IP Library › Granted Patent US 8,831,311
Granted Patent B2
US 8,831,311 · App. 13/731,140 · Granted Sep 9, 2014

Methods and systems for automated soft tissue segmentation, circumference estimation and plane guidance in fetal abdominal ultrasound images

Inventors: Gokul Swamy (Bangalore, IN); Rui Li (Niskayuna, NY)
Assignee: General Electric Company
G06K9/46
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 8,831,311
App. No.
13/731,140
Filed
Dec 31, 2012
Granted
Sep 9, 2014
Kind
B2
Art Unit
2665
USPC
382/128
Abstract

A computer-implemented method for analyzing a fetal ultrasound image includes accessing a first statistical model calculated from training data representing shapes of conforming fetal abdominal tissue exemplars and accessing image data representing a scan plane in an ultrasound image. The method further includes identifying a region of interest including an abdomen in the scan plane using the first statistical model, accessing a second statistical model calculated from training data representing shapes of conforming fetal anatomical structure exemplars, determining whether one or more anatomical structures are present within the region of interest using the second statistical model, and assigning a rating to the scan plane based on the presence of the one or more anatomical structures in the region of interest. The anatomical structures may include a stomach and/or a portal vein. The method may include calculating an estimated circumference of the abdomen.

Claims (62)

1. A computer-implemented method for analyzing a fetal ultrasound image, the computer including a processor and a memory operatively coupled to the processor, the method comprising:

accessing, in the memory, a first statistical model calculated from training data representing shapes of conforming fetal abdominal tissue exemplars;

accessing, in the memory, image data representing a scan plane in an ultrasound image;

identifying, by the processor, a region of interest including an abdomen in the scan plane using the first statistical model;

accessing, in the memory, a second statistical model calculated from training data representing shapes of conforming fetal anatomical structure exemplars;

determining, by the processor, whether one or more anatomical structures are present within the region of interest using the second statistical model; and

assigning, by the processor, a rating to the scan plane based on the presence of the one or more anatomical structures in the region of interest.

2. The computer-implemented method of claim 1 , wherein the one or more anatomical structures include at least one of a stomach and a portal vein.

3. The computer-implemented method of claim 2 , further comprising assigning the rating to be one of:

good, if both the stomach and the portal vein are present in the scan plane,

acceptable, if either the stomach or the portal vein is present in the scan plane; and

bad, otherwise.

4. The computer-implemented method of claim 3 , further comprising displaying, by the processor via an operator display operatively coupled to the processor, the rating and the region of interest.

5. The computer-implemented method of claim 1 , further comprising calculating, by the processor, an estimated circumference of the abdomen.

6. The computer-implemented method of claim 5 , further comprising enhancing, by the processor, the ultrasound image using a filter so as to increase a contrast between the abdomen and other anatomical structures present in the scan plane.

7. The computer-implemented method of claim 6 , wherein calculating the estimated circumference comprises:

generating, by the processor, a contour of the abdomen, wherein the contour is coincident to a boundary between the abdomen and the other anatomical structures present in the scan plane; and

measuring a length of the contour.

8. The computer-implemented method of claim 7 , further comprising removing, by the processor, noise artifacts adjacent to the contour.

9. The computer-implemented method of claim 8 , further comprising fitting a predefined geometric shape to the contour.

10. A non-transitory computer-readable medium having stored thereon computer-executable instructions that when executed by a computer cause the computer to:

access a first statistical model calculated from training data representing shapes of conforming fetal abdominal tissue exemplars;

access image data representing a scan plane in an ultrasound image;

identify a region of interest including an abdomen in the scan plane using the first statistical model;

access a second statistical model calculated from training data representing shapes of conforming fetal anatomical structure exemplars;

determine whether one or more anatomical structures are present within the region of interest using the second statistical model; and

assign a rating to the scan plane based on the presence of the one or more anatomical structures in the region of interest.

11. The computer-readable medium of claim 10 , wherein the one or more anatomical structures include at least one of a stomach and a portal vein.

