METHOD AND SYSTEM FOR AUTOMATED POSITIONING OF A MEDICAL DIAGNOSTIC DEVICE

• US 20180028142A1
• Filed: 01/29/2016
• Published: 02/01/2018
• Est. Priority Date: 02/23/2015
• Status: Active Grant

• Current Assignee: Siemens Healthineers AG (Siemens AG)
• Original Assignee: Siemens Healthcare GMBH (Siemens AG)
• Inventors: Bhatia, Parmeet Singh, Douglas, Antony Louis Piriyakumar
• Granted Patent: US 10,398,402 B2
• Time in Patent Office: Days
• CPC Class Codes: A61B 6/547 involving tracking of position of the device or parts of the device
• CPC Class Codes: A61B 8/4263 using sensors not mounted on the probe, e.g. mounted on an external reference frame
• CPC Class Codes: G06T 2207/10 Image acquisition modality

Abstract

A method and system are provided for automatically positioning a medical diagnostic device. The method and system use a database of images that includes reference images and user-preferred images to position the medical diagnostic device. The medical diagnostic device in an initial position is moved to a final position based on the images in the database.

Claims

1. A method for positioning a medical diagnostic device, the method comprising:

determining, by a processor, a current position of the medical diagnostic device, the determining of the current position of the medical diagnostic device comprising comparing a current image with at least one reference image in a first database;

determining, by the processor, target position coordinates and a similarity score, iteratively, the determining of the target position coordinates and the similarity score comprising comparing the current image with the at least one reference image, a user preferred image in a second database, or the at least one reference image and the user preferred image;

computing, by the processor, one or more motion parameters associated with the target position coordinates of the medical diagnostic device;

actuating, by the processor, movement of the medical diagnostic device to a target position based on the one or more motion parameters.

2. The method of in accordance with claim 1, wherein the similarity score is based on a similarity between the current image and the at least one reference image and position coordinates associated with the current first image, and the at least one reference image.

3. The method of claim 1, wherein determining the target position coordinates iteratively further comprises computing one or more intermediate position coordinates for one or more intermediate positions when the similarity score is below a threshold value.

4. The method of claim 3, wherein the current image is updated when the medical diagnostic device is in the one or more intermediate positions.

5. The method of claim 1, wherein the second database comprises one or more reference images generated during a manual operation of the medical diagnostic device.

6. The method of claim 1, further comprising identifying, using a machine learning model, feedback position coordinates when the target position is changed manually.

7. The method of claim 1, further comprising generating personalized position coordinates and motion parameters for different users based on one or more machine learning models.

8. The method of claim 1, wherein the at least one reference image in the first database and the user preferred image in the second database include position coordinates as meta information.

16. The system of claim 1, wherein the medical diagnostic device is a medical imaging device.

17. The method of claim 1, wherein the medical diagnostic device is a patient care device.

9. A system for positioning a medical diagnostic device, the system comprising:

a processor; and

a memory coupled with the processor, wherein the memory includes processor executable instructions in the form of a position guidance module to;

determine a current position of the medical diagnostic device, the determination of the current position of the medical diagnostic device comprising comparison of a current image with at least one reference image in a first database;

determine target position coordinates, the determination of the target position coordinates comprising comparison of the current image with at least one preferred image in a second database;

calculate a similarity score for the current image;

calculate one or more motion parameters of the target position coordinates of the medical diagnostic device iteratively, based on the similarity score; and

actuate movement of the medical diagnostic device to a target position based on the one or more motion parameters.

10. The system of claim 9, wherein the position guidance module is configured to calculate the similarity score based on a similarity between the current image, the at least one preferred image, or the current image and the at least one preferred image and motion coordinates associated with the current image and the at least one preferred image.

11. The system of claim 9, wherein the position guidance module is further configured to use machine learning models to incorporate feedback based on a change in the target position.

12. The system of claim 9, wherein the position guidance module is further configured to calculate one or more intermediate position coordinates and one or more intermediate motion parameters based on the similarity score.

13. The system of claim 9, wherein the position guidance module is further configured to generate personalized position coordinates and personalized motion parameters for different users based on one or more machine learning models.

14. The system of claim 9, wherein the medical diagnostic device is a medical imaging device.

15. The system of claim 9, wherein the medical diagnostic device is a patient care device.