Adaptive ultrasound scanning

Patent metadata

Field	Value
Publication number	US-2021137416-A1
Application number	US-201917048169-A
Country	US
Kind code	A1
Filing date	Apr 11, 2019
Priority date	Apr 20, 2018
Publication date	May 13, 2021
Grant date	—

Abstract

The present disclosure describes imaging systems configured to generate adaptive scanning protocols based on anatomical features and conditions identified during a prenatal scan of an object. Systems may include an ultrasound transducer configured to acquire echo signals responsive to ultrasound pulses transmitted toward a target region. Processors coupled with the transducer can generate an image frame from the echoes and provide the image frame to a first neural network. The first neural network may be configured to identify an anatomical feature in the image frame. An indication of the anatomical feature may be provided a second neural network. The second neural network may then determine an anatomical measurement to be obtained based, in part, on the feature identified. The processors may be further configured to cause an indicator of the anatomical measurement to be obtained to be displayed on a user interface.

First claim

1 . An ultrasound imaging system comprising:
an ultrasound transducer configured to acquire echo signals responsive to ultrasound pulses transmitted toward a target region; and one or more processors in communication with the ultrasound transducer and configured to: generate at least one image frame from the ultrasound echoes; provide the image frame to a first neural network, the first neural network configured to identify an anatomical feature of an object in the image frame; provide an indication of the anatomical feature to a second neural network, the second neural network configured to determine an anatomical measurement to be obtained based, in part, on the anatomical feature identified by the first neural network in accordance with a list of required measurements; and cause an indicator of the anatomical measurement to be obtained to be displayed on a user interface in communication with the processors.

2 . The ultrasound imaging system of claim 1 , wherein the processors are further configured to generate an instruction for adjusting the ultrasound transducer based on the anatomical measurement to be obtained.

3 . The ultrasound imaging system of claim 1 , wherein the processors are further configured to identify a movement of the object and a current position of the object.

4 . The ultrasound imaging system of claim 3 , wherein the processors are further configured to provide an indication of the movement and current position of the object to the second neural network which is configured to determine the anatomical measurement to be obtained based in part on the movement and current position of the object.

5 . The ultrasound imaging system of claim 3 , wherein the processors are configured to identify a movement of the object by cross-correlating a subset of lines of consecutive image frames generated from the ultrasound echoes.

6 . The ultrasound imaging system of claim 3 , wherein the processors are configured to identify a current position of the object by extracting anatomical features from the image frame and inputting the extracted anatomical features into a recurrent neural network.

7 . The ultrasound imaging system of claim 1 , wherein the second neural network is configured to implement a recommender system configured to associate the anatomical feature identified by the first neural network with an action for obtaining the anatomical measurement to be obtained.

8 . The ultrasound imaging system of claim 1 , wherein the first neural network is operatively associated with a training algorithm configured to receive an array of training inputs and known outputs, wherein the training inputs comprise ultrasound image frames containing anatomical features of an object, and the known outputs comprise a view classification based on the anatomical features.

9 . The ultrasound imaging system of claim 1 , wherein the user interface is configured to display the list of required measurements.

10 . The ultrasound imaging system of claim 9 , wherein the user interface is configured to update the list of required measurements based in part on measurements that have been obtained by a user.

11 . The ultrasound imaging system of claim 1 , wherein the anatomical measurement to be obtained comprises a measurement obtainable by implementing a smallest possible adjustment of the ultrasound transducer.

12 . The ultrasound imaging system of claim 1 , wherein the anatomical measurement to be obtained comprises a measurement obtainable at or above an accuracy threshold.

13 . A method of ultrasound imaging, the method comprising:
acquiring echo signals responsive to ultrasound pulses transmitted into a target region by a transducer operatively coupled to an ultrasound system; generating at least one image frame from the ultrasound echoes; providing the image frame to a first neural network, the first neural network configured to identify an anatomical feature of an object in the image frame; providing an indication of the anatomical feature to a second neural network, the second neural network configured to determine an anatomical measurement to be obtained based in part on the anatomical feature identified by the first neural network in accordance with a list of required measurements; and causing an indicator of the anatomical measurement to be obtained to be displayed on a user interface in communication with the processors.

14 . The method of claim 13 , further comprising generating an instruction for adjusting the ultrasound transducer based on the anatomical measurement to be obtained.

15 . The method of claim 13 , further comprising identifying a movement of the object and a current position of the object.

16 . The method of claim 15 , further comprising providing an indication of the movement and current position of the object to the second neural network which determines the anatomical measurement to be obtained.

17 . The method of claim 15 , wherein identifying the movement of the object comprises cross-correlating a subset of lines of consecutive image frames generated from the ultrasound echoes.

18 . The method of claim 15 , wherein identifying the current position of the object comprises extracting anatomical features from the image frame and inputting the extracted anatomical features into a recurrent neural network.

19 . The method of claim 13 , further comprising displaying and updating the list of requirement measurements based in part on measurements that have been obtained by a user.

20 . A non-transitory computer-readable medium comprising executable instructions, which when executed cause a processor of a medical imaging system to perform the method of claim 13 .

Assignees

• Koninklijke Philips Nv

Inventors

• Canfield Earl M
• Nguyen Man M
• Xie Hua

Classifications

• G06T2207/30044

  Fetus; Embryo · CPC title

• A61B5/107 Primary

  Measuring physical dimensions, e.g. size of the entire body or parts thereof · CPC title

• G16H50/30

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

• G06T2207/10132

  Ultrasound image · CPC title

• G06T2207/20084

  Artificial neural networks [ANN] · CPC title