Granted Patent B2

US 12,383,155 · App. 18/633,176 · Granted Aug 12, 2025

Inventors: Carlos Castro-Gonzalez (Cambridge, MA); Ian Butterworth (Somerville, MA); Aurelien Bourquard (Cambridge, MA); Alvaro Sanchez Ferro (Madrid, ES); Jason Tucker-Schwartz (Melrose, MA); Alberto Pablo Trinidad (Madrid, ES); Maria J. Ledesma Carbayo (Madrid, ES); Tom Vettenburg (Dundee, GB)

Assignee: Universidad Politecnica De Madrid

A61B5/0261A61B5/14546A61B5/1455A61B5/489A61B5/6826A61B5/7203A61B5/7267G06T7/0014G06V40/10A61B2576/02G06T2207/10016G06T2207/10152G06T2207/20081G06T2207/20084G06T2207/30101G06V40/14G06V40/15Y02A90/10

Abstract

Claims (53)

1. A system for non-invasive in vivo hematological measurement, the system comprising:

a platform to receive a body portion of a user during use, the body portion having capillary structure;

an imaging device coupled to the platform and to acquire a time-lapse series of images of the capillary structure, wherein each image resolves multiple capillaries; and

an imaging objective coupled to the imaging device, wherein the imaging device is configured to provide the time-lapse series of images of the capillary structure to a controller; and

the controller that is adapted to:

process the time-lapse series of images to perform the hematological measurement for one or more capillaries of the multiple capillaries, wherein the hematological measurement comprises:

detecting passage, along a length of a capillary of the one or more capillaries, of a cell that produces a contrast in optical absorption relative to red blood cells in the capillary in the time-lapse series of images; and

generating an event count for the capillary based on detected cellular events for the capillary, wherein a cellular event of the detected cellular events is associated with the passage of the cell along the length of the capillary.

2. The system of claim 1 , wherein the cell is a circulating tumor cell or a white blood cell (WBC).

3. The system of claim 1 , wherein the cell is a WBC and the controller is further adapted to:

generate the event count based on the detected cellular events in the one or more capillaries, wherein each cellular event of the detected cellular events is associated with passage of a type of WBC in the capillary of the one or more capillaries;

compare the event count to an event count threshold associated with a minimum number of cellular events for classification of the user to a first user type, wherein the one or more capillaries comprises those capillaries having a diameter selected to be approximately equal to or less than a diameter of any WBC of the one or more types of WBCs; and

classify, based on the event count comparison to the event count threshold, the user to a first user type of a set of user types, at least one user type of the set of user types associated with a condition of neutropenia.

4. The system of claim 3 , wherein the controller is further adapted to detect each cellular event of the cellular events by detecting an optical absorption gap during passage of the one or more types of WBCs in the capillary of the one or more capillaries.

5. The system of claim 3 , wherein the controller is further adapted to:

detect each cellular event of the detected cellular events based on the contrast in absorption relative to red blood cells.

6. The system of claim 3 , further comprising an illumination source ( 2320 ) to illuminate the capillary structure with blue light.

7. The system of claim 3 , wherein the diameter is from 10 microns to 20 microns.

8. The system of claim 3 , wherein the controller is further adapted to apply the time-lapse series of images to a neural network to identify the one or more capillaries.

9. The system of claim 3 , wherein the controller is further adapted to:

receive a set of training images associated with capillary beds in body portions of a set of training users; and

generate, via supervised learning, the event count threshold based on the set of training images.

10. The system of claim 3 , wherein the controller is further adapted to:

generate a bounding box for each detected capillary in each image of the time-lapse series of images;

generate a confidence value associated with a likelihood that detection of the detected capillary corresponds to a capillary and not another structure/artifact; and

include the detected capillary in the one or more capillaries if the confidence value meets or exceed a predetermined confidence threshold.

11. The system of claim 3 , wherein the controller is further adapted to:

apply a band-pass filter in the discrete Fourier domain, the band-pass filter having a low-frequency band-pass parameter and a high-frequency band-pass parameter fitting a range of expected cellular event sizes.

12. The system of claim 3 , wherein the controller is further adapted to:

compile profiles extracted from the time-lapse series of images into at least one spatiotemporal profile to analyze WBC events for a capillary of the one or more capillaries.

13. The system of claim 12 , wherein the controller is further adapted to determine a flow speed of WBCs from the at least one spatiotemporal profile.

14. The system of claim 12 , wherein the controller is further adapted to determine a total number of WBC events per microliter from the at least one spatiotemporal profile.

15. A method for non-invasive in vivo hematological measurement, the method comprising:

receiving on a platform a body portion of a user, the body portion having capillary structure;

acquiring, with an imaging device comprising an imaging objective, a time-lapse series of images of the capillary structure, wherein each image resolves multiple capillaries;

providing the time-lapse series of images of the capillary structure to a controller, wherein the controller is communicatively coupled to the imaging device; and

processing, by the controller, the time-lapse series of images to perform the hematological measurement for one or more capillaries of the multiple capillaries, wherein the hematological measurement comprises:

detecting passage, along a length of a capillary of the one or more capillaries, of a cell that produces a contrast in optical absorption relative to red blood cells in the capillary in the time-lapse series of images; and

generating, by the controller, an event count for the capillary based on detected cellular events for the capillary, wherein a cellular event of the detected cellular events is associated with the passage of the cell along the length of the capillary.

16. The method of claim 15 , wherein the cell is a circulating tumor cell or a white blood cell (WBC).

17. The method of claim 15 , further comprising:

generating, by the controller, the event count based on the detected cellular events in the one or more capillaries, wherein each cellular event of the detected cellular events is associated with passage of a type of WBC in the capillary of the one or more capillaries;

comparing, by the controller, the event count to an event count threshold associated with a minimum number of cellular events for classification of the user to a first user type, wherein the one or more capillaries comprises those capillaries having a diameter selected to be approximately equal to or less than a diameter of any WBC of the one or more types of WBCs; and

classifying, by the controller, based on the event count comparison to the event count threshold, the user to a first user type of a set of user types, at least one user type of the set of user types associated with a condition of neutropenia.

18. The method of claim 17 , further comprising:

detecting, by the controller, each cellular event of the detected cellular events based on the contrast in absorption relative to red blood cells.

19. The method of claim 17 , further comprising:

receiving, by the controller, a set of training images associated with capillary beds in body portions of a set of training users; and

generating, via supervised learning, the event count threshold based on the set of training images.

20. The method of claim 17 , further comprising:

generating, by the controller, a bounding box for each detected capillary in each image of the time-lapse series of images;

generating, by the controller, a confidence value associated with a likelihood that detection of the detected capillary corresponds to a capillary and not another structure/artifact; and

including, by the controller, the detected capillary in the one or more capillaries if the confidence value meets or exceed a predetermined confidence threshold.

Assignments (3)

Continuity (4)

References Cited (233)