Tuning ultrasound acquisition parameters

• US 9,918,700 B2
• Filed: 06/27/2013
• Issued: 03/20/2018
• Est. Priority Date: 02/01/2013
• Status: Active Grant

• Current Assignee: Siemens Medical Solutions USA Incorporated (Siemens AG)
• Original Assignee: Siemens Medical Solutions USA Incorporated (Siemens AG)
• Inventors: El-Zehiry, Noha Youssry, Yan, Michelle xiaohong, Good, Sara, Grady, Leo
• Primary Examiner(s): Fernandez, Katherine
• Assistant Examiner(s): Saboktakin, Marjan
• Application Number:
  US13/928,763
• Publication Number:
  US 20140221832A1
• Time in Patent Office: 1,727 Days
• Field of Search: None
• CPC Class Codes: A61B 8/5223 for extracting a diagnostic or physiological parameter from medical diagnostic data for algorithms to analyse biomedical images G06T7/0012
• CPC Class Codes: A61B 8/54 Control of the diagnostic device
• CPC Class Codes: A61B 8/585 Automatic set-up of the device
• CPC Class Codes: G16H 30/20 for handling medical images, e.g. DICOM, HL7 or PACS
• CPC Class Codes: G16H 30/40 for processing medical images, e.g. editing
• CPC Class Codes: G16H 40/63 for local operation
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16Z 99/00 Subject matter not provided for in other main groups of this subclass

Abstract

Values for ultrasound acquisition parameters are altered in a manifold space. The number of parameters to be set is reduced using a manifold. Virtual parameters different than the acquisition parameters are used to alter the greater number of acquisition parameters. In a further use, optimum image settings may be obtained in an automated system by measuring image quality for feeding back to virtual parameter adjustment.

Claims

1. A method for tuning ultrasound acquisition parameters, the method comprising:

acquiring by scanning a patient with ultrasound using a transducer of an ultrasound system, first ultrasound data with a first set of acquisition parameters of a plurality of sets of acquisition parameters;

calculating, with a processor, a first quality score for the first ultrasound data;

projecting, with the processor, the first set of acquisition parameters to first coordinates in a manifold space, wherein the manifold space comprises a plurality of coordinates for each of the plurality of sets of acquisition parameters, wherein the manifold space describes a relationship between each of the plurality of sets of acquisition parameters, wherein the dimensionality of the coordinates of the manifold space is lower than a number of acquisition parameters in each of the sets of acquisitions parameters;

selecting second coordinates adjacent on the manifold space to the first coordinates;

the second coordinates corresponding to a second set of acquisition parameters of the plurality of sets of acquisition parameters;

acquiring, by the ultrasound system using the transducer to scan the patient with ultrasound, second ultrasound data with the second set of acquisition parameters

calculating, with the processor, a second quality score for the second ultrasound data;

comparing the first and second quality scores;

comparing the second quality score to a quality threshold level;

imaging the patient by the ultrasound system using the second set of acquisition parameters when the second quality score is equal to or above the quality threshold level;

selecting, when the second quality score is lower than the quality threshold level, third coordinates adjacent on the manifold space to the second coordinates or first coordinates, the third coordinates adjacent to the first coordinates when, based on the comparison of the first and second quality scores, the first quality score is determined to be higher than the second quality score, and the third coordinates adjacent to the second coordinates when the second quality score is determined to be higher than the first quality score;

the third coordinates corresponding to a third set of acquisition parameters of the plurality of sets of acquisition parameters;

acquiring, by the ultrasound system using the transducer to scan the patient with ultrasound, third ultrasound data with the third set of acquisition parameters;

calculating, with the processor, a third quality score for the third ultrasound data

determining, by the processor, that the third quality score is equal to or higher than the quality threshold level; and

when the third quality score is equal or above the quality threshold level, imaging the patient, by the ultrasound system, using the third set of acquisition parameters

when the third quality score is lower than the quality threshold level, repeating the steps of;

