Systems and methods for image processing

Patent metadata

Field	Value
Publication number	US-11769249-B2
Application number	US-202016994733-A
Country	US
Kind code	B2
Filing date	Aug 17, 2020
Priority date	Dec 31, 2015
Publication date	Sep 26, 2023
Grant date	Sep 26, 2023

Abstract

An image processing method is provided, including: obtaining image data of a cavity wall of an organ; unfolding the cavity wall; and generating an image of the unfolded cavity wall. The unfolding of the cavity wall may include: obtaining a mask and a centerline of the organ; obtaining a connected region of the mask; dividing the connected region into at least one equidistant block; determining an orientation of the equidistant block in a three-dimensional coordinate system including a first direction, a second direction and a third direction; determining an initial normal vector and an initial tangent vector of a center point of the centerline; assigning a projection of the initial normal vector to a normal vector of a light direction of the center point; assigning the third direction or an reverse direction of the third direction to a tangent vector of the light direction of the center point.

First claim

What is claimed is:

1. An image processing method implemented on at least one machine each of which has at least one processor and at least one storage device, the method comprising:
obtaining an image relating to volume data of a plurality of tissues, wherein tissue labels of the plurality of tissues are organized in a tissue set;
selecting a sample point based on the volume data;
obtaining one or more neighboring points of the sample point, wherein one or more neighboring labels corresponding to the one or more neighboring points respectively are organized in a neighboring point set;
determining whether the one or more neighboring labels belong to the tissue set;
determining a color of the sample point based on the determination result, wherein the determining a color of the sample point based on the determination result comprises:
in response to determining that a target neighboring label of the one or more neighboring labels does not belong to the tissue set, obtaining a first color list based on the target neighboring label, the first color list including preset color attributes corresponding to image values respectively; and
determining the color of the sample point based on an image value of the sample point and the first color list; and

obtaining a volume rendering result of the plurality of tissues based on the color of the sample point.

2. The method of claim 1 , the determining whether the one or more neighboring labels belong to the tissue set comprising:
determining whether the target neighboring label is the same as one of the tissue labels in the tissue set;
in response to determining that the target neighboring label is the same as one of the tissue labels in the tissue set, determining that the target neighboring label belongs to the tissue set; and
in response to determining that the target neighboring label is different from any one of the tissue labels in the tissue set, determining that the target neighboring label does not belong to the tissue set.

3. The method of claim 1 , wherein the target neighboring label is a closest neighboring point of the sample point.

4. The method of claim 2 , the determining a color of the sample point based on the determination result further comprising:
in response to determining that the target neighboring point belongs to the tissue set, selecting a tissue label in the tissue set and normalizing image values of the plurality of neighboring points based on the selected tissue label;
obtaining an interpolation result of the sample point based on an interpolation of the normalized image values of the plurality of neighboring points; and
determining the color of the sampling point based on the interpolation result.

5. The method of claim 4 , the normalizing image values of the plurality of neighboring points based on the selected tissue label comprising:
traversing the neighboring labels in the neighboring point set;
for each of the traversed neighboring labels in the neighboring point set,
determining whether the neighboring label is identical to the selected tissue label;
in response to determining that the neighboring label is identical to the selected tissue label, designating a neighboring point corresponding to the neighboring label as belonging to a foreground region and setting an image value of the neighboring point as a first value; and
in response to determining that the neighboring label is not identical to the selected tissue label, designating the neighboring point corresponding to the neighboring label as belonging to a background region and setting the image value of the neighboring point as a second value.

6. The method of claim 5 , wherein the first value is 1 and the second value is 0.

7. The method of claim 4 , the determining the color of the sampling point based on the interpolation result comprising:
comparing the interpolation result of the sampling point with a threshold;
in response to determining that the interpolation result of the sampling point is greater than the threshold, obtaining a second color list based on the selected tissue label, the second color list including preset color attributes corresponding to image values respectively; and
determining the color of the sample point based on an image value of the sample point and the second color list.

8. The method of claim 7 , the determining the color of the sampling point based on the interpolation result further comprising:
in response to determining that the interpolation result of the sampling point is less than the threshold, selecting another tissue label from rest tissue labels in the rest tissue set and normalizing the image values of the plurality of neighboring points based on the updated selected tissue label;
obtaining an updated interpolation result of the sample point based on an interpolation of the updated normalized image values of the plurality of neighboring points;
comparing the updated interpolation result of the sampling point with a threshold; and
in response to determining that the updated interpolation result of the sampling point is less than the threshold, repeating operations of selecting another tissue label in rest tissue labels in the tissue set, normalizing the image values of the plurality of neighboring points based on the updated selected tissue label, and obtaining an updated interpolation result of the sample point based on an interpolation of the updated normalized image values of the plurality of neighboring points, until the updated interpolation result is larger than the threshold or otherwise all the tissue labels in the tissue set are traversed.

9. The method of claim 4 , wherein the interpolation includes at least one of a linear interpolation, a nonlinear interpolation, an interpolation based on a regularization function, or a diffusion interpolation based on a partial differential equation.

10. A system for image processing, comprising:
at least one storage device storing a set of instructions; and
at least one processor configured to communicate with the at least one storage device, wherein when executing the set of instructions, the at least one processor is directed to cause the system to:
obtain an image relating to volume data of a plurality of tissues, wherein tissue labels of the plurality of tissues are organized in a tissue set;
select a sample point based on the volume data;
obtain one or more neighboring points of the sample point, wherein one or more neighboring labels corresponding to the one or more neighboring points respectively are organized in a neighboring point set;
determine whether the one or more neighboring labels belong to the tissue set;
determine a color of the sample point based on the determination result, wherein to determine a color of the sample point based on the determination result, the at least one processor is directed to cause the system to:
in response to determining that a target neighboring label of the one or more neighboring labels does not belong to the tissue set, obtain a first color list based on the target neighboring label, the first color list including preset color attributes corresponding to image values respectively; and
determine the color of the sample point based on an image value of the sample point and the first color list; and

obtain a volume rendering result of the plurality of tissues based on the color of the sample point.

11. The system of claim 10 , wherein to determine whether the one or more neighboring labels belong to the tissue set, the at least one processor is directed to cause the system to:
determine whether the target neighboring label is the same as one of the tissue labels in the tissue set;

Assignees

• Shanghai United Imaging Healthcare Co Ltd

Inventors

• Meng Xiaolin
• Weng Xin
• Zhang Libo
• Duan Qi
• Wang Shuai

Classifications

• G06T7/0012 Primary

  Biomedical image inspection · CPC title

• G06T3/00

  Geometric image transformations in the plane of the image · CPC title

• G06T3/0037

  Physics · mapped topic

• G06T7/11

  Region-based segmentation · CPC title

• G06T7/187 Primary

  involving region growing; involving region merging; involving connected component labelling · CPC title