Information processing device, information processing method, and computer program

Patent metadata

Field	Value
Publication number	US-11810293-B2
Application number	US-201917056876-A
Country	US
Kind code	B2
Filing date	Feb 20, 2019
Priority date	May 23, 2018
Publication date	Nov 7, 2023
Grant date	Nov 7, 2023

Abstract

The present invention has been made in view of the foregoing, and an object thereof is to provide an information processing device capable of appropriately determining a necessity of the ultrasonography even when a high-density mammary gland area exists in a narrow area. The present invention provides an information processing device comprising: a mammary gland area extractor configured to extract a mammary gland area in a mammography image; a mammary gland pixel detector configured to detect a mammary gland pixel in the mammary gland area; and a mammary gland density calculator configured to calculate a mammary gland density based on a ratio of the mammary gland pixels to the mammary gland area, wherein the mammary gland area is a narrower area than an entire breast in the mammography image.

First claim

The invention claimed is:

1. An information processing device comprising:
a mammary gland area extractor configured to extract a mammary gland area in a mammography image, wherein the mammary gland area extractor comprises:
a mammary gland area probability calculator configured to calculate a probability that an area in the mammography image is the mammary gland area; and
a post-processor configured to extract the mammary gland area based on the probability;

a mammary gland pixel detector configured to detect a mammary gland pixel in the mammary gland area; and
a mammary gland density calculator configured to calculate a mammary gland density based on a ratio of the mammary gland pixels to the mammary gland area, wherein the mammary gland area is a narrower area than an entire breast in the mammography image.

2. The information processing device of claim 1 , wherein the post-processor further comprises:
a candidate pixel extractor configured to generate a candidate pixel map by extracting, as a candidate pixel, a pixel having the probability that is equal to or greater than a first threshold; and
an area generator configured to form the mammary gland area by filling in a missing area with respect to the candidate pixel map.

3. The information processing device of claim 1 , wherein the mammary gland area probability calculator is further configured to calculate the probability based on a learning model that outputs the probability when the mammography image is input.

4. The information processing device of claim 3 , wherein the learning model is trained outside the information processing device in advance.

5. The information processing device of claim 3 , wherein the learning model is configured to be trainable in the information processing device.

6. The information processing device of claim 1 , wherein the mammary gland area probability calculator is further configured to calculate the probability based on a learning model that outputs the probability when the mammography image and first additional data are input, and
the first additional data is data relating to a position of a nipple in the mammography image.

7. The information processing device of claim 6 , wherein the first additional data is image data in which a pixel value of a human body pixel in the mammography image is corrected based on a position of a nipple pixel in the mammography image.

8. The information processing device of claim 7 , wherein the first additional data is the image data in which the pixel value of the human body pixel in the mammography image is corrected so that the pixel value of the human body pixel in the mammography image changes according to a linear distance between the nipple pixel and the human body pixel.

9. The information processing device of claim 8 , wherein the first additional data is the image data in which the pixel value of the human body pixel in the mammography image is corrected so that the pixel value of the human body pixel increases as the linear distance between the nipple pixel and the human body pixel decreases.

10. The information processing device of claim 7 , wherein the first additional data further comprises:
first image data in which the pixel value of the human body pixel in the mammography image is corrected so that the pixel value of the human body pixel in the mammography image changes in a first direction of the mammography image second image data in which the pixel value of the human body pixel in the mammography image is corrected so that the pixel value of the human body pixel in the mammography image changes in a second direction of the mammography image, and the first direction and the second direction cross.

11. The information processing device of claim 10 , wherein the first additional data is the image data in which the pixel value of the human body pixel in the mammography image is corrected so that the pixel value of the human body pixel increases as the linear distance in the first direction between the nipple pixel and the human body pixel decreases, and the second additional data is the image data in which the pixel value of the human body pixel in the mammography image is corrected so that the pixel value of the human body pixel increases from an upper side in the second direction to a lower side in the second direction.

12. The information processing device of claim 1 , wherein the mammary gland area probability calculator is further configured to calculate the probability based on a learning model that outputs the probability when the mammography image and second additional data are input, and the second additional data is data indicating distribution of representative brightness value of the mammography image or brightness value of the mammography image.

13. The information processing device of claim 12 , wherein the second additional data is image data in which the brightness value of a human body pixel in the mammography image is corrected based on the representative brightness value or the distribution.

14. The information processing device of claim 1 , wherein the mammary gland area probability calculator is further configured to calculate the probability without removing a pectoralis major muscle area in the mammography image.

15. The information processing device of claim 1 , wherein the mammary gland pixel detector is further configured to detect the mammary gland pixel in the mammary gland area based on the probability.

16. The information processing device of claim 15 , wherein the mammary gland pixel detector is further configured to detect a pixel, as the mammary gland pixel, having the probability that is equal to or greater than a second threshold, and the probability of the mammary gland area is higher when the second threshold is used than when the first threshold is used.

17. The information processing device of claim 1 , wherein the mammary gland pixel detector is further configured to detect the mammary gland pixel based on a brightness value of the mammary gland area.

18. An information processing method comprising:
calculating a probability that an area in a mammography image is a mammary gland area in the mammography image;
extracting the mammary gland area in the mammography image based on the probability;
detecting a mammary gland pixel in the mammary gland area; and
calculating a ratio of the mammary gland pixels to the mammary gland area, wherein the mammary gland area is a narrower area than an entire breast in the mammography image.

19. A non-transitory computer readable medium that stores a computer program causing a computer to execute an information processing method, the information processing method comprising:
calculating a probability that an area in a mammography image is a mammary gland area in the mammography image;
extracting the mammary gland area in the mammography image based on the probability;
detecting a mammary gland pixel in the mammary gland area; and
calculating a ratio of the mammary gland pixels to the mammary gland area, wherein the mammary gland area is a narrower area than an entire breast in the mammography image.

Assignees

• Eizo Corp

Inventors

• Kato Yu
• Higashi Masafumi
• Aoki Reo
• Ogaki Mamoru
• Arai Ikumi
• Hashimoto Noriyuki
• Hirata Naoaki

Classifications

• G06T7/0012 Primary

  Biomedical image inspection · CPC title

• G06T7/62

  of area, perimeter, diameter or volume · CPC title

• G06T2207/30068

  Mammography; Breast · CPC title

• A61B6/502 Primary

  for diagnosis of breast, i.e. mammography · CPC title

• A61B6/5217 Primary

  extracting a diagnostic or physiological parameter from medical diagnostic data · CPC title