Method for filtering normal medical image, method for interpreting medical image, and computing device implementing the methods

Patent metadata

Field	Value
Publication number	US-11928817-B2
Application number	US-202218086962-A
Country	US
Kind code	B2
Filing date	Dec 22, 2022
Priority date	Jun 15, 2020
Publication date	Mar 12, 2024
Grant date	Mar 12, 2024

Abstract

A method of reading a medical image by a computing device operated by at least one processor is provided. The method includes obtaining an abnormality score of the input image using an abnormality prediction model, filtering the input image so as not to be subsequently analyzed when the abnormality score is less than or equal to a cut-off score based on the cut-off score which makes a specific reading sensitivity; and obtaining an analysis result of the input image using a classification model that distinguishes the input image into classification classes when the abnormality score is greater than the cut-off score.

First claim

What is claimed is:

1. A method of reading a medical image by a computing device operated by at least one processor, the method comprising:
obtaining an abnormality score of an input image using an artificial intelligence model;
performing a first stage analysis on the input image based on the abnormality score, performing the first stage analysis including classifying the input image as strong normal or non-strong normal, and excluding the input image classified as the strong normal from being subsequently analyzed by the artificial intelligence model that distinguishes the input image into classes including weak normal or abnormal when the abnormality score is less than or equal to a cut-off score; and
performing a second stage analysis subsequent to the first stage analysis on the input image when the abnormality score is greater than the cut-off score, performing the second stage analysis including obtaining an analysis result of the input image using the artificial intelligence model that distinguishes the input image into classes including weak normal or abnormal when the abnormality score is greater than the cut-off score.

2. The method of claim 1 , further comprising
adding the input image having the analysis result to a worklist.

3. The method of claim 2 , wherein the input image in the worklist is required to be checked by reader.

4. The method of claim 2 , further comprising
when a specific image in the worklist is selected, displaying corresponding analysis result of the specific image.

5. The method of claim 4 , wherein the corresponding analysis result is visually displayed as a secondary capture image.

6. The method of claim 4 , wherein
when the specific image analyzed as abnormal is selected, displaying a heatmap visually indicating a position or predicted value of an abnormal lesion.

7. The method of claim 1 , wherein
the input image being strong normal is excluded from a worklist, and provided as a different form than the worklist.

8. The method of claim 1 , wherein the cut-off score is determined by adjusting trade-off between a reading sensitivity and a specificity.

9. The method of claim 1 , wherein the cut-off score makes a specific reading sensitivity.

10. The method of claim 1 , further comprising:
generating a report with an analysis result for the input image classified as the strong normal, without adding the input image being the strong normal to a worklist.

11. A computing device comprising:
a memory; and
at least one processor that executes instructions of a program loaded in the memory,
wherein the processor
obtains an abnormality score of an input image using an artificial intelligence model;
performs a first stage analysis on the input image based on the abnormality score, performing the first stage analysis including classifying the input image as strong normal or non-strong normal, and excluding the input image classified as the strong normal from being subsequently analyzed by the artificial intelligence model that distinguishes the input image into classes including weak normal or abnormal when the abnormality score is less than or equal to a cut-off score; and
performs a second stage analysis subsequent to the first stage analysis on the input image when the abnormality score is greater than the cut-off score, performing the second stage analysis including obtaining an analysis result of the input image using the artificial intelligence model that distinguishes the input image into classes including weak normal or abnormal when the abnormality score is greater than the cut-off score.

12. The computing device of claim 11 , wherein the processor adds the input image having the analysis result to a worklist.

13. The computing device of claim 12 , wherein the input image in the worklist is required to be checked by reader.

14. The computing device of claim 12 , wherein the processor provides corresponding analysis result of specific image, when the specific image in the worklist is selected.

15. The computing device of claim 14 , wherein the corresponding analysis result is visually displayed as a secondary capture image.

16. The computing device of claim 14 , wherein the processor provides a heatmap visually indicating a position or predicted value of an abnormal lesion, when the specific image analyzed as abnormal is selected.

17. The computing device of claim 11 , wherein the input image being strong normal is excluded from a worklist, and provided as a different form than the worklist.

18. The computing device of claim 11 , wherein the cut-off score is determined by adjusting trade-off between a reading sensitivity and a specificity.

19. The computing device of claim 11 , wherein the cut-off score makes a specific reading sensitivity.

20. The computing device of claim 11 , wherein the processor generates a report with an analysis result for the input image classified as the strong normal, without adding the input image being the strong normal to a worklist.

Assignees

• Lunit Inc

Inventors

• Park Jongchan

Classifications

• G06T7/0012 Primary

  Biomedical image inspection · CPC title

• G16H30/40

  for processing medical images, e.g. editing · CPC title

• G16H50/20

  for computer-aided diagnosis, e.g. based on medical expert systems · CPC title

• G06T2207/10116

  X-ray image · CPC title

• G06T2207/20024

  Filtering details · CPC title