# US 2017/0255745 A1 · System and Method for Medical Image Based Cardio-Embolic Stroke Risk Prediction

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2017/0255745 A1
- Document ID: US20170255745A1
- Status: Published application
- Kind: A1
- Application number: 15/424,911
- Filed: 2017-02-06
- Published: 2017-09-07
- Earliest claimed: 2016-03-01
- Assignees: Siemens Healthcare GmbH
- Applicants: Siemens Healthcare GmbH
- Inventors: Viorel Mihalef; Puneet Sharma
- Web page: https://patentgrep.com/patent/US20170255745A1

## CPC

- G16H 10/60: for patient-specific data, e.g. for electronic patient records
- G06F 17/11: for solving equations {, e.g. nonlinear equations, general mathematical optimization problems (optimization specially adapted for a specific administrative, business or logistic context G06Q10/04)}
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/09: Supervised learning
- G06T 7/12: Edge-based segmentation
- G06T 7/149: involving deformable models, e.g. active contour models
- G16H 30/20: for handling medical images, e.g. DICOM, HL7 or PACS
- G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems
- G16H 50/30: for calculating health indices; for individual health risk assessment
- G16H 50/50: for simulation or modelling of medical disorders
- G06N 3/08: Learning methods
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- G06T 2207/20081: Training; Learning
- G06T 2207/30048: Heart; Cardiac
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

A system and method for medical image based patient-specific ischemic stroke risk prediction is disclosed. Left atrium (LA) and left atrium appendage (LAA) measurements are extracted from medical image data of a patient. Derived metrics for the LA and LAA of the patient are computed using a patient-specific computational model of cardiac function based on the LA and LAA measurements extracted from the medical image data of the patient. A stroke risk score for the patient is calculated based on the extracted LA and LAA measurements and the computed derived metrics for the LA and LAA of the patient using a trained machine learning based classifier, which inputs the extracted LA and LAA measurements and the computed derived metrics for the LA and LAA as features.

## Claims

### Claim 1

A method for medical image based patient-specific stroke risk prediction, comprising:
extracting left atrium (LA) and left atrium appendage (LAA) measurements from medical image data of a patient;
computing derived metrics for the LA and LAA of the patient using a patient-specific computational model of cardiac function based on the LA and LAA measurements extracted from the medical image data of the patient; and
calculating a stroke risk score for the patient based on the extracted LA and LAA measurements and the computed derived metrics for the LA and LAA of the patient using a trained machine learning based classifier, wherein the extracted LA and LAA measurements and the computed derived metrics for the LA and LAA are input as features to the trained machine learning based classifier.

### Claim 2 (depends on 1)

The method of claim 1, wherein extracting left atrium (LA) and left atrium appendage measurements from medical image data of a patient comprises:
segmenting the LA in the medical image data of the patient.

### Claim 3 (depends on 2)

The method of claim 2, wherein segmenting the LA in the medical image data of the patient comprises:
generating a 3D LA mesh from 3D medical image data of the patient.

### Claim 4 (depends on 3)

The method of claim 3, wherein generating a 3D LA mesh from 3D medical image data of the patient comprises:
segmenting a plurality of LA parts in the medical image data using a multi-part atria model; and
generating a consolidated LA mesh from the segmented plurality of atria parts.

### Claim 5 (depends on 2)

The method of claim 2, wherein segmenting the LA in the medical image data of the patient comprises:
generating a sequence of LA meshes from 4D (3D+time) medical image data of the patient.

### Claim 6 (depends on 2)

The method of claim 2, wherein extracting left atrium (LA) and left atrium appendage measurements from medical image data of a patient further comprises:
extracting an LA volume, LAA volume, and a number of LAA lobes based on the segmented LA, wherein the LA volume, LAA volume, and number of LAA lobes are input as features to the machine learning based classifier.

### Claim 7 (depends on 2)

The method of claim 2, wherein extracting left atrium (LA) and left atrium appendage measurements from medical image data of a patient further comprises:
extracting hemodynamic measurements for the LA and LAA from the medical image data of the patient.

### Claim 8 (depends on 1)

The method of claim 1, wherein computing derived metrics for the LA and LAA of the patient using a patient-specific computational model of cardiac function based on the LA and LAA measurements extracted from the medical image data of the patient comprises:
simulating blood flow in the LA and LAA using the patient-specific computational model of heart function; and
computing hemodynamic features for the LA and LAA based on the simulated blood flow in the LA and LAA, wherein the hemodynamic features are input to the trained machine learning based classifier.

### Claim 9 (depends on 8)

The method of claim 8, wherein computing hemodynamic features for the LA and LAA based on the simulated blood flow in the LA and LAA comprises:
computing derived hemodynamic parameters for at least a plurality of locations in the LAA based on the simulated blood flow in the LA and LAA, wherein the derived hemodynamic parameters include one or more of relative residence time (RRT), energy loss, pressure loss coefficient, wall-shear stress (WSS), or oscillatory index (OSI).

