Method and apparatus for automated platelet identification within a whole blood sample from microscopy images
A method and apparatus for identifying platelets within a whole blood sample. The method includes the steps of: a) adding at least one colorant to the whole blood sample, which colorant is operable to tag platelets; b) disposing the blood sample into a chamber defined by at least one transparent panel; c) imaging at least a portion of the sample quiescently residing within the chamber to create one or more images; and d) identifying one or more platelets within the sample using an analyzer adapted to identify the platelets based on quantitatively determinable features within the image using a analyzer, which quantitatively determinable features include intensity differences.
1. A method for identifying platelets within a whole blood sample, comprising:
adding at least one colorant to the whole blood sample, which colorant is operable to tag platelets;
disposing the blood sample into a chamber defined by at least one transparent panel;
imaging at least a portion of the sample quiescently residing within the chamber to create at least one image comprised of incremental units, each unit having an intensity value; and
identifying one or more platelet candidates within the image based on per unit intensity value differences in local regions within the image;
identifying at least one platelet from the identified platelet candidates using an analyzer adapted to identify the platelet based on quantitatively determinable features associated with the per unit intensity values, and based on a directional contrast of per unit intensity values extending outwardly from a peak intensity.
2. The method of claim 1 , wherein the step of identifying one or more platelet candidates includes applying a global threshold to the intensity value differences within the image and eliminating those platelet candidates having an intensity value difference below the threshold.
3. The method of claim 1 , further comprising identifying anomaly image portions and estimating the number of platelets in the anomaly image portions.
4. The method of claim 1 , wherein the step of identifying one or more platelet candidates includes accounting for an image intensity of plasma.
5. The method of claim 1 , further comprising determining a value of an incremental decrease in per unit intensity value within the image in a direction extending away from the peak intensity.
6. The method of claim 5 , further comprising determining a circumferential uniformity of the incremental decrease in per unit intensity value.
7. The method of claim 5 , further comprising determining a Gaussian distribution of the incremental decrease in per unit intensity value.
8. The method of claim 1 , wherein the step of identifying one or more platelet candidates includes evaluating the image to determine a presence of one or more platelet clusters within the sample.
9. The method of claim 1 , wherein the step of identifying at least one platelet from the identified platelet candidates includes analyzing one or more of the platelet candidates using a rule based classifier.
10. The method of claim 1 , wherein the intensity values are representative of emitted fluorescent light intensity.
11. An apparatus for identifying platelets within a whole blood sample, comprising:
an analysis cartridge having an analysis chamber with a pair of planar members, at least one of which is transparent, which cartridge is operable to add at least one colorant to the whole blood sample, which colorant is operable to tag platelets, and which chamber is operable to hold the sample quiescently between the planar members; and
an analysis device that is operable to image at least a portion of the sample quiescently residing within the chamber to create at least one image comprised of incremental units, each unit having an intensity value, and operable to identify one or more platelet candidates within the image based on per unit intensity value differences in local regions within the image, and operable to identify at least one platelet from the identified platelet candidates based on quantitatively determinable features associated with the per unit intensity values, and based on a directional contrast of per unit intensity values extending outwardly from a peak intensity.
12. The apparatus of claim 11 , wherein the analysis device is adapted to apply a global threshold to the intensity value differences within the image and eliminating those platelet candidates having an intensity value difference below the threshold.
13. The apparatus of claim 11 , wherein the analysis device is adapted to identify anomaly image portions and estimate the number of platelets in the anomaly image portions.
14. The apparatus of claim 11 , wherein the analysis device is adapted to account for an image intensity of plasma.
15. The apparatus of claim 11 , wherein the analysis device is adapted to determine a value of an incremental decrease in per unit intensity value within the image in a direction extending away from the peak intensity.
16. The apparatus of claim 15 , wherein the analysis device is adapted to determine a circumferential uniformity of the incremental decrease in per unit intensity value.
17. The apparatus of claim 15 , wherein the analysis device is adapted to determine a Gaussian distribution of the incremental decrease in per unit intensity value.
18. The apparatus of claim 11 , wherein the analysis device is adapted to evaluate the image to determine a presence of one or more platelet clusters within the sample.
19. The apparatus of claim 11 , wherein the analysis device is adapted to analyze one or more of the platelet candidates using a rule based classifier.
20. The apparatus of claim 11 , wherein the intensity values are representative of emitted fluorescent light intensity.