System for processing a whole slide image, WSI, of a biopsy

1 . A system for processing a whole slide image, WSI, of a biopsy, comprising;

a display; and

a processor which is adapted to:

detect, using a first machine learning algorithm, tissue present in the WSI relating to the biopsy;

create a skeleton of a shape of the detected tissue;

select a skeleton path as the longest continuous path through the tissue;

determine one or more tissue pathologies of the detected tissue;

determine, using a second machine learning algorithm in series with the first machine learning algorithm, a line representing the skeleton path with different line representations along the line representing different determined tissue pathologies;

determine a pathology summary for the line representing the skeleton path, wherein the pathology summary comprises: (i) a determined biopsy length expressed in a standard unit of length; (ii) a determined pathology length for one or more of the determined tissue pathologies, expressed in the same standard unit of length and/or in a subunit thereof; and (iii) a determined fraction of the line occupied by a particular type of tissue pathology, wherein the determined fraction is determined using the determined biopsy length and the determined pathology length; and

provide, via the display, the determined pathology summary alongside the determined line.

2 . The system as claimed in claim 1 , wherein the different line representations comprise different colors or line thickness.

3 . The system as claimed in claim 1 , wherein the particular type of tissue pathology is tumor tissue.

4 . The system as claimed in claim 1 , wherein generating an image comprising the line representing the skeleton path comprises overlaying the determined tissue pathologies over the skeleton path, and selecting a representative tissue pathology for a point along the skeleton path.

5 . The system as claimed in claim 4 , wherein the representative tissue pathology is selected to be tumor tissue if tumor tissue is present at or perpendicular to the point along the line representing the skeleton path.

6 . The system of claim 1 , wherein the processor is further configured to:

receive input from a viewer of the generated image to zoom in on an identified portion of the displayed image;

adjust the generated image to zoom, via the display, into the identified portion of the image, wherein the zooming comprises removing the determined line from the image; and

display the zoomed image.

7 . A computer-implemented method for processing a whole slide image, WSI, of a biopsy, comprising:

detecting, using a first machine learning algorithm, tissue present in the WSI relating to the biopsy;

creating a skeleton of a shape of the detected tissue;

selecting a skeleton path as the longest continuous path through the tissue;

determining, using a second machine learning algorithm in series with the first machine learning algorithm, one or more tissue pathologies of the detected tissue;

determining a line representing the skeleton path with different line representations along the line representing different tissue pathologies;

determining a pathology summary for the line representing the skeleton path, wherein the pathology summary comprises: (i) a determined biopsy length expressed in a standard unit of length; (ii) a determined pathology length for one or more of the determined tissue pathologies, expressed in the same standard unit of length and/or in a subunit thereof; and (iii) a determined fraction of the line occupied by a particular type of tissue pathology, wherein the determined fraction is determined using the determined biopsy length and the determined pathology length; and

providing, via a display, the determined pathology summary alongside the determined line.

8 . The method as claimed in claim 7 , wherein generating an image comprising the determined pathology summary comprises generating the image with different colors of the line representing the different tissue pathologies.

9 . The method as claimed in claim 7 , comprising overlaying or juxtaposing the determined tissue pathologies over the skeleton path, and selecting an associated tissue pathology for a point along the skeleton path.

10 . The method of claim 7 , further comprising:

receiving input from a viewer of the generated image to zoom in on an identified portion of the displayed image;

adjusting the generated image to zoom, via the display, into the identified portion of the image, wherein the zooming comprises removing the determined line from the image; and

displaying the zoomed image.

11 . A non-transitory computer readable medium comprising a computer program such that when said program is run on a computer, the computer:

detects, using a first machine learning algorithm, tissue present in a whole slide image, WSI, relating to the biopsy;

creates a skeleton of a shape of the detected tissue;

selects a skeleton path as the longest continuous path through the tissue;

determines, using a second machine learning algorithm in series with the first machine learning algorithm, tissue pathologies of the detected tissue;

determines a line representing the skeleton path with different line representations along the line representing different tissue pathologies;

determines a pathology summary for the line representing the skeleton path, wherein the pathology summary comprises: (i) a determined biopsy length expressed in a standard unit of length; (ii) a determined pathology length for one or more of the determined tissue pathologies, expressed in the same standard unit of length and/or in a subunit thereof; and (iii) a determined fraction of the line occupied by a particular type of tissue pathology, wherein the determined fraction is determined using the determined biopsy length and the determined pathology length; and

provides, via a display, the determined pathology summary alongside the determined line.

12 . The computer readable medium of claim 11 , wherein the computer generates the determined pathology summary with different colors of the line representing the different tissue pathologies.

13 . The computer readable medium of claim 11 , wherein the computer generates an image comprising the determined pathology summary by overlaying or juxtaposing the determined tissue pathologies over the skeleton path, and selecting an associated tissue pathology for a point along the skeleton path.

14 . The computer readable medium of claim 11 , wherein the computer generates the determined pathology summary by overlaying the determined tissue pathologies over the skeleton path and selecting a representative tissue pathology for a point along the skeleton path.

15 . The computer readable medium of claim 14 , wherein the representative tissue pathology is selected to be tumor tissue if tumor tissue is present at or perpendicular to the respective point along the line representing the skeleton path.