IP Library › Granted Patent US 12,749,196
Granted Patent B2
US 12,749,196 · App. 18/539,651 · Granted Sep 29, 2026

Left atrial appendage segmentation and quantification in 3D and 4D cardiac ultrasound

Inventors: Yue Zhang (Jersey City, NJ); Puneet Sharma (Princeton Junction, NJ)
Assignee: Siemens Medical Solutions USA, Inc.
G06T7/11A61B8/085A61B8/0883A61B8/12A61B8/466A61B8/469A61B8/48A61B8/483A61B8/5207G06T7/149G06T7/246G06T7/62G06T7/73G06T2207/10028G06T2207/10136G06T2207/20081G06T2207/20104G06T2207/20132G06T2207/30048
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 12,749,196
App. No.
18/539,651
Granted
Sep 29, 2026
Kind
B2
Abstract

Systems and methods for real time three-dimensional left atrial appendage (LAA) quantification. Deep learning is used to perform LAA segmentation, tracking and live quantification on critical measurement in 4D ultrasound sequences. The collected information may be used for device selection and anomaly detection to assist early-phase disease finding.

Claims (54)

1 . A method for real time three-dimensional left atrial appendage quantification, the method comprising:

acquiring a real time three-dimensional ultrasound sequence of a patient;

selecting a seed location of the left atrial appendage in a frame of the real time three-dimensional ultrasound sequence;

cropping the frame to a region of interest based on the seed location;

generating an initial three-dimensional left atrial appendage segmentation from the region of interest;

extracting one or more landmarks from the three-dimensional left atrial appendage segmentation;

slicing the initial three-dimensional left atrial appendage segmentation into a plurality of two-dimensional slices, wherein the plurality of two-dimensional slices each include a portion of a contour of the left atrial appendage;

tracking the contour of the left atrial appendage in the plurality of two-dimensional slices for a plurality of subsequent frames of the real time three-dimensional ultrasound sequence and tracking the one or more landmarks in the real time three-dimensional ultrasound sequence;

generating a real time three-dimensional left atrial appendage segmentation for each of the plurality of subsequent frames by aggregating the tracked contours from the two-dimensional slices for each respective subsequent frame; and

quantifying at least one morphological metric from the tracked contour and/or the tracked one or more landmarks, wherein the at least one morphological metric comprises a diameter of the left atrial appendage over time, wherein the quantified diameter is used to determine a property of a device in a left atrial appendage closure procedure.

2 . The method of claim 1 , wherein selecting the seed location comprises:

freezing the real time three-dimensional ultrasound sequence; and

clicking, by a user, on the seed location inside the left atrial appendage in a frame of the frozen real time three-dimensional ultrasound sequence;

wherein the real time three-dimensional ultrasound sequence is unfrozen after selecting the seed location.

3 . The method of claim 1 , wherein cropping comprises:

calculating an estimated shape and size of the left atrial appendage from a collected dataset of images of left atrial appendages of a plurality of patients; and

centering the region of interest around the seed location based on the estimated shape and size.

4 . The method of claim 1 , wherein the three-dimensional left atrial appendage segmentation is generated using a machine trained network.

5 . The method of claim 1 , wherein the one or more landmarks comprises at least one of ostium and neck landmarks that determine diameters of the ostium and neck area of the left atrial appendage.

6 . The method of claim 1 , wherein the contour and the one or more landmarks are tracked in real time using respective neural networks trained using a cycle-consistency loss.

7 . The method of claim 1 , wherein the diameter of the left atrial appendage is used to determine and select properties of the device in the left atrial appendage closure procedure that matches characteristics of the patient's left atrial appendage.

8 . The method of claim 1 , wherein the real time three-dimensional ultrasound sequence is provided by an ultrasound system configured for Intracardiac Echocardiography.

9 . A system for real time three-dimensional left atrial appendage segmentation, the system comprising:

an ultrasound imaging system configured to acquire a 4D ultrasound sequence of patient; and

a processor configured to:

select a seed location of the left atrial appendage in a frame of the 4D ultrasound sequence,

crop the frame to a region of interest based on the seed location,

generate an initial three-dimensional left atrial appendage segmentation from the region of interest,

extract one or more landmarks from the initial three-dimensional left atrial appendage segmentation,

slice the initial three-dimensional left atrial appendage segmentation into a plurality of two-dimensional slices, wherein the plurality of two-dimensional slices each include a portion of a contour of the left atrial appendage,

track the contour in the plurality of two-dimensional slices over time and the one or more landmarks in the 4D ultrasound sequence,

generate a real time three-dimensional left atrial appendage segmentation for each of the plurality of subsequent frames by aggregating the tracked contours from the two-dimensional slices for each respective subsequent frame,

quantify at least one morphological metric from the tracked contour and/or the tracked one or more landmarks, wherein the at least one morphological metric comprises a diameter of the left atrial appendage over time, and

cause a display to present the quantified diameter for use in determining a property of a device in a left atrial appendage closure procedure.

10 . The system of claim 9 , wherein cropping comprises:

calculating an estimated shape and size of the left atrial appendage from a collected dataset of images of left atrial appendages of a plurality of patients; and

centering the region of interest around the seed location based on the estimated shape and size.

11 . The system of claim 9 , wherein the processor is configured to generate the three-dimensional left atrial appendage segmentation using a machine trained network.

12 . The system of claim 9 , wherein the one or more landmarks comprises at least one of ostium and neck landmarks that determine diameters of the ostium and neck area of the left atrial appendage.

13 . The system of claim 9 , wherein the processor is configured to track the contour and the one or more landmarks in real time using respective neural networks trained using a cycle-consistency loss.

