# US 2026/0060642 A1 · Guiding instrument insertion

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

- Number: US 2026/0060642 A1
- Document ID: US20260060642A1
- Status: Published application
- Kind: A1
- Application number: 19/381,954
- Filed: 2025-11-06
- Published: 2026-03-05
- Earliest claimed: 2021-04-23
- Assignees: Fujifilm Sonosite, Inc.
- Applicants: Fujifilm Sonosite, Inc.
- Inventors: Davinder S. DHATT; Christopher Aleksandr WHITE; Adam Benjamin PELY; Thomas Michael DUFFY; Paul Tomotaro DANSET; Diku Pranav MANDAVIA
- Web page: https://patentgrep.com/patent/US20260060642A1

## CPC

- A61B 8/0841: {for locating instruments}
- 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 8/12: in body cavities or body tracts, e.g. by using catheters
- A61B 8/4427: {Device being portable or laptop-like}
- A61B 8/445: {Details of catheter construction}
- A61B 8/4472: {Wireless probes}
- A61B 8/461: {Displaying means of special interest}
- A61B 8/467: {characterised by special input means}
- A61B 8/5207: {involving processing of raw data to produce diagnostic data, e.g. for generating an image}
- A61B 8/5223: {for extracting a diagnostic or physiological parameter from medical diagnostic data (for algorithms to analyse biomedical images G06T7/0012)}
- G06N 3/02: Neural networks
- G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/09: Supervised learning
- G06N 3/045: Combinations of networks
- G06N 3/08: Learning methods
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A method and apparatus for identifying blood vessels in ultrasound images and displaying blood vessels in ultrasound images are described. In some embodiments, the method is implemented by a computing device and includes receiving an ultrasound image that includes one or more blood vessels, and determining, with a neural network implemented at least partially in hardware of the computing device, diameters of the one or more blood vessels in the ultrasound image. The method includes receiving a user selection of an instrument size, and indicating, in the ultrasound image, at least one blood vessel of the one or more blood vessels based on the instrument size and the diameters of the one or more blood vessels.

## Claims

### Claim 1

An ultrasound system for identifying blood vessels, the ultrasound system comprising:
an image module to generate one or more ultrasound images based on ultrasound echo signals;
a neural network module to:
identify the blood vessels in the one or more ultrasound images; and
assign one of a vein classification or an artery classification to each blood vessel of the blood vessels; and
a processor to:
determine, for said each blood vessel, a confidence level for the vein classification or the artery classification; and
cause display in the one or more ultrasound images of an outline of at least one blood vessel of the blood vessels with an opacity based on the confidence level determined for the at least one blood vessel.

### Claim 2 (depends on 1)

The ultrasound system as described in claim 1, wherein:
the neural network module is implemented to determine diameters and depths of the blood vessels; and
the processor is implemented to:
determine, for a blood vessel of the blood vessels, a threshold insertion length of a catheter to be inserted into the blood vessel based on a diameter of the blood vessel determined by the neural network module, the threshold insertion length indicating an amount of the catheter inside the blood vessel;
determine a length of the catheter based on the threshold insertion length and a depth of the blood vessel determined by the neural network module; and
cause display in the one or more ultrasound images of an indication of the length of the catheter to be inserted into the blood vessel.

### Claim 3 (depends on 2)

The ultrasound system as described in claim 2, wherein the processor is implemented to:
determine an insertion angle for the catheter; and
determine the length of the catheter based on the insertion angle.

### Claim 4 (depends on 3)

The ultrasound system as described in claim 3, further comprising a transducer to generate ultrasound signals and receive the ultrasound echo signals based on the ultrasound signals;
wherein the processor is implemented to:
determine an insertion point for a needle of the catheter based on the depth of the blood vessel and the insertion angle for the catheter; and
indicate the insertion point as a distance from the transducer.

### Claim 5 (depends on 4)

The ultrasound system as described in claim 4, wherein the processor is implemented to determine the distance from a face of the transducer.

### Claim 6 (depends on 3)

The ultrasound system as described in claim 3, wherein the processor is implemented to determine the insertion angle for the catheter not based on the diameter or the depth of the blood vessel.

### Claim 7 (depends on 1)

The ultrasound system as described in claim 1, wherein the processor is further to:
determine a distance of at least one blood vessel to an edge of an ultrasound image, and
display the outline with the opacity based on the distance.

