Methods and apparatus for detecting an entity in a bodily sample

• US 10,488,644 B2
• Filed: 09/15/2016
• Issued: 11/26/2019
• Est. Priority Date: 09/17/2015
• Status: Active Grant

• Current Assignee: S.D. Sight Diagnostics Ltd
• Original Assignee: S.D. Sight Diagnostics Ltd
• Inventors: Eshel, Yochay Shlomo, Lezmy, Natalie, Gluck, Dan, Houri Yafin, Arnon, Pollak, Joseph Joel
• Primary Examiner(s): Johns, Andrew W
• Application Number:
  US15/760,782
• Publication Number:
  US 20180246313A1
• Time in Patent Office: 1,167 Days
• CPC Class Codes: G01N 2021/8887 based on image processing techniques
• CPC Class Codes: G01N 21/8851 Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges G01N21/8806 and G01N21/93 - G01N21/95692 take precedence; optical measurement of dimensions G01B11/00; optical scanning G02B26/10; image transformation G06T3/00; computerised image enhancement G06T5/00; image processing per se for flaw detection G06T7/0002
• CPC Class Codes: G02B 21/365 Control or image processing arrangements for digital or video microscopes G02B21/361, G02B21/362 take precedence
• CPC Class Codes: G02B 21/367 providing an output produced by processing a plurality of individual source images, e.g. image tiling, montage, composite images, depth sectioning, image comparison
• CPC Class Codes: G06T 2207/10056 Microscopic image
• CPC Class Codes: G06T 2207/30024 Cell structures in vitro; Tissue sections in vitro
• CPC Class Codes: G06T 2207/30101 Blood vessel; Artery; Vein; Vascular
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G06V 20/693 Acquisition
• CPC Class Codes: G06V 20/698 Matching; Classification
• CPC Class Codes: Y02A 90/10 Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation

Abstract

Apparatus and methods are described including a microscope system (11) configured to acquire one or more microscope images of a bodily sample, an output device (34), and at least one computer processor (28). The computer processor identifies, in the one or more images, at least one element as being a pathogen candidate, and extracts, from the one or more images, at least one candidate-informative feature associated with the pathogen candidate. The compute processor extracts, from the one or more images, at least one sample-informative feature that is indicative of contextual information related to the bodily sample. The computer processor classifies a likelihood of the bodily sample being infected with a pathogenic infection, by processing the candidate-informative feature in combination with the sample-informative feature, and generates an output upon the output device, in response thereto. Other applications are also described.

Claims

1. Apparatus comprising:

a microscope system configured to acquire one or more microscope images of a bodily sample selected from the group consisting of;

a blood sample, a diluted blood sample, a sample comprising predominantly red blood cells, and a diluted sample comprising predominantly red blood cells;

an output device; and

at least one computer processor configured to;

identify, in the one or more images, at least one element as being a pathogen candidate,

extract, from the one or more images, at least one candidate-informative feature associated with the pathogen candidate,

extract, from the one or more images, at least one sample-informative feature that is indicative of contextual information related to the bodily sample, the sample-informative feature being selected from the group consisting of;

an indication of a presence of Howell Jolly bodies within the bodily sample, a concentration of platelets within the bodily sample, a relationship between a number of reticulocytes associated with candidates and a number of mature red blood cells associated with candidates, and a concentration of reticulocyte bodies within the bodily sample;

determining a likelihood of the bodily sample being infected with a pathogenic infection, by processing the candidate-informative feature in combination with the sample-informative feature, and

generate an output upon the output device, in response thereto.

2. The apparatus according to claim 1, wherein:

the microscope system is configured to acquire one or more microscope images of the selected bodily sample, by acquiring one or more microscope images of a bodily sample that is stained with a stain; and

the at least one computer processor is configured to identify at least one element as being a pathogen candidate by identifying the at least one element as being a pathogen candidate by identifying that the at least one element is stained.

3. The apparatus according to claim 1, wherein the at least one computer processor is configured to process the candidate-informative feature in combination with the sample-informative feature by:

in response to the candidate-informative feature, performing a first determining step, in which a likelihood of the pathogen candidate being a pathogen is determined, and

in response to the first determining step in combination with the sample-informative feature, performing a second determining step in which a likelihood of the bodily sample containing a pathogenic infection is determined.

4. The apparatus according to claim 1, wherein the at least one computer processor is configured to process the candidate-informative feature in combination with the sample-informative feature by:

in response to the candidate-informative feature in combination with the sample-informative feature, performing a first determining step, in which a likelihood of the pathogen candidate being a pathogen is determined, and

at least partially in response to the first determining step, performing a second determining step, in which in which a likelihood of the bodily sample containing a pathogenic infection is determined.

