SMART 3D PACS WORKFLOW BY LEARNING

• US 20130129198A1
• Filed: 06/29/2012
• Published: 05/23/2013
• Est. Priority Date: 11/23/2011
• Status: Active Grant

• Current Assignee: General Electric Company
• Original Assignee: General Electric Company
• Inventors: Dekel, Shai, Ranjan, Sohan Rashmi, Sherman, Alexander
• Granted Patent: US 9,152,760 B2
• Time in Patent Office: Days
• US Class Current: 382/159
• CPC Class Codes: G16H 30/20 for handling medical images, e.g. DICOM, HL7 or PACS

Abstract

Methods and systems to provide a hanging protocol including three-dimensional manipulation for display of clinical images in an exam are disclosed. An example method includes detecting selection of a new image exam for display by a user. The example method includes automatically identifying at least one of a) a previously learned hanging protocol saved for the user and b) a saved hanging protocol associated with a prior image exam corresponding to the new image exam. The example method includes applying the saved hanging protocol to the new image exam, the saved hanging protocol including three-dimensional manipulation to be automatically applied to the new image exam as part of the hanging protocol configuration for display. The example method includes facilitating display of the new image exam based on the saved hanging protocol.

Claims

1. A method to automatically apply advanced three-dimensional manipulation to an image exam via a hanging protocol for clinical image display, said method comprising:

detecting selection of a new image exam for display by a user;

automatically identifying at least one of a) a previously learned hanging protocol saved for the user and b) a saved hanging protocol associated with a prior image exam corresponding to the new image exam;

applying the saved hanging protocol to the new image exam, the saved hanging protocol including three-dimensional manipulation to be automatically applied to the new image exam as part of the hanging protocol configuration for display; and

facilitating display of the new image exam based on the saved hanging protocol.

2. The method of claim 1, wherein the three-dimension manipulation comprises at least one of multi-planar reconstruction and maximum intensity projection.

3. The method of claim 1, further comprising triggering a hanging protocol learning session for machine learning of the hanging protocol configuration from the user.

4. The method of claim 3, wherein the learning session is triggered based on a failure to identify a) and b).

5. The method of claim 3, further comprising monitoring, in the learning session, user workflow including three-dimensional manipulation of image data from the new image exam and accepting, using a processor, user input to record/teach at least a portion of the workflow for repeat setup.

6. The method of claim 1, wherein the saved hanging protocol is learned based on images from a first patient and applied to images from a second patient.

7. The method of claim 1, further comprising facilitating user modification of a saved workflow element in a saved hanging protocol.

8. The method of claim 1, wherein the three-dimensional manipulation includes registering pixel values from a fixed image and an interpolated moving image based on one or more transform parameters.

9. A tangible computer-readable storage medium including a set of instructions for execution by a processor, the instructions, when executed, to implement a method to automatically apply advanced three-dimensional manipulation to an image exam via a hanging protocol for clinical image display, said method comprising:

detecting selection of a new image exam for display by a user;

automatically identifying at least one of a) a previously learned hanging protocol saved for the user and b) a saved hanging protocol associated with a prior image exam corresponding to the new image exam;

applying the saved hanging protocol to the new image exam, the saved hanging protocol including three-dimensional manipulation to be automatically applied to the new image exam as part of the hanging protocol configuration for display; and

facilitating display of the new image exam based on the saved hanging protocol.

10. The computer-readable storage medium of claim 9, wherein the three-dimension manipulation comprises at least one of multi-planar reconstruction and maximum intensity projection.

11. The computer-readable storage medium of claim 9, wherein the method further comprises triggering a hanging protocol learning session for machine learning of the hanging protocol configuration from the user.

12. The computer-readable storage medium of claim 11, wherein the learning session is triggered based on a failure to identify a) and b).

13. The computer-readable storage medium of claim 11, wherein the method further comprises monitoring, in the learning session, user workflow including three-dimensional manipulation of image data from the new image exam and accepting, using a processor, user input to record/teach at least a portion of the workflow for repeat setup.

14. The computer-readable storage medium of claim 9, wherein the saved hanging protocol is learned based on images from a first patient and applied to images from a second patient.

15. The computer-readable storage medium of claim 9, wherein the method further comprises facilitating user modification of a saved workflow element in a saved hanging protocol.

16. The computer-readable storage medium of claim 9, wherein the three-dimensional manipulation includes registering pixel values from a fixed image and an interpolated moving image based on one or more transform parameters.

17. A machine learning hanging protocol analysis system comprising:

an image processor to process image data to provide three-dimensional image manipulation in conjunction with a hanging protocol; and

a learning engine to capture and store the hanging protocol including three-dimensional image manipulation configured by a monitored user,

the image processor to automatically apply three-dimensional manipulation to an image exam via the hanging protocol for clinical image display at least in part by;

detecting selection of a new image exam for display by a user;

automatically identifying at least one of a) a previously learned hanging protocol saved for the user and b) a saved hanging protocol associated with a prior image exam corresponding to the new image exam;

applying the saved hanging protocol to the new image exam, the saved hanging protocol including three-dimensional manipulation to be automatically applied to the new image exam as part of the hanging protocol configuration for display; and

facilitating display of the new image exam based on the saved hanging protocol.

18. The system of claim 17, wherein the three-dimension manipulation comprises at least one of multi-planar reconstruction and maximum intensity projection.

19. The system of claim 17, wherein the learning engine is to be triggered based on a failure to identify a) and b).

20. The system of claim 17, wherein the saved hanging protocol is to be learned based on images from a first patient and applied to images from a second patient.

21. The system of claim 17, wherein the image processor further comprises:

a metric generator to receive pixel data from a fixed image and a moving image and generate a fitness value for registration between the fixed image and the moving image;

an interpolator to interpolate pixel data from the moving image and to provide the interpolated moving image pixel data to the metric generator;

an optimizer to generate one or more transform parameters based on the fitness value; and

a transformer to generate one or more spatial mapping points for the moving image based on the one or more transform parameters.