# US 12,758,252 B2 · Systems and methods for automatic determination of needle guides for vascular access

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

- Number: US 12,758,252 B2
- Document ID: US12758252B2
- Status: Granted
- Kind: B2
- Application number: 17/859,980
- Filed: 2022-07-07
- Published: 2024-01-11
- Granted: 2026-10-13
- Earliest claimed: 2022-07-07
- Assignees: Bard Access Systems, Inc.
- Applicants: Bard Access Systems, Inc.
- Inventors: Steffan Sowards; Anthony K. Misener; William Robert McLaughlin
- Web page: https://patentgrep.com/patent/US12758252B2

## CPC

- A61B 17/3403: {Needle locating or guiding means}
- A61B 8/085: {for locating body or organic structures, e.g. tumours, calculi, blood vessels, nodules}
- A61B 8/0891: {for diagnosis of blood vessels}
- A61B 8/463: {characterised by displaying multiple images or images and diagnostic data on one display}
- A61B 8/488: {involving Doppler signals}
- G06N 20/00: Machine learning
- G16H 30/20: for handling medical images, e.g. DICOM, HL7 or PACS
- A61B 2017/3405: {using mechanical guide means}
- A61B 2017/3413: {guided by ultrasound}
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)
- 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

Disclosed are systems and methods for automatically determining needle guides for establishing vascular access. For example, a system can include an ultrasound probe, a console operably coupled to the ultrasound probe, and a display screen integrated into the console. The console can include one or more processors and memory including instructions configured to instantiate one or more processes when executed by the one-or-more processors for automatic determination of a needle guide in accordance with ultrasound-imaging data, historical data, or a combination thereof. The automatic determination of such a needle guide can use logic, algorithms, machine learning, artificial intelligence, or a combination thereof. The display screen can be configured to display an ultrasound image including one or more blood vessels below a skin surface of a patient as well as the needle guide resulting from the automatic determination for establishing vascular access to the one-or-more blood vessels in the ultrasound image.

## Claims

### Claim 1

A system configured for automatic determination of a needle guide for establishing vascular access, comprising:
an ultrasound probe;
a console operably coupled to the ultrasound probe, the console including:
one or more processors;
a memory including instructions configured to instantiate one or more processes when executed by the one or more processors for:
the automatic determination of the needle guide in accordance with ultrasound-imaging data and historical data including data from previous procedures regarding whether a previous needle guide was successful for establishing vascular access in a patient, the automatic determination of the needle guide using at least a machine-learning model trained with the historical data;
automatic selection of a blood vessel of one or more blood vessels below a skin surface of the patient for establishing vascular access in accordance with the ultrasound-imaging data and the historical data, the automatic selection of the blood vessel using at least the machine-learning model trained with the historical data; and
automatic determination of a vascular access device (“VAD”) from an inventory of available VADs in accordance with the ultrasound-imaging data, the automatic determination of the VAD using at least the machine-learning model trained with the historical data in view of VAD occupancy of the blood vessel or VAD purchase length of the blood vessel for each VAD of the inventory of available VADs; and
a display screen optionally integrated into the console, the display screen configured to display: an ultrasound image including the one or more blood vessels below the skin surface of the patient; and
the needle guide resulting from the automatic determination of the needle guide for establishing vascular access to the one or more blood vessels in the ultrasound image.

### Claim 2 (depends on 1)

The system of claim 1, wherein the machine-learning model trained with the historical data performs image recognition using the ultrasound-imaging data for the automatic selection of the blood vessel.

### Claim 3 (depends on 2)

The system of claim 2, wherein the automatic selection of the blood vessel is optimized within an image buffer or a window via one or more blood vessel-selection algorithms.

### Claim 4 (depends on 1)

The system of claim 1, wherein the machine-learning model trained with the historical data analyzes Doppler ultrasound-imaging data when available for the automatic selection of the blood vessel.

### Claim 5 (depends on 1)

The system of claim 1, wherein the automatic determination of the needle guide is further in accordance with a location of the blood vessel resulting from the automatic selection of the blood vessel.