5. The apparatus according to claim 1, wherein the at least one computer processor is configured to extract, from the one or more images, at least one candidate-informative feature associated with the pathogen candidate by extracting, from the one or more images, at least one candidate-informative feature associated with the pathogen candidate, the candidate-informative feature being a feature selected from the group consisting of:

a size of the pathogen candidate, a shape of the pathogen candidate, a motion of the pathogen candidate, an intensity of the pathogen candidate, a location of the pathogen candidate within the bodily sample, a property of a cell overlapping the pathogen candidate, a color of the pathogen candidate, a texture of the pathogen candidate, and a sharpness of a boundary of the pathogen candidate.

6. The apparatus according to claim 1, wherein the at least one computer processor is configured to extract, from the one or more images, at least one sample-informative feature that is indicative of contextual information related to the bodily sample by extracting, from the one or more images, the indication of the presence of Howell Jolly bodies within the bodily sample.

7. The apparatus according to claim 1, wherein the at least one computer processor is configured to extract, from the one or more images, at least one sample-informative feature that is indicative of contextual information related to the bodily sample by extracting, from the one or more images, the concentration of platelets within the bodily sample.

8. The apparatus according to claim 1, wherein the at least one computer processor is configured to extract, from the one or more images, at least one sample-informative feature that is indicative of contextual information related to the bodily sample by extracting, from the one or more images, the relationship between the number of reticulocytes associated with candidates and the number of mature red blood cells associated with candidates.

9. The apparatus according to claim 1, wherein the at least one computer processor is configured to extract, from the one or more images, at least one sample-informative feature that is indicative of contextual information related to the bodily sample by extracting, from the one or more images, the concentration of reticulocyte bodies within the bodily sample.

10. The apparatus according to claim 9, wherein the at least one computer processor is configured to determine the likelihood of the bodily sample being infected with the pathogenic infection by adjusting a threshold for a positive determination of a pathogenic infection, based upon the concentration of the reticulocyte bodies within the bodily sample.

11. The apparatus according to claim 1, wherein the at least one computer processor is configured to classify a pathogenic infection in the bodily sample as containing one or more given types of pathogen, by processing the candidate-informative feature in combination with the sample-informative feature.

12. The apparatus according to claim 11, wherein the at least one computer processor is configured to classify the pathogenic infection in the bodily sample as containing one or more given types of pathogen by classifying the pathogenic infection as containing one or more categories of pathogen selected from the group consisting of:

Plasmodium, a given strain of Plasmodium, Plasmodium of a given age, and Plasmodium of a given age range.

13. The apparatus according to claim 11, wherein:

the at least one computer processor is configured to extract, from the one or more images, at least one sample-informative feature that is indicative of contextual information related to the bodily sample by extracting, from the one or more images, the relationship between the number of reticulocytes associated with candidates and the number of mature red blood cells associated with candidates; and

the at least one computer processor is configured to classify the pathogenic infection in the bodily sample as containing one or more given types of pathogen by classifying the pathogenic infection in the bodily sample as containing the given type of pathogen, at least partially based upon the relationship between the number of reticulocytes associated with candidates and the number of mature red blood cells associated with candidates.

14. A method comprising:

acquiring one or more microscope images of a bodily sample, using a microscope, the bodily sample being selected from the group consisting of;

a blood sample, a diluted blood sample, a sample comprising predominantly red blood cells, and a diluted sample comprising predominantly red blood cells;

using at least one computer processor;

in the one or more images, identifying at least one element as being a pathogen candidate;

extracting, from the one or more images, at least one candidate-informative feature associated with the pathogen candidate;

extracting, from the one or more images, at least one sample-informative feature that is indicative of contextual information related to the bodily sample, the sample-informative feature being selected from the group consisting of;

an indication of a presence of Howell Jolly bodies within the bodily sample, a concentration of platelets within the bodily sample, a relationship between a number of reticulocytes associated with candidates and a number of mature red blood cells associated with candidates, and a concentration of reticulocyte bodies within the bodily sample;

determining a likelihood of the bodily sample being infected with a pathogenic infection, by processing the candidate-informative feature in combination with the sample-informative feature; and

generating an output, in response thereto.

15. The method according to claim 14, wherein:

acquiring one or more microscope images of the selected bodily sample comprises acquiring one or more microscope images of a bodily sample that is stained with a stain; and

identifying at least one element as being a pathogen candidate comprises identifying the at least one element as being a pathogen candidate by identifying that the at least one element is stained.

