Methods and systems for assessing histological stains
The present disclosure includes methods of assessing a histologically stained specimen based on a determined color signature of a region of interest of the specimen. Such assessments may be performed for a variety of purposes including but not limited to assessing the quality of the histological stain, as part of identifying one or more biologically relevant features of the image, as part of differentiating one feature of the image from other features of the image, identifying an anomalous area of the stained specimen, classifying cells of the specimen, etc. Also provided are systems configured for performing the disclosed methods and computer readable medium storing instructions for performing steps of the disclosed methods.
1. A system for assessing a histologically stained specimen, the system comprising:
a) a microscope;
b) a digital color camera attached to the microscope and configured to obtain a digital color image of the specimen;
c) a library comprising a plurality of reference color signatures specific to biological features of histologically stained reference specimens;
d) image processing circuitry configured to:
i) define on the digital color image a region of interest (ROI) based on a biological feature of the specimen;
ii) separate the digital color image into individual color channels; and
iii) determine a color signature for the ROI, wherein the color signature comprises quantification of one or more color parameters over the ROI for one or more of the individual color channels, wherein the color signature comprises a color coefficient calculated by determining the ratio of the mean intensity value for a first color channel to the mean intensity value for a second color channel; and
iv) compare the determined color signature to one or more reference color signatures of the plurality of reference color signatures of the library to assess the histologically stained specimen.
2. The system of claim 1 , wherein the system comprises a single memory connected to the image processing circuitry that stores the library and is configured to receive the digital color image.
3. The system of claim 1 , wherein the system comprises a first memory connected to the image processing circuitry that stores the library and a second memory connected to the image processing circuitry configured to receive the digital color image.
4. The system of claim 1 , wherein the system further comprises a signal system to report the result of the assessment.
5. The system of claim 1 , wherein the one or more color parameters comprises the mean intensity of an individual color channel.
6. The system of claim 1 , wherein the color signature further comprises a second color coefficient calculated by determining the ratio of the mean intensity value for a third color channel to the mean intensity for the first or the second color channel.
7. The system of claim 6 , wherein the color signature further comprises a third color coefficient calculated by determining the ratio of the first color coefficient to the second color coefficient.
8. The system of claim 1 , wherein the plurality of reference color signatures are derived from reference histologically stained specimens.
9. The system of claim 1 , wherein the system assesses whether the determined color signature is within a predetermined range and, when within the range, the specimen is released for further processing.
10. The system of claim 1 , wherein the system assesses whether the determined color signature is outside of a predetermined range and, when outside the range, the specimen is held to prevent further processing.
11. The system of claim 1 , wherein the system assesses histological stain quality.
12. The system of claim 1 , wherein the image processing circuitry is further configured to identify the ROI based on the assessment.
13. The system of claim 12 , wherein the image processing circuitry is further configured to differentiate the ROI from other features of the image based on the assessment.
14. A system for assessing the quality of a histologically stained specimen, the system comprising:
a) a microscope;
b) a digital color camera attached to the microscope and configured to obtain a digital color image of the specimen;
c) a library comprising a plurality of reference quality color signatures specific to biological features of histologically stained reference specimens;
d) image processing circuitry configured to:
i) define on the digital color image a region of interest (ROI) based on a biological feature of the specimen, wherein the color signature comprises a cytoplasmic stain color vector (CSCV);
ii) determine a color signature for the ROI, wherein the color signature comprises quantification of one or more color parameters over the ROI; and
iii) compare the determined color signature to one or more reference quality color signatures of the plurality of reference quality color signatures of the library to assess the quality of the histologically stained specimen.
15. The system of claim 14 , wherein the system comprises a single memory connected to the image processing circuitry that stores the library and is configured to receive the digital color image.
16. The system of claim 14 , wherein the system comprises a first memory connected to the image processing circuitry that stores the library and a second memory connected to the image processing circuitry configured to receive the digital color image.
17. The system of claim 14 , wherein the system further comprises a signal system to report the result of the assessment.
18. The system of claim 14 , wherein the image processing circuitry is further configured to separate the digital color image into individual color channels.
