Granted Patent B2

US 12,390,196 · App. 17/838,106 · Granted Aug 19, 2025

Inventors: Jingyi Yin (Nanjing, CN); Jue Zhang (Nanjing, CN)

Assignee: Nanjing Leapsonics Technology Co., Ltd.

A61B8/481A61B8/0891G06T2207/10136

Abstract

Claims (60)

1. An image processing method based on contrast-enhanced ultrasound images, applied to a first contrast-enhanced ultrasound image sequence comprising microbubbles, comprising:

performing a first decoupling operation on the first contrast-enhanced ultrasound image sequence to generate a second contrast-enhanced ultrasound image sequence corresponding to the first contrast-enhanced ultrasound image sequence, the first decoupling operation being used to improve spatial sparsity of the microbubbles; and

performing a second decoupling operation on the second contrast-enhanced ultrasound image sequence to generate a third contrast-enhanced ultrasound image sequence corresponding to the second contrast-enhanced ultrasound image sequence, the second decoupling operation being used to improve temporal sparsity of the microbubbles;

wherein the performing a second decoupling operation on the second contrast-enhanced ultrasound image sequence to generate a third contrast-enhanced ultrasound image sequence corresponding to the second contrast-enhanced ultrasound image sequence comprises: determining one-dimensional grayscale fluctuation signals corresponding to a plurality of pixel coordinates respectively, based on the plurality of pixel coordinates corresponding to the second contrast-enhanced ultrasound image sequence and pixel value sets corresponding to the plurality of pixel coordinates respectively; and

generating the third contrast-enhanced ultrasound image sequence corresponding to the second contrast-enhanced ultrasound image sequence based on the one-dimensional grayscale fluctuation signals corresponding to the plurality of pixel coordinates respectively;

before the determining one-dimensional grayscale fluctuation signals corresponding to a plurality of pixel coordinates respectively, based on the plurality of pixel coordinates corresponding to the second contrast-enhanced ultrasound image sequence and pixel value sets corresponding to the plurality of pixel coordinates respectively, further comprising:

determining a space coordinate system corresponding to the second contrast-enhanced ultrasound image sequence, the space coordinate system being capable to represent image sequence information; and

determining the plurality of pixel coordinates corresponding to the second contrast-enhanced ultrasound image sequence and the pixel value sets corresponding to the plurality of pixel coordinates respectively, based on the second contrast-enhanced ultrasound image sequence and the spatial coordinate system.

2. The image processing method based on contrast-enhanced ultrasound images according to claim 1 , wherein the generating the third contrast-enhanced ultrasound image sequence corresponding to the second contrast-enhanced ultrasound image sequence based on the one-dimensional grayscale fluctuation signals corresponding to the plurality of pixel coordinates respectively comprises:

performing a multi-scale decomposition operation on the one-dimensional grayscale fluctuation signals corresponding to the plurality of pixel coordinates to generate first multi-scale decomposition signal sets corresponding to the plurality of pixel coordinates respectively;

performing, for each pixel coordinate in the plurality of pixel coordinates, a filtering operation on the first multi-scale decomposition signal set corresponding to the pixel coordinate to generate a second multi-scale decomposition signal set corresponding to the pixel coordinate, the filtering operation being used to filter out a decomposition signal of a preset scale in the first multi-scale decomposition signal set;

performing a splicing operation on the second multi-scale decomposition signal set corresponding to the pixel coordinate to generate a splicing signal corresponding to the pixel coordinate; and

generating the third contrast-enhanced ultrasound image sequence corresponding to the second contrast-enhanced ultrasound image sequence based on splicing signals corresponding to the plurality of pixel coordinates respectively.

3. The image processing method based on contrast-enhanced ultrasound images according to claim 2 , wherein the performing a splicing operation on the second multi-scale decomposition signal set corresponding to the pixel coordinate to generate a splicing signal corresponding to the pixel coordinate comprises:

performing, for the second multi-scale decomposition signal set corresponding to the pixel coordinate, the splicing operation on decomposition signals corresponding to decomposition scales sequentially in an ascending order of decomposition levels or scales to generate the splicing signal corresponding to the pixel coordinate.

4. The image processing method based on contrast-enhanced ultrasound images according to claim 2 , wherein the decomposition signal of the preset scale comprises a decomposition signal with a smallest scale in the first multi-scale decomposition signal set.

5. The image processing method based on contrast-enhanced ultrasound images according to claim 3 , wherein the decomposition signal of the preset scale comprises a decomposition signal with a smallest scale in the first multi-scale decomposition signal set.

6. The image processing method based on contrast-enhanced ultrasound images according to claim 4 , wherein the decomposition signal of the preset scale further comprises a decomposition signal with a second smallest scale in the first multi-scale decomposition signal set.