selecting next corresponding coordinates adjacent on the manifold space to the current coordinates or previous coordinates, the next corresponding coordinates corresponding to a next set of acquisition parameters of the sets of acquisition parameters and the next corresponding coordinates adjacent to the previous coordinates when the previous quality score is higher than the current quality score, and the next corresponding coordinates adjacent to the current coordinates when the current quality score is higher than the previous quality score;

acquiring, by the ultrasound system using the transducer to scan the patient with ultrasound, next corresponding ultrasound data with the next corresponding set of acquisition parameters;

calculating, with the processor, a next corresponding quality score;

determining, by the processor, that the next corresponding quality score to the threshold level; and

comparing the next corresponding quality score to the current quality score;

until a respective next corresponding quality score is equal or above the quality threshold level; and

scanning, by an ultrasound system, the patient using the set of acquisition parameters that corresponds to the quality score that is equal or above the threshold quality score.

2. The method of claim 1 wherein acquiring the first and second ultrasound data comprises acquiring the first, second, and each next corresponding ultrasound data representing a two or three-dimensional region of a patient in a same scan mode.

3. The method of claim 1 wherein acquiring the first, second, and each next corresponding ultrasound data comprises acquiring B-mode data.

4. The method of claim 1 wherein acquiring the first, second, and each next corresponding ultrasound data comprises acquiring with the acquisition parameters being depth, frequency, focus location, and fundamental or harmonic reception, the first coordinates differing from the second coordinates and each next corresponding coordinates for at least one of the acquisition parameters.

5. The method of claim 1 wherein calculating the first, second, and each next corresponding quality scores comprises calculating with a support vector machine.

6. The method of claim 1 wherein calculating the first, second, and each next corresponding quality scores comprises determining input features from resolution pyramids derived from the first, second, and each next corresponding ultrasound data, respectively, and applying the input features to a machine-learnt classifier.

7. The method of claim 6 wherein determining the input features comprises:

Gabor filtering the first, second; and

each next corresponding ultrasound data;

calculating local invariance from an output of the Gabor filtering;

matching a template to the local invariance; and

calculating a global invariance from an output of the matching.

8. The method of claim 1 wherein selecting second, and each next corresponding coordinates adjacent on the manifold space comprises incrementing along the manifold space.

9. The method of claim 1 wherein the second, and each next corresponding coordinates are selected as a function of user input.

10. A system for tuning ultrasound acquisition parameters, the system comprising:

an ultrasound system configurable to scan a patient using a first set of scan variables and generate a first image in response to the scan;

a memory operable to project in a manifold space the first set of scan variables as first coordinates in the manifold space, wherein the manifold space comprises a plurality of coordinates for each of a plurality of sets of scan variables including the first set of scan variables, wherein the manifold space describes a relationship between the variables in each of the plurality of sets of scan variables, wherein the dimensionality of coordinates of the manifold space is lower than a number of scan variables in each of the sets of scan variables; and

a processor configured to select second coordinates adjacent on the manifold space to the first coordinates;

the second coordinates corresponding to a second set of scan variables of the plurality of sets of scan variables;

wherein the ultrasound system is further configured to scan a patient with the second set of scan variables and generate a second image in response to the scan;

wherein the processor is configured to calculate a first quality score for the first image and a second quality score for the second image;

wherein the processor is further configured to compare the first quality score and second quality score to a quality threshold, the ultrasound system is configured to image the patient by the ultrasound system using the second set of scan variables when the second quality score equal to or above a quality threshold level; and

the processor is configure to select, when the second quality score is lower than the quality threshold level, third coordinates adjacent on the manifold space to the second coordinates or first coordinates, the third coordinates adjacent to the first coordinates when the first quality score is higher than the second quality score, and the third coordinates adjacent to the second coordinates when the second quality score is higher than the first quality score, the third coordinates corresponding to a third set of acquisition parameters of the plurality of sets of acquisition parameters, wherein the ultrasound system is configured using the transducer to scan the patient using the third set of acquisition parameters, and generate a third image in response to the scan, wherein the processor is configured to calculate a third quality score for the third image, and compare the third quality score with the quality threshold level;

