Deep learning based medical system and method for image acquisition

Patent metadata

Field	Value
Publication number	US-2022375035-A1
Application number	US-202117325010-A
Country	US
Kind code	A1
Filing date	May 19, 2021
Priority date	May 19, 2021
Publication date	Nov 24, 2022
Grant date	—

Abstract

A medical imaging system having at least one medical imaging device providing image data of a subject is provided. The medical imaging system further includes a processing system programmed to train a deep learning (DL) network using a plurality of training images to predict noise in input data. The plurality of training images includes a plurality of excitation (NEX) images acquired for each line of k-space training data. The processing system is further programmed to use the trained DL network to determine noise in the image data of the subject and to generate a denoised medical image of the subject having reduced noise based on the determined noise in the image data.

First claim

1 . A medical imaging system comprising:
at least one medical imaging device providing image data of a subject; a processing system programmed to:
train a deep learning (DL) network using a plurality of training images to predict noise in input data, wherein the plurality of training images includes a plurality of excitation (NEX) images acquired for each line of k-space training data;
use the trained DL network to determine noise in the image data of the subject; and
generate a denoised medical image of the subject having reduced noise based on the determined noise in the image data.

2 . The medical imaging system of claim 1 , wherein the plurality of NEX images includes at least one pair of NEX images.

3 . The medical imaging system of claim 2 , wherein the processing system is programmed to train the DL network by providing one of the NEX images of the at least one pair as an input image and target noise derived from NEX images of the at least one pair as a target image for the DL network.

4 . The medical imaging system of claim 3 , wherein the DL network includes two cascaded Dense Blocks to predict noise in the input image.

5 . The medical imaging system of claim 4 , wherein the target noise is a realization of the true noise present in the input image.

6 . The medical imaging system of claim 4 , wherein an output image of the DL network is generated by adding the predicted noise in the input image.

7 . The medical imaging system of claim 4 , wherein parameter values of dense blocks are adjusted to reduce differences between the output of the DL network and the target image of the DL network.

8 . The medical imaging system of claim 7 , wherein a loss function is applied to the differences between the output of the DL network and the target image of the DL network to adjust the parameter values of Dense Blocks.

9 . The medical imaging system of claim 1 , wherein generating the denoised medical image comprises subtracting the noise of the image data from the image data of the subject.

10 . A method for imaging a subject comprising:
training a deep learning (DL) network using a plurality of training images to predict noise in input data, wherein the plurality of training images includes a plurality of excitation (NEX) images acquired for each line of k-space training data using a magnetic resonance (MR) imaging device; generating image data of the subject with the MR imaging device; providing the image data of the subject as an input to the trained deep learning network model to determine noise in the image data of the subject; generating a denoised medical image of the subject having reduced artifacts based on the determined noise in the image data.

11 . The method of claim 10 , wherein the plurality of NEX images includes at least one pair of NEX images.

12 . The method of claim 11 , wherein training the DL network comprises providing one of the NEX images of the at least one pair as an input image and target noise derived from another NEX image of the at least one pair as a target image for the DL network.

13 . The method of claim 10 , wherein the DL network includes two cascaded Dense Blocks to predict noise in the input image.

14 . The method of claim 13 , wherein the method further comprises adjusting parameter values of dense blocks to reduce differences between the output of the DL network and the target image of the DL network.

15 . The method of claim 14 , wherein adjusting the parameter values of the Dense Blocks comprises applying a loss function to assess DL input and output mismatch.

16 . The method of claim 10 , wherein generating the denoised medical image comprises subtracting the noise of the image data from the image data of the subject.

Assignees

• Ge Prec Healthcare Llc

Inventors

• Chatterjee Sudhanya
• Shanbhag Dattesh Dayanand

Classifications

• G06N3/045

  Combinations of networks · CPC title

• G06N3/08 Primary

  Learning methods · CPC title

• G06T7/0002

  Inspection of images, e.g. flaw detection · CPC title

• G06T2207/20081

  Training; Learning · CPC title

• G06T2207/20084

  Artificial neural networks [ANN] · CPC title