Methods and systems for characterizing fluids from a patient
Methods and systems for characterizing fluids from a patient are disclosed. The method includes receiving a time series of images of a conduit receiving fluids from the patient, identifying a conduit image region in each of the images, classifying a flow type through the conduit based on an evaluation of the conduit image region in the time series of images, and estimating at least one of a volume of fluids and a quantity of a blood component that has passed through the conduit within a predetermined period of time, based at least in part on the classification of the flow type.
1. A method comprising:
accessing, by one or more processors of a machine, a set of images that depict a conduit containing a flow of fluids that include a mixture of gas and liquid;
determining, by the one or more processors of the machine, a volumetric flow rate of the flow of fluids in the conduit depicted in the set of images;
determining, by the one or more processors of the machine, a proportion of liquid in the flow of fluid; and
estimating, by the one or more processors of the machine, a volume of liquid passed through the conduit based on the volumetric flow rate of the flow of fluids and on the proportion of liquid in the flow of fluid.
2. The method of claim 1 , further comprising:
identifying and tracking a plurality of gas-liquid boundaries in the conduit based on the set of images; and wherein:
the determining of the volumetric flow rate of the flow of fluids in the conduit is based on the tracking of the plurality of gas-liquid boundaries in the conduit depicted in the set of images.
3. The method of claim 2 , wherein:
the tracking of the plurality of gas-liquid boundaries in the conduit depicted in the set of images includes tracking sets of one or more pixels in at least a subset of the set of images.
4. The method of claim 1 , further comprising:
identifying and tracking a plurality of gas-liquid boundaries in the conduit based on the set of images; and wherein:
the determining of the proportion of liquid in the flow of fluid is based on the plurality of gas-liquid boundaries in the conduit depicted in the set of images.
5. The method of claim 4 , wherein:
the tracking of the plurality of gas-liquid boundaries in the conduit depicted in the set of images includes detecting a color change across a gas-liquid boundary among the plurality of gas-liquid boundaries in the conduit.
6. The method of claim 1 , further comprising:
classifying a flow type of the flow of fluids in the conduit based on the set of images; and wherein:
the estimating of the volume of liquid passed through the conduit is based on the classified flow type of the flow of fluids in the conduit.
7. The method of claim 6 , wherein:
the classifying of the flow type of the flow of fluids in the conduit classifies the flow type as laminar liquid; and
the estimating of the volume of liquid passed through the conduit is based on the flow type being classified as laminar liquid.
8. The method of claim 1 , further comprising:
classifying a flow type of the flow of fluids in the conduit based on the set of images; and wherein:
the determining of the proportion of liquid in the flow of fluid is based on the classifying of the flow type of the flow of fluids in the conduit.
9. The method of claim 8 , wherein:
the classifying of the flow type of the flow of fluids in the conduit classifies the flow type as laminar liquid; and
the determining of the proportion of liquid in the flow of fluid is based on the flow type being classified as laminar liquid.
10. The method of claim 1 , further comprising:
estimating a concentration of a blood component in the estimated volume of liquid passed through the conduit; and
estimating a quantity of the blood component that has passed through the conduit based on the estimated concentration of the blood component and on the estimated volume of liquid passed through the conduit.
11. A system comprising:
one or more processors; and
a memory storing instructions that, when executed by at least one processor among the one or more processors, cause the system to perform operations comprising:
accessing a set of images that depict a conduit containing a flow of fluids that include a mixture of gas and liquid;
determining a volumetric flow rate of the flow of fluids in the conduit depicted in the set of images;
determining a proportion of liquid in the flow of fluid; and
estimating a volume of liquid passed through the conduit based on the volumetric flow rate of the flow of fluids and on the proportion of liquid in the flow of fluid.
12. The system of claim 11 , wherein the operations further comprise:
identifying and tracking a plurality of gas-liquid boundaries in the conduit based on the set of images; and wherein:
the determining of the volumetric flow rate of the flow of fluids in the conduit is based on the tracking of the plurality of gas-liquid boundaries in the conduit depicted in the set of images.
13. The system of claim 11 , wherein the operations further comprise:
identifying and tracking a plurality of gas-liquid boundaries in the conduit based on the set of images; and wherein:
the determining of the proportion of liquid in the flow of fluid is based on the plurality of gas-liquid boundaries in the conduit depicted in the set of images.
14. The system of claim 11 , wherein the operations further comprise:
classifying a flow type of the flow of fluids in the conduit based on the set of images; and wherein:
the estimating of the volume of liquid passed through the conduit is based on the classified flow type of the flow of fluids in the conduit.
15. The system of claim 11 , wherein the operations further comprise:
classifying a flow type of the flow of fluids in the conduit based on the set of images; and wherein:
the determining of the proportion of liquid in the flow of fluid is based on the classifying of the flow type of the flow of fluids in the conduit.
16. The system of claim 15 , wherein:
the classifying of the flow type of the flow of fluids in the conduit classifies the flow type as laminar liquid; and
the determining of the proportion of liquid in the flow of fluid is based on the flow type being classified as laminar liquid.
17. The system of claim 11 , wherein the operations further comprise:
estimating a concentration of a blood component in the estimated volume of liquid passed through the conduit; and
estimating a quantity of the blood component that has passed through the conduit based on the estimated concentration of the blood component and on the estimated volume of liquid passed through the conduit.
18. A non-transitory machine-readable storage medium comprising instructions that, when executed by one or more processors of a machine, cause the machine to perform operations comprising:
accessing a set of images that depict a conduit containing a flow of fluids that include a mixture of gas and liquid;
determining a volumetric flow rate of the flow of fluids in the conduit depicted in the set of images;
determining a proportion of liquid in the flow of fluid; and
estimating a volume of liquid passed through the conduit based on the volumetric flow rate of the flow of fluids and on the proportion of liquid in the flow of fluid.
19. The non-transitory machine-readable storage medium of claim 18 , wherein the operations further comprise:
identifying and tracking a plurality of gas-liquid boundaries in the conduit based on the set of images; and wherein:
the determining of the volumetric flow rate of the flow of fluids in the conduit is based on the tracking of the plurality of gas-liquid boundaries in the conduit depicted in the set of images.
20. The non-transitory machine-readable storage medium of claim 18 , wherein:
identifying and tracking a plurality of gas-liquid boundaries in the conduit based on the set of images; and wherein:
the determining of the proportion of liquid in the flow of fluid is based on the plurality of gas-liquid boundaries in the conduit depicted in the set of images.