Preset free imaging for ultrasound device
View Patent ↗Aspects of the disclosed technology provide ways to detect the object of ultrasound scanning and to automatically, load system settings and image preferences necessary to generate high quality output images. In some aspects, an ultrasound system can be configured to perform steps including receiving a selection of a first transducer, identifying a body structure or organ based on a signal received in response to an activation of the first transducer, retrieving a first set of image parameters corresponding with the body structure, and configuring the first transducer based on the first set of image parameters. Methods and machine-readable media are also provided.
1. An ultrasound imaging system, comprising:
an ultrasound transducer; and
a processor coupled to the ultrasound transducer, wherein the processor is configured to:
automatically identify, using a machine learning (ML) classifier, an anatomical structure within a patient's body based on a signal received from the ultrasound transducer;
retrieve, from a computer-readable storage medium, a first set of transducer parameters corresponding to the anatomical structure;
configure the ultrasound transducer based on the first set of transducer parameters; and
collect a first image of the anatomical structure via the ultrasound transducer using the first set of transducer parameters.
2. The ultrasound imaging system of claim 1 , wherein the processor is further configured to:
determine whether the first image meets a desired image quality;
if the first image does not meet the desired image quality, update the first set of transducer parameters to generate a second set of transducer parameters;
configure the ultrasound transducer based on the second set of transducer parameters; and
collect a second image of the anatomical structure via the ultrasound transducer, using the second set of transducer parameters.
3. The ultrasound imaging system of claim 2 , wherein the processor automatically determines whether the first image meets the desired image quality based on image characteristics of the first image.
4. The ultrasound imaging system of claim 3 , wherein the processor automatically determines whether the first image meets a desired image quality by comparing the image characteristics with a database of known user preferences or image characteristics of images previously accepted by a user.
5. The ultrasound imaging system of claim 2 , wherein the processor determines whether the first image meets the desired image quality based on manual input from a user whether the first image is accepted.
6. The ultrasound imaging system of claim 1 , wherein the first set of transducer parameters are previously provided by a user for the anatomical structure.
7. The ultrasound imaging system of claim 6 , wherein the first set of transducer parameters are previously provided by the user for the anatomical structure in response to an A/B comparison based on images generated by different image parameters.
8. The ultrasound imaging system of claim 2 , wherein the processor is configured to update the first set of transducer parameters based on user input.
9. The ultrasound imaging system of claim 8 , wherein the processor is further configured to update the ML classifier based on the user input.
10. The ultrasound imaging system of claim 8 , wherein at least one parameter of the first set of transducer parameters comprises an aperture, a delay profile, a windowing function, or a power of a transmit profile.
11. The ultrasound imaging system of claim 8 , wherein the ML classifier comprises a multilayer perceptron neural network.
12. A computer-implemented method for optimizing sonogram images, comprising:
automatically identifying, using a machine learning (ML) classifier, an anatomical structure within a patient's body based on a signal received from an ultrasound transducer;
retrieving, from a computer-readable storage medium, a first set of transducer parameters corresponding to the anatomical structure;
configuring the ultrasound transducer based on the first set of transducer parameters; and
collecting a first image of the anatomical structure via the ultrasound transducer using the first set of transducer parameters.
13. The computer-implemented method of claim 12 , further comprising:
determining whether the first image meets a desired image quality;
if the first image does not meet the desired image quality, updating the first set of transducer parameters to generate a second set of transducer parameters;
configuring the ultrasound transducer based on the second set of transducer parameters; and
collecting a second image of the anatomical structure via the ultrasound transducer, using the second set of transducer parameters.
14. The computer-implemented method of claim 13 , wherein determining whether the first image meets the desired image quality comprises determining whether the first image meets the desired image quality based on image characteristics of the first image.
15. The computer-implemented method of claim 14 , wherein determining whether the first image meets the desired image quality comprises comparing the image characteristics with a database of known user preferences or image characteristics of images previously accepted by a user.
16. The computer-implemented method of claim 13 , wherein determining whether the first image meets the desired image quality comprises receiving manual input from a user as to whether the first image is accepted.
17. The computer-implemented method of claim 13 , wherein the first set of transducer parameters are previously specified by a user for the anatomical structure or determined in response to an A/B comparison by the user based on images generated by different image parameters.
18. The computer-implemented method of claim 13 , wherein updating the first set of transducer parameters comprises updating the first set of transducer parameters and the ML classifier based on user input.
19. The computer-implemented method of claim 12 , wherein at least one transducer parameter of the first set of transducer parameters comprises an aperture, a delay profile, a windowing function, or a power of a transmit profile.
20. The computer-implemented method of claim 12 , wherein the ML classifier comprises a multilayer perceptron neural network.
21. A non-transitory computer-readable storage medium comprising instructions stored therein, which when executed by a processor, causes the processor to perform operations comprising:
automatically identifying, using a machine learning (ML) classifier, an anatomical structure within a patient's body based on a signal received from an ultrasound transducer;
retrieving, from a computer-readable storage medium, a first set of transducer parameters corresponding to the anatomical structure;
configuring the ultrasound transducer based on the first set of transducer parameters; and
collecting a first image of the anatomical structure via the ultrasound transducer using the first set of transducer parameters.