Methods and systems for processing biological specimens utilizing multiple wavelengths
View Patent ↗Methods, systems and computer readable media for processing one or more biological specimens carried by specimen slides. Images of objects in a specimen are acquired and objects of interest in the acquired images are identified. Additional images of identified objects of interest may be acquired at multiple wavelengths. Cellular features of objects of interest are extracted from images and may be used for classifying the specimen, e.g., as normal or suspicious/abnormal, based a probabilistic model that utilizes the extracted features.
1. A method for classifying a biological specimen on a specimen carrier to determine whether the specimen requires further analysis, the method comprising:
acquiring images of objects in the specimen;
identifying objects of interest in the images;
acquiring additional images of the identified objects of interest at a plurality of different wavelengths;
extracting cellular features of the identified objects of interest from the additional images;
using the extracted cellular features and a first probability function to determine a probability that the identified objects of interest are artifacts; and
classifying the specimen according to a probabilistic model based on the first probability function to determine whether the specimen requires further analysis.
2. The method of claim 1 , wherein the additional images of the identified objects of interest are acquired at more than three different wavelengths.
3. The method of claim 1 , the extracted cellular features being nucleus-related features.
4. The method of claim 3 , the nucleus-related features comprising a texture of the nucleus, a standard deviation of an optical density within the nucleus, a variation of an optical density within the nucleus, a corrected optical density of the nucleus, and a shape of a boundary of the nucleus.
5. The method of claim 1 , the probabilistic model including the first probability function and a second probability function, results of the first and second probability functions being used to classify the specimen and determine whether the specimen requires further analysis.
6. The method of claim 5 , the second probability function being based in part on a result of the first probability function.
7. The method of claim 5 , the extracted cellular features being nucleus-related features, and both of the first and second probability functions being based on extracted nucleus-related features.
8. The method of claim 7 , the first probability function being based on nucleus-related features, including
a texture of a nucleus,
a standard deviation of an optical density within a nucleus,
a variation of an optical density within a nucleus,
a corrected optical density of a nucleus, and
a shape of a boundary of a nucleus.
9. The method of claim 7 , the second probability function being based on nucleus-related features, including
an average of gray value contrast of pixels of images of nuclei of cells of identified objects of interest, and
a range of gray value contrast of pixels of images of nuclei of cells of identified objects of interest.
10. The method of claim 7 , the first and second probability functions being based on different types and different numbers of nucleus-related features.
11. The method of claim 5 , the first and second probability functions comprising first and second posterior probability functions.
12. The method of claim 5 , further comprising
generating a graphical representation of results of the first probability function versus results of the second probability function, the specimen being classified based on the graphical representation.
13. A method for automatically classifying a biological specimen carried on a specimen carrier to determine whether the specimen requires further analysis, the method comprising:
acquiring images of objects in the specimen;
identifying objects of interest from the acquired images;
acquiring additional images of the identified objects of interest at a plurality of different wavelengths;
extracting nucleus-related features of the identified objects of interest from the additional images; and
classifying the specimen according to a probabilistic model based on the extracted nucleus-related features, the probabilistic model including a first probability function and a second probability function, the first probability function indicating a probability that an identified object of interest is an artifact, and the second probability function being based in part on a result of the first probability function,
wherein the combination of the first and second probability functions is used to classify the specimen and to determine whether the specimen requires further analysis.
14. The method of claim 13 , the first probability function indicating an average probability that an identified object of interest of a biological specimen is an artifact.
15. The method of claim 13 , the first probability function being based on nucleus-related features including
a texture of a nucleus,
a standard deviation of an optical density within the nucleus,
a variation of an optical density within the nucleus,
a corrected optical density of the nucleus, and
a shape of a boundary of the nucleus.
16. The method of claim 13 , the second probability function being based on nucleus-related features including
an average of gray value contrast of pixels of images of nuclei of cells of identified objects of interest, and
a range of gray value contrast of pixels of images of nuclei of cells of identified objects of interest.
17. The method of claim 13 , wherein the first and second probability functions are based on different types and different numbers of nucleus-related features.
18. The method of claim 13 , the first and second probability functions comprising first and second posterior probability functions.
19. The method of claim 13 , further comprising
generating a graphical representation of results of the first probability function versus results of the second probability function, the biological specimen being classified based on the graphical representation.
20. A biological screening system for classifying a biological specimen carried on a specimen carrier to determine whether the biological specimen requires further analysis, the system comprising:
an imaging component configured to acquire digital image data of objects in the biological specimen; and
a processor configured to process and identify objects of interest from the digital image data,
the imaging component being further configured to acquire additional images of the identified objects of interest at a plurality of different wavelengths,
the processor being further configured to extract cellular features of the identified objects of interest from the additional images, to use the extracted cellular features and a first probability function to determine a probability that the identified objects of interest are artifacts, and to classify the biological specimen according to a probabilistic model based on the first probability function to determine whether the biological specimen requires further analysis.
21. The system of claim 20 , the imaging component being configured to acquire additional images of identified objects of interest at more than three different wavelengths.
22. The system of claim 20 , the extracted cellular features being nucleus-related features.
23. The system of claim 20 , the probabilistic model including the first probability function and a second probability function, results of the first and second probability functions being used to classify the specimen and determine whether the specimen requires further analysis.
24. The system of claim 23 , the second probability function being based in part on a result of the first probability function.
25. A biological screening system for classifying biological specimens carried on specimen carriers to determine whether a biological specimen requires further analysis, the system comprising:
an imaging component configured to acquire images of objects in the biological specimen; and
a processor configured to process and identify objects of interest from the acquired images,
the imaging component being further configured to obtain additional images of the identified objects of interest at a plurality of different wavelengths,
the processor being further configured to extract nucleus-related features of identified objects of interest from the additional images acquired at different wavelengths, and to classify the biological specimen according to a probabilistic model that is based on the extracted nucleus-related features,
the probabilistic model including a first probability function and a second probability function, the first probability function indicating a probability that a selected object is an artifact, and the second probability function being based in part on a result of the first probability function, the combination of the first and second probability functions being used to classify the biological specimen and determine whether the biological specimen requires further analysis.
26. The system of claim 25 , the imaging component being configured to acquire additional images of identified objects of interest at more than three different wavelengths.
27. The system of claim 25 , the first probability function indicating an average probability that an identified object of interest of a specimen is an artifact.