Systems, devices, and methods for detection of malaria

• US 9,524,417 B2
• Filed: 06/18/2014
• Issued: 12/20/2016
• Est. Priority Date: 02/10/2010
• Status: Expired due to Fees

• Current Assignee: Tokitae LLC (Intellectual Ventures LLC)
• Original Assignee: Tokitae LLC (Intellectual Ventures LLC)
• Inventors: Behrend, Matthew R., Hegg, Michael C., Horning, Matthew P., Wilson, Benjamin K.
• Primary Examiner(s): Lu, Tom Y
• Application Number:
  US14/307,724
• Publication Number:
  US 20140294280A1
• Time in Patent Office: 916 Days
• US Class Current: 1/1
• CPC Class Codes: A61B 2562/0238 Optical sensor arrangements for performing transmission measurements on body tissue
• CPC Class Codes: A61B 3/1233 for measuring blood flow, e.g. at the retina
• CPC Class Codes: A61B 5/0059 using light, e.g. diagnosis by transillumination, diascopy, fluorescence A61B5/0093, A61B5/1455, A61B5/02416 and A61B5/0261 take precedence
• CPC Class Codes: A61B 5/0062 Arrangements for scanning
• CPC Class Codes: A61B 5/05 Detecting, measuring or recording for diagnosis by means of electric currents or magnetic fields; Measuring using microwaves or radio waves impedance plethysmography A61B5/0295; measuring movement of the entire body or parts thereof A61B5/11; detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof A61B5/24
• CPC Class Codes: A61B 5/14546 for measuring analytes not otherwise provided for, e.g. ions, cytochromes
• CPC Class Codes: A61B 8/06 Measuring blood flow measuring volume flow in general G01F, e.g. G01F1/66, G01F1/72; measuring speed of fluids in general G01P5/00
• CPC Class Codes: G01N 21/49 within a body or fluid
• CPC Class Codes: G01N 2333/445 Plasmodium
• CPC Class Codes: G06T 2207/20076 Probabilistic image processing
• CPC Class Codes: G06T 2207/30024 Cell structures in vitro; Tissue sections in vitro
• CPC Class Codes: G06T 7/0014 using an image reference approach
• CPC Class Codes: G06V 20/698 Matching; Classification
• CPC Class Codes: Y02A 50/30 Against vector-borne diseases, e.g. mosquito-borne, fly-borne, tick-borne or waterborne diseases whose impact is exacerbated by climate change

Abstract

Systems, devices, and methods are described for providing a monitor or treatment device configured to, for example, detect hemozoin, as well as to monitor or treat a malarial infection.

Claims

1. A system, comprising:

a resolution modification circuit configured to modify a pixel count of at least one micrograph of a biological sample acquired at one or more fields of view and to generate at least a first modified micrograph;

a filter-kernel generation circuit configured to generate a kernel for filtering a plurality of pixels forming the first modified micrograph based on a filtering characteristic, and to generate at least a first significance image representative of the at least one modified micrograph; and

an object identification circuit configured to identify groups of pixels in the first significance image indicative of one or more objects imaged in the at least one micrograph, and to generate one or more connected components of a graph representative of groups of pixels indicative of the one or more objects imaged in the at least one micrograph,

wherein the object identification circuit is configured to determine a probability that the biological sample is infected with malaria, and to determine a confidence level associated with the determined probability that the biological sample is infected with malaria.

2. The system of claim 1, further comprising:

a circuit configured to compare the generated one or more connected components of the graph to reference object information stored in one or more data structures, and to generate a response based on the comparison of the generated one or more connected components of the graph to the reference object information.

3. The system of claim 2, wherein the circuit configured to compare the generated one or more connected components of the graph includes one or more data structures having reference object information stored thereon, the reference object information including at least one of erythrocyte graph information, malaria-infected erythrocyte graph information, or hemozoin graph information.

4. The system of claim 2, wherein the circuit configured to compare the generated one or more connected components of the graph includes a circuit configured to generate a response including at least one of object identification information, a disease state, a parasitemia level, an erythrocyte count, a ratio of malaria-infected erythrocytes to total erythrocyte present in the at least one micrograph, or probability and confidence level information associated with an identified object.

5. The system of claim 1, wherein the object identification circuit includes a circuit configured to identify groups of pixels in the first significance image indicative of at least one of a hemozoin nanoparticle, a malaria-infected erythrocyte, or a non-infected erythrocyte in the at least one micrograph.

6. The system according to claim 1, wherein the resolution modification circuit includes one or more computing devices configured to modify a micrograph pixel resolution.

7. The system according to claim 1, wherein the resolution modification circuit includes at least one computing device, and one or more data structures operable to generate and store a threshold comparison value, and to generate and store a kernel for filtering a plurality of pixels forming a micrograph based on the threshold comparison value.

