System and method for finding regions of interest for microscopic digital montage imaging
View Patent ↗A system for processing a thumbnail image from a microscope slide to determine tissue locations on the slide. The system comprises an image cropping component, a tissue finding component, and a scan control component. The image cropping component crops the thumbnail image and removes portions of the image that fall outside of determined slide boundaries. The cropped image from the image cropping component is inputted into the tissue finding component. The tissue finding component identifies tissue regions by applying a sequence of filters that incorporate knowledge of typical appearance and location of tissue and non-tissue slide regions. The tissue finding component outputs a tiling matrix whose values indicate which tiles should be imaged. The scan control component interprets the tiling matrix and transposes positions of the tiling matrix into actual stage coordinate for a microscopic imaging.
1. A method for processing a low resolution image from a slide to determine a specimen locations on the slide, the method comprising:
cropping the low resolution image to remove portions of the low resolution image that correspond to non-slide objects, said cropping including determining a location of at least one boundary by searching at least one interval corresponding to at least one boundary region;
inputting the cropped image into a tissue finding component, wherein the tissue finding component identifies a region containing the specimen by applying a filter that incorporates knowledge of typical appearance and location of specimen and non-specimen slide regions and outputs a matrix whose values indicate which regions of the slide should be imaged, the matrix not including portions of the image falling outside of the boundary; and
transposing positions of the matrix into actual stage coordinates, and capturing a microscopic image at those stage coordinates.
2. The method of claim 1 , wherein the cropping further comprises:
determining location of a slide boundary by searching upper and lower intervals corresponding to boundary regions expected to contain upper and lower edges of the slide; and
not including in the matrix portions of the image falling outside of the determined slide boundary.
3. The method of claim 1 , further comprising converting a copy of the low resolution image to a grayscale image.
4. The method of claim 2 , wherein the low resolution image is a color image, further comprising cropping the color low resolution image at the slide boundary.
5. The method of claim 4 , further comprising reducing the color image size to produce a small thumbnail image of the specimen for rapid visual identification.
6. The method of claim 1 , further comprising identifying pixel blocks in the cropped image that are likely to contain remaining slide edge features; and
flagging these features as edges that should not be considered for high resolution imaging.
7. The method of claim 1 , further comprising:
converting a copy of the low resolution image to grayscale; and
analyzing at least one of mean and standard deviation of local pixel intensities to generate a threshold value.
8. The method of claim 7 , further comprising using the pixel intensity to differentiate tissue-containing regions from blank regions and other non-tissue containing regions.
9. The method of claim 1 , further comprising applying a morphological filter to the matrix to identify slide regions that can be imaged individually during a high-resolution imaging process.
10. The method of claim 1 , wherein the low resolution image is taken automatically without human intervention, the low resolution image is cropped automatically without human intervention, the specimen containing region is identified automatically without human intervention, and the positions of the matrix are transposed automatically without human intervention.
11. The method of claim 1 , further comprising flat-field correcting the image using a blank slide image to remove anomalies from the low resolution image.
12. The method of claim 1 , wherein the components are software components executed by a computer.