19. The system of claim 14 , wherein the one or more color parameters comprises optical density.
20. The system of claim 14 , wherein the one or more color parameters comprises hue.
21. The system of claim 14 , wherein the one or more color parameters comprises lightness.
22. The system of claim 14 , wherein the one or more color parameters comprises saturation.
23. The system of claim 14 , wherein the one or more color parameters comprises the mean intensity of an individual color channel.
24. The system of claim 14 , wherein the color signature comprises two or more color parameters selected from the group consisting of: optical density, hue, lightness, saturation and the mean intensity of an individual color channel.
25. The system of claim 14 , wherein the color signature comprises three or more color parameters selected from the group consisting of: optical density, hue, lightness, saturation and the mean intensity of an individual color channel.
26. The system of claim 14 , wherein the CSCV is determined based on red, green, and blue color channels and is calculated according to the equation:
CSCV
rgb
=
(
Mean
red
)
2
+
(
Mean
green
)
2
+
(
Mean
blue
)
2
,
wherein “Mean” represents the mean intensity value for each color channel over a ROI comprising the cytoplasm of a cell or a portion thereof.
27. The system of claim 26 , wherein the CSCV comprises one or more directional components calculated according to the equation:
β CSCV rgb =cos −1 (Mean blue /CSCV rgb )
or the equation:
θ CSCV rgb =(cos −1 (Mean red ))√{square root over ((Mean red ) 2 +(Mean green ) 2 )}
or a combination thereof.
28. The system of claim 14 , wherein the cytoplasmic stain color vector is determined based on hue, saturation and luminosity values and is calculated according to the equation:
CSCV
hsl
=
(
Mean
hue
)
2
+
(
Mean
saturation
)
2
+
(
Mean
luminosity
)
2
,
wherein “Mean” represents the mean hue, saturation and luminosity values over a ROI comprising the cytoplasm of a cell or a portion thereof.
29. The method of claim 28 , wherein the CSCV further comprises one or more directional components calculated according to the equation:
β CSCV hsl =cos −1 (Mean lightness /CSCV hsl )
or the equation:
θ CSCV hsl =(cos −1 (Mean hue ))√{square root over ((Mean hue ) 2 +(Mean saturation ) 2 )}
or a combination thereof.
30. The system of claim 14 , wherein the color signature further comprises a nuclear stain color vector (NSCV).
31. The system of claim 30 , wherein the nuclear stain color vector is determined based on red, green and blue color channels and is calculated according to the equation:
NSCV
rgb
=
(
Mean
red
)
2
+
(
Mean
green
)
2
+
(
Mean
blue
)
2
,
wherein “Mean” represents the mean intensity value for each color channel over a ROI comprising the nucleus of a cell or a portion thereof.
32. The method of claim 31 , wherein the NSCV comprises one or more directional components calculated according to the equation:
β NSCV rgb =cos −1 (Mean blue /NSCV rgb )
or the equation:
θ NSCV rgb =(cos −1 (Mean red ))√{square root over ((Mean red ) 2 +(Mean green ) 2 )}
or a combination thereof.
33. The system of claim 30 , wherein the nuclear stain color vector is determined based on hue, saturation and luminosity values and is calculated according to the equation:
NSCV
hsl
=
(
Mean
hue
)
2
+
(
Mean
saturation
)
2
+
(
Mean
luminosity
)
2
,
wherein “Mean” represents the mean hue, saturation and luminosity values over a ROI comprising the nucleus of a cell or a portion thereof.
34. The method of claim 33 , wherein the NSCV further comprises one or more directional components calculated according to the equation:
β NSCV hsl =cos −1 (Mean lightness /NSCV hsl )
or the equation:
θ NSCV hsl =(cos −1 (Mean hue ))√{square root over ((Mean hue ) 2 +(Mean saturation ) 2 )}
or a combination thereof.
35. The system of claim 14 , wherein the color signature further comprises the ratio of the cytoplasmic stain color vector to a nuclear stain color vector.
36. The system of claim 14 , wherein the plurality of reference quality color signatures are derived from reference histologically stained specimens of known quality.
