Automatic detection and setting of magnetic resonance protocols based on read-in image data

Patent metadata

Field	Value
Publication number	US-10663547-B2
Application number	US-201816051919-A
Country	US
Kind code	B2
Filing date	Aug 1, 2018
Priority date	Aug 1, 2017
Publication date	May 26, 2020
Grant date	May 26, 2020

Abstract

In a method and apparatus for determining measurement protocol parameters of a magnetic resonance (MR) image, a first MR image exhibiting first contrast properties, is read into a computer and at least one first contrast ratio is determined in the computer from the first contrast properties. The computer then determines the measurement protocol parameters dependent on the at least one first contrast ratio, in order to generate a second MR image exhibiting second contrast properties such that the second contrast properties approximate, as closely as possible, to the first contrast properties. The measurement protocol parameters are presented as an output from the computer.

First claim

The invention claimed is:

1. A method for operating a magnetic resonance (MR) scanner of an MR apparatus in order to conduct an examination of a subject, said method comprising:
reading a first MR image, exhibiting first contrast properties, into a computer;
in said computer, automatically determining a first contrast ratio from said first contrast properties;
in said computer, determining measurement protocol parameters, using said first contrast ratio, in order to generate, by simulation, a second MR image that exhibits second contrast properties that approximate as closely as possible said first contrast properties; and
in said computer, generating a measurement protocol comprising control signals corresponding said measurement protocol parameters, and emitting said control signals from said computer to said MR scanner in a form for operating the MR scanner so as to conduct said examination of said subject according to said measurement protocol parameters.

2. A method as claimed in claim 1 wherein said second contrast properties comprise a second contrast ratio in said simulated second MR image, and comprising:
determining said first contrast ratio from said first contrast properties by identifying at least two first image areas in said first MR image, said at least two image areas being respectively assigned to different regions that are in a list of regions of anatomical features in said first MR image; and
determining said measurement protocol parameters so as to make said first contrast ratio respectively in each of said at least two first image areas as similar as possible to said second contrast ratio.

3. A method as claimed in claim 2 comprising assigning said at least two first image areas to said list by execution of a deep-learning method in said computer.

4. A method as claimed in claim 1 comprising determining said measurement protocol parameters by executing a deep-learning method in said computer.

5. A method as claimed in claim 4 comprising, in said deep-learning method, accessing a database comprising measurement protocol parameters, contrast properties, and information describing anatomical regions.

6. A method as claimed in claim 1 comprising determining said measurement parameters by simulating a third MR image with third contrast properties therein being simulated iteratively for different measurement protocol parameters until said third contrast properties approximate said first contrast properties as closely as possible.

7. A method as claimed in claim 6 comprising using Bloch equations to simulate said third MR image in said third contrast properties, with knowledge of at least T 1 or T 2 in anatomical regions identified in said first MR image.

8. A method as claimed in claim 1 comprising determining at least some of said measurement protocol parameters from meta information associated with said first MR image.

9. A method as claimed in claim 1 wherein said first MR image has a protocol name associated therewith, and determining said measurement protocol parameters using said protocol name.

10. A method as claimed in claim 1 comprising reading said first MR image into said computer as a digitized file obtained from a printout, a screen display, or a photograph.

11. A method as claimed in claim 1 wherein said MR scanner that conducts said examination is different from an MR scanner used to generate said first MR image.

12. A method as claimed in claim 1 comprising determining, as said measurement protocol parameters, at least one measurement protocol parameter selected from the group consisting of a field of view, a number of slices of the subject from which MR data are to be obtained, a designation of the MR scanner that is to be used in said examination, a configuration of said MR scanner, a partition of an imaging volume of the subject, a rotation of an imaging volume of the subject, rotational alignment, windowing setting, radio-frequency or gradient pulses to be used in said examination, pre-pulses to be used in said examination.

13. A magnetic resonance (MR) apparatus comprising:
an MR scanner that is to be used to acquire MR data from a subject in an examination;
a computer configured to receive a first MR image, exhibiting first contrast properties, as an input into said computer;
said computer being configured to automatically determine a first contrast ratio from said first contrast properties;
said computer being configured to determine measurement protocol parameters, using said first contrast ratio, in order to generate, by simulation, a second MR image that exhibits second contrast properties that approximate as closely as possible said first contrast properties; and
said computer being configured to generate a measurement protocol comprising control signals corresponding said measurement protocol parameters, and to emit said control signals from said computer to said MR scanner in a form for operating the MR scanner so as to conduct said examination of said subject according to said measurement protocol parameters.

14. A non-transitory, computer-readable data storage medium encoded with programming instructions, said storage medium being loaded into a computer of a magnetic resonance (MR) apparatus comprising an MR scanner to be used to conduct an examination of a subject, and said programming instructions causing said computer to:
receive a first MR image, exhibiting first contrast properties;
determine a first contrast ratio from said first contrast properties;
determine measurement protocol parameters, using said first contrast ratio, in order to generate, by simulation, a second MR image that exhibits second contrast properties that approximate as closely as possible said first contrast properties; and
generate a measurement protocol comprising control signals corresponding said measurement protocol parameters, and emit said control signals from said computer to said MR scanner in a form for operating the MR scanner so as to conduct said examination of said subject according to said measurement protocol parameters.

Assignees

• Siemens Healthcare Gmbh

Inventors

• Grodzki David
• Hardie Donald
• Hesels Katharina
• Lauer Lars
• Mueller Edgar

Classifications

• A61B5/0037

  Performing a preliminary scan, e.g. a prescan for identifying a region of interest · CPC title

• G06N3/08

  Learning methods · CPC title

• G01R33/543

  Control of the operation of the MR system, e.g. setting of acquisition parameters prior to or during MR data acquisition, dynamic shimming, use of one or more scout images for scan plane prescription (G01R33/546 takes precedence) · CPC title

• G01R33/546 Primary

  Interface between the MR system and the user, e.g. for controlling the operation of the MR system or for the design of pulse sequences · 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