### Claim 10 (depends on 8)

The method of claim 8, wherein computing hemodynamic features for the LA and LAA based on the simulated blood flow in the LA and LAA comprises:
computing for at least a plurality of locations in the LAA, a statistical characterization of at least one of blood flow velocity or pressure based on the simulated blood flow in the LA and LAA.

### Claim 11 (depends on 8)

The method of claim 8, wherein computing derived metrics for the LA and LAA of the patient using a patient-specific computational model of cardiac function based on the LA and LAA measurements extracted from the medical image data of the patient further comprises:
simulating electrical signal propagation in the LA using the patient-specific computational model of cardiac function; and
computing electrophysiological features for the LA and LAA from the simulated electrical signal propagation in the LA, wherein the computed electrophysiological features are input as features to the machine learning based classifier.

### Claim 12 (depends on 1)

The method of claim 1, wherein the extracted LA and LAA measurements input as features to the machine learning based classifier include LA volume, LAA volume, and number of LAA lobes, and the computed derived metrics input as features to the machine learning based classifier include one or more of relative residence time (RRT), energy loss, pressure loss coefficient, wall-shear stress (WSS), oscillatory index (OSI), mean blood flow velocity, or mean blood pressure, at one or more points in the LA and LAA.

### Claim 13 (depends on 1)

The method of claim 1, wherein calculating a stroke risk score of the patient based on the extracted LA and LAA measurements and the computed derived metrics for the LA and LAA of the patient using a trained machine learning based classifier comprises:
calculating the stroke risk score of the patient based on the extracted LA and LAA measurements and the computed derived metrics for the LA and LAA of the patient using a trained deep neural network.

### Claim 14

An apparatus for medical image based patient-specific stroke risk prediction, comprising:
means for extracting left atrium (LA) and left atrium appendage (LAA) measurements from medical image data of a patient;
means for computing derived metrics for the LA and LAA of the patient using a patient-specific computational model of cardiac function based on the LA and LAA measurements extracted from the medical image data of the patient; and
means for calculating a stroke risk score for the patient based on the extracted LA and LAA measurements and the computed derived metrics for the LA and LAA of the patient using a trained machine learning based classifier, wherein the extracted LA and LAA measurements and the computed derived metrics for the LA and LAA are input as features to the trained machine learning based classifier.

### Claim 15 (depends on 14)

The apparatus of claim 14, wherein the means for extracting left atrium (LA) and left atrium appendage measurements from medical image data of a patient comprises:
means for segmenting the LA in the medical image data of the patient.

### Claim 16 (depends on 15)

The apparatus of claim 15, wherein the left atrium (LA) and left atrium appendage measurements input as features to the trained machine learning based classifier include an LA volume, LAA volume, and a number of LAA lobes determined based on the segmented LA.

### Claim 17 (depends on 15)

The apparatus of claim 15, wherein the means for extracting left atrium (LA) and left atrium appendage measurements from medical image data of a patient further comprises:
means for extracting hemodynamic measurements for the LA and LAA from the medical image data of the patient.

### Claim 18 (depends on 14)

The apparatus of claim 14, wherein the means for computing derived metrics for the LA and LAA of the patient using a patient-specific computational model of cardiac function based on the LA and LAA measurements extracted from the medical image data of the patient comprises:
means for simulating blood flow in the LA and LAA using the patient-specific computational model of heart function; and
means for computing hemodynamic features for the LA and LAA based on the simulated blood flow in the LA and LAA, wherein the hemodynamic features are input to the trained machine learning based classifier.

### Claim 19 (depends on 18)

The apparatus of claim 18, wherein the means for computing hemodynamic features for the LA and LAA based on the simulated blood flow in the LA and LAA comprises:
means for computing derived hemodynamic parameters for at least a plurality of locations in the LAA based on the simulated blood flow in the LA and LAA, wherein the derived hemodynamic parameters include one or more of relative residence time (RRT), energy loss, pressure loss coefficient, wall-shear stress (WSS), or oscillatory index (OSI).

### Claim 20 (depends on 18)

The apparatus of claim 18, wherein the means for computing hemodynamic features for the LA and LAA based on the simulated blood flow in the LA and LAA comprises:
means for computing for at least a plurality of locations in the LAA, a statistical characterization of at least one of blood flow velocity or pressure based on the simulated blood flow in the LA and LAA.

### Claim 21 (depends on 18)

The method of claim 18, wherein the means for computing derived metrics for the LA and LAA of the patient using a patient-specific computational model of cardiac function based on the LA and LAA measurements extracted from the medical image data of the patient further comprises:
means for simulating electrical signal propagation in the LA using the patient-specific computational model of cardiac function; and
means for computing electrophysiological features for the LA and LAA from the simulated electrical signal propagation in the LA, wherein the computed electrophysiological features are input as features to the machine learning based classifier.

