Image enhancement to enable improved nuclei detection and segmentation
Aspects of the present disclosure pertain to systems and methods for enhancing brightfield or darkfield images to better enable nucleus detection. In some embodiments, the systems and methods described herein are useful for identifying membrane stain biomarkers as well as nuclear/cytoplasm stain biomarkers in stained images of biological samples. In some embodiments, the presently disclosed systems and methods enable quick and accurate nucleus detection in stained images of biological samples, especially for original stained images of biological samples where the nuclei appear faint.
1. A method of enhancing the detection of cell nuclei within a whole slide image of a stained biological sample comprising:
(a) obtaining one or more input image channel images, wherein each obtained input channel image comprises signals corresponding to the presence of a nuclear biomarker stain or a membrane biomarker stain;
(b) enhancing the membrane biomarker stain or the nuclear biomarker stain in a first of the one or more obtained input channel images by applying at least a boundary structure enhancing filter to the first of the one or more obtained input channel images to provide a first enhanced image; and
(c) generating a refined image based at least upon the first enhanced image.
2. The method of claim 1 , further comprising detecting nuclei within the generated refined image.
3. The method of claim 2 , further comprising superimposing the detected nuclei over the whole slide image of the stained biological sample.
4. The method of claim 3 , wherein the second image is a second of the one or more obtained input channel images.
5. The method of claim 4 , wherein the nuclear biomarker stain is hematoxylin.
6. The method of claim 4 , wherein the membrane biomarker stain identifies one or more lymphocyte biomarkers.
7. The method of claim 1 , wherein the refined image is generated by computing a summation of the first enhanced image or a further processed variant image thereof and at least a second image.
8. The method of claim 7 , wherein the first of the one or more obtained input channel images comprises signals corresponding to the membrane biomarker stain, and wherein the second of the one or more obtained input channel images comprises signals corresponding to the nuclear biomarker stain.
9. The method of claim 7 , wherein the further processed variant image is an inverse of the first enhanced image.
10. The method of claim 1 , wherein the refined image is a combination of the first enhanced image and a second enhanced image, wherein the second enhanced image is generated by applying the at least the boundary structure enhancing filter to a second of the one or more obtained input channel images.
11. The method of claim 10 , wherein the first of the one or more obtained input channel images comprises signals corresponding to the presence of the nuclear biomarker stain; and wherein the second of the one or more obtained input channel images comprise signals corresponding to the presence of the membrane biomarker stain.
12. The method of claim 10 , wherein the combination of the first enhanced image and the second enhanced image is weighted.
13. The method of claim 10 , wherein the refined image further comprises a third enhanced image derived from a third of the one or more obtained input channel images.
14. The method of claim 1 , wherein the biological sample is stained in a darkfield multiplex immunohistochemical assay.
15. The method of claim 1 , wherein the biological sample is stained in a brightfield multiplex immunohistochemical assay.
16. A method of enhancing detection of cell nuclei within an image of a stained biological sample comprising:
(a) obtaining one or more unmixed image channel images from a whole slide image stained for the presence of at least one nuclear stain and for at least one membrane stain, wherein each obtained unmixed image channel image comprises signals corresponding to the at least one membrane stain or the at least one nuclear stain;
(b) enhancing the signals corresponding to the at least one membrane stain or the at least one nuclear stain in a first of the one or more obtained unmixed image channel images by applying a Frangi filter at a first scaling factor to the first of the one or more obtained unmixed image channel images to provide a first enhanced image; and
(c) generating a refined image, wherein the refined image is generated by combining the first enhanced image with at least a second enhanced image, wherein the second enhanced image is derived from the first of the one or more input channel images, and wherein the second enhanced image is generated by applying the Frangi filter at a second scaling factor to the first of the one or more input channel images, wherein the second scaling factor is different from the first scaling factor.
17. The method of claim 16 , further comprising detecting nuclei within the generated refined image.
18. The method of claim 17 , further comprising superimposing seed points representing the detected nuclei over the whole slide image.
19. The method of claim 16 , wherein the refined image further comprises a third image, wherein the third image is derived from a second of the one or more unmixed image channel images, and wherein the third image is an enhanced image generated by applying the Frangi filter to the second of the one or more unmixed image channel images.
20. The method of claim 16 , wherein the second of the one or more unmixed image channel images is different than the first of the one or more unmixed image channel images.