Back to results
US 10,762,603 B2Granted
System and method for image denoising
AssigneeShanghai United Imaging Healthcare Co., Ltd.
InventorsStanislav Zabic, Zhicong Yu
Life of this patent
Estimating the term…
Abstract
Systems and methods for image noise reduction are provided. The methods may include obtaining first image data, determining a restriction or a gradient of the first image data, determining a regularization parameter for the first image data based on the restriction or the gradient, generating second image data based on the regularization parameter and the first image data, and generating a regularized image based on the second image data.
Claims20
A system comprising:
- a processor;
- and
- storage configured to store instructions, the instructions, when executed by the processor, cause the processor to perform operations including;
- obtaining image data corresponding to one or ore pixels or voxels;
- determining a regularization item that regularizes the image data;
- determining an assessment parameter of the image data, wherein the assessment parameter includes a restriction or a gradient of the image data, the assessment parameter including one or more assessment elements each of which corresponds to one of the one or more pixels or voxels;
- determining a regularization parameter for the image data by a process, wherein the regularization parameter relates to strength of the regularization item, the process including:
- for each of the one or more pixels or voxels and a corresponding parameter value of the each of the one or more pixels or voxels,
- obtaining a corresponding assessment element of the each of the one or more pixels or voxels;
- boosting the parameter value if the assessment element is in a range;
- and
- maintaining the parameter value if the assessment element is outside the range;
- and
- generating a regularized image based on the regularization parameter and the regularization item.
11 more elements
A method implemented on at least one device each of which has at least one processor and storage, the method comprising:
- obtaining image data corresponding to one or more pixels or voxels;
- determining a regularization item that regularizes the image data;
- determining an assessment parameter of the image data, wherein the assessment parameter include a restriction or a gradient of the image data, the assessment parameter including one or more assessment elements each of which corresponds to one of the one or more pixels or voxels;
- determining a regularization parameter for the image data by a process, wherein the regularization parameter relates to strength of the regularization item, the process including:
- for each of the one or more pixels or voxels and a corresponding parameter value of the each of the one or more pixels or voxels,
- obtaining a corresponding assessment element of the each of the one or more pixels or voxels;
- boosting the parameter value if the assessment element is within a range;
- and
- maintaining the parameter value if the assessment element is outside the range;
- and
- generating a regularized image based on the regularization parameter and the regularization item.
8 more elements
A system comprising:
- at least one storage medium including a set of instructions for processing a projection image;
- an image generation module configured to obtain image data corresponding to one or more pixels or voxels;
- at least one processor in communication with the at least one storage medium, wherein when executing the set of instructions, the at least one processor is configured to cause the system to:
- determine a regularization item that regularizes the image data;
- determine an assessment parameter of the image data, wherein the assessment parameter includes a restriction or a gradient of the image data, the assessment parameter including one or more assessment elements each of which corresponds to one of the one or more pixels or voxels;
- determine a regularization parameter for the image data by a process, wherein the regularization parameter relates to strength of the regularization item, the process including:
- for each of the one or more pixels or voxels and a corresponding parameter value of the each of the one or more pixels or voxels,
- obtain a corresponding assessment element of the each of the one or more pixels or voxels;
- boost the parameter value if the assessment element is within a range;
- and
- maintain the parameter value if the assessment element is outside the range;
- and
- generate a regularized image based on the regularization parameter and the regularization item.
10 more elements
Dependencies are inferred from the claim text.