Systems and methods for image processing

Patent metadata

Field	Value
Publication number	US-12469144-B2
Application number	US-202217816382-A
Country	US
Kind code	B2
Filing date	Jul 29, 2022
Priority date	Dec 29, 2021
Publication date	Nov 11, 2025
Grant date	Nov 11, 2025

Abstract

The present disclosure is related to systems and methods for image processing. The method includes obtaining an original image. The original image includes at least one blood vessel region and at least one scalp region. The method includes determining an intermediate image by removing the at least one scalp region from the original image. The method includes generating at least one target image by performing a maximum intensity projection operation on the intermediate image. The at least one target image represents the at least one blood vessel region in the original image.

First claim

What is claimed is:

1 . A method for image processing, which is implemented on a computing device including at least one processor and at least one storage device, comprising:
obtaining an original image, wherein the original image includes at least one blood vessel region and at least one scalp region; determining an intermediate image by removing the at least one scalp region from the original image; and generating at least one target image based on the intermediate image, wherein the at least one target image represents the at least one blood vessel region in the original image, wherein the generating at least one target image based on the intermediate image comprises:
generating a reference image by inputting the intermediate image into a segmentation model, wherein the reference image includes at least one marker corresponding to the at least one blood vessel region;
generating at least one candidate image based on the reference image; and
generating the at least one target image by performing a maximum intensity projection operation on the at least one candidate image.

2 . The method of claim 1 , wherein the generating the at least one candidate image based on the reference image comprises:
generating the at least one candidate image by dividing the intermediate image based on a location of the at least one blood vessel region.

3 . The method of claim 1 , wherein the generating the at least one candidate image based on the reference image comprises:
for each marker of the at least one marker, generating a candidate image corresponding to the marker by weakening, based on the marker, a reference region in the reference image, wherein the reference region is a region other than a blood vessel region corresponding to the marker in the reference image.

4 . The method of claim 1 , wherein the at least one target image includes a first target image corresponding to a first blood vessel region and a second target image corresponding to a second blood vessel region.

5 . The method of claim 1 , wherein the determining an intermediate image by removing the at least one scalp region from the original image comprises:
obtaining a first image based on the original image using a recognition model, wherein the first image includes a first region, and the at least one scalp region is located outside the first region; obtaining a mask image by performing a binarization operation on the first image; and determining the intermediate image by performing, based on the mask image, a masking operation on the original image.

6 . The method of claim 5 , wherein the obtaining a first image based on the original image using a recognition model comprises:
obtaining a second image by performing a down-sampling operation on the original image; obtaining a third image by performing a brightness normalization operation on the second image; and obtaining the first image by inputting the third image into the recognition model.

7 . The method of claim 6 , wherein the obtaining a mask image by performing a binarization operation on the first image comprises:
obtaining a fourth image by performing an up-sampling operation on the first image; and obtaining the mask image by performing the binarization operation on the fourth image.

8 . The method of claim 1 , wherein the at least one target image includes a plurality of target images corresponding to a plurality of view angles of each of the at least one blood vessel region.

9 . The method of claim 1 , wherein the original image includes a magnetic resonance imaging (MRI) image obtained using a time of flight (TOF)-magnetic resonance angiography (MRA) technique.

10 . A system for image processing, comprising:
at least one storage device including 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 configured to direct the system to perform operations including: obtaining an original image, wherein the original image includes at least one blood vessel region and at least one scalp region; determining an intermediate image by removing the at least one scalp region from the original image; and generating at least one target image based on the intermediate image, wherein the at least one target image represents the at least one blood vessel region in the original image, wherein the generating at least one target image based on the intermediate image comprises:
generating a reference image by inputting the intermediate image into a segmentation model, wherein the reference image includes at least one marker corresponding to the at least one blood vessel region;
generating at least one candidate image based on the reference image; and
generating the at least one target image by performing a maximum intensity projection operation on the at least one candidate image.

11 . The system of claim 10 , wherein the generating the at least one candidate image based on the reference image comprises:
generating the at least one candidate image by dividing the intermediate image based on a location of the at least one blood vessel region.

12 . The system of claim 10 , wherein the generating the at least one candidate image based on the reference image comprises:
for each marker of the at least one marker, generating a candidate image corresponding to the marker by weakening, based on the marker, a reference region in the reference image, wherein the reference region is a region other than a blood vessel region corresponding to the marker in the reference image.

13 . The system of claim 10 , wherein the at least one target image includes a first target image corresponding to a first blood vessel region and a second target image corresponding to a second blood vessel region.

14 . The system of claim 10 , wherein the determining an intermediate image by removing the at least one scalp region from the original image comprises:
obtaining a first image based on the original image using a recognition model, wherein the first image includes a first region, and the at least one scalp region is located outside the first region; obtaining a mask image by performing a binarization operation on the first image; and determining the intermediate image by performing, based on the mask image, a masking operation on the original image.

15 . The system of claim 14 , wherein the obtaining a first image based on the original image using a recognition model comprises:
obtaining a second image by performing a down-sampling operation on the original image; obtaining a third image by performing a brightness normalization operation on the second image; and obtaining the first image by inputting the third image into the recognition model.

16 . The system of claim 15 , wherein the obtaining a mask image by performing a binarization operation on the first image comprises:
obtaining a fourth image by performing an up-sampling operation on the first image; and obtaining the mask image by performing the binarization operation on the fourth image.

17 . The system of claim 10 , wherein the at least one target image includes a plurality of target images corresponding to a plurality of view angles of each of the at least one blood vessel region.

18 . A non-transitory computer readable medium, comprising executable instructions that, when executed by at least one processor, direct the at least one processor to perform a method for image processing, the method compri

Assignees

• Shanghai United Imaging Healthcare Co Ltd

Inventors

• Xin Yang
• Wang Xu
• Li Guobin

Classifications

• G06T12/30 Primary

  Image post-processing, e.g. metal artefact correction · CPC title

• G01R33/5608

  Data processing and visualization specially adapted for MR, e.g. for feature analysis and pattern recognition on the basis of measured MR data, segmentation of measured MR data, edge contour detection on the basis of measured MR data, for enhancing measured MR data in terms of signal-to-noise ratio by means of noise filtering or apodization, for enhancing measured MR data in terms of resolution by means for deblurring, windowing, zero filling, or generation of gray-scaled images, colour-coded images or images displaying vectors instead of pixels (image data processing or generation, in general G06T) · CPC title

• G06T2210/41

  Medical · CPC title

• G06T2207/30204

  Marker · CPC title

• G06T2207/30101

  Blood vessel; Artery; Vein; Vascular · CPC title