14 . The system of claim 9 , wherein the diameter of the left atrial appendage is used to determine and select properties of the device in the left atrial appendage closure procedure that matches characteristics of the patient's left atrial appendage.

15 . The system of claim 9 , wherein the ultrasound imaging system is configured for Intracardiac Echocardiography.

16 . A system comprising:

an ultrasound imaging system configured to acquire a 4D ultrasound sequence of patient;

a display configured to display the 4D ultrasound sequence;

an input device configured to identify a seed location for a left atrial appendage in a frame of the 4D ultrasound sequence; and

a processor configured to:

crop the frame to a region of interest based on the seed location,

generate an initial three-dimensional left atrial appendage segmentation from the region of interest,

slice the initial three-dimensional left atrial appendage segmentation into a plurality of two-dimensional slices, wherein the plurality of two-dimensional slices each include a portion of a contour of the left atrial appendage,

track the contour in the plurality of two-dimensional slices in real time,

generate a real time three-dimensional left atrial appendage segmentation for each of the plurality of subsequent frames by aggregating the tracked contours from the two-dimensional slices for each respective subsequent frame,

identify one or more landmarks in the three-dimensional left atrial appendage segmentation and track the one or more landmarks over time in the 4D ultrasound sequence, and

quantify at least one metric from the real time three-dimensional left atrial appendage segmentation and/or the tracked one or more landmarks.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 19, 2023
From: ZHANG, YUE; SHARMA, PUNEET
To: SIEMENS MEDICAL SOLUTIONS USA, INC.
Reel/Frame 065906/0379 →
Continuity (1)
Related Publication 20250200752A1 · Jun 19, 2025
References Cited (28)
US 7516556B2 · Yepes Segovia et al. · 2009 [cited by applicant]
US 7783094B2 · Collins et al. · 2010 [cited by applicant]
US 7940995B2 · Lee et al. · 2011 [cited by applicant]
US 12376830B2 · Miyaki et al. · 2025 [cited by applicant]
US 20120065499A1 · Chono · 2012 [cited by applicant]
US 20190374251A1 · Lin et al. · 2019 [cited by applicant]
US 20240024037A1 · Matsumura · 2024 [cited by examiner]
US 20240206852A1 · Jiang · 2024 [cited by examiner]
AU 200620164B2 · 2011 [cited by applicant]
JP 2006192254A · 2006 [cited by applicant]
JP 2006305361A · 2006 [cited by applicant]
JP 2008511889A · 2008 [cited by applicant]
JP 2008541889A · 2008 [cited by applicant]
JP 2022164469A · 2022 [cited by applicant]
WO 2010134512A1 · 2010 [cited by applicant]
Xiaofei Sun et al 2023 Phys. Med. Biol. 68 125007 Published Jun. 12, 2023 (Year: 2023). [cited by examiner]
Guicheng Liang, Beizhu Xu, Shirong Wang, Chengxuan Li, Guoqiang Zhong. Imaging with intracardiac echocardiography compared to transesophageal echocardiography during left atrial appendage occlusion. Rev. Cardiovasc. Med… [cited by examiner]
Huang, Y., He, J., Wu, X., Zhao, X. and Wu, J. (2021), Tracking 3D ultrasound anatomical landmarks via three orthogonal plane-based scale discriminative correlation filter network. Med. Phys., 48: 2127-2135. https://doi… [cited by examiner]
Kinda, Anna & Saddi, Kinda & Rousson, Mikaël & Cheriet, Farida. (2007). Global-to-Local Shape Matching for Liver Segmentation in CT Imaging. Proc. MICCAI Workshop 3-D Segmentation Clinic: A Grand Challenge. (Year: 2007). [cited by examiner]
Extended European Search Report (EESR) mailed Apr. 14, 2025 in related European Patent Application No. 24219437.1. [cited by applicant]
Moghadam Pakizeh et al:; “Semi-Automated Algorithm for Segmentation of the Left Atrial Appendage Landing Zone: Application in Left Atrial Appendage Occlusion Procedures”; Journal of Biomedical Physics and Engineering; A… [cited by applicant]
Crestan Albereta et al:; “Automatic Segmentation Framework for Left Atrial Appendage Orifice Identification from 3D Echocardiography”; Apr. 4, 2024. [cited by applicant]
Jin, Cheng, et al. “Detection of Substances in the Left Atrial Appendage by Spatiotemporal Motion Analysis Based on 4D-CT.” Statistical Atlases and Computational Models of the Heart. ACDC and MMWHS Challenges: 8th Inter… [cited by applicant]
Jin, Cheng, et al. “Left atrial appendage segmentation and quantitative assisted diagnosis of atrial fibrillation based on fusion of temporal-spatial information.” Computers in biology and medicine 96 (2018): 52-68. [cited by applicant]
Leventic, Hrvoje, et al. “A survey of left atrial appendage segmentation and analysis in 3D and 4D medical images.” The 28th International Conference on Systems, Signals and Image Processing, IWSSIP 2021. 2021. [cited by applicant]
Morais, Pedro, et al. “Fast segmentation of the left atrial appendage in 3-D transesophageal echocardiographic images.” IEEE transactions on ultrasonics, ferroelectrics, and frequency control 65.12 (2018): 2332-2342. [cited by applicant]
Park, Jai-Wun, et al. “Left atrial appendage closure with Amplatzer cardiac plug in atrial fibrillation: initial European experience.” Catheterization and Cardiovascular Interventions 77.5 (2011): 700-706. [cited by applicant]
Zheng, Yefeng, et al. “Four-chamber heart modeling and automatic segmentation for 3-D cardiac CT vols. using marginal space learning and steerable features.” IEEE transactions on medical imaging 27.11 (2008): 1668-1681. [cited by applicant]