# US 12,008,742 B2 · Method and system for computer-aided aneurysm triage

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

- Number: US 12,008,742 B2
- Document ID: US12008742B2
- Status: Granted
- Kind: B2
- Application number: 17/716,258
- Filed: 2022-04-08
- Published: 2022-07-21
- Granted: 2024-06-11
- Earliest claimed: 2020-07-24
- Assignees: Viz.ai Inc.
- Applicants: Viz.ai Inc.
- Inventors: Gil Levi; Yoni Donner; David Golan; Christopher Mansi
- Web page: https://patentgrep.com/patent/US12008742B2

## CPC

- G06T 7/00: Image analysis
- G06T 7/0012: {Biomedical image inspection}
- G06N 3/045: Combinations of networks
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/084: Backpropagation, e.g. using gradient descent
- G06N 3/09: Supervised learning
- G06T 3/00: Geometric image transformations in the plane of the image
- G06T 3/14: Transformations for image registration, e.g. adjusting or mapping for alignment of images
- G06T 7/10: Segmentation; Edge detection (motion-based segmentation G06T7/215)
- G16H 10/20: for electronic clinical trials or questionnaires
- G16H 20/40: relating to mechanical, radiation or invasive therapies, e.g. surgery, laser therapy, dialysis or acupuncture
- G16H 30/20: for handling medical images, e.g. DICOM, HL7 or PACS
- G16H 30/40: for processing medical images, e.g. editing
- 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 50/70: for mining of medical data, e.g. analysing previous cases of other patients
- G06N 3/044: Recurrent networks, e.g. Hopfield networks
- G06N 3/047: Probabilistic or stochastic networks
- G06N 3/088: Non-supervised learning, e.g. competitive learning
- G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
- G06N 5/025: Extracting rules from data
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- G06N 20/10: using kernel methods, e.g. support vector machines [SVM]
- G06N 20/20: Ensemble learning
- G06T 2207/10081: Computed x-ray tomography [CT]
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T 2207/20128: Atlas-based segmentation
- G06T 2207/30016: Brain
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA

## Abstract

A system for computer-aided triage includes and/or interfaces with a computing system. A method for computer-aided triage includes receiving a data packet including a set of images; and processing the set of images to determine a suspected condition and/or associated features. Additionally or alternatively, the method can include any or all of: preprocessing the set of images; triggering an action based on the suspected condition and/or associated features; determining a recipient based on the suspected condition; preparing a data packet for transfer; transmitting information to a device associated with the recipient; receiving an input from the recipient and triggering an action based on the input; aggregating data; and/or any other suitable processes.

## Claims

### Claim 1

A method for computer-aided detection and decision-making associated with a suspected pathology, the method comprising:
receiving a set of images associated with a patient;
processing the set of images with a set of trained models to automatically identify the suspected pathology;
in response to automatically identifying the suspected pathology, triggering an action at a mobile user device associated with a specialist; and
monitoring for an input from the specialist at the mobile user device, wherein in an event that the input is not received within a predetermined time threshold, triggering a second action at a second mobile user device associated with a second specialist.

### Claim 2 (depends on 1)

The method of claim 1, wherein the suspected pathology is a suspected aneurysm, and wherein processing the set of images with the set of trained models comprises a set of multiple segmentation processes.

### Claim 3 (depends on 2)

The method of claim 2, wherein the set of multiple segmentation processes comprises:
a first segmentation process performed with a first subset of the set of trained models; and
a second segmentation process performed with a second subset of the set of trained models.

### Claim 4 (depends on 3)

The method of claim 3, wherein:
the first segmentation process produces a first set of probability scores; and
the second segmentation process produces a second set of probability scores.

### Claim 5 (depends on 4)

The method of claim 4, further comprising:
aggregating the first and second sets of probability scores to determine an aggregated set of probability scores;
comparing the aggregated set of probability scores with a predetermined set of thresholds; and
automatically identifying the suspected aneurysm based on the comparison.

### Claim 6 (depends on 1)

The method of claim 1, wherein triggering the action at the mobile user device comprises automatically determining and transmitting a notification to an application executing on the mobile user device.

### Claim 7 (depends on 6)

The method of claim 6, wherein triggering the second action comprises transmitting the notification to the second mobile user device.

### Claim 8 (depends on 1)

The method of claim 1, wherein each of the first and second actions further comprises transmitting a second set of images to the first and second mobile user devices, the second set of images determined based on the first set of images.

### Claim 9 (depends on 8)

The method of claim 8, wherein the second set of images is a compressed version of the first set of images.

### Claim 10 (depends on 8)

The method of claim 8, wherein the second set of images is a subset of the first set of images.

### Claim 11 (depends on 8)

The method of claim 8, wherein monitoring for the input from the specialist further comprises, in response to receiving the input, the method further comprises initiating a transfer of the patient.

### Claim 12 (depends on 11)

The method of claim 11, wherein the set of images is taken at an imaging modality located at a first point of care, wherein the specialist is associated with a second point of care, and wherein the transfer is from the first point of care to the second point of care.

### Claim 13 (depends on 12)

The method of claim 12, wherein the method further comprises, in response to receiving the input, assigning treatment of the patient to the specialist.

### Claim 14

A system for computer-aided detection and decision-making associated with a suspected pathology, the system comprising:
a computing subsystem, wherein the computing subsystem:
receives a set of images associated with a patient;
processes the set of images with a set of trained models to automatically identify the suspected pathology;
a first application executing on a first mobile user device associated with a first specialist, wherein the first application:
in response to identification of the suspected pathology, triggers an action at the first mobile user device;
monitors for an input from the first specialist; and
a second application associated with a second specialist, wherein the second application:
in an event that the input is not received within a predetermined time threshold, triggers a second action.

### Claim 15 (depends on 14)

The system of claim 14, wherein the set of trained models comprises:
a first set of neural networks configured to perform a first segmentation process; and
a second set of neural networks configured to perform a second segmentation process.

### Claim 16 (depends on 15)

The system of claim 15, wherein the first segmentation process is a single stage segmentation process and wherein the second segmentation process is a multi-stage segmentation process.

### Claim 17 (depends on 16)

The system of claim 16, further comprising processing the set of images with a third set of neural networks to determine a predetermined set of anatomical regions, wherein the first segmentation process is performed based on the predetermined set of anatomical regions.

### Claim 18 (depends on 14)

The system of claim 14, wherein the second application is executing on a second mobile user device associated with the second specialist, wherein the second action is triggered at the second mobile user device.

### Claim 19 (depends on 14)

The system of claim 14, wherein the first application, in response to receiving the input, automatically initiates a transfer of the patient from a first point of care to a second point of care located remote from the first point of care.

### Claim 20 (depends on 14)

The system of claim 14, wherein each of the first and second actions comprises the transmission of a notification and a second set of images, the second set of images determined based on the first set of images, to at least one of the first mobile user device and the second mobile user device.