an internal volume of the conduit, and a flow resistance of the conduit.

7. The method of claim 1 , wherein the conduit-related information includes a cross-sectional flow area of the conduit.

8. The method of claim 1 , wherein the step of estimating the concentration of the blood component of the fluids passing through the conduit further comprises:
determining a color intensity value of a pixel or pixel cluster within the conduit image region in the time series of images; and
correlating the color intensity value to associated blood component concentration value.

9. The method of claim 1 , wherein the step of classifying the flow type of the fluids further comprises evaluating at least one of a pixel cluster and/or an air-liquid boundary within the conduit image region in the time series of images to classify the flow type as one of air, laminar liquid, and turbulent liquid.

10. The method of claim 1 , wherein the step of estimating the volume of blood passing through the conduit further comprises estimating the volume of blood that has passed through the conduit over a predetermined period of time, wherein the method further comprises updating, on the display, a total blood loss based on intermittent estimated volumes of the estimated volume of blood.

11. A computer-implemented method for characterizing fluids from a patient, the method comprising:
receiving a time series of images of a conduit configured to receive the fluids from the patient;
receiving conduit-related information associated with the conduit;
identifying a conduit image region in the time series of images;
estimating a volumetric flow rate of the fluids in the conduit based on time series of images and the conduit-related information;
estimating a concentration of a blood component of the fluids passing through the conduit;
estimating a volume of blood passing through the conduit based on the estimated concentration of the blood component and the estimated volumetric flow rate; and
updating, on a display, a total blood loss based on the estimated volume of blood.

12. The method of claim 11 , wherein the conduit-related information includes a cross-sectional flow area of the conduit.

13. The method of claim 12 , further comprising:
determining a length of the conduit image region;
tracking a pixel cluster or an air-liquid boundary that traverses the length of the conduit image region in the time series of images;
determining a period of time for the pixel cluster or the air-liquid boundary to traverse the length of the conduit image region; and
estimating a total volumetric flow rate of the fluids in the conduit over the period of time based on the length of the conduit image region and the cross-sectional flow area of the conduit.

14. The method of claim 11 , wherein the step of estimating the concentration of the blood component of the fluids passing through the conduit further comprises:
determining a color intensity value of a pixel or a pixel cluster within the conduit image region in the time series of images; and
correlating the color intensity value to associated blood component concentration value.

15. The method of claim 14 , wherein the pixel color values are correlated to the associated blood component concentration values using at least one of a template matching technique and a parametric technique.

16. A computer-implemented method for characterizing fluids from a patient, the method comprising:
receiving a time series of images of a conduit configured to receive the fluids from the patient;
identifying an optical fiducial in at least one image of the time series of images;
determining at least one of a conduit-related information, an assigned color value, and a spatial position associated with the optical fiducial;
identifying a conduit image region in the time series of images;
estimate a volumetric flow rate of the fluids in the conduit based on the time series of images;
estimating a concentration of a blood component of the fluids passing through the conduit;
estimating a volume of blood passing through the conduit based on the estimated concentration of the blood component and the estimated volumetric flow rate; and
updating, on a display, a total blood loss based on the estimated volume of blood.

17. The method of claim 16 , wherein the conduit-related information includes a cross-sectional flow area of the conduit, wherein the method further comprises estimating a total volumetric flow rate of the fluids in the conduit based on the estimated volumetric flow rate and the cross-sectional area of the conduit.

18. The method of claim 16 , further comprising normalizing the time series of images based on the assigned color value of the optical fiducial by adjusting the images such that the color value of the optical fiducial in the images substantially matches the assigned color value associated with the optical fiducial.

19. The method of claim 18 , wherein estimating the concentration of the blood component of the fluids passing through the conduit further comprises:
determining a color intensity value of a pixel or pixel cluster within the conduit image region in the time series of images; and
correlating the color intensity value to associated blood component concentration value.

20. The method of claim 16 , further comprising spatially aligning a first image of the time series of images to a second image of the time series of images such that the spatial position associated with the optical fiducial in the first image matches the spatial position associated with the optical fiducial in the second image.

Assignees

• Gauss Surgical Inc

Inventors

• Satish Siddarth
• Miller Kevin

Classifications

• G06T7/0016 Primary

  involving temporal comparison · CPC title

• G06F18/24

  Classification techniques · CPC title

• G06T7/62

  of area, perimeter, diameter or volume · CPC title

• G06V10/764

  using classification, e.g. of video objects · CPC title

• G01F1/00

  Measuring the volume flow or mass flow of fluid or fluent solid material wherein the fluid passes through a meter in a continuous flow (measuring a proportion of the volume flow G01F5/00) · CPC title