### Claim 6 (depends on 1)

The system of claim 1, wherein the needle guide resulting from the automatic determination of the needle guide is further in accordance with blood-vessel size of the blood vessel resulting from the automatic selection of the blood vessel.

### Claim 7 (depends on 1)

The system of claim 1, wherein the needle guide resulting from the automatic determination of the needle guide is from a group of possible needle guides that vary by angle of approach, depth at image intersection, compatible needle sizes, or a combination thereof.

### Claim 8 (depends on 7)

The system of claim 7, wherein the needle guide resulting from the automatic determination of the needle guide is further in accordance with trigonometric calculations resulting from a trigonometric algorithm of one or more blood vessel-selection algorithms.

### Claim 9 (depends on 1)

The system of claim 1, wherein the historical data includes clinician feedback entered into the console on whether the needle guide resulting from the automatic determination of the needle guide was successful in establishing vascular access.

### Claim 10 (depends on 1)

The system of claim 1, wherein the machine-learning model is trained to learn from the historical data in accordance with supervised learning.

### Claim 11 (depends on 1)

The system of claim 1, wherein the machine-learning model is trained to learn from the historical data in accordance with semi-supervised learning.

### Claim 12 (depends on 1)

The system of claim 1, wherein the machine-learning model is trained to learn from the historical data in accordance with unsupervised learning.

### Claim 13

A method of a system for automatic determination of a needle guide for establishing vascular access, comprising:
instantiating one or more processes by executing instructions therefor stored in memory of a console of the system by one or more processors of the console;
automatically determining of the needle guide in accordance with ultrasound-imaging data gathered by an ultrasound probe operably coupled to the console and historical data including data from previous procedures regarding whether a previous needle guide was successful for establishing vascular access in a patient, the automatic determining of the needle guide using at least a machine-learning model trained with the historical data;
automatically selecting a blood vessel of one-or-more blood vessels below a skin surface of the patient for establishing vascular access in accordance with the ultrasound-imaging data and the historical data, the automatic selecting of the blood vessel using at least the machine-learning model trained with the historical data;
automatically determining a vascular access device (“VAD”) from an inventory of available VADs in accordance with the ultrasound-imaging data, the automatic determination of the VAD using at least the machine-learning model trained with the historical data in view of VAD occupancy of the blood vessel or VAD purchase length of the blood vessel for each VAD of the inventory of available VADs; and
displaying on a display screen optionally integrated into the console an ultrasound image including the one or more blood vessels below the skin surface of the patient and the needle guide resulting from the automatic determination of the needle guide for establishing vascular access to the one-or-more blood vessels in the ultrasound image.

### Claim 14 (depends on 13)

The method of claim 13, further comprising: performing image recognition with the machine learning model trained with the historical data using the ultrasound-imaging data for the automatic selection of the blood vessel.

### Claim 15 (depends on 14)

The method of claim 14, further comprising: optimizing the automatic selection of the blood vessel within an image buffer or window via one or more blood vessel-selection algorithms.

### Claim 16 (depends on 13)

The method of claim 13, further comprising: analyzing Doppler ultrasound-imaging data with the machine learning model trained with the historical data for the automatic selection of the blood vessel.

### Claim 17 (depends on 13)

The method of claim 13, wherein the automatic determination of the needle guide is further in accordance with a location of the blood vessel resulting from the automatic selection of the blood vessel.

### Claim 18 (depends on 13)

The method of claim 13, wherein the needle guide resulting from the automatic determination of the needle guide is further in accordance with blood-vessel size of the blood vessel resulting from the automatic selection of the blood vessel.

### Claim 19 (depends on 13)

The method of claim 13, wherein the needle guide resulting from the automatic determination of the needle guide is from a group of possible needle guides that vary by angle of approach, depth at image intersection, compatible needle sizes, or a combination thereof.

### Claim 20 (depends on 19)

The method of claim 19, wherein the needle guide resulting from the automatic determination of the needle guide is further in accordance with trigonometric calculations resulting from a trigonometric algorithm of one or more blood vessel selection algorithms.

### Claim 21 (depends on 13)

The method of claim 13, wherein the historical data includes clinician feedback entered into the console on whether the needle guide resulting from the automatic determination of the needle guide was successful in establishing vascular access.