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 finding a regions of interest in a first image of a tissue-containing slide having a label and a cover slip having at least one cover slip boundary placed thereon, said method comprising:
acquiring a first low resolution image of a least a portion of the tissue-containing slide;
identifying a first tissue-containing region in the first low resolution image, said first tissue containing region comprising a first portion of the tissue;
identifying a second tissue-containing region in the first low resolution image, said second tissue-containing region comprising a second portion of the tissue;
identifying at least one label-containing region in the first low resolution image, said at least one label-containing region comprising a portion of the label;
identifying at least one cover slip boundary-containing region in the first low resolution image, said at least one cover slip boundary-containing region comprising a portion of the cover-slip;
identifying, in the first low resolution image, a staining artifacts region, said staining artifacts region comprising staining artifacts near the at least one cover slip boundary of the cover slip; and
segmenting the first image into at least five regions, the at least five regions comprising:
the first tissue-containing region;
the second tissue-containing region;
the at least one label-containing region;
the at least one cover slip boundary-containing region; and
the staining artifacts region;
merging the first tissue-containing region and the second tissue-containing region into a single region of interest; and
acquiring a subsequent image of only the single region of interest, after the merging step.
2. The method of claim 1 wherein the low resolution image is a thumbnail image that consists of a representation of the tissue-containing slide as a whole.
3. The method of claim 2 where the thumbnail image includes the label and the actual tissue spread on the tissue-containing slide.
4. The method of claim 3 wherein the thumbnail image can be used an identifier.
5. The method of claim 4 wherein the label image has a barcode specifying the details of a case and a stain type used.
6. The method of claim 5 wherein the label is used as a cross verification tool to correlate the tissue-containing slide with the actual image.
7. The method of claim 1 , wherein the low resolution image is a thumbnail image.
8. The method of claim 1 , wherein the segmenting step is based on an intensity threshold that separates pixels of the first image into tissue-containing pixels and non tissue-containing pixels.
9. The method of claim 1 , wherein the step of identifying the first tissue-containing region and the second tissue-containing region involves separating pixels of the first low resolution image into tissue-containing pixels and non tissue-containing pixels to identify a kernel region of tissue, and wherein the kernel region of tissue is grown to incorporate an entire tissue region.
10. The method of claim 1 wherein the step of identifying the first tissue-containing region and the second tissue-containing region involves automatic detection of an intensity threshold that separates tissue-containing pixels from non tissue-containing pixels.