EP-4371060-B1 - PROCESSING PATHOLOGY IMAGES

Inventors

• REUNANEN, JUHA

Dates

Publication Date

20260506

Application Date

20220621

Claims (18)

1. A computer-implemented method of facilitating processing of pathology images, the method comprising: receiving (502) pathology image data representing a pathology image having a plurality of image regions, wherein the pathology image data includes, for each of the plurality of image regions, a respective plurality of representations of the image region including a first representation and a second representation, the second representation having a smaller data size than the first representation; for each of the plurality of image regions: determining (506), based at least in part on the first representation of the image region, a first set of image properties; determining (508) whether the first set of image properties meets first image property criteria; and if the first set of image properties meets the first image property criteria, producing signals (510) for causing the second representation to be used in place of the first representation, wherein for each of the plurality of image regions, the first set of image properties represents a difference between the first and second representations of the image region, wherein, for each of the plurality of image regions, determining the first set of image properties comprises determining based on at least the first and second representations, a first image difference representing the difference between the first and second representations of the image region, and wherein, for each of the plurality of image regions, determining the first image difference comprises: upscaling (542) the second representation of the image region to generate a first upscaled representation of the image region, the first upscaled representation of the image region having the same pixel dimensions as the first representation of the image region; and for each pixel position in the first representation and the first upscaled representation, determining (544) a pixel value difference between respective pixels of the first representation and the first upscaled representation.
2. The method of claim 1 wherein the second representation has a pixel width smaller than a pixel width of the first representation and the second representation has a pixel height smaller than a pixel height of the first representation.
3. The method of claim 1 wherein, for each of the plurality of image regions: determining the first image difference comprises determining from the pixel value differences, a first maximum pixel value difference; and determining whether the first set of image properties meets the first image property criteria comprises comparing the first maximum pixel value difference with a first maximum pixel difference threshold.
4. The method of any preceding claim wherein, for each of the plurality of image regions: determining the first image difference comprises: determining from the pixel value differences, an extreme negative pixel value difference; and determining from the pixel value differences, an extreme positive pixel value difference; and determining whether the first set of image properties meets the first image property criteria comprises: comparing the extreme negative pixel value difference with an extreme negative pixel difference threshold; and comparing the extreme positive pixel value difference with an extreme positive pixel difference threshold, the extreme positive pixel difference threshold being different from the extreme negative pixel difference threshold.
5. The method of any preceding claim wherein, for each pixel position in the first representation and the first upscaled representation, determining the pixel value difference comprises scaling the pixel value difference by a pixel value scaling factor, the pixel value scaling factor based at least in part on an overall pixel value intensity of the first representation.
6. The method of any preceding claim wherein, for each of the plurality of image regions, the plurality of representations of the image region includes a third representation, the third representation having a smaller data size than the second representation and wherein determining whether the first set of image properties meets the first image property criteria comprises: determining, based at least in part on the second representation of the image region, a second set of image properties; determining whether the second set of image properties meets second image property criteria; and if the second set of image properties meets the second image property criteria, producing signals for causing the third representation to be used in place of the first representation.
7. The method of claim 6 wherein, for each of the plurality of image regions, determining the second set of image properties comprises determining based on at least the second and third representations, a second image difference representing a difference between the second and third representations of the image region and wherein, for each of the plurality of image regions, determining the second image difference comprises: upscaling the third representation of the image region to generate a second upscaled representation of the image region, the second upscaled representation of the image region having the same pixel dimensions as the second representation of the image region; for each pixel position in the second representation and the second upscaled representation, determining a second pixel value difference between respective pixels of the second representation and the second upscaled representation; and determining from the second pixel value differences, a second maximum pixel value difference; and wherein determining whether the second set of image properties meets the second image property criteria comprises comparing the second maximum pixel value difference with a second maximum pixel difference threshold, wherein the second maximum pixel difference threshold has a lower magnitude than the first maximum pixel difference threshold.
8. The method of any preceding claim wherein producing signals for causing the second representation to be used in place of the first representation comprises producing signals for causing the second representation to be displayed by at least one display in place of the first representation.
9. The method of any preceding claim further comprising receiving a request for the first representation and wherein producing signals for causing the second representation to be used in place of the first representation comprises producing signals for causing the second representation to be provided in response to the request for the first representation.
10. The method of any preceding claim wherein, for each of the plurality of image regions, determining the first set of image properties comprises inputting at least the first representation of the image region into a machine learning model to cause the machine learning model to generate at least one machine learning model image property.
11. The method of claim 10 wherein the machine learning model includes a convolutional neural network.
12. The method of any preceding claim comprising, for each of the plurality of image regions, whether the first set of image properties meets or does not meet the first image property criteria, causing the second representation to be stored such that the second representation is configured to be provided when requested.
13. The method of any preceding claim wherein producing signals for causing the second representation to be used in place of the first representation comprises producing signals identifying the first representation as replaceable by the second representation.
14. The method of claim 13 wherein producing signals identifying the first representation as replaceable by the second representation comprises including an identifier of the first representation in a replaceable first representation record.
15. The method of claim 14 wherein the replaceable first representation record includes an identifying image.
16. The method of claim 15 wherein the identifying image includes a binary image.
17. A system for facilitating processing of pathology images, the system comprising at least one processor configured to perform the method of any one of claims 1 to 16.
18. A non-transitory computer-readable medium having stored thereon codes that when executed by at least one processor cause the at least one processor to perform the method of any one of claims 1 to 16.

