Method and device for automatic identification of measurement item and ultrasound imaging apparatus

Patent metadata

Field	Value
Publication number	US-10898109-B2
Application number	US-201615271095-A
Country	US
Kind code	B2
Filing date	Sep 20, 2016
Priority date	Mar 20, 2014
Publication date	Jan 26, 2021
Grant date	Jan 26, 2021

Abstract

A method for automatic identification of a measurement item is provided. The method comprises acquiring, via an image acquisition module, gray values of pixels of a specified section image corresponding to ultrasonic echoes generated by reflection of ultrasound waves by a tissue under examination; identifying, via an identification module, at least one measurement item corresponding to the specified section image based on the gray values of the pixels; and measuring, via a measuring module, a measurement item parameter of the specified section image based on the measurement item identified. Because the measurement item of a specified section image can be automatically identified based on the content thereof, the user does not need to move a trackball to select measurement items, and therefore efficiency is increased.

First claim

What is claimed is:

1. A method for automatic identification of a measurement item, comprising:
acquiring gray values of pixels of a specified section image, wherein the gray values of the pixels correspond to ultrasound echoes generated by reflection of ultrasound waves by a tissue under examination;
automatically determining a section type of the specified section image based on one or more characteristics defined by the gray values of the pixels, the section type identifying a particular section of a particular area of the tissue from which the specified section image was acquired;
obtaining a correspondence between the section type and one or more measurement items which are measurable in an image of the section type;
automatically identifying at least one measurement item which is measurable in the specified section image according to the correspondence and the section type of the specified section image;
detecting an object corresponding to the identified at least one measurement item in the specified section image; and
obtaining a value of the identified at least one measurement item by performing a measurement on the detected object.

2. The method of claim 1 , wherein the measurement item is identified based on a comparative analysis of the gray values of the pixels with a preset data mode.

3. The method of claim 2 , further comprising acquiring a measuring mode used during tissue examination.

4. The method of claim 1 , wherein automatically determining a section type of the specified section image based on one or more characteristics defined by the gray values of the pixels comprises:
generating a characteristic of the specified section image based on the gray values of the pixels of the specified section image;
comparing the characteristic of the specified section image with characteristics of training samples in a preset training sample mode, respectively; and
searching a training sample whose characteristic is most similar to the characteristic of the specified section image and determining section type of the training sample searched out as the section type of the specified section image.

5. The method of claim 4 , wherein the characteristic of the training sample is a projection coefficient of an eigenvector of the training sample on a mean value of the training sample, and the characteristic of the specified section image is a projection coefficient of an eigenvector of the specified section image on the mean value of the training sample.

6. The method of claim 5 , wherein the characteristic of the specified section image is calculated by the following formula:
w=E T ( I test −m )

wherein I test is the eigenvector of the specified section image, m is the mean value of the training sample, T represents matrix transpose, E is an orthogonalized eigenvector, and w is the projection coefficient of the eigenvector of the specified section image on the mean value of the training sample.

7. The method of claim 3 , wherein automatically determining a section type of the specified section image based on one or more characteristics defined by the gray values of the pixels comprises:
extracting high intensity portions from the specified section image based on the gray values of the pixels of the specified section image; and
performing an identification on the high intensity portions based on the measuring mode to determine the section type of the specified section image.

8. The method of claim 7 , wherein extracting high intensity portions from the specified section image comprises:
categorizing the gray values of the pixels of the specified section image into a plurality of categories using a cluster segmentation method;
keeping pixels which have gray values of one or more categories with maximum gray values unchanged while assigning zero to pixels which have gray values of other categories to obtain a characteristic image; and
identifying connected regions in the characteristic image and determining one or more connected regions with maximum intensity to obtain the high intensity portions.

9. The method of claim 8 , wherein performing an identification on the high intensity portions based on the measuring mode comprises:
analyzing intensities and shapes of the connected regions identified; and
determining the section type of the specified section image based on the measuring mode and results of the analysis.

10. The method of claim 1 , wherein obtaining a value of the identified at least one measurement item comprises obtaining a value of the identified at least one measurement item manually, semi-automatically or automatically.

11. The method of claim 1 , wherein the particular section of the section type corresponds to a direction along which a desired section image is acquired from the particular area of the tissue.

12. The method of claim 1 , wherein automatically determining a section type of the specified section image based on one or more characteristics defined by the gray values of the pixels comprises:
extracting section type characteristics of the specified section image based on which one section type is distinguished with another section type; and
determining the section type of the specified section imaged based on the extracted section type characteristics.

13. The method of claim 1 , wherein the determined section type is a head circumference section which contains a skull of a fetus, an abdominal circumference section which contains an abdomen of a fetus or a femur section which contains a thigh bone of a fetus.

14. The method of claim 1 , wherein the one or more characteristics defined by the gray values of the pixels are a shape, a brightness range or a size define by the gray values of the pixels.

15. An ultrasound imaging apparatus, comprising:
a probe which transmits ultrasound waves to a tissue and receives ultrasound echoes;
a signal processor which processes the ultrasound echoes to generate ultrasound image data; and
an image processor which processes the ultrasound image data and generates section images;
wherein the image processor is further configured to:
acquire gray values of pixels of a specified section image, wherein the gray values of the pixels correspond to ultrasound echoes generated by reflection of ultrasound waves by a tissue under examination;
automatically determine a section type of the specified section image based on one or more characteristics defined by the gray values of the pixels, the section type identifying a particular section of a particular area of the tissue from which the specified section image was acquired;
obtain a correspondence between the section type and one or more measurement items which are measurable in an image of the section type;
automatically identify at least one measurement item which is measurable in the specified section image according to the correspondence and the section type of the specified section image;
detect an object corresponding to the identified at least one measurement item in the specified section image; and
obtain a value of the identified at least one measurement item by performing a measurement on the detected object.

16. The apparatus of claim 15 , wherein the image processor is further configured to identify the measurement item based on a comparative analysis of the gray values of the pixels with a preset data mode.

17. The apparatus of claim 16 , wherein the image processor is further configured to acquire a measuring mode used during tissue examination.

18. The apparatus of claim 15 , wherein the i

Assignees

• Shenzhen Mindray Biomedical Electronics Co Ltd

Inventors

• Zou Yaoxian
• Yao Bin
• Wei Yi
• Lin Muqing
• Zeng Zuoqi

Classifications

• A61B8/08 Primary

  Clinical applications (A61B8/02, A61B8/04, A61B8/06 take precedence) · CPC title

• A61B8/469

  for selection of a region of interest · CPC title

• A61B8/5223

  for extracting a diagnostic or physiological parameter from medical diagnostic data (for algorithms to analyse biomedical images G06T7/0012) · CPC title

• A61B8/0866

  involving foetal diagnosis; pre-natal or peri-natal diagnosis of the baby · CPC title

• G16H50/30

  for calculating health indices; for individual health risk assessment · CPC title