8. A system comprising:

a resolution modification circuit configured to modify a pixel count of at least one micrograph of a biological sample acquired at one or more fields of view and to generate at least a first modified micrograph;

a filter-kernel generation circuit configured to generate a kernel for filtering a plurality of pixels forming the first modified micrograph based on a filtering characteristic, and to generate at least a first significance image representative of the at least one modified micrograph;

an object identification circuit configured to identify groups of pixels in the first significance image indicative of one or more objects imaged in the at least one micrograph, and to generate one or more connected components of a graph representative of groups of pixels indicative of the one or more objects imaged in the at least one micrograph; and

a spatial frequency generation circuit configured to

determine a spatial frequency spectrum of at least a first subset of pixels of the at least one micrograph,

compare the spatial frequency spectrum of the first subset of pixels to reference spatial frequency spectrum information, and

generate a response based on the comparison of the spatial frequency spectrum of the first subset of pixels to the reference spatial frequency spectrum information.

9. The system of claim 8, wherein the spatial frequency generation circuit includes one or more data structures having at least one of reference erythrocyte spatial frequency spectrum information, reference malaria-infected erythrocyte spatial frequency spectrum information, or reference hemozoin spatial frequency spectrum information.

10. The system of claim 8, wherein the spatial frequency generation circuit is further configured to partition the spatial frequency spectrum of the at least first subset of pixels into one or more information subsets using at least one of a Clustering protocol or a Learning protocol.

11. The system of claim 8, wherein the spatial frequency generation circuit is further configured to partition the spatial frequency spectrum of the at least first subset of pixels into one or more information subsets using at least one of a Fuzzy C-Means Clustering protocol, a Graph-Theoretic protocol, a Hierarchical Clustering protocol, a K-Means Clustering protocol, a Locality-Sensitive Hashing protocol, a Mixture of Gaussians protocol, a Model-Based Clustering protocol, a Cluster-Weighted Modeling protocol, an Expectations-Maximization protocol, a Principal Components Analysis protocol, or a Partitioning protocol.

12. A method, comprising:

modifying a resolution of one or more micrographs of a biological sample acquired at one or more fields of view and generating at least a first modified micrograph;

generating a first filtered micrograph by filtering the at least first modified micrograph based on a filtering protocol; and

determining a disease state by identifying objects of the biological sample in the filtered micrograph, wherein determining the disease state includes determining a probability that the biological sample is infected with malaria.

13. The method of claim 12, wherein modifying the micrograph resolution includes performing a resizing operation on the micrograph.

14. The method of claim 12, wherein modifying the micrograph resolution includes performing a pixel binning protocol on the micrograph.

15. The method of claim 12, wherein modifying the micrograph resolution includes performing an optimization protocol that resizes one or more pixels in the micrograph based on an object detection protocol.

16. The method of claim 12, wherein generating the first filtered micrograph includes convolving a filter kernel with one or more pixel parameters associated with the first modified micrograph to generate a filtered micrograph.

17. The method of claim 12, wherein generating the first filtered micrograph includes determining whether an intensity of one or more pixels of the at least first modified micrograph satisfies a threshold value.

18. The method of claim 12, wherein generating the first filtered micrograph includes convolving at least a portion of the micrograph with a filter kernel.

19. The method of claim 12, wherein generating the first filtered micrograph includes convolving a filter kernel with the one or more pixel parameters and determining connected components of a graph for a plurality of pixels based on a result of the convolve.

20. The method of claim 12, wherein generating the first filtered micrograph includes convolving a filter kernel with the one or more pixel parameters and generating a probability-value image associated with the first filtered micrograph.

21. The method of claim 20, wherein determining the disease state includes comparing the probability-value to threshold criteria to identify objects in the micrograph.

22. The method of claim 20, wherein determining the disease state includes determining connected components of a graph representative of the object content in the first modified micrograph based on the comparing of a probability-value image to threshold criteria.

23. The method of claim 12, wherein determining the disease state further includes determining a confidence level associated with a determined probability that the biological sample is infected with malaria.

24. The method of claim 12, wherein determining the disease state further includes applying a Dulmage-Mendelsohn decomposition protocol to at least a portion of the micrograph to identify connected components.

25. The method of claim 12, wherein generating the first filtered micrograph includes partitioning the at least one micrograph into the one or more pixel subsets using at least one of a Clustering protocol or a Learning protocol.

26. The method of claim 12, wherein generating the first filtered micrograph includes partitioning the at least one micrograph into the one or more pixel subsets using at least one of a Fuzzy C-Means Clustering protocol, a Graph-Theoretic protocol, a Hierarchical Clustering protocol, a K-Means Clustering protocol, a Locality-Sensitive Hashing protocol, a Mixture of Gaussians protocol, a Model-Based Clustering protocol, a Cluster-Weighted Modeling protocol, an Expectations-Maximization protocol, a Principal Components Analysis protocol, or a Partitioning protocol.

27. The method of claim 12, further comprising:

acquiring one or more micrographs of a biological sample at one or more focal depths.

28. The method of claim 12, further comprising:

causing the storage of the acquired one or more micrographs of the biological sample on to a physical data structure.