7. The image processing method based on contrast-enhanced ultrasound images according to claim 2 , before the determining one-dimensional grayscale fluctuation signals corresponding to a plurality of pixel coordinates respectively, based on the plurality of pixel coordinates corresponding to the second contrast-enhanced ultrasound image sequence and pixel value sets corresponding to the plurality of pixel coordinates respectively, further comprising:

determining a space coordinate system corresponding to the second contrast-enhanced ultrasound image sequence, the space coordinate system being capable to represent image sequence information; and

determining the plurality of pixel coordinates corresponding to the second contrast-enhanced ultrasound image sequence and the pixel value sets corresponding to the plurality of pixel coordinates respectively, based on the second contrast-enhanced ultrasound image sequence and the spatial coordinate system.

8. The image processing method based on contrast-enhanced ultrasound images according to claim 1 , wherein the determining one-dimensional grayscale fluctuation signals corresponding to a plurality of pixel coordinates respectively, based on the plurality of pixel coordinates corresponding to the second contrast-enhanced ultrasound image sequence and pixel value sets corresponding to the plurality of pixel coordinates respectively comprises:

splicing, for each pixel coordinate in the plurality of pixel coordinates, the pixel value set corresponding to the pixel coordinate into the one-dimensional grayscale fluctuation signal based on image sequence order represented by a spatial coordinate system, so as to determine the one-dimensional grayscale fluctuation signals corresponding to the plurality of pixel coordinates respectively.

9. The image processing method based on contrast-enhanced ultrasound images according to claim 1 , wherein the performing a first decoupling operation on the first contrast-enhanced ultrasound image sequence to generate a second contrast-enhanced ultrasound image sequence corresponding to the first contrast-enhanced ultrasound image sequence comprises:

determining, for each contrast-enhanced ultrasound image in the first contrast-enhanced ultrasound image sequence, distance information between a microbubble region in the contrast-enhanced ultrasound image and a background region corresponding to the microbubble region;

performing a pixel weighting operation on the contrast-enhanced ultrasound image based on the distance information corresponding to the contrast-enhanced ultrasound image to generate a weighted image corresponding to the contrast-enhanced ultrasound image; and

generating the second contrast-enhanced ultrasound image sequence corresponding to the first contrast-enhanced ultrasound image sequence based on weighted images respectively corresponding to contrast-enhanced ultrasound images of the first contrast-enhanced ultrasound image sequence.

10. The image processing method based on contrast-enhanced ultrasound images according to claim 9 , wherein the performing a pixel weighting operation on the contrast-enhanced ultrasound image based on the distance information corresponding to the contrast-enhanced ultrasound image to generate a weighted image corresponding to the contrast-enhanced ultrasound image comprises:

determining, based on each pixel coordinate corresponding to the microbubble region, a pixel grayscale value and a shortest distance corresponding to the pixel coordinate;

multiplying the pixel grayscale value and the shortest distance corresponding to the pixel coordinate to determine a weighted value corresponding to the pixel coordinate; and

determining the weighted image corresponding to the contrast-enhanced ultrasound image based on weighted values respectively corresponding to all pixel coordinates corresponding to the microbubble region.

11. The image processing method based on contrast-enhanced ultrasound images according to claim 9 , wherein the determining distance information between a microbubble region in the contrast-enhanced ultrasound image and a background region corresponding to the microbubble region comprises:

performing a binarization processing on the contrast-enhanced ultrasound image based on the microbubble region and the background region to generate a binarized image; and

determining the distance information between the microbubble region and the background region based on the binarized image.

12. The image processing method based on contrast-enhanced ultrasound images according to claim 10 , wherein the determining distance information between a microbubble region in the contrast-enhanced ultrasound image and a background region corresponding to the microbubble region comprises:

performing a binarization processing on the contrast-enhanced ultrasound image based on the microbubble region and the background region to generate a binarized image; and

determining the distance information between the microbubble region and the background region based on the binarized image.

13. The image processing method based on contrast-enhanced ultrasound images according to claim 9 , wherein the microbubble region comprises a plurality of pixel blocks, and the determining distance information between a microbubble region in the contrast-enhanced ultrasound image and a background region corresponding to the microbubble region comprises:

determining, for each pixel block of the plurality of pixel blocks, a shortest distance from the pixel block to the background region; and

determining the distance information based on shortest distances respectively corresponding to the plurality of pixel blocks.

14. The image processing method based on contrast-enhanced ultrasound images according to claim 10 , wherein the microbubble region comprises a plurality of pixel blocks, and the determining distance information between a microbubble region in the contrast-enhanced ultrasound image and a background region corresponding to the microbubble region comprises:

determining, for each pixel block of the plurality of pixel blocks, a shortest distance from the pixel block to the background region; and

determining the distance information based on shortest distances respectively corresponding to the plurality of pixel blocks.