### Claim 22 (depends on 14)

The apparatus of claim 14, wherein the extracted LA and LAA measurements input as features to the machine learning based classifier include LA volume, LAA volume, and number of LAA lobes, and the computed derived metrics input as features to the machine learning based classifier include one or more of relative residence time (RRT), energy loss, pressure loss coefficient, wall-shear stress (WSS), oscillatory index (OSI), mean blood flow velocity, or mean blood pressure, at one or more points in the LA and LAA.

### Claim 23

A non-transitory computer readable medium storing computer program instructions for medical image based patient-specific stroke risk prediction, the computer program instructions when executed by a processor cause the processor to perform operations comprising:
extracting left atrium (LA) and left atrium appendage (LAA) measurements from medical image data of a patient;
computing derived metrics for the LA and LAA of the patient using a patient-specific computational model of cardiac function based on the LA and LAA measurements extracted from the medical image data of the patient; and
calculating a stroke risk score for the patient based on the extracted LA and LAA measurements and the computed derived metrics for the LA and LAA of the patient using a trained machine learning based classifier, wherein the extracted LA and LAA measurements and the computed derived metrics for the LA and LAA are input as features to the trained machine learning based classifier.

### Claim 24 (depends on 23)

The non-transitory computer readable medium of claim 23, wherein extracting left atrium (LA) and left atrium appendage measurements from medical image data of a patient comprises:
segmenting the LA in the medical image data of the patient.

### Claim 25 (depends on 23)

The non-transitory computer readable medium of claim 23, wherein extracting left atrium (LA) and left atrium appendage measurements from medical image data of a patient further comprises:
extracting an LA volume, LAA volume, and a number of LAA lobes based on the segmented LA, wherein the LA volume, LAA volume, and number of LAA lobes are input as features to the machine learning based classifier.

### Claim 26 (depends on 23)

The non-transitory computer readable medium of claim 23, wherein extracting left atrium (LA) and left atrium appendage measurements from medical image data of a patient further comprises:
extracting hemodynamic measurements for the LA and LAA from the medical image data of the patient.

### Claim 27 (depends on 23)

The non-transitory computer readable medium of claim 23, wherein computing derived metrics for the LA and LAA of the patient using a patient-specific computational model of cardiac function based on the LA and LAA measurements extracted from the medical image data of the patient comprises:
simulating blood flow in the LA and LAA using the patient-specific computational model of heart function; and
computing hemodynamic features for the LA and LAA based on the simulated blood flow in the LA and LAA, wherein the hemodynamic features are input to the trained machine learning based classifier.

### Claim 28 (depends on 27)

The non-transitory computer readable medium of claim 27, wherein computing hemodynamic features for the LA and LAA based on the simulated blood flow in the LA and LAA comprises:
computing derived hemodynamic parameters for at least a plurality of locations in the LAA based on the simulated blood flow in the LA and LAA, wherein the derived hemodynamic parameters include one or more of relative residence time (RRT), energy loss, pressure loss coefficient, wall-shear stress (WSS), or oscillatory index (OSI).

### Claim 29 (depends on 27)

The non-transitory computer readable medium of claim 27, wherein computing hemodynamic features for the LA and LAA based on the simulated blood flow in the LA and LAA comprises:
computing for at least a plurality of locations in the LAA, a statistical characterization of at least one of blood flow velocity or pressure based on the simulated blood flow in the LA and LAA.

### Claim 30 (depends on 27)

The non-transitory computer readable medium of claim 27, wherein computing derived metrics for the LA and LAA of the patient using a patient-specific computational model of cardiac function based on the LA and LAA measurements extracted from the medical image data of the patient further comprises:
simulating electrical signal propagation in the LA using the patient-specific computational model of cardiac function; and
computing electrophysiological features for the LA and LAA from the simulated electrical signal propagation in the LA, wherein the computed electrophysiological features are input as features to the machine learning based classifier.

### Claim 31 (depends on 23)

The non-transitory computer readable medium of claim 23, wherein the extracted LA and LAA measurements input as features to the machine learning based classifier include LA volume, LAA volume, and number of LAA lobes, and the computed derived metrics input as features to the machine learning based classifier include one or more of relative residence time (RRT), energy loss, pressure loss coefficient, wall-shear stress (WSS), oscillatory index (OSI), mean blood flow velocity, or mean blood pressure, at one or more points in the LA and LAA.

### Claim 32 (depends on 23)

The non-transitory computer readable medium of claim 23, wherein calculating a stroke risk score of the patient based on the extracted LA and LAA measurements and the computed derived metrics for the LA and LAA of the patient using a trained machine learning based classifier comprises:
calculating the stroke risk score of the patient based on the extracted LA and LAA measurements and the computed derived metrics for the LA and LAA of the patient using a trained deep neural network.
