# US 2023/0058384 A1 · Systems and methods for image processing

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2023/0058384 A1
- Document ID: US20230058384A1
- Status: Published application
- Kind: A1
- Application number: 18/047,267
- Filed: 2022-10-17
- Published: 2023-02-23
- Earliest claimed: 2018-05-30
- Assignees: Shanghai United Imaging Healthcare Co., Ltd.
- Applicants: Shanghai United Imaging Healthcare Co., Ltd.
- Inventors: Liang XU; Jing YAN; Hanyu WANG; Jie NIU; Haihua ZHOU; Juan FENG; Le YANG; Na ZHANG; Yange MA
- Web page: https://patentgrep.com/patent/US20230058384A1

## CPC

- G06T 7/11: Region-based segmentation
- A61B 6/06: Diaphragms
- A61B 6/502: {for diagnosis of breast, i.e. mammography}
- A61B 6/547: {involving tracking of position of the device or parts of the device}
- G06T 5/77: Retouching; Inpainting; Scratch removal
- G06T 7/0014: {using an image reference approach}
- G06T 7/13: Edge detection
- G06T 7/136: involving thresholding
- G06T 7/194: involving foreground-background segmentation
- G06T 7/70: Determining position or orientation of objects or cameras (camera calibration G06T7/80)
- G06V 10/28: Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
- G06V 10/32: Normalisation of the pattern dimensions
- G06T 2207/10116: X-ray image
- G06T 2207/30068: Mammography; Breast
- G06V 2201/03: Recognition of patterns in medical or anatomical images
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

A method may include obtaining an original image. The method may also include determining a plurality of decomposition coefficients of the original image by decomposing the original image. The method may also include determining at least one enhancement coefficient by performing enhancement to at least one of the plurality of decomposition coefficients using a coefficient enhancement model. The method may also include generating an enhanced image corresponding to the original image based on the at least one enhancement coefficient.

## Claims

### Claim 1

A method for image enhancement implemented on a machine having at least one storage device and at least one processor, the method comprising:
obtaining an original image;
determining a plurality of decomposition coefficients of the original image by decomposing the original image;
determining at least one enhancement coefficient by performing enhancement to at least one of the plurality of decomposition coefficients using a coefficient enhancement model; and
generating an enhanced image corresponding to the original image based on the at least one enhancement coefficient.

### Claim 2 (depends on 1)

The method of claim 1, wherein the coefficient enhancement model is obtained by performing operations including:
obtaining a training set including a plurality of sample pairs, each of the plurality of sample pairs including a plurality of first decomposition coefficients of a sample image and a plurality of second decomposition coefficients corresponding to the first decomposition coefficients; and
obtaining the coefficient enhancement model by training, based on the training set, a preliminary model.

### Claim 3 (depends on 2)

The method of claim 2, wherein obtaining the training set including the plurality of sample pairs includes:
obtaining an enhanced image corresponding to the sample image by performing image processing on the sample image;
obtaining the plurality of first decomposition coefficients of the sample image and the plurality of second decomposition coefficients of the enhanced image corresponding to the sample image by decomposing the sample image and the corresponding enhanced image; and
determining the plurality of first decomposition coefficients and the plurality of second decomposition coefficients as the sample pair.

### Claim 4 (depends on 2)

The method of claim 2, wherein obtaining the training set including the plurality of sample pairs includes:
obtaining the plurality of first decomposition coefficients of the sample image by decomposing the sample image;
obtaining the plurality of second decomposition coefficients by performing enhancement to the plurality of first decomposition coefficients of the sample image; and
determining the plurality of first decomposition coefficients of the sample image and the plurality of second decomposition coefficients as the sample pair.

### Claim 5 (depends on 4)

The method of claim 4, wherein the image processing includes at least one of a histogram equalization algorithm, a gamma conversion algorithm, an exponential image enhancement algorithm, or a logarithmic image enhancement algorithm.

### Claim 6 (depends on 1)

The method of claim 1, wherein the coefficient enhancement model includes a trained deep learning model.