12. The computer-readable medium of claim 11 , further comprising computer-executable instructions that when executed by the computer cause the computer to assign the rating to be one of:

good, if both the stomach and the portal vein are present in the scan plane,

acceptable, if either the stomach or the portal vein is present in the scan plane; and

bad, otherwise.

13. The computer-readable medium of claim 12 , further comprising computer-executable instructions that when executed by the computer cause the computer to display, via an operator display, the rating and the region of interest.

14. The computer-readable medium of claim 10 , further comprising computer-executable instructions that when executed by the computer cause the computer to calculate an estimated circumference of the abdomen.

15. The computer-readable medium of claim 14 , further comprising computer-executable instructions that when executed by the computer cause the computer to enhance the ultrasound image using a filter so as to increase a contrast between the abdomen and other anatomical structures present in the scan plane.

16. The computer-readable medium of claim 15 , further comprising computer-executable instructions that when executed by the computer cause the computer to:

generate a contour of the abdomen, wherein the contour is coincident to a boundary between the abdomen and the other anatomical structures in the scan plane; and

measure a length of the contour.

17. The computer-readable medium of claim 16 , further comprising computer-executable instructions that when executed by the computer cause the computer to remove noise artifacts adjacent to the contour.

18. The computer-readable medium of claim 17 , further comprising computer-executable instructions that when executed by the computer cause the computer to fit a predefined geometric shape to the contour.

19. A system for analyzing a fetal abdominal ultrasound image, the system comprising:

a processor;

an input operatively coupled to the processor and configured to receive image data representing a scan plane in an ultrasound image; and

a memory operatively coupled to the processor, the memory including computer-executable instructions that when executed by the processor cause the processor to:

access a first statistical model calculated from training data representing shapes of conforming fetal abdominal tissue exemplars;

access the image data;

identify a region of interest including an abdomen in the scan plane using the first statistical model;

access a second statistical model calculated from training data representing shapes of conforming fetal anatomical structure exemplars;

determine whether one or more anatomical structures are present within the region of interest using the second statistical model; and

assign a rating to the scan plane based on the presence of the one or more anatomical structures in the region of interest.

20. The system of claim 19 , wherein the one or more anatomical structures include at least one of a stomach and a portal vein.

21. The system of claim 20 , wherein the memory further includes computer-executable instructions that when executed by the processor cause the processor to assign the rating to be one of:

good, if both the stomach and the portal vein are present in the scan plane, acceptable, if either the stomach or the portal vein is present in the scan plane; and

bad, otherwise.

22. The system of claim 21 , wherein the memory further includes computer-executable instructions that when executed by the processor cause the processor to display, via an operator display, the rating and the region of interest.

23. The system of claim 19 , wherein the memory further includes computer-executable instructions that when executed by the processor cause the processor to calculate an estimated circumference of the abdomen.

24. The system of claim 23 , wherein the memory further includes computer-executable instructions that when executed by the processor cause the processor to enhance the ultrasound image using a filter so as to increase a contrast between the abdomen and other anatomical structures present in the scan plane.

25. The system of claim 24 , wherein the memory further includes computer-executable instructions that when executed by the processor cause the processor to:

generate a contour of the abdomen, wherein the contour is coincident to a boundary between the abdomen and the other anatomical structures in the scan plane; and

measure a length of the contour.

26. The system of claim 25 , wherein the memory further includes computer-executable instructions that when executed by the processor cause the processor to remove noise artifacts adjacent to the contour.

27. The system of claim 26 , wherein the memory further includes computer-executable instructions that when executed by the processor cause the processor to fit a predefined geometric shape to the contour.

Assignments (2)
NUNC PRO TUNC ASSIGNMENT Recorded May 8, 2025
From: GENERAL ELECTRIC COMPANY
To: GE PRECISION HEALTHCARE LLC
Reel/Frame 071225/0218 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 31, 2012
From: SWAMY, GOKUL; LI, RUI
To: GENERAL ELECTRIC COMPANY
Reel/Frame 029545/0835 →
Continuity (1)
Related Publication 20140185895A1 · Jul 3, 2014