Systems and methods for processing digital images to adapt to color vision deficiency

Patent metadata

Field	Value
Publication number	US-12592000-B2
Application number	US-202218060358-A
Country	US
Kind code	B2
Filing date	Nov 30, 2022
Priority date	Dec 20, 2021
Publication date	Mar 31, 2026
Grant date	Mar 31, 2026

Abstract

A computer-implemented method for processing medical images, the method including receiving one or more of medical images of at least one pathology specimen, the pathology specimen being associated with a patient, wherein the medical image is a stained histology image. The method may further include receiving a stain type associated with the one or more medical images and identifying a color vision deficiency for one or more users. Next the method may include identifying a pixel transformation for the one or more medical images based on the stain type and color vision deficiency of the one or more users. Next the method may include applying a pixel transformation to each pixel within the one or more medical images. Lastly the method may include displaying the transformed one or more medical images to the one or more users.

First claim

What is claimed is:

1 . A computer-implemented method for processing electronic medical images, comprising:
receiving one or more of medical images of at least one pathology specimen, the pathology specimen being associated with a subject, wherein the one or more medical images are stained histology images; receiving a stain type associated with the one or more medical images; identifying a color vision deficiency for one or more users from a plurality of color vision deficiencies; identifying a pixel transformation for the one or more medical images based on the stain type and color vision deficiency of the one or more users; applying a pixel transformation to each pixel within the one or more medical images, wherein applying the pixel transformation includes:
applying the pixel transformation for each pixel of the one or more medical images based on an identified look-up table from a plurality of look-up tables, wherein the identified look-up table is determined based on the stain type and color deficiency of the one or more users; or
applying the pixel transformation for each pixel of the one or more medical images to convert the one or more medical images to an alternate color space, wherein the alternate color space is determined based on the stain type and color deficiency of the one or more users; and
displaying the transformed one or more medical images to the one or more users.

2 . The method of claim 1 , further comprising:
applying staining normalization to the one or more medical images prior to applying the pixel transformation.

3 . The method of claim 1 , further comprising:
saving the pixel transformation for a particular user for future use.

4 . The method of claim 1 , wherein color vision deficiency for one or more users is determined by administering a spectral sensitivity test to the one or more users.

5 . The method of claim 1 , wherein applying the pixel transformation includes for each pixel of the medical images, updating a corresponding red, green, blue (RGB) intensity value based on the identified look-up table.

6 . The method of claim 1 , wherein multiple pixel transformations may be created for a particular user and the user may select what pixel transformation to apply.

7 . The method of claim 1 , wherein applying the pixel transformation for each pixel of the one or more medical images based on the identified look-up table includes:
determining whether each pixel of the one or more medical images has an exact value in the identified look-up table; and for pixels that do not have an exact value in the look-up table, applying an interpolation to generate red, green, blue (RGB) intensity values for the pixels; and updating red, green, and blue intensity values for each pixel based on the identified look-up table values and the interpolated values.

8 . The method of claim 1 , wherein applying the pixel transformation includes:
applying artificial intelligence techniques to apply recoloring algorithms to enhance morphologies in the one or more medical images based on the color vision deficiency for one or more users.

9 . The method of claim 1 , wherein applying the pixel transformation for each pixel of the one or more medical images to convert the one or more medical images to an alternate color space includes applying a non-linear transformation to the pixels of the one or more medical images.

10 . A system for processing electronic digital medical images, the system comprising:
at least one memory storing instructions; and at least one processor configured to execute the instructions to perform operations comprising:
receiving one or more of medical images of at least one pathology specimen, the pathology specimen being associated with a subject, wherein the one or more medical images are stained histology images;
receiving a stain type associated with the one or more medical images;
identifying a color vision deficiency for one or more users from a plurality of color vision deficiencies;
identifying a pixel transformation for the one or more medical images based on the stain type and color vision deficiency of the one or more users;
applying a pixel transformation to each pixel within the one or more medical images, wherein applying the pixel transformation includes:
applying the pixel transformation for each pixel of the one or more medical images based on an identified look-up table from a plurality of look-up tables, wherein the identified look-up table is determined based on the stain type and color deficiency of the one or more users; or
applying the pixel transformation for each pixel of the one or more medical images to convert the one or more medical images to an alternate color space, wherein the alternate color space is determined based on the stain type and color deficiency of the one or more users; and

displaying the transformed one or more medical images to the one or more users.

11 . The system of claim 10 , further comprising:
applying staining normalization to the one or more medical images prior to applying the pixel transformation.

12 . The system of claim 10 , further comprising:
saving the pixel transformation for a particular user for future use.

13 . The system of claim 10 , wherein color vision deficiency for one or more users is determined by administering a spectral sensitivity test to the one or more users.

14 . The system of claim 10 , wherein applying the pixel transformation includes for each pixel of the medical images, updating a corresponding red, green, blue (RGB) intensity value based on the identified look-up table.

15 . The system of claim 10 , wherein multiple pixel transformations may be created for a particular user and the user may select what pixel transformation to apply.

16 . The system of claim 10 , wherein applying the pixel transformation for each pixel of the one or more medical images based on a look-up table includes:
determining whether each pixel of the one or more medical images has an exact value in the identified look-up table; and for pixels that do not have an exact value in the look-up table, applying an interpolation to generate red, green, blue (RGB) intensity values for the pixels; and updating red, green, and blue intensity values for each pixel based on the identified look-up table values and the interpolated values.

17 . The system of claim 10 , wherein applying the pixel transformation includes:
applying artificial intelligence techniques to apply recoloring algorithms to enhance morphologies in the one or more medical images based on the color vision deficiency for one or more users.

18 . The system of claim 10 , wherein applying the pixel transformation for each pixel of the one or more medical images to convert the one or more medical images to an alternate color space includes applying a non-linear transformation to the pixels of the one or more medical images.

19 . A non-transitory computer-readable medium storing instructions that, when executed by a processor, perform operations processing electronic digital medical images, the operations comprising:
receiving one or more of medical images of at least one pathology specimen, the pathology specimen being associated with a subject, wherein the one or more medical images are stained histology images; receiving a stain type associated with the one or more medical images; identifying a color vision deficiency for one or more users from a plurality of color vision deficiencies; identifying a pixel transformat

Assignees

• Paige Ai Inc

Inventors

• Ruben Kristin
• Ondy Kyle
• Kanan Christopher

Classifications

• G06T2207/20081

  Training; Learning · CPC title

• G06T2207/10056

  Microscopic image · CPC title

• G06T7/0012 Primary

  Biomedical image inspection · CPC title

• G06T2207/30041

  Eye; Retina; Ophthalmic · CPC title

• G06T2207/20084

  Artificial neural networks [ANN] · CPC title