# US 2025/0143809 A1 · Port placement recommendation in a surgical robotic system

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

- Number: US 2025/0143809 A1
- Document ID: US20250143809A1
- Status: Published application
- Kind: A1
- Application number: 18/086,306
- Filed: 2022-12-21
- Published: 2025-05-08
- Earliest claimed: 2022-12-21
- Applicants: Verb Surgical Inc.
- Inventors: Suryansh Saxena; Shaun Schaeffer; Pranathi Chunduru; Rohit Shinde; Isaac Isukapati; Robert Jablonowski; Yusi Ou; Narendran Narasimhan
- Web page: https://patentgrep.com/patent/US20250143809A1

## CPC

- A61B 34/10: Computer-aided planning, simulation or modelling of surgical operations
- A61B 34/30: Surgical robots
- G06N 3/08: Learning methods
- G06N 20/00: Machine learning
- G16H 10/60: for patient-specific data, e.g. for electronic patient records
- A61B 2034/105: {Modelling of the patient, e.g. for ligaments or bones}
- A61B 2034/107: {Visualisation of planned trajectories or target regions}
- A61B 2034/2051: {Electromagnetic tracking systems}
- A61B 2034/306: {Wrists with multiple vertebrae}
- 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

For a surgical robotic system, a machine-learned model is used to determine port placement. For example, a machine-learned model indicates internal regions based on input of external measurements on a patient. An overlap of an inverse-kinematics-based operation region of the surgical robotic system and the internal regions of the patient is optimized based on port placement. In an alternative or additional approach, information about the surgeon (e.g., handedness) is used with the machine-learned model to determine port placement.

## Claims

### Claim 1

A method for port placement recommendation for a surgical robotic system, the method comprising:
inputting a plurality of external patient measurements of a patient to a machine-learned model;
in response to the inputting, outputting by the machine-learned model one or more internal volumes of the patient;
optimizing overlap of an operating region of the surgical robotic system with the one or more internal volumes based on the port placement; and
displaying an indication of the port placement from the optimized overlap.

### Claim 2 (depends on 1)

The method of claim 1 wherein inputting comprises inputting the external patient measurements as height, weight, gender, body mass index, abdominal width, and pelvic location.

### Claim 3 (depends on 1)

The method of claim 1 wherein the machine-learned model comprises a regression trained model, and wherein outputting comprises outputting by the regression trained model in response to the inputting of the external patient measurements.

### Claim 4 (depends on 1)

The method of claim 1 wherein the machine-learned model comprises a multi-layer perceptron neural network, and wherein outputting comprises outputting by the multi-layer perceptron neural network in response to the inputting of the external patient measurements.

### Claim 5 (depends on 1)

The method of claim 1 wherein outputting the one or more internal volumes comprises outputting a centroid and radius for each of the one or more internal volumes.

### Claim 6 (depends on 1)

The method of claim 1 wherein optimizing comprises identifying the operating region of the surgical robotic system with inverse kinematics.

### Claim 7 (depends on 1)

The method of claim 1 wherein optimizing comprises identifying a part of the one or more internal volumes outside of the operating region for a port location for each of a plurality of arm of the surgical robotic system, identifying the arm of the surgical robotic system associated with a larger part, and changing the port location.

### Claim 8 (depends on 1)

The method of claim 1 wherein displaying comprises displaying the indication as part of a pre-operative plan.

### Claim 9 (depends on 1)

The method of claim 1 wherein inputting further comprises inputting a profile of a surgeon to the machine-learned model, and wherein outputting comprises outputting the one or more internal volumes in response to the inputting of the profile and the external patient measurements, the one or more internal volumes accounting for the profile of the surgeon.

### Claim 10

A method for port placement recommendation for a surgical robotic system, the method comprising:
inputting a profile of a surgeon to a machine-learned model;
in response to the inputting, outputting by the machine-learned model one or more internal volumes of a patient, the one or more internal volumes accounting for the profile of the surgeon; and
displaying an indication of port placement based on the one or more internal volumes.

### Claim 11 (depends on 10)

The method of claim 10 wherein outputting comprises outputting the internal volumes as regions for surgical interaction based on a characteristic of the surgeon reflected in the profile.

### Claim 12 (depends on 11)

The method of claim 11 wherein the characteristic is handedness of the surgeon or surgical trajectory used by the surgeon, and wherein outputting comprises outputting the internal volumes based on the handedness or the surgical trajectory.

### Claim 13 (depends on 11)

The method of claim 11 wherein inputting further comprises inputting external measurements of the patient to the machine-learned model, and wherein outputting comprises outputting the one or more internal volumes based on the external measurements of the patient.

### Claim 14 (depends on 13)

The method of claim 13 further comprising optimizing overlap of an operating region of the surgical robotic system with the one or more internal volumes based on the port placement, and
wherein displaying comprises displaying the indication of the port placement from the optimized overlap.

### Claim 15

A surgical robotic system for port placement recommendation, the surgical robotic system comprising:
a robotic arm configured to hold and operate a surgical tool; and
a processor configured to determine a location of a port for the surgical tool to enter a patient, the location determined from an output of artificial intelligence generated in response to input of patient measurements and surgeon information.

### Claim 16 (depends on 15)

The surgical robotic system of claim 15 wherein the output of the artificial intelligence is one or more internal regions of the patient, the one or more internal regions being regions for interaction of the surgical tool with the patient, and wherein the processor is configured to optimize the location of the port based on overlap of the one or more internal regions and an operating region accessible by the surgical tool using the robotic arm, the operating region based on inverse kinematics.

### Claim 17 (depends on 16)

The surgical robotic system of claim 16 wherein the surgeon information comprises a handedness of a surgeon controlling the robotic arm, the one or more internal regions being positioned based on the handedness.

### Claim 18 (depends on 16)

The surgical robotic system of claim 16 wherein the surgeon information comprises a trajectory of a surgeon controlling the robotic arm, the trajectory being a sequence or route to be used by the surgeon during operation on the patient with the surgical tool, the one or more internal regions being positioned based on the trajectory.

### Claim 19 (depends on 15)

The surgical robotic system of claim 15 wherein the patient measurements comprise external measurements of the patient.

### Claim 20 (depends on 15)

The surgical robotic system of claim 15 wherein the artificial intelligence comprises a machine-learned regression model or a machine-learned neural network.