### Claim 7 (depends on 1)

The method of claim 1, wherein the plurality of decomposition coefficients of the original image is obtained by decomposing the original image using a multi-resolution analysis algorithm.

### Claim 8 (depends on 7)

The method of claim 7, wherein the multi-resolution analysis algorithm includes at least one of a Gauss-Laplace pyramid decomposition algorithm or a wavelet decomposition algorithm.

### Claim 9 (depends on 1)

The method of claim 1, further comprising:
performing a pre-processing operation on the original image.

### Claim 10

A system for image enhancement, comprising:
at least one storage device including a set of instructions; and
at least one processor in communication with the at least one storage device, wherein when executing the set of instructions, the at least one processor is directed to perform operations including:
obtaining an original image;
determining a plurality of decomposition coefficients of the original image by decomposing the original image;
determining at least one enhancement coefficient by performing enhancement to at least one of the plurality of decomposition coefficients using a coefficient enhancement model; and
generating an enhanced image corresponding to the original image based on the at least one enhancement coefficient.

### Claim 11 (depends on 10)

The system of claim 10, wherein the coefficient enhancement model is provided by:
obtaining a training set including a plurality of sample pairs, each of the plurality of sample pairs including a plurality of first decomposition coefficients of a sample image and a plurality of second decomposition coefficients corresponding to the first decomposition coefficients; and
obtaining the coefficient enhancement model by training, based on the training set, a preliminary model.

### Claim 12 (depends on 11)

The system of claim 11, wherein obtaining the training set including the plurality of sample pairs includes:
obtaining an enhanced image corresponding to the sample image by performing image processing on the sample image;
obtaining the plurality of first decomposition coefficients of the sample image and the plurality of second decomposition coefficients of the enhanced image corresponding to the sample image by decomposing the sample image and the corresponding enhanced image; and
determining the plurality of first decomposition coefficients and the plurality of second decomposition coefficients as the sample pair.

### Claim 13 (depends on 12)

The system of claim 12, wherein the image processing includes at least one of a histogram equalization algorithm, a gamma conversion algorithm, an exponential image enhancement algorithm, or a logarithmic image enhancement algorithm.

### Claim 14 (depends on 11)

The system of claim 11, wherein obtaining the training set including the plurality of sample pairs includes:
obtaining the plurality of first decomposition coefficients of the sample image by decomposing the sample image;
obtaining the plurality of second decomposition coefficients by performing enhancement to the plurality of first decomposition coefficients of the sample image; and
determining the plurality of first decomposition coefficients of the sample image and the plurality of second decomposition coefficients as the sample pair.

### Claim 15 (depends on 10)

The system of claim 10, wherein the coefficient enhancement model includes a trained deep learning model.

### Claim 16 (depends on 10)

The system of claim 10, wherein the plurality of decomposition coefficients of the original image is obtained by decomposing the original image using a multi-resolution analysis algorithm.

### Claim 17 (depends on 16)

The system of claim 16, wherein the multi-resolution analysis algorithm includes at least one of a Gauss-Laplace pyramid decomposition algorithm or a wavelet decomposition algorithm.

### Claim 18 (depends on 10)

The system of claim 10, wherein the at least one processor is directed to perform the operations including:
performing a pre-processing operation on the original image.

### Claim 19 (depends on 18)

The system of claim 18, wherein performing the pre-processing operation on the original image includes:
obtaining a pre-processed image by adjusting one or more display parameters of the original image.

### Claim 20

A non-transitory computer readable medium, comprising at least one set of instructions for image enhancement, wherein when executed by one or more processors of a computing device, the at least one set of instructions causes the computing device to perform a method, the method comprising:
obtaining an original image;
determining a plurality of decomposition coefficients of the original image by decomposing the original image;
determining at least one enhancement coefficient by performing enhancement to at least one of the plurality of decomposition coefficients using a coefficient enhancement model; and
generating an enhanced image corresponding to the original image based on the at least one enhancement coefficient.