when the third quality score is equal to or higher than the quality threshold level, the ultrasound system images the patient using the third set of acquisition parameters;

when the third quality score is lower than the quality threshold level, repeating the steps of;

selecting next corresponding coordinates adjacent on the manifold space to the current coordinates or previous coordinates, the next corresponding coordinates corresponding to a next set of acquisition parameters of the sets of acquisition parameters and the next corresponding coordinates adjacent to the previous coordinates when the previous quality score is higher than the current quality score, and the next corresponding coordinates adjacent to the current coordinates when the current quality score is higher than the previous quality score;

the ultrasound system is further configured to scan a patient with the next corresponding set of acquisition parameters and generate a next corresponding image in response to the scan;

wherein the processor is configured to calculate a next corresponding quality score for the next corresponding image;

wherein the processor is configured to compare the next corresponding quality score to the quality threshold; and

wherein the processor is further configured to compare next corresponding quality score to the current quality score;

until a respective next corresponding quality score is equal or above the quality threshold; and

wherein the ultrasound system is configured to scan the patient using the set of acquisition parameters that corresponds to the quality score that is equal or above the threshold quality.

11. A Method for tuning ultrasound acquisition parameters, the method comprising:

acquiring, by a processor, a first image of a patient using a first set of scan variables that corresponds to a first set of coordinates in a manifold space, wherein the manifold space comprises a plurality of sets of coordinates, each set of coordinates of the plurality of sets of coordinates corresponding to a set of scan variables, wherein the dimensionality of coordinates of the manifold space is lower than a number of scan variables in each of the sets of scan variables;

acquiring, by the processor, a second image of the patient using a second set of scan variables that corresponds to a second set of coordinates in the manifold space;

scoring, by the processor, the first and second image, resulting in a first image score and a second image score;

wherein when the second image score is higher than the first image score, the processor selects a third coordinate in the manifold space adjacent to the second coordinate;

wherein when the first image score is higher than the second image score, then the processor selects a third coordinate in the manifold space adjacent to the first coordinate;

scoring, by the processor, the third image resulting in a third image score; and

when the third quality score is equal or above the quality threshold level, imaging the patient, by the ultrasound system, using the third set of acquisition parameters;

when the third quality score is lower than the quality threshold level, repeating the steps of;

selecting next corresponding set of coordinates adjacent on the manifold space to the current set of coordinates or previous set of coordinates, the next corresponding set of coordinates corresponding to a next set of acquisition parameters of the sets of acquisition parameters and the next corresponding set of coordinates adjacent to the previous coordinates when the previous quality score is higher than the current quality score, and the next corresponding set of coordinates adjacent to the current set of coordinates when the current quality score is higher than the previous quality score;

acquiring, by the ultrasound system using the transducer to scan the patient with ultrasound, next corresponding ultrasound data with the next corresponding set of acquisition parameters;

calculating, with the processor, a next corresponding quality score;

comparing, by the processor, the next corresponding quality score to the threshold level; and

comparing the next corresponding quality score to the current quality score;

until a respective next corresponding quality score is equal or above the quality threshold level, or a maximum number of iterations are reached;

wherein the maximum number of iterations are inputted by the user;

when a respective next corresponding quality score is equal or above the quality threshold level;

scanning, by an ultrasound system, the patient, using the set of acquisition parameters that corresponds to the quality score that is equal or above the threshold quality score;

when the maximum number of iterations have been reached but a respective next corresponding quality score is still lower than the quality threshold, scanning, by an ultrasound system, the patient, using the set of acquisition parameters that corresponds to the highest quality score among the first, second, third and each next corresponding quality scores lower or equal to the maximum number of iterations.