IP Library Granted Patent US 9,179,890
Granted Patent B2
US 9,179,890 · App. 13/546,066 · Granted Nov 10, 2015

Model-based positioning for intracardiac echocardiography volume stitching

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 9,179,890
App. No.
13/546,066
Granted
Nov 10, 2015
Kind
B2
Abstract

Different intracardiac echocardiography volumes are stitched together. Different volumes of a patient are scanned with ICE. To stitch the volumes together, creating a larger volume, the volumes are spatially aligned. The alignment is based on feature, surface, or both feature and surface matching of the ICE volumes with a preoperative model of the same patient. The matching with the model indicates a relative position of the ICE volumes with each other. Using machine-trained classifiers may speed performance, allowing for real-time assembling of a volume from ICE data as the catheter is moved within the patient.

Claims (41)

1. A method for stitching intracardiac echocardiography volumes, the method comprising:

scanning first and second different cardiac volumes with ultrasound from a catheter within a patient;

acquiring a model of at least a part of the cardiac system, the model being from preoperative data representing the part of the cardiac system;

aligning the first and second cardiac volumes with the model;

combining ultrasound data of the first and second cardiac volumes into a third volume based on the aligning; and

generating an image of the part of the cardiac system from the combined ultrasound data of the third volume.

2. The method of claim 1 wherein scanning comprises scanning with the catheter comprising an intracardiac echocardiography catheter.

3. The method of claim 1 wherein scanning comprises scanning the first cardiac volume, moving the catheter, and scanning the second cardiac volume, the first cardiac volume overlapping the second cardiac volume.

4. The method of claim 1 wherein acquiring the model comprises acquiring the model as a plurality of surfaces and landmarks.

5. The method of claim 1 wherein acquiring the model comprises acquiring from the preoperative data comprising transesophageal ultrasound data, magnetic resonance data, computed tomography data, or combinations thereof.

6. The method of claim 1 wherein acquiring the model comprises estimating parameters of the model from the preoperative data with a machine-learnt detector.

7. The method of claim 1 wherein aligning comprises:

detecting first and second features in the first and second cardiac volumes, respectively; and

registering the first and second features with third and fourth features of the model.

8. The method of claim 1 wherein aligning comprises:

registering first and second surfaces of the model with the ultrasound data of the first and second volumes.

9. The method of claim 8 wherein aligning also comprises:

detecting first and second features in the first and second cardiac volumes, respectively;

registering the first and second features with third and fourth features of the model; and

iteratively solving for an alignment using the registering of the first and second features and the first and second surfaces.

10. The method of claim 9 further comprising:

initializing the aligning by deforming the model to the first and second features.

11. The method of claim 1 wherein combining comprises interpolating to a same coordinate system.

12. The method of claim 1 wherein generating comprises three-dimensionally rendering the image or generating a multi-planar reconstruction from the combined ultrasound data of the third volume.

13. In a non-transitory computer readable storage medium having stored therein data representing instructions executable by a programmed processor for stitching intracardiac echocardiography volumes, the storage medium comprising instructions for:

registering intracardiac echocardiography data from different scans with a physiological model, the model and the intracardiac echocardiography data being derived from a same patient, the different scans having an unknown relationship between coordinate systems; and

generating a volume with a common coordinate system from the different scans as a function of the registering.

14. The non-transitory computer readable storage medium of claim 13 wherein registering comprises:

extracting landmarks represented by the intracardiac echocardiography data; and

aligning the landmarks with the model.

15. The non-transitory computer readable storage medium of claim 13 wherein registering comprises:

correlating surfaces of the model with the intracardiac echocardiography data;

aligning based on the correlating.

16. The non-transitory computer readable storage medium of claim 13 wherein generating comprises interpolating the intracardiac echocardiography data to the common coordinate system.

17. A system for stitching intracardiac echocardiography volumes, the system comprising:

an ultrasound scanner configured to scan with a catheter in a patient a plurality of volumes of the patient, the ultrasound scanner generating sets of ultrasound data representing the volumes, the volumes being for different regions of the patient; and

a processor configured to generate a model of part of the patient from preoperative data scanned from the patient, to spatially register the sets of ultrasound data with the model, and to fuse the sets of ultrasound data as spatially registered.

18. The system of claim 17 wherein the processor is configured to generate the model by acquiring the preoperative data as transesophageal ultrasound data, magnetic resonance data, computed tomography data or combinations thereof and applying a machine trained detector to the preoperative data, the machine trained detector outputting landmarks and surfaces; and

configured to spatially register by aligning the surfaces of the model with the ultrasound data, aligning the landmarks with landmarks extracted from the ultrasound data, and jointly solving from both alignments using probabilities.

19. The system of claim 17 wherein the processor is configured to fuse by interpolating the ultrasound data of the sets to a common coordinate system.

20. The system of claim 17 wherein the processor is configured to generate an image as a function of the fused sets of ultrasound data.

Assignments (7)
CORRECTIVE ASSIGNMENT TO CORRECT THE ASSIGNEE PREVIOUSLY RECORDED AT REEL: 066088 FRAME: 0256. ASSIGNOR(S) HEREBY CONFIRMS THE ASSIGNMENT. Recorded Jan 17, 2024
From: SIEMENS HEALTHCARE GMBH
To: SIEMENS HEALTHINEERS AG
Reel/Frame 071178/0246 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 20, 2023
From: SIEMENS HEALTHCARE GMBH
To: SIEMENS HEALTHINEERS AG
Reel/Frame 066088/0256 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 27, 2016
From: SIEMENS AKTIENGESELLSCHAFT
To: SIEMENS HEALTHCARE GMBH
Reel/Frame 039011/0400 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 5, 2015
From: SIEMENS CORPORATION
To: SIEMENS MEDICAL SOLUTIONS USA, INC.
Reel/Frame 036722/0690 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 11, 2013
From: CAMUS, ESTELLE
To: SIEMENS MEDICAL SOLUTIONS USA, INC.
Reel/Frame 029609/0814 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 26, 2012
From: IONASEC, RAZVAN IOAN; COMANICIU, DORIN
To: SIEMENS CORPORATION
Reel/Frame 029347/0990 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 19, 2012
From: GRBIC, SASA
To: SIEMENS AKTIENGESELLSCHAFT
Reel/Frame 029159/0131 →