Digital microscope slide scanning system and methods
Provided herein are systems methods including a design of a microscope slide scanner for digital pathology applications which provides high quality images and automated batch-mode operation at low cost. The instrument architecture is advantageously based on a convergence of high performance, yet low cost, computing technologies, interfaces and software standards to enable high quality digital microscopy at very low cost. Also provided is a method based in part on a stitching method that allows for dividing an image into a number of overlapping tiles and reconstituting the image with a magnification without substantial loss of accuracy. A scanner is employed in capturing snapshot images. The method allows for overlapping images captured in consecutive snapshots.
1. A method for reconstituting an image comprising:
dividing the image into a number of overlapping tiles captured in a series of snapshots and reconstituting the image with a magnification without substantial loss of accuracy; the method for reconstituting the image further comprising:
capturing at least two consecutive snapshot images through a digital scanner;
calculating stitch points between the at least two consecutive snapshots defining a first tile and a second tile, respectively; wherein the first and second tile images have a common overlap of at least N pixels between them; the method of calculating stitch points comprising:
a. detecting and recording corner points in a minimum overlap region and a maximum overlap region, whereby detected corner points or a selected subset of corner points are sorted and maintained in a list;
b. for each corner point selected in the first tile, determining a set of possible stitch points in the second tile; wherein candidate points are selected using a goodness criterion;
c. maintaining a pair of stitch points that have a matching score that is greater than a defined or computed threshold;
d. computing a displacement between the tiles;
e. calculating a confidence score associated with the computed displacement; and
f. determining a stitching point for stitching the first and second tiles; and displaying a stitched image or storing a stitched image.
2. The method of claim 1 , wherein stitch points identify an area of overlap between the first tile and the second tile.
3. The method of claim 2 , further comprising cropping the overlap area from one of the image tiles such that when the first and second tiles are put together an entire scene is rendered without significant loss of information.
4. The method of claim 1 , wherein the at least two consecutive snapshots are adjacent.
5. The method of claim 1 , wherein the at least two consecutive snapshots overlap by up to 300 pixels.
6. A method for reconstituting an image comprising:
dividing the image into a number of overlapping tiles captured in a series of snapshots and reconstituting the image with a magnification without substantial loss of accuracy; the method for reconstituting the image further comprising:
capturing at least two consecutive snapshot images through a digital scanner;
calculating stitch points between the at least two consecutive snapshots defining a first tile and a second tile, respectively; wherein the first and second tile images have a common overlap of at least N pixels between them; the method of calculating stitch points comprising:
a. detecting and recording corner points in a minimum overlap region and a maximum overlap region, whereby detected corner points or a selected subset of corner points are sorted and maintained in a list;
b. for each corner point selected in the first tile, determining a set of possible stitch points in the second tile; wherein candidate points are selected using a goodness criterion;
c. maintaining a pair of stitch points that have a matching score that is greater than a defined or computed threshold;
d. computing a displacement between the tiles;
e. calculating a confidence score associated with the computed displacement; and
f. determining a stitching point for stitching the first and second tiles; and displaying a stitched image or storing a stitched image, wherein stitch points identify an area of overlap between the first tile and the second tile, and further comprising cropping the overlap area from one of the image tiles such that when the first and second tiles are put together an entire scene is rendered without significant loss of information, and further comprising:
a method for computing pixel correction factors, said method for computing pixel correction factors comprising:
g. capturing a glass blank image or Air-blank image;
h. smoothing the glass blank image or Air-blank image;
i. determining a Max of R, G, B values over the entire glass blank image or Air-blank image;
j. dividing at least one of a R, G, and B value associated with each pixel in the glass blank image or Air-blank image by the corresponding Max of R, G and B values, and generating a normalized image of the glass blank image or Air-blank image; and
k. forming a reciprocal image by taking the inverse of the at least one pixel of the normalized image of the glass blank image or Air-blank image, and generating pixel correction factors, wherein each of the at least one of a R, G, and B value associated with each pixel in the reciprocal image corresponds to one of the pixel correction factors.