16. The method according to claim 14, wherein processing the candidate-informative feature in combination with the sample-informative feature comprises:

in response to the candidate-informative feature, performing a first determining step, in which a likelihood of the pathogen candidate being a pathogen is determined; and

in response to the first determining step in combination with the sample-informative feature, performing a second determining step in which a likelihood of the bodily sample containing a pathogenic infection is determined.

17. The method according to claim 14, wherein processing the candidate-informative feature in combination with the sample-informative feature comprises:

in response to the candidate-informative feature in combination with the sample-informative feature, performing a first determining step, in which a likelihood of the pathogen candidate being a pathogen is determined; and

at least partially in response to the first determining step, performing a second determining step in which in which a likelihood of the bodily sample containing a pathogenic infection is determined.

18. The method according to claim 14, wherein extracting, from the one or more images, at least one candidate-informative feature associated with the pathogen candidate comprises extracting, from the one or more images, at least one candidate-informative feature associated with the pathogen candidate, the candidate-informative feature being a feature selected from the group consisting of:

a size of the pathogen candidate, a shape of the pathogen candidate, a motion of the pathogen candidate, an intensity of the pathogen candidate, a location of the pathogen candidate within the bodily sample, a property of a cell overlapping the pathogen candidate, a color of the pathogen candidate, a texture of the pathogen candidate, and a sharpness of a boundary of the pathogen candidate.

19. The method according to claim 14, wherein extracting, from the one or more images, at least one sample-informative feature that is indicative of contextual information related to the bodily sample comprises extracting, from the one or more images, the indication of the presence of Howell Jolly bodies within the bodily sample.

20. The method according to claim 14, wherein extracting, from the one or more images, at least one sample-informative feature that is indicative of contextual information related to the bodily sample comprises extracting, from the one or more images, the concentration of platelets within the bodily sample.

21. The method according to claim 14, wherein extracting, from the one or more images, at least one sample-informative feature that is indicative of contextual information related to the bodily sample comprises extracting, from the one or more images, the relationship between the number of reticulocytes associated with candidates and the number of mature red blood cells associated with candidates.

22. The method according to claim 14, wherein extracting, from the one or more images, at least one sample-informative feature that is indicative of contextual information related to the bodily sample comprises extracting, from the one or more images, the concentration of reticulocyte bodies within the bodily sample.

23. The method according to claim 22, wherein determining the likelihood of the bodily sample being infected with the pathogenic infection comprises adjusting a threshold for a positive determination of a pathogenic infection, based upon the concentration of the reticulocyte bodies within the bodily sample.

24. The method according to claim 14, further comprising classifying a pathogenic infection in the bodily sample as containing one or more given types of pathogen, by processing the candidate-informative feature in combination with the sample-informative feature.

25. The method according to claim 24, wherein classifying the pathogenic infection in the bodily sample as containing the one or more given types of pathogenic infection comprises classifying the pathogenic infection as containing one or more categories of pathogen selected from the group consisting of:

Plasmodium, a given strain of Plasmodium, Plasmodium of a given age, and Plasmodium of a given age range.

26. The method according to claim 24, wherein

extracting, from the one or more images, at least one sample-informative feature that is indicative of contextual information related to the bodily sample comprises extracting, from the one or more images, the relationship between the number of reticulocytes associated with candidates and the number of mature red blood cells associated with candidates, and

classifying the pathogenic infection in the bodily sample as containing the given type of pathogen comprises classifying the pathogenic infection in the bodily sample as containing the given type of pathogen, at least partially based upon the relationship between the number of reticulocytes associated with candidates and the number of mature red blood cells associated with candidates.

27. A computer software product, for use with a bodily sample, an output device, and a microscope system configured to acquire one or more microscope images of a bodily sample selected from the group consisting of:

a blood sample, a diluted blood sample, a sample comprising predominantly red blood cells, and a diluted sample comprising predominantly red blood cells, the computer software product comprising a non-transitory computer-readable medium in which program instructions are stored, which instructions, when read by a computer cause the computer to perform the steps of;

in the one or more images, identifying at least one element as being a pathogen candidate;

extracting, from the one or more images, at least one candidate-informative feature associated with the pathogen candidate;

extracting, from the one or more images, at least one sample-informative feature that is indicative of contextual information related to the bodily sample the sample-informative feature being selected from the group consisting of;

an indication of a presence of Howell Jolly bodies within the bodily sample, a concentration of platelets within the bodily sample, a relationship between a number of reticulocytes associated with candidates and a number of mature red blood cells associated with candidates, and a concentration of reticulocyte bodies within the bodily sample;

determining a likelihood of the bodily sample being infected with a pathogenic infection, by processing the candidate-informative feature in combination with the sample-informative feature; and

generating an output upon the output device, in response thereto.