Performance of machine learning models for automatic quantification of coronary artery disease

Patent metadata

Field	Value
Publication number	US-11030490-B2
Application number	US-201916556324-A
Country	US
Kind code	B2
Filing date	Aug 30, 2019
Priority date	Aug 30, 2019
Publication date	Jun 8, 2021
Grant date	Jun 8, 2021

Abstract

Systems and methods for retraining a trained machine learning model are provided. One or more input medical images are received. Measures of interest for a primary task and a secondary task are predicted from the one or more input medical images using a trained machine learning model. The predicted measures of interest for the primary task and the secondary task are output. User feedback on the predicted measure of interest for the secondary task is received. The trained machine learning model is retrained for predicting the measures of interest for the primary task and the secondary task based on the user feedback on the output for the secondary task.

First claim

The invention claimed is:

1. A method for retraining a trained machine learning model, comprising:
receiving one or more input medical images;
predicting measures of interest for a primary task and a secondary task from the one or more input medical images using a trained machine learning model;
outputting the predicted measures of interest for the primary task and the secondary task;
receiving user feedback on the predicted measure of interest for the secondary task; and
retraining the trained machine learning model for predicting the measures of interest for the primary task and the secondary task based on the user feedback on the output for the secondary task.

2. The method of claim 1 , wherein the measure of interest for the primary task cannot be directly validated by a user from the one or more input medical images and the measure of interest for the secondary task can be directly validated by the user from the one or more input medical images.

3. The method of claim 1 , wherein the user feedback comprises an acceptance or a rejection of the predicted measure of interest for the secondary task.

4. The method of claim 1 , wherein the user feedback comprises a modification to the predicted measure of interest for the secondary task.

5. The method of claim 1 , further comprising:
predicting additional measures of interest for the primary task and the secondary task from the one or more input medical images using the retrained machine learning model; and
determining a measure of confidence in the predicted additional measures of interest for the primary task and the secondary task based on a difference between the measures of interest predicted using the trained machine learning model and the additional measures of interest predicted using the retrained machine learning model.

6. The method of claim 1 , wherein predicting measures of interest for a primary task and a secondary task from the one or more input medical images using a trained machine learning model comprises predicting the measures of interest for the primary task and the secondary task from a single input medical image from a first sequence of images and a single input medical image from a second sequence of images using the trained machine learning model, and the method further comprises:
predicting additional measures of interest for the primary task and the secondary task from two input medical images from the first sequence of images and two input medical image from the second sequence of images using the trained machine learning model; and
determining a measure of confidence in the predicted measures of interest and/or the predicted additional measures of interest for the primary task and the secondary task based on a difference between 1) the measures of interest predicted from the single input medical image from the first sequence of images and the single input medical image from the second sequence of images using the trained machine learning model, and 2) the additional measures of interest predicted from the two input medical image from the first sequence of images and the two input medical image from the second sequence of images using the trained machine learning model.

7. The method of claim 1 , wherein the measure of interest for the primary task comprises a hemodynamic index.

8. The method of claim 7 , wherein the hemodynamic index is a virtual fractional flow reserve.

9. The method of claim 1 , wherein the measure of interest for the secondary task comprises at least one of: a location of a measurement point, a location of a common image point, a location of a stenosis, and a segmentation of a vessel.

10. The method of claim 1 , further comprising selecting the one or more input medical images by:
receiving respective electrocardiogram signals acquired during acquisition of a first sequence of images and a second sequence of images;
associating an index with each image in the first sequence of images and the second sequence of images based on their respective electrocardiogram signals;
matching images of the first sequence of images with images of the second sequence of images based on their associated index; and
selecting an image of the first sequence and an image of the second sequence that match as the one or more input medical images.

11. An apparatus for retraining a trained machine learning model, comprising:
means for receiving one or more input medical images;
means for predicting measures of interest for a primary task and a secondary task from the one or more input medical images using a trained machine learning model;
means for outputting the predicted measures of interest for the primary task and the secondary task;
means for receiving user feedback on the predicted measure of interest for the secondary task; and
means for retraining the trained machine learning model for predicting the measures of interest for the primary task and the secondary task based on the user feedback on the output for the secondary task.

12. The apparatus of claim 11 , wherein the measure of interest for the primary task cannot be directly validated by a user from the one or more input medical images and the measure of interest for the secondary task can be directly validated by the user from the one or more input medical images.

13. The apparatus of claim 11 , wherein the user feedback comprises an acceptance or a rejection of the predicted measure of interest for the secondary task.

14. The apparatus of claim 11 , wherein the user feedback comprises a modification to the predicted measure of interest for the secondary task.

15. A non-transitory computer readable medium storing computer program instructions for retraining a trained machine learning model, the computer program instructions when executed by a processor cause the processor to perform operations comprising:
receiving one or more input medical images;
predicting measures of interest for a primary task and a secondary task from the one or more input medical images using a trained machine learning model;
outputting the predicted measures of interest for the primary task and the secondary task;
receiving user feedback on the predicted measure of interest for the secondary task; and
retraining the trained machine learning model for predicting the measures of interest for the primary task and the secondary task based on the user feedback on the output for the secondary task.

16. The non-transitory computer readable medium of claim 15 , the operations further comprising:
predicting additional measures of interest for the primary task and the secondary task from the one or more input medical images using the retrained machine learning model; and
determining a measure of confidence in the predicted additional measures of interest for the primary task and the secondary task based on a difference between the measures of interest predicted using the trained machine learning model and the additional measures of interest predicted using the retrained machine learning model.

17. The non-transitory computer readable medium of claim 15 , wherein predicting measures of interest for a primary task and a secondary task from the one or more input medical images using a trained machine learning model comprises predicting the measures of interest for the primary task and the secondary task from a single input medical image from a first sequence of images and a single input medical image from a second sequence of images using the trained machine learning model, and the operations further comprises:
predicting additional measures of interes

Assignees

• Siemens Healthcare Gmbh

Inventors

• Itu Lucian Mihai
• Passerini Tiziano
• Redel Thomas
• Sharma Puneet

Classifications

• A61B5/0044 Primary

  for the heart · CPC title

• G06V10/776

  Validation; Performance evaluation · CPC title

• G06F18/2178

  based on feedback of a supervisor · CPC title

• G06F18/41

  Interactive pattern learning with a human teacher · CPC title

• G06V2201/03

  Recognition of patterns in medical or anatomical images · CPC title