Description

BACKGROUND 1. Field Embodiments of the present disclosure relate to processing pathology images and more particularly to facilitating processing of pathology images. 2. Description of Related Art Image analysis is playing an increasing role globally in pathology and various medical diagnostic applications. Image analysis may involve processing and/or manipulating pathology images, which in some cases may be extremely large and/or difficult to process and/or manipulate. In order to process and/or manipulate pathology images, some known systems may be slow, costly and/or inefficient. United States patent application no. US-A-2016/247310 describes systems and methods for displaying data on a display device. An example method of displaying data on a display device includes computing a texture based on a difference between a high quality (HQ) tile and a corresponding low quality (LQ) tile. The method also includes storing the texture into an alpha channel of the LQ tile. The method further includes compositing the LQ tile onto the display device when an attribute of the alpha channel satisfies a threshold. SUMMARY In accordance with the present invention, there is provided a method of facilitating processing of pathology images. The method involves receiving pathology image data representing a pathology image having a plurality of image regions, wherein the pathology image data includes, for each of the plurality of image regions, a respective plurality of representations of the image region including a first representation and a second representation, the second representation having a smaller data size than the first representation. The method involves, for each of the plurality of image regions: determining, based at least in part on the first representation of the image region, a first set of image properties, determining whether the first set of image properties meets first image property criteria, and, if the first set of image properties meets the first image property criteria, producing signals for causing the second representation to be used in place of the first representation. For each of the plurality of image regions, the first set of image properties represent a difference between the first and second representations of the image region. For each of the plurality of image regions, determining the first set of image properties involves determining based on at least the first and second representations, a first image difference representing the difference between the first and second representations of the image region. For each of the plurality of image regions, determining the first image difference involves upscaling the second representation of the image region to generate a first upscaled representation of the image region, the first upscaled representation of the image region having the same pixel dimensions as the first representation of the image region, and, for each pixel position in the first representation and the first upscaled representation, determining a pixel value difference between respective pixels of the first representation and the first upscaled representation. The second representation may have a pixel width smaller than a pixel width of the first representation and the second representation may have a pixel height smaller than a pixel height of the first representation. For each of the plurality of image regions, determining the first image difference may involve determining from the pixel value differences, a first maximum pixel value difference, and determining whether the first set of image properties meets the first image property criteria may involve comparing the first maximum pixel value difference with a first maximum pixel difference threshold. For each of the plurality of image regions, determining the first image difference may involve determining from the pixel value differences, an extreme negative pixel value difference, and determining from the pixel value differences, an extreme positive pixel value difference. For each of the plurality of image regions, determining whether the first set of image properties meets the first image property criteria may involve comparing the extreme negative pixel value difference with an extreme negative pixel difference threshold, and comparing the extreme positive pixel value difference with an extreme positive pixel difference threshold, the extreme positive pixel difference threshold being different from the extreme negative pixel difference threshold. For each pixel position in the first representation and the first upscaled representation, determining the pixel value difference may involve scaling the pixel value difference by a pixel value scaling factor, the pixel value scaling factor based at least in part on an overall pixel value intensity of the first representation. For each of the plurality of image regions, the plurality of representations of the image region may include a third representation, the third represent