7. A method for reconstituting an image comprising:
dividing the image into a number of overlapping tiles captured in a series of snapshots and reconstituting the image with a magnification without substantial loss of accuracy; the method for reconstituting the image further comprising:
capturing at least two consecutive snapshot images through a digital scanner;
calculating stitch points between the at least two consecutive snapshots defining a first tile and a second tile, respectively; wherein the first and second tile images have a common overlap of at least N pixels between them; the method of calculating stitch points comprising:
a. detecting and recording corner points in a minimum overlap region and a maximum overlap region, whereby detected corner points or a selected subset of corner points are sorted and maintained in a list;
b. for each corner point selected in the first tile, determining a set of possible stitch points in the second tile; wherein candidate points are selected using a goodness criterion;
c. maintaining a pair of stitch points that have a matching score that is greater than a defined or computed threshold;
d. computing a displacement between the tiles;
e. calculating a confidence score associated with the computed displacement; and
f. determining a stitching point for stitching the first and second tiles; and displaying a stitched image or storing a stitched image, wherein stitch points identify an area of overlap between the first tile and the second tile, and further comprising cropping the overlap area from one of the image tiles such that when the first and second tiles are put together an entire scene is rendered without significant loss of information, and further comprising:
a method for computing pixel correction factors, said method for computing pixel correction factors comprising:
g. capturing a glass blank image or Air-blank image;
h. smoothing the glass blank image or Air-blank image;
i. determining a Max of R, G, B values over the entire glass blank image or Air-blank image;
j. dividing at least one of a R, G, and B value associated with each pixel in the glass blank image or Air-blank image by the corresponding Max of R, G and B values, and generating a normalized image of the glass blank image or Air-blank image; and
k. forming a reciprocal image by taking the inverse of the at least one pixel of the normalized image of the glass blank image or Air-blank image, and generating pixel correction factors, wherein each of the at least one of a R, G, and B value associated with each pixel in the reciprocal image corresponds to one of the pixel correction factors and, further comprising:
capturing an image of a biological specimen on a slide via a digital scanner; and
multiplying at least one of a R, G, and B value associated with each pixel of the image of the biological specimen on the slide by the corresponding at least one of R, G, and B pixel correction factors.
8. A method for reconstituting an image comprising:
dividing the image into a number of overlapping tiles captured in a series of snapshots and reconstituting the image with a magnification without substantial loss of accuracy; the method for reconstituting the image further comprising:
capturing at least two consecutive snapshot images through a digital scanner;
calculating stitch points between the at least two consecutive snapshots defining a first tile and a second tile, respectively; wherein the first and second tile images have a common overlap of at least N pixels between them; the method of calculating stitch points comprising:
a. detecting and recording corner points in a minimum overlap region and a maximum overlap region, whereby detected corner points or a selected subset of corner points are sorted and maintained in a list;
b. for each corner point selected in the first tile, determining a set of possible stitch points in the second tile; wherein candidate points are selected using a goodness criterion;
c. maintaining a pair of stitch points that have a matching score that is greater than a defined or computed threshold;
d. computing a displacement between the tiles;
e. calculating a confidence score associated with the computed displacement; and
f. determining a stitching point for stitching the first and second tiles; and displaying a stitched image or storing a stitched image, wherein stitch points identify an area of overlap between the first tile and the second tile, and further comprising cropping the overlap area from one of the image tiles such that when the first and second tiles are put together an entire scene is rendered without significant loss of information, and further comprising:
a method for computing pixel correction factors, said method for computing pixel correction factors comprising:
g. capturing a glass blank image or Air-blank image;
h. smoothing the glass blank image or Air-blank image;
i. determining a Max of R, G, B values over the entire glass blank image or Air-blank image;
j. dividing at least one of a R, G, and B value associated with each pixel in the glass blank image or Air-blank image by the corresponding Max of R, G and B values, and generating a normalized image of the glass blank image or Air-blank image; and
k. forming a reciprocal image by taking the inverse of the at least one pixel of the normalized image of the glass blank image or Air-blank image, and generating pixel correction factors, wherein each of the at least one of a R, G, and B value associated with each pixel in the reciprocal image corresponds to one of the pixel correction factors, further comprising:
capturing an image of a biological specimen on a slide via a digital scanner; and
multiplying at least one of a R, G, and B value associated with each pixel of the image of the biological specimen on the slide by the corresponding at least one of R, G, and B pixel correction factors, wherein the step of multiplying the at least one of a R, G, and B value associated with each pixel of the image of the biological specimen on the slide by the at least one of R, G, and B pixel correction factors corresponds to flat-field correction of the image of the biological specimen on the slide.