### Claim 8

A method implemented by a computing device to identify blood vessels, the method comprising:
generating, using an image module coupled to the computing device, one or more ultrasound images based on ultrasound echo signals;
identifying, using a neural network implemented at least partially in hardware of the computing device, the blood vessels in the one or more ultrasound images;
assigning, using the neural network, one of a vein classification or an artery classification to each blood vessel of the blood vessels;
determining for said each blood vessel, a confidence level for the vein classification or the artery classification; and
causing display in the one or more ultrasound images of an outline of at least one blood vessel of the blood vessels with an opacity based on the confidence level determined for the at least one blood vessel.

### Claim 9 (depends on 8)

The method as described in claim 8, further comprising:
determining diameters and depths of the blood vessels; and
determining for a blood vessel of the blood vessels, a threshold insertion length of a catheter to be inserted into the blood vessel based on a diameter of the blood vessel determined by the neural network, the threshold insertion length indicating an amount of the catheter inside the blood vessel;
determining a length of the catheter based on the threshold insertion length and a depth of the blood vessel determined by the neural network; and
causing display in the one or more ultrasound images of an indication of the length of the catheter to be inserted into the blood vessel.

### Claim 10 (depends on 9)

The method as described in claim 9, further comprising:
determining an insertion angle for the catheter; and
determining the length of the catheter based on the insertion angle.

### Claim 11 (depends on 10)

The method as described in claim 10, further comprising:
generating, using a transducer coupled to the computing device, ultrasound signals;
receiving the ultrasound echo signals based on the ultrasound signals;
determining an insertion point for a needle of the catheter based on the depth of the blood vessel and the insertion angle for the catheter; and
indicating the insertion point as a distance from the transducer.

### Claim 12 (depends on 11)

The method as described in claim 11, further comprising:
determining the distance from a face of the transducer.

### Claim 13 (depends on 10)

The method as described in claim 10, further comprising:
determining the insertion angle for the catheter not based on the diameter or the depth of the blood vessel.

### Claim 14 (depends on 8)

The method as described in claim 8, further comprising:
determining a distance of at least one blood vessel to an edge of an ultrasound image, and displaying the outline with the opacity based on the distance.

### Claim 15

A non-transitory machine-readable medium storing executable instructions to cause a computing device to perform a method to identify blood vessels, comprising:
generating, using an image module coupled to the computing device, one or more ultrasound images based on ultrasound echo signals;
identifying, using a neural network implemented at least partially in hardware of the computing device, the blood vessels in the one or more ultrasound images;
assigning, using the neural network, one of a vein classification or an artery classification to each blood vessel of the blood vessels;
determining for said each blood vessel, a confidence level for the vein classification or the artery classification; and
causing display in the one or more ultrasound images of an outline of at least one blood vessel of the blood vessels with an opacity based on the confidence level determined for the at least one blood vessel.

### Claim 16 (depends on 15)

The non-transitory machine-readable medium as described in claim 15, wherein the method further comprises:
determining diameters and depths of the blood vessels; and
determining for a blood vessel of the blood vessels, a threshold insertion length of a catheter to be inserted into the blood vessel based on a diameter of the blood vessel determined by the neural network, the threshold insertion length indicating an amount of the catheter inside the blood vessel;
determining a length of the catheter based on the threshold insertion length and a depth of the blood vessel determined by the neural network; and
causing display in the one or more ultrasound images of an indication of the length of the catheter to be inserted into the blood vessel.

### Claim 17 (depends on 16)

The non-transitory machine-readable medium as described in claim 16, wherein the method further comprises:
determining an insertion angle for the catheter; and
determining the length of the catheter based on the insertion angle.

### Claim 18 (depends on 17)

The non-transitory machine-readable medium as described in claim 17, wherein the method further comprises:
generating, using a transducer coupled to the computing device, ultrasound signals;
receiving the ultrasound echo signals based on the ultrasound signals;
determining an insertion point for a needle of the catheter based on the depth of the blood vessel and the insertion angle for the catheter; and
indicating the insertion point as a distance from the transducer.

### Claim 19 (depends on 18)

The non-transitory machine-readable medium as described in claim 18, wherein the method further comprises:
determining the insertion angle for the catheter not based on the diameter or the depth of the blood vessel.

### Claim 20 (depends on 15)

The non-transitory machine-readable medium as described in claim 15, further comprising:
determining a distance of at least one blood vessel to an edge of an ultrasound image, and
displaying the outline with the opacity based on the distance.
