Systems and methods for image processing

Patent metadata

Field	Value
Publication number	US-12430536-B2
Application number	US-202117456597-A
Country	US
Kind code	B2
Filing date	Nov 26, 2021
Priority date	Nov 27, 2020
Publication date	Sep 30, 2025
Grant date	Sep 30, 2025

Abstract

The present disclosure relates to systems and methods for image processing. The systems may acquire imaging data. The systems may generate multiple intermediate images based on the imaging data by performing image optimization of multiple image optimization dimensions using a plurality of trained machine learning models. The systems may generate a target image based on the intermediate images.

First claim

What is claimed is:

1. A system, 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:
acquiring imaging data;
generating multiple intermediate images based on the imaging data by performing image optimization of multiple image optimization dimensions using a plurality of trained machine learning models; and
generating a target image based on the intermediate images,
wherein each of the plurality of trained machine learning models is executed by one of a plurality of image processing subassemblies, the plurality of image processing subassemblies include a first module and at least one second module downstream to the first module, and each of the first module and the at least one second module includes:
a reconstruction unit configured to generate an initial image based on the imaging data;
an optimization unit configured to generate, using a trained machine learning model corresponding to one of the multiple image optimization dimensions, an optimized image of the optimization dimension based on the initial image; and
a fusion unit configured to generate an intermediate image of the optimization dimension by fusing the initial image and the optimized image of the optimization dimension.

2. The system of claim 1 , wherein the image optimization of multiple image optimization dimensions includes at least one of noise reduction, contrast improvement, resolution improvement, artifact correction, or brightness improvement.

3. The system of claim 1 , wherein the reconstruction unit in the first module is configured to generate the initial image based on the imaging data and a preset initial image.

4. The system of claim 1 , wherein the reconstruction unit in one of the at least one second module is configured to generate the initial image based on the imaging data and the intermediate image generated by the fusion unit in the first module or a previous second module connected to the second module.

5. The system of claim 1 , wherein the trained machine learning model in the first module corresponds to an image optimization dimension of noise reduction.

6. The system of claim 1 , wherein the generating the target image based on the intermediate images includes:
designating the intermediate image generated by the fusion unit in a last second module of the at least one second module as the target image.

7. The system of claim 1 , wherein the trained machine learning model is obtained by a training process including:
obtaining a plurality of training samples, each of the plurality of training samples including a sample input image and a sample target image both of which are generated based on a sample data set; and
determining the trained machine learning model by training a preliminary machine learning model based on the plurality of training samples.

8. The system of claim 7 , wherein at least one of the sample input image of a training sample or the sample target image of the training sample is generated by an iterative reconstruction operation including at least one iteration.

9. The system of claim 8 , wherein the sample input images of at least two of the plurality of training samples are generated based on a same sample data set.

10. The system of claim 8 , wherein at least two of the plurality of training samples share a same sample target image.

11. The system of claim 8 , wherein
the sample input image of a training sample is generated based on a sample data set by a first process including:
determining, based on the sample data set, a sample data subset by retrieving a portion of the sample data set that corresponds to a first sampling time; and
determining, based on the sample data subset, the sample input image by a first iterative reconstruction operation including a first count of iterations; and

the target image of the training sample is generated based on the sample data set by a second process including determining, based on the entire sample data set, the sample target image by a second iterative reconstruction operation including a second count of iterations, wherein
the entire sample data set corresponds to a second sampling time that is longer than the first sampling time, and
the first count is the same as the second count.

12. The system of claim 8 , wherein
the sample input image of a training sample is generated based on a sample data set by a third process including:
determining, based on the sample data set, a sample data subset by retrieving a portion of the sample data set that corresponds to a third sampling time; and
determining, based on the sample data subset, the sample input image by a third iterative reconstruction operation including a third count of iterations; and

the target image of the training sample is generated based on the sample data set by a fourth process including determining, based on the sample data subset, the sample target image by a fourth iterative reconstruction operation including a fourth count of iterations, wherein
the fourth count is larger than the third count.

13. The system of claim 8 , wherein
the sample input image of a training sample is generated based on a sample data set by a fifth process including:
determining, based on the sample data set, a first sample data subset by retrieving a portion of the sample data set that is subjected to a smoothing filtering operation; and
determining, based on the first sample data subset, the sample input image by a fourth iterative reconstruction operation including a fourth count of iterations; and

the sample target image of the training sample is generated based on the sample data set by a sixth process including:
determining, based on the sample data set, a second sample data subset by retrieving a portion of the sample data set that is not subjected to a smoothing filtering operation; and
determining, based on the second sample data subset, the sample target image by the fourth iterative reconstruction operation including the fourth count of iterations.

14. The system of claim 1 , wherein
the trained machine learning model is a trained Feedback Convolutional Neural Network (FB-CNN) including a plurality of sequentially connected subnets, and
an input of the FB-CNN is connected to an output of each of the plurality of subnets by a first connection component.

15. The system of claim 14 , wherein
each of the plurality of subnets includes at least one convolution block, at least one deconvolution block, and a feedback block (FB-block), an output of the FB-block in the subnet being inputted into a next subnet connected to the subnet,
the FB-block includes a plurality of convolution layers and deconvolution layers, a portion of the plurality of convolution layers and deconvolution layers forming projection groups each of which includes paired convolution layer and deconvolution layer, and
different layers in at least part of the plurality of convolution layers and deconvolution layers are connected via a second connection component.

16. A method for image processing, implemented on a computing device having at least one storage device storing a set of instructions, and at least one processor in communication with the at least one storage device, the method comprising:
acquiring imaging data;
generating multiple intermediate images based on the imaging data by performing image optimization of multiple image optimization dimensions using

Assignees

• Shanghai United Imaging Healthcare Co Ltd

Inventors

• Lyu Yang
• Xi Chen

Classifications

• G06T12/00 Primary

  Tomographic reconstruction from projections · CPC title

• G06T5/60

  using machine learning, e.g. neural networks · CPC title

• G06T5/92

  based on global image properties · CPC title

• G06T5/70

  Denoising; Smoothing · CPC title

• G06T2207/30016

  Brain · CPC title