Medical scan header standardization system and methods for use therewith

Patent metadata

Field	Value
Publication number	US-11829914-B2
Application number	US-202217680493-A
Country	US
Kind code	B2
Filing date	Feb 25, 2022
Priority date	Nov 21, 2018
Publication date	Nov 28, 2023
Grant date	Nov 28, 2023

Abstract

A medical scan header standardization system is operable to determine a plurality of counts for a plurality of entries of at least one of a standard set of fields for headers of a plurality of medical images. A standard set of header entries is determined for at least one of the standard set of fields based on including ones of the entries for the each of the standard set of fields with counts of the plurality of counts that compare favorably to a threshold. One of the standard set of header entries is selected to replace an entry of a field of a header of a medical image. A computer vision model is trained utilizing a training set of images that includes the medical image and the selected one of the standard set of header entries. Inference data for at least one new medical scan is generated based on utilizing the computer vision model.

First claim

What is claimed is:

1. A medical scan header standardization system, comprising:
at least one processor; and
a memory that stores executable instructions that, when executed by the at least one processor, cause the medical scan header standardization system to:
receive a plurality of DICOM images;
determine a plurality of counts for a plurality of entries of at least one of a standard set of fields for headers of the plurality of DICOM images;
determine a standard set of Digital Imaging and Communications in Medicine (DICOM) header entries for at least one of the standard set of fields by including ones of the entries for the each of the standard set of fields with counts of the plurality of counts that compare favorably to a threshold;
receive a DICOM image;
determine to correct an entry of a field the header of the DICOM image;
select one of the standard set of DICOM header entries for the field to replace the entry of the field of the header of the DICOM image;
train a computer vision model via artificial intelligence utilizing a training set of DICOM images that includes the DICOM image and the one of the standard set of DICOM header entries; and
generate inference data for at least one new medical scan based on performing an inference function on image data of the at least one new medical scan via artificial intelligence by utilizing the computer vision model.

2. The medical scan header standardization system of claim 1 , wherein determining to correct the entry of the header of the DICOM image is based on determining the header is incorrect.

3. The medical scan header standardization system of claim 2 , wherein determining to correct the entry of the field the header of the DICOM image includes determining the entry of the field of the header is not included in the standard set of DICOM header entries for one of the at least one of the standard set of fields corresponding to the field.

4. The medical scan header standardization system of claim 3 , wherein selecting the one of the standard set of DICOM header entries includes determining one of the standard set of DICOM header entries for the field that compares most favorably to the entry.

5. The medical scan header standardization system of claim 3 ,
wherein the memory stores, for each of the standard set of fields, a mapping of incorrect entries to ones of the standard set of DICOM header entries to one of the standard set of DICOM header entries for the each of the standard set of fields; and
wherein selecting the one of the standard set of DICOM header entries includes determining one of the standard set of DICOM header entries of the one of the standard set of fields by utilizing the mapping.

6. The medical scan header standardization system of claim 5 , wherein the executable instructions, when executed by the at least one processor, further cause the medical scan header standardization system to:
transmit a notification to a client device for display to a user via a display device in response to determining the mapping does not include an incorrect entry that compares favorably to the entry, wherein the notification indicates the entry;
receive, from the client device, an identified one of the standard set of DICOM header entries, wherein the identified one of the standard set of DICOM header entries is generated by the client device based on user input via an interactive interface in response to a prompt displayed by the display device to select one of the standard set of DICOM header entries for the entry; and
generate a new mapping entry that maps the entry to the identified one of the standard set of DICOM header entries;
wherein the one of the standard set of DICOM header entries includes the identified one of the standard set of DICOM header entries.

7. The medical scan header standardization system of claim 1 , wherein the executable instructions, when executed by the at least one processor, further cause the medical scan header standardization system to:
receive a second DICOM image;
determine a second header of the second DICOM image is incorrect; and
update the second header of the second DICOM image based on the standard set of DICOM header entries.

8. The medical scan header standardization system of claim 7 ,
wherein determining the second header is incorrect includes:
automatically determining at least one property of the second DICOM image;
determining a second field of the standard set of fields corresponding to the at least one property; and
determining a second entry of the second field of the second header compares unfavorably to the at least one property;

wherein updating the second header includes:
selecting a second one of the standard set of DICOM header entries for the field that compares favorably to the at least one property; and
replacing the second entry of the second field of the second header with the second one of the standard set of DICOM header entries.

9. The medical scan header standardization system of claim 8 , wherein the second entry of the second field of the second header is included in the standard set of DICOM header entries for the field, and wherein the second one of the standard set of DICOM header entries replacing the second entry is different from the second entry.

10. The medical scan header standardization system of claim 8 , wherein the property corresponds to one of: a modality of the DICOM image or an anatomical region of the DICOM image.

11. The medical scan header standardization system of claim 8 , wherein the executable instructions, when executed by the at least one processor, further cause the medical scan header standardization system to:
train a second computer vision model via artificial intelligence utilizing a training set of DICOM images; and
automatically determine the at least one property of the second DICOM image based on performing a second inference function on second image data of the second DICOM image via artificial intelligence by utilizing the second computer vision model.

12. The medical scan header standardization system of claim 7 , wherein the executable instructions, when executed by the at least one processor, further cause the medical scan header standardization system to:
train a second computer vision model via artificial intelligence utilizing a training set of DICOM images; and
automatically identify detected text in image data of the second DICOM image based on performing an inference function on the image data of the DICOM image via artificial intelligence by utilizing the second computer vision model;
wherein determining that the second header of the second DICOM image is incorrect is based on determining the second header of the second DICOM image compares unfavorably to the detected text, and wherein the second header of the second DICOM image is updated further based on the detected text.

13. The medical scan header standardization system of claim 7 , wherein determining that a second header of the DICOM image is incorrect includes determining a set of fields of the second header does not match the standard set of fields based on determining at least one of: a number of the set of fields compares unfavorably to a number of the standard set of fields, or an ordering of the set of fields compares unfavorably to a standard ordering of the standard set of fields.

14. The medical scan header standardization system of claim 7 , wherein determining that the second header of the second DICOM image is incorrect includes determining that at least one field of the second header is null, and wherein updating the second header includes selecting includes

Assignees

• Enlitic Inc

Inventors

• Lyman Kevin
• Upton Anthony
• Yao Li
• Prosky Jordan
• Poblenz Eric C
• Croswhite Chris
• Covington Ben

Classifications

• G06T12/20

  Inverse problem, i.e. transformations from projection space into object space · CPC title

• G06T11/26

  Drawing of charts or graphs · CPC title

• G06T11/10

  Texturing; Colouring; Generation of textures or colours (retouching, inpainting or scratch removal G06T5/77) · CPC title

• G06N3/045

  Combinations of networks · CPC title

• G06N3/09

  Supervised learning · CPC title