Deep learning medical systems and methods for image acquisition

• US 10,127,659 B2
• Filed: 11/23/2016
• Issued: 11/13/2018
• Est. Priority Date: 11/23/2016
• Status: Active Grant

• Current Assignee: General Electric Company
• Original Assignee: General Electric Company
• Inventors: Hsieh, Jiang, Avinash, Gopal, Sirohey, Saad
• Primary Examiner(s): Akhavannik, Hadi
• Application Number:
  US15/360,626
• Publication Number:
  US 20180144466A1
• Time in Patent Office: 720 Days
• Field of Search: None
• CPC Class Codes: G06N 3/04 Architecture, e.g. interconnection topology
• CPC Class Codes: G06N 3/08 Learning methods
• CPC Class Codes: G06T 2207/10004 Still image; Photographic image
• CPC Class Codes: G06T 2207/20081 Training; Learning
• CPC Class Codes: G06T 2207/20084 Artificial neural networks [ANN]
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G16H 30/40 for processing medical images, e.g. editing
• CPC Class Codes: G16H 40/40 for the management of medical equipment or devices, e.g. scheduling maintenance or upgrades
• CPC Class Codes: G16Z 99/00 Subject matter not provided for in other main groups of this subclass

Abstract

Methods and apparatus for improved deep learning for image acquisition are provided. An imaging system configuration apparatus includes a training learning device including a first processor to implement a first deep learning network (DLN) to learn a first set of imaging system configuration parameters based on a first set of inputs from a plurality of prior image acquisitions to configure at least one imaging system for image acquisition, the training learning device to receive and process feedback including operational data from the plurality of image acquisitions by the at least one imaging system. The example apparatus includes a deployed learning device including a second processor to implement a second DLN, the second DLN generated from the first DLN of the training learning device, the deployed learning device configured to provide a second imaging system configuration parameter to the imaging system in response to receiving a second input for image acquisition.

Claims

1. An imaging system configuration apparatus comprising:

a training learning device including a first processor to implement a first deep learning network to learn a first set of imaging system configuration parameters based on a first set of inputs from a plurality of prior image acquisitions to configure at least one imaging system for image acquisition, the training learning device to receive and process feedback including operational data from the plurality of image acquisitions by the at least one imaging system; and

a deployed learning device including a second processor to implement a second deep learning network, the second deep learning network generated from the first deep learning network of the training learning device, the deployed learning device configured to provide a second imaging system configuration parameter to the imaging system in response to receiving a second input for image acquisition.

2. The apparatus of claim 1, further including an interface to connect to the imaging system, the interface, once connected, enabling automated exchange of data between the imaging system and at least one of the training learning device and the deployed learning device.

3. The apparatus of claim 1, wherein the second input includes patient information for a subject of the image acquisition.

4. The apparatus of claim 1, wherein the feedback includes image reconstruction quality information.

5. The apparatus of claim 4, wherein the deployed learning device is to generate a recommendation for next action when the image reconstruction quality information fails to satisfy a threshold.

6. The apparatus of claim 4, wherein the processor is to set the first set of imaging system configuration parameters as a default set of parameters for the imaging system when the image reconstruction quality information satisfies a threshold.

7. The apparatus of claim 1, wherein the second input includes a purpose of a medical exam associated with the image acquisition.

21. The system of claim 1, wherein the first set of inputs includes data pertaining to at least one patient who has been imaged.

22. The system of claim 21, wherein the data includes imaging data and non-imaging data.

8. A non-transitory computer readable medium comprising instructions which, when executed, configure a machine to implement an imaging system configuration apparatus, the apparatus including:

a training learning device including a first processor to implement a first deep learning network to learn a first set of imaging system configuration parameters based on a first set of inputs from a plurality of prior image acquisitions to configure at least one imaging system for image acquisition, the training learning device to receive and process feedback including operational data from the plurality of image acquisitions by the at least one imaging system; and

a deployed learning device including a second processor to implement a second deep learning network, the second deep learning network generated from the first deep learning network of the training learning device, the deployed learning device configured to provide a second imaging system configuration parameter to the imaging system in response to receiving a second input for image acquisition.

9. The computer readable medium of claim 8, wherein the instructions, when executed, further configure the machine to include an interface to connect to the imaging system, the interface, once connected, enabling automated exchange of data between the imaging system and at least one of the training learning device and the deployed learning device.

10. The computer readable medium of claim 8, wherein the second input includes patient information for a subject of the image acquisition.

11. The computer readable medium of claim 8, wherein the feedback includes image reconstruction quality information.

12. The computer readable medium of claim 11, wherein the first deep learning network is to generate a recommendation for next action when the image reconstruction quality information fails to satisfy a threshold.

13. The computer readable medium of claim 11, wherein the first set of imaging system configuration parameters is set as a default set of parameters for the imaging system when the image reconstruction quality information satisfies a threshold.

14. The computer readable medium of claim 8, wherein the second input includes a purpose of a medical exam associated with the image acquisition.

15. A method comprising:

training a first deep learning network at a training learning device to learn a first set of imaging system configuration parameters based on a first set of inputs from a plurality of prior image acquisitions to configure at least one imaging system for image acquisition, the training learning device to receive and process feedback including operational data from the plurality of image acquisitions by the at least one imaging system;

generating a second deep learning network at a deployed learning device using the first deep learning network;

deploying the deployed learning device with the second deep learning network to provide a second imaging system configuration parameter to the imaging system in response to receiving a second input for image acquisition;

receiving feedback from the imaging system, the feedback including operational data from the image acquisition by the imaging system; and

updating the first deep learning network of the training learning device based on the received feedback.

16. The method of claim 15, further including connecting the image acquisition configuration device to the imaging system via an interface, wherein the interface, once connected, enables automated exchange of data between the imaging system and at least one of the training learning device and the deployed learning device.

17. The method of claim 15, wherein the second input includes patient information for a subject of the image acquisition.

18. The method of claim 15, wherein the feedback includes image reconstruction quality information.

19. The method of claim 18, wherein the second deep learning network is to generate a recommendation for next action when the image reconstruction quality information fails to satisfy a threshold.

20. The method of claim 18, further including wherein the image acquisition configuration device is to set the first set of imaging system configuration parameters as a default set of parameters when the image reconstruction quality information satisfies a threshold.