37. The system of claim 14 , wherein the system assesses whether the determined color signature is within a predetermined range and, when within the range, the specimen is identified as adequate quality and released for further processing.
38. The system of claim 14 , wherein the system assesses whether the determined color signature is outside of a predetermined range and, when outside the range, the specimen is identified as inadequate quality and held to prevent further processing.
39. A system for assessing a histologically stained specimen, the system comprising:
a) a microscope;
b) a digital color camera attached to the microscope and configured to obtain a digital color image of the specimen;
c) a library comprising a plurality of reference color signatures specific to biological features of histologically stained reference specimens;
d) image processing circuitry configured to:
i) define on the digital color image a region of interest (ROI) based on a biological feature of the specimen;
ii) separate the digital color image into individual color channels; and
iii) determine a color signature for the ROI, wherein the color signature comprises quantification of one or more color parameters over the ROI for one or more of the individual color channels;
iv) compare the determined color signature to one or more reference color signatures of the plurality of reference color signatures of the library to assess the histologically stained specimen; and
v) release the specimen for further processing when the determined color signature is within a predetermined range, or hold the specimen from further processing when the determined color signature is outside the predetermined range.
40. The system of claim 39 , wherein the system comprises a single memory connected to the image processing circuitry that stores the library and is configured to receive the digital color image.
41. The system of claim 39 , wherein the system comprises a first memory connected to the image processing circuitry that stores the library and a second memory connected to the image processing circuitry configured to receive the digital color image.
42. The system of claim 39 , wherein the system further comprises a signal system to report the result of the assessment.
43. The system of claim 39 , wherein the one or more color parameters comprises the mean intensity of an individual color channel.
44. The system of claim 39 , wherein the color signature comprises a color coefficient calculated by determining the ratio of the mean intensity value for a first color channel to the mean intensity value for a second color channel.
45. The system of claim 39 , wherein the color signature comprises a first color coefficient calculated by determining the ratio of the mean intensity value for a first color channel to the mean intensity value for a second color channel and a second color coefficient calculated by determining the ratio of the mean intensity value for a third color channel to the mean intensity for the first or the second color channel.
46. The system of claim 45 , wherein the color signature further comprises a third color coefficient calculated by determining the ratio of the first color coefficient to the second color coefficient.
47. The system of claim 39 , wherein the plurality of reference color signatures are derived from reference histologically stained specimens.
48. The system of claim 39 , wherein the system assesses histological stain quality.
49. The system of claim 39 , wherein the image processing circuitry is further configured to identify the ROI based on the assessment.
50. The system of claim 49 , wherein the image processing circuitry is further configured to differentiate the ROI from other features of the image based on the assessment.
51. A system for assessing the quality of a histologically stained specimen, the system comprising:
a) a microscope;
b) a digital color camera attached to the microscope and configured to obtain a digital color image of the specimen;
c) a library comprising a plurality of reference quality color signatures specific to biological features of histologically stained reference specimens;
d) image processing circuitry configured to:
i) define on the digital color image a region of interest (ROI) based on a biological feature of the specimen;
ii) determine a color signature for the ROI, wherein the color signature comprises quantification of one or more color parameters over the ROI; and
iii) compare the determined color signature to one or more reference quality color signatures of the plurality of reference quality color signatures of the library to assess the quality of the histologically stained specimen; and
iv) release the specimen for further processing when the determined color signature is within a predetermined range, or hold the specimen from further processing when the determined color signature is outside the predetermined range.
52. The system of claim 51 , wherein the system comprises a single memory connected to the image processing circuitry that stores the library and is configured to receive the digital color image.
53. The system of claim 51 , wherein the system comprises a first memory connected to the image processing circuitry that stores the library and a second memory connected to the image processing circuitry configured to receive the digital color image.
54. The system of claim 51 , wherein the system further comprises a signal system to report the result of the assessment.
55. The system of claim 51 , wherein the image processing circuitry is further configured to separate the digital color image into individual color channels.
