Systems and methods for image processing

Patent metadata

Field	Value
Publication number	US-11935211-B2
Application number	US-202117445611-A
Country	US
Kind code	B2
Filing date	Aug 23, 2021
Priority date	Sep 21, 2020
Publication date	Mar 19, 2024
Grant date	Mar 19, 2024

Abstract

Systems and methods for image processing are provided in the present disclosure. The systems and methods may obtain an image; determine a current resolution level of the image; determine, based on the current resolution level of the image, from a group of resolution level ranges, a reference resolution level range corresponding to the image; determine a target processing model corresponding to the reference resolution level range; and/or determine a processed image with a target resolution level by processing the image using the target processing model, the target resolution level of the processed image being higher than the current resolution level of the image.

First claim

What is claimed is:

1. A method implemented on a computing device including a storage device and at least one processor for image processing, comprising:
obtaining an image;
determining a current resolution level of the image;
determining, based on the current resolution level of the image, from a group of resolution level ranges, a reference resolution level range corresponding to the image;
determining a target processing model corresponding to the reference resolution level range, wherein the target processing model is generated by:
obtaining a plurality of sample images with relatively low resolution levels and a plurality of sample images with relatively high resolution levels;
grouping the plurality of sample images with relatively low resolution levels and grouping the plurality of sample images with relatively high resolution levels, each group of sample images with relatively low resolution levels corresponding to a group of sample images with relatively high resolution levels, and the each group of sample images with relatively low resolution levels corresponding to a resolution level range of the group of resolution level ranges;
obtaining a plurality of processing models by training each processing model using a corresponding group of sample images with relatively low resolution levels and a corresponding group of sample images with relatively high resolution levels; and
selecting, from the plurality of processing models, the target processing model corresponding to the reference resolution level range, wherein
resolution levels of the sample images with relatively low resolution levels are lower than a resolution level threshold, and resolution levels of the sample images with relatively high resolution levels are higher than or equal to a resolution level threshold; and

determining a processed image with a target resolution level by processing the image using the target processing model, the target resolution level of the processed image being higher than the current resolution level of the image.

2. The method of claim 1 , wherein the determining, based on the current resolution level of the image, from a group of resolution level ranges, a reference resolution level range corresponding to the image comprises:
designating, from the group of resolution level ranges, a resolution level range including the current resolution level as the reference resolution level range corresponding to the image.

3. The method of claim 1 , wherein the group of resolution level ranges is generated according to a process including:
determining an upper limit of resolution levels;
determining a lower limit of resolution levels;
determining a scaling factor; and
determining the group of resolution level ranges based on the upper limit of resolution levels, the lower limit of resolution levels, and the scaling factor.

4. The method of claim 3 , wherein the determining the group of resolution level ranges based on the upper limit of resolution levels, the lower limit of resolution levels, and the scaling factor comprises:
determining the group of resolution level ranges based on the upper limit of resolution levels, the lower limit of resolution levels, and the scaling factor multiplied by different multiplies.

5. The method of claim 1 , wherein the group of resolution level ranges is generated according to a process including:
determining an upper limit of resolution levels;
determining a lower limit of resolution levels;
determining an interval value; and
determining the group of resolution level ranges with an equal interval based on the upper limit of resolution levels, the lower limit of resolution levels, and the interval value.

6. The method of claim 1 , wherein the group of resolution level ranges is generated according to a process including:
determining an upper limit of resolution levels;
determining a lower limit of resolution levels;
determining an interval value; and
determining the group of resolution level ranges based on the upper limit of resolution levels, the lower limit of resolution levels, and the interval value, the group of resolution level ranges including at least two resolution level ranges with unequal intervals.

7. The method of claim 1 , wherein the group of resolution level ranges is generated according to a process including:
determining the group of resolution level ranges based on a scanning protocol and/or a scanning region of the image.

8. The method of claim 1 , wherein the group of resolution level ranges is generated according to a process including:
determining a magnetic field intensity and/or a pulse sequence used in generating the image; and
determining the group of resolution level ranges based on the magnetic field intensity and/or the pulse sequence.

9. The method of claim 1 , wherein the target processing model corresponding to the reference resolution level range is generated by training an initial processing model using sample images with resolution levels in the reference resolution level range.

10. The method of claim 1 , wherein the training each processing model using a corresponding group of sample images with relatively low resolution levels and a corresponding group of sample images with relatively high resolution levels comprises:
generating estimated images by inputting the corresponding group of sample images with relatively low resolution levels into the each processing model;
determining a value of a cost function based on the estimated images and the corresponding group of sample images with relatively high resolution levels;
determining whether a termination condition is satisfied based on the value of the cost function; and
in response to a determination that the termination condition is not satisfied, updating one or more parameters of the each processing model; or
in response to a determination that the termination condition is satisfied, determining the each processing model based on the updated parameters.

11. The method of claim 1 , wherein the grouping the plurality of sample images with relatively low resolution levels and grouping the plurality of sample images with relatively high resolution levels comprises:
grouping, based on the group of resolution level ranges, the plurality of sample images with relatively low resolution levels to obtain a plurality of groups of sample images with relatively low resolution levels; and
grouping the plurality of sample images with relatively high resolution levels based on the plurality of groups of sample images with relatively low resolution levels.

12. The method of claim 1 , wherein the grouping the plurality of sample images with relatively low resolution levels and grouping the plurality of sample images with relatively high resolution levels comprises:
grouping, based on the group of resolution level ranges, the plurality of sample images with relatively high resolution levels to obtain a plurality of groups of sample images with relatively high resolution levels; and
grouping the plurality of sample images with relatively low resolution levels based on the plurality of groups of sample images with relatively high resolution levels.

13. The method of claim 1 , wherein the obtaining a plurality of sample images with relatively low resolution levels and a plurality of sample images with relatively high resolution levels comprises:
acquiring first data associated with the plurality of sample images with relatively low resolution levels using a magnetic resonance imaging device;
generating the plurality of sample images with relatively low resolution levels based on the first data;
acquiring second

Assignees

• Shanghai United Imaging Healthcare Co Ltd

Inventors

• Li Guobin
• Zhai Renkuan
• Ji Meiling

Classifications

• G06T3/4053 Primary

  based on super-resolution, i.e. the output image resolution being higher than the sensor resolution · CPC title

• G06T7/97

  Determining parameters from multiple pictures (depth or shape recovery from multiple images G06T7/55; stereo camera calibration G06T7/85) · CPC title

• G06T2207/20016

  Hierarchical, coarse-to-fine, multiscale or multiresolution image processing; Pyramid transform · CPC title

• G06T3/4046

  using neural networks · CPC title

• G06T5/50

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