US 12,740,760 B1Granted

Apparatus and method for reconstruction of anatomical structure using transesophageal echocardiography (TEE) imaging

AssigneeAnumana, Inc.

InventorsAbhijith Chunduru, Animesh Agarwal, Suthirth Vaidya Subramany, Rakesh Barve

Life of this patent

Estimating the term…

Loading patent…

Abstract

An apparatus and method for reconstruction of anatomical structure using Transesophageal Echocardiography (TEE) imaging. The apparatus includes at least a processor and a memory communicatively connected to the at least a processor configured to receive first image data corresponding to a first sweep of the at least a transducer from the TEE probe, generate, using a 3D reconstruction model, at least a 3D model representative of the at least a structure, as a function of image data, receive second image data corresponding to a second sweep of the at least a transducer from the TEE probe, refine, using the 3D reconstruction model, the at least a 3D model as a function of the second image data, identify, using the at least a processor, a confidence score of a refined 3D model, and display, using a graphical user interface of a downstream device, the refined 3D model and the confidence score.

Claims18

Dependent claims

An apparatus for reconstruction of anatomical structure using Transesophageal Echocardiography (TEE) imaging, wherein the apparatus comprises:

at least a TEE probe comprising at least a transducer, wherein the at least a transducer is configured to capture ultrasound signal data and generate image data of at least a structure of a subject;
at least a computing device, wherein the computing device is communicatively connected to the at least a transducer, the computing device comprises:
a memory;
and
at least a processor communicatively connected to the memory, wherein the memory contains instructions configuring the at least a processor to:
receive first image data corresponding to a first sweep of the at least a transducer from the TEE probe;
generate, using a 3D reconstruction model, at least a 3D model representative of the at least a structure, as a function of the first image data, wherein generating the at least a 3D model comprises:
segmenting, using a segmentation algorithm, the at least a structure in each frame of the image data;
determining, using the 3D reconstruction model, an orientation of the at least a transducer based on probe position data obtained from the transducer comprising the TEE probe;
and
constructing, using the 3D reconstruction model, a first 3D model of the at least a structure as a function of segmented image data and the orientation of the at least a transducer;
receive second image data corresponding to a second sweep of the at least a transducer from the TEE probe;
refine, using the 3D reconstruction model, the at least a 3D model as a function of the second image data, wherein refining the at least a 3D model comprises:
identifying using the at least a processor, a confidence score of a refined 3D model;
and
iteratively refining, using the 3D reconstruction model, the first 3D model using successive video frames of the second image data to generate the refined 3D model;
and
display, using a graphical user interface of a downstream device, the refined 3D model and the confidence score.

15 more elements

A method for reconstruction of anatomical structure using Transesophageal Echocardiography (TEE) imaging, wherein the method comprises:

capturing, using at least a transducer of a TEE probe, ultrasound signal data and generate image data of at least a structure of a subject;
receiving, using at least a processor communicatively connected to the at least a transducer, first image data corresponding to a first sweep of the at least a transducer from the TEE probe;
generating, using a 3D reconstruction model, at least a 3D model representative of the at least a structure, as a function of image data, wherein the 3D reconstruction model is configured to:
segment, using a segmentation algorithm, the at least a structure in each frame of the image data;
determine, using the 3D reconstruction model, an orientation of the at least a transducer based on probe position data obtained from the transducer comprising the TEE probe;
and
construct, using the 3D reconstruction model, a first 3D model of the at least a structure as a function of segmented image data and the orientation of the at least a transducer;
receiving, using the at least a processor, second image data corresponding to a second sweep of the at least a transducer from the TEE probe;
refining, using the 3D reconstruction model, the at least a 3D model as a function of the second image data, wherein refining the at least a 3D model comprises:
identifying, using the at least a processor, a confidence score of a refined 3D model;
and
iteratively refining, using the 3D reconstruction model, the first 3D model using successive video frames of the second image data to generate the refined 3D model;
and
displaying, using a graphical user interface of a downstream device, the refined 3D model and the confidence score.

11 more elements

Dependencies are inferred from the claim text.