Image quality assessment for refinement of imaging rendering parameters for rendering medical images

Patent metadata

Field	Value
Publication number	US-12106469-B2
Application number	US-202217653516-A
Country	US
Kind code	B2
Filing date	Mar 4, 2022
Priority date	Mar 4, 2022
Publication date	Oct 1, 2024
Grant date	Oct 1, 2024

Abstract

Systems and methods for automatically determining an image quality assessment of a rendered medical image are provided. A rendered medical image is received. One or more measures of interest are extracted from the rendered medical image. An image quality assessment of the rendered medical image is determined using a machine learning based image quality assessment network based on the one or more measures of interest. The image quality assessment of the rendered medical image is output.

First claim

The invention claimed is:

1. A computer-implemented method, comprising:
receiving a rendered medical image and an input depth map of the rendered medical image;
generating an estimated depth map from the rendered medical image;
comparing the input depth map with the estimated depth map;
extracting one or more measures of interest from the rendered medical image;
determining an image quality assessment of the rendered medical image using a machine learning based image quality assessment network based on the one or more measures of interest and results of the comparison; and
outputting the image quality assessment of the rendered medical image.

2. The computer-implemented method of claim 1 , further comprising:
comparing the image quality assessment with a threshold; and
in response to determining that the image quality assessment does not satisfy the threshold, modifying imaging rendering parameters from which the rendered medical image was rendered.

3. The computer-implemented method of claim 2 , further comprising:
in response to determining that the image quality assessment does not satisfy the threshold:
generating an updated rendered medical image based on the modified imaging rendering parameters; and
repeating the extracting, the determining, and the modifying using the updated rendered medical image as the rendered medical image until the image quality assessment satisfies a threshold.

4. The computer-implemented method of claim 2 , further comprising:
in response to determining that the image quality assessment satisfies the threshold, retraining the machine learning based image quality assessment network based on the rendered medical image and the image quality assessment.

5. The computer-implemented method of claim 2 , further comprising:
in response to determining that the image quality assessment satisfies the threshold, storing the imaging rendering parameters in memory.

6. The computer-implemented method of claim 1 , wherein the one or more measures of interest comprise natural scene statistics.

7. An apparatus, comprising:
means for receiving a rendered medical image and an input depth map of the rendered medical image;
means for generating an estimated depth map from the rendered medical image;
means for comparing the input depth map with the estimated depth map;
means for extracting one or more measures of interest from the rendered medical image;
means for determining an image quality assessment of the rendered medical image using a machine learning based image quality assessment network based on the one or more measures of interest and results of the comparison; and
means for outputting the image quality assessment of the rendered medical image.

8. The apparatus of claim 7 , further comprising:
means for comparing the image quality assessment with a threshold; and
means for modifying imaging rendering parameters from which the rendered medical image was rendered in response to determining that the image quality assessment does not satisfy the threshold.

9. The apparatus of claim 8 , further comprising:
in response to determining that the image quality assessment does not satisfy the threshold:
means for generating an updated rendered medical image based on the modified imaging rendering parameters; and
means for repeating the extracting, the determining, and the modifying using the updated rendered medical image as the rendered medical image until the image quality assessment satisfies a threshold.

10. The apparatus of claim 8 , further comprising:
means for retraining the machine learning based image quality assessment network based on the rendered medical image and the image quality assessment in response to determining that the image quality assessment satisfies the threshold.

11. The apparatus of claim 8 , further comprising:
means for storing the imaging rendering parameters in memory in response to determining that the image quality assessment satisfies the threshold.

12. The apparatus of claim 7 , wherein the one or more measures of interest comprise natural scene statistics.

13. A non-transitory computer readable medium storing computer program instructions, the computer program instructions when executed by a processor cause the processor to perform operations comprising:
receiving a rendered medical image and an input depth map of the rendered medical image;
generating an estimated depth map from the rendered medical image;
comparing the input depth map with the estimated depth map;
extracting one or more measures of interest from the rendered medical image;
determining an image quality assessment of the rendered medical image using a machine learning based image quality assessment network based on the one or more measures of interest and results of the comparison; and
outputting the image quality assessment of the rendered medical image.

14. The non-transitory computer readable medium of claim 13 , the operations further comprising:
comparing the image quality assessment with a threshold; and
in response to determining that the image quality assessment does not satisfy the threshold, modifying imaging rendering parameters from which the rendered medical image was rendered.

15. The non-transitory computer readable medium of claim 14 , the operations further comprising:
in response to determining that the image quality assessment does not satisfy the threshold:
generating an updated rendered medical image based on the modified imaging rendering parameters; and
repeating the extracting, the determining, and the modifying using the updated rendered medical image as the rendered medical image until the image quality assessment satisfies a threshold.

16. The non-transitory computer readable medium of claim 14 , the operations further comprising:
in response to determining that the image quality assessment satisfies the threshold, retraining the machine learning based image quality assessment network based on the rendered medical image and the image quality assessment.

17. The non-transitory computer readable medium of claim 14 , the operations further comprising:
in response to determining that the image quality assessment satisfies the threshold, storing the imaging rendering parameters in memory.

Assignees

• Siemens Healthineers Ag

Inventors

• Sudarsky Sandra
• Petkov Kaloian
• Yu Daphne

Classifications

• G06T2207/30168

  Image quality inspection · CPC title

• G06T2207/30004

  Biomedical image processing · CPC title

• G06T2207/20081

  Training; Learning · CPC title

• G06T5/50

  using two or more images, e.g. averaging or subtraction · CPC title

• G06T1/60

  Memory management · CPC title