Ultrasound system with automated wall tracing

Patent metadata

Field	Value
Publication number	US-12133770-B2
Application number	US-202318155171-A
Country	US
Kind code	B2
Filing date	Jan 17, 2023
Priority date	May 8, 2018
Publication date	Nov 5, 2024
Grant date	Nov 5, 2024

Abstract

An ultrasound imaging system computes real time physiological parameters from measurements of anatomical features in ultrasound image data using a neural network to identify the location of the anatomical features. In one embodiment, cardiac parameters are computed from endocardial wall tracings in M-mode ultrasound image data that are identified by the neural network.

First claim

I claim:

1. An ultrasound imaging system, comprising:
a transducer configured to transmit ultrasound signals generated according to a first imaging modality and a second imaging modality which is different from the first imaging modality, to a subject and to receive ultrasound echo signals corresponding to the first imaging modality and the second imaging modality from the subject, the first imaging modality and the second imaging modality being interleaved;
a processor configured to:
produce an ultrasound image from the ultrasound echo signals of the first imaging modality;
produce ultrasound image data from the ultrasound echo signals of the second imaging modality; and
identify, based on the ultrasound image data, an endocardial border in the ultrasound image; and

a display configured to simultaneously display one or more physiological parameters and the ultrasound image;
wherein the ultrasound image data from the echo signals of the second imaging modality is not shown on the display.

2. The ultrasound imaging system of claim 1 , wherein the processor is further configured to supply the ultrasound image data to a trained neural network as a frame of the ultrasound image is created and the display is configured to simultaneously display the ultrasound image and the one or more physiological parameters.

3. The ultrasound imaging system of claim 1 , wherein the display is further configured to simultaneously display the one or more physiological parameters and the ultrasound image in which the endocardial border is identified by a neural network.

4. The ultrasound system of claim 1 , wherein the processor is further configured to receive signals from a respiration sensor and ignore a portion of the ultrasound image data if the portion of the image data is obtained when the respiration sensor indicates that the subject is breathing.

5. The ultrasound imaging system of claim 1 , wherein the first imaging modality is a B-Mode and the second imaging modality is an M-Mode.

6. The ultrasound imaging system of claim 5 , wherein the one or more physiological parameters include one or more of ejection fraction, fractional shortening, stroke volume and cardiac output.

7. The ultrasound imaging system of claim 1 , wherein the processor is further configured to compute the one or more physiological parameters over a number of cardiac cycles.

8. The ultrasound imaging system of claim 7 , wherein:
the processor is further configured to determine an average of at least one physiological parameter of the one or more physiological parameters over the number of cardiac cycles; and
the display is further configured to display the average of the at least one physiological parameter.

9. The ultrasound imaging system of claim 7 , wherein:
the processor is further configured to determine a variance of the one or more physiological parameters; and
the display is further configured to display the variance of the one or more physiological parameters.

10. The ultrasound imaging system of claim 1 , wherein the processor is further configured to:
compare the one or more physiological parameters to a threshold and produce a comparison; and
trigger an alert based on the comparison.

11. The ultrasound imaging system of claim 10 , wherein the processor is further configured to read the threshold from a patient record.

12. The ultrasound imaging system of claim 1 , wherein the processor is further configured to:
determine additional physiological parameters from a patient record; and
compare the one or more physiological parameters to the additional physiological parameters.

13. The ultrasound imaging system of claim 1 , wherein:
the processor is further configured to determine at least one anatomical measurement of the endocardial border; and
the display is configured to display the at least one anatomical measurement.

14. The ultrasound system of claim 1 , wherein the processor is further configured to determine when a patient's heart is in at least one of a systolic phase and a diastolic phase.

15. The ultrasound system of claim 1 , wherein the processor is further configured to supply the ultrasound image data to a trained neural network that is configured to identify a physical feature, wherein training the trained neural network comprises:
supplying a plurality of ultrasound test images having identifying features;
acquiring data from the ultrasound test image; and
determining a plurality of filter weights and bias values.

16. The ultrasound imaging system of claim 1 , wherein a trained neural network is configured to receive an image having a number of pixel data columns that is equal to that of a plurality of images with which the neural network was trained, and to produce an output data set marking two most likely locations of the endocardial border in each image pixel data column.

17. The ultrasound imaging system of claim 1 , wherein the processor is further configured to identify a first interior wall and a second interior wall of a heart muscle; and
determine a distance between the first interior wall and the second interior wall of the heart muscle by analyzing a distance between pixels in each column of an image.

18. The ultrasound imaging system of claim 8 , wherein the processor is further configured to determine the average based at least on a pulse sensor.

19. A method of operating a processor in an ultrasound imaging system, the method comprising:
producing an ultrasound image from ultrasound image data received ultrasound echo signals of a first imaging modality;
producing ultrasound image data from received ultrasound echo signals of a second imaging modality which is different from the first imaging modality: wherein the received ultrasound echo signals of the first imaging modality and the received ultrasound echo signals of the second imaging modality are interleaved;
identifying an endocardial border in the ultrasound image data; and
computing one or more physiological parameters of a subject based on the endocardial border;
producing an alert if at least one of the one or more physiological parameters varies by more than a threshold amount from a baseline value; and
displaying the one or more physiological parameters and the ultrasound image simultaneously;
wherein the ultrasound image data from the echo signals of the second imaging modality is not shown on the display.

20. The method of claim 19 , further comprising:
determining one or more of the threshold amount and the baseline value based on a previous physiological parameter computed for the subject.

21. The method of claim 20 , further comprising:
determining at least one of the baseline value and the threshold amount based on at least one of the subject's race, age, sex and previous medical history.

22. The method of claim 19 , further comprising receiving signals from a respiration sensor ignoring a portion of the ultrasound image data if the portion of the image data are obtained when the respiration sensor indicates that the subject is breathing.

23. The ultrasound imaging system of claim 4 , wherein the processor is further configured to automatically determine start and stop points in the ultrasound image data based on the signals from the respiration sensor in real time without user intervention.

24. The method of claim 19 , further comprising determining when a patient's heart is in at least one of a systolic phase and a diastolic

Assignees

• Fujifilm Sonosite Inc

Inventors

• White Christopher A

Classifications

• A61B8/5261

  combining images from different diagnostic modalities, e.g. ultrasound and X-ray · CPC title

• A61B8/5276

  due to motion · CPC title

• A61B8/5292

  using additional data, e.g. patient information, image labeling, acquisition parameters · CPC title

• A61B8/065

  to determine blood output from the heart · CPC title

• A61B8/463

  characterised by displaying multiple images or images and diagnostic data on one display · CPC title