15. The image processing method based on contrast-enhanced ultrasound images according to claim 10 , wherein the shortest distance is a Euclidean distance or a Manhattan distance.

16. A non-transitory computer readable storage medium storing a computer program for executing the image processing method based on contrast-enhanced ultrasound images, applied to a first contrast-enhanced ultrasound image sequence comprising microbubbles, comprising:

performing a first decoupling operation on the first contrast-enhanced ultrasound image sequence to generate a second contrast-enhanced ultrasound image sequence corresponding to the first contrast-enhanced ultrasound image sequence, the first decoupling operation being used to improve spatial sparsity of the microbubbles; and

performing a second decoupling operation on the second contrast-enhanced ultrasound image sequence to generate a third contrast-enhanced ultrasound image sequence corresponding to the second contrast-enhanced ultrasound image sequence, the second decoupling operation being used to improve temporal sparsity of the microbubbles;

wherein the performing a second decoupling operation on the second contrast-enhanced ultrasound image sequence to generate a third contrast-enhanced ultrasound image sequence corresponding to the second contrast-enhanced ultrasound image sequence comprises: determining one-dimensional grayscale fluctuation signals corresponding to a plurality of pixel coordinates respectively, based on the plurality of pixel coordinates corresponding to the second contrast-enhanced ultrasound image sequence and pixel value sets corresponding to the plurality of pixel coordinates respectively; and

generating the third contrast-enhanced ultrasound image sequence corresponding to the second contrast-enhanced ultrasound image sequence based on the one-dimensional grayscale fluctuation signals corresponding to the plurality of pixel coordinates respectively;

before the determining one-dimensional grayscale fluctuation signals corresponding to a plurality of pixel coordinates respectively, based on the plurality of pixel coordinates corresponding to the second contrast-enhanced ultrasound image sequence and pixel value sets corresponding to the plurality of pixel coordinates respectively, further comprising:

determining a space coordinate system corresponding to the second contrast-enhanced ultrasound image sequence, the space coordinate system being capable to represent image sequence information; and

determining the plurality of pixel coordinates corresponding to the second contrast-enhanced ultrasound image sequence and the pixel value sets corresponding to the plurality of pixel coordinates respectively, based on the second contrast-enhanced ultrasound image sequence and the spatial coordinate system.

17. An image processing apparatus based on contrast-enhanced ultrasound images, applied to a first contrast-enhanced ultrasound image sequence comprising microbubbles, comprising a memory, a processor, and a computer program stored in the memory and executed by the processor, wherein when the computer program is executed by the processor, the processor implements the following steps:

performing a first decoupling operation on the first contrast-enhanced ultrasound image sequence to generate a second contrast-enhanced ultrasound image sequence corresponding to the first contrast-enhanced ultrasound image sequence, the first decoupling operation being used to improve spatial sparsity of the microbubbles; and

performing a second decoupling operation on the second contrast-enhanced ultrasound image sequence to generate a third contrast-enhanced ultrasound image sequence corresponding to the second contrast-enhanced ultrasound image sequence, the second decoupling operation being used to improve temporal sparsity of the microbubbles;

wherein the performing a second decoupling operation on the second contrast-enhanced ultrasound image sequence to generate a third contrast-enhanced ultrasound image sequence corresponding to the second contrast-enhanced ultrasound image sequence comprises: determining one-dimensional grayscale fluctuation signals corresponding to a plurality of pixel coordinates respectively, based on the plurality of pixel coordinates corresponding to the second contrast-enhanced ultrasound image sequence and pixel value sets corresponding to the plurality of pixel coordinates respectively; and

generating the third contrast-enhanced ultrasound image sequence corresponding to the second contrast-enhanced ultrasound image sequence based on the one-dimensional grayscale fluctuation signals corresponding to the plurality of pixel coordinates respectively:

before the determining one-dimensional grayscale fluctuation signals corresponding to a plurality of pixel coordinates respectively, based on the plurality of pixel coordinates corresponding to the second contrast-enhanced ultrasound image sequence and pixel value sets corresponding to the plurality of pixel coordinates respectively, further comprising:

determining a space coordinate system corresponding to the second contrast-enhanced ultrasound image sequence, the space coordinate system being capable to represent image sequence information; and

determining the plurality of pixel coordinates corresponding to the second contrast-enhanced ultrasound image sequence and the pixel value sets corresponding to the plurality of pixel coordinates respectively, based on the second contrast-enhanced ultrasound image sequence and the spatial coordinate system.

Assignments (2)

Priority Claims (1)

Continuity (2)

References Cited (12)