56. The system of claim 51 , wherein the one or more color parameters comprises optical density.
57. The system of claim 51 , wherein the one or more color parameters comprises hue.
58. The system of claim 51 , wherein the one or more color parameters comprises lightness.
59. The system of claim 51 , wherein the one or more color parameters comprises saturation.
60. The system of claim 51 , wherein the one or more color parameters comprises the mean intensity of an individual color channel.
61. The system of claim 51 , wherein the color signature comprises two or more color parameters selected from the group consisting of: optical density, hue, lightness, saturation and the mean intensity of an individual color channel.
62. The system of claim 51 , wherein the color signature comprises three or more color parameters selected from the group consisting of: optical density, hue, lightness, saturation and the mean intensity of an individual color channel.
63. The system of claim 51 , wherein the color signature comprises a cytoplasmic stain color vector (CSCV).
64. The system of claim 63 , wherein the CSCV is determined based on red, green and blue color channels and is calculated according to the equation:
CSCV
rgb
=
(
Mean
red
)
2
+
(
Mean
green
)
2
+
(
Mean
blue
)
2
,
wherein “Mean” represents the mean intensity value for each color channel over a ROI comprising the cytoplasm of a cell or a portion thereof.
65. The system of claim 64 , wherein the CSCV comprises one or more directional components calculated according to the equation:
β CSCV rgb =cos −1 (Mean blue /CSCV rgb )
or the equation:
θ CSCV rgb =(cos −1 (Mean red ))√{square root over ((Mean red ) 2 +(Mean green ) 2 )}
or a combination thereof.
66. The system of claim 63 , wherein the cytoplasmic stain color vector is determined based on hue, saturation and luminosity values and is calculated according to the equation:
CSCV
hsl
=
(
Mean
hue
)
2
+
(
Mean
saturation
)
2
+
(
Mean
luminosity
)
2
,
wherein “Mean” represents the mean hue, saturation and luminosity values over a ROI comprising the cytoplasm of a cell or a portion thereof.
67. The method of claim 66 , wherein the CSCV comprises one or more directional components calculated according to the equation:
β CSCV hsl =cos −1 (Mean lightness /CSCV hsl )
or the equation:
θ CSCV hsl =(cos −1 (Mean hue ))√{square root over ((Mean hue ) 2 +(Mean saturation ) 2 )}
or a combination thereof.
68. The system of claim 51 , wherein the color signature comprises a nuclear stain color vector (NSCV).
69. The system of claim 68 , wherein the nuclear stain color vector is determined based on red, green and blue color channels and is calculated according to the equation:
NSCV
rgb
=
(
Mean
red
)
2
+
(
Mean
green
)
2
+
(
Mean
blue
)
2
,
wherein “Mean” represents the mean intensity value for each color channel over a ROI comprising the nucleus of a cell or a portion thereof.
70. The method of claim 69 , wherein the NSCV comprises one or more directional components calculated according to the equation:
β NSCV rgb =cos −1 (Mean blue /NSCV rgb )
or the equation:
θ NSCV rgb =(cos −1 (Mean red ))√{square root over ((Mean red ) 2 +(Mean green ) 2 )}
or a combination thereof.
71. The system of claim 68 , wherein the nuclear stain color vector is determined based on hue, saturation and luminosity values and is calculated according to the equation:
NSCV
hsl
=
(
Mean
hue
)
2
+
(
Mean
saturation
)
2
+
(
Mean
luminosity
)
2
,
wherein “Mean” represents the mean hue, saturation and luminosity values over a ROI comprising the nucleus of a cell or a portion thereof.
72. The method of claim 71 , wherein the NSCV comprises one or more directional components calculated according to the equation:
β NSCV hsl =cos −1 (Mean lightness /NSCV hsl )
or the equation:
θ NSCV hsl =(cos −1 (Mean hue ))√{square root over ((Mean hue ) 2 +(Mean saturation ) 2 )}
or a combination thereof.
73. The system of claim 51 , wherein the color signature comprises the ratio of the cytoplasmic stain color vector to a nuclear stain color vector.
74. The system of claim 51 , wherein the plurality of reference quality color signatures are derived from reference histologically stained specimens of known quality.