Granted Patent B2

US 12,245,823 · App. 18/163,686 · Granted Mar 11, 2025

Inventors: Yash Evalekar (Princeton, NJ); Yuanfeng Mao (Princeton, NJ); Guo-Qing Wei (Plainsboro, NJ); Li Fan (Belle Mead, NJ); Xiaolan Zeng (Princeton, NJ); Jianzhong Qian (Princeton Junction, NJ)

Assignee: EDDA TECHNOLOGY, INC.

A61B34/10A61B17/3403A61B17/3423A61B17/3476B25J9/1605A61B2017/3409A61B2034/104A61B2034/105A61B2034/107G05B2219/45117

Abstract

Claims (84)

1. A method implemented on at least one processor, a memory, and a communication platform, comprising:

receiving input related to a surgical operation, including a three-dimensional (3D) model of an organ, wherein the 3D model includes a list of cut points on the organ forming a planned surgical trajectory, wherein a surgical instrument controlled by a robot is used to reach each of the cut points to carry out the surgical operation;

identifying an insertion location on skin of a patient for inserting the surgical instrument, wherein the surgical instrument inserted at the insertion location is controlled by the robot to reach each of the list of cut points;

identifying, with respect to the insertion location, a robot base location, where the robot is to be stationed and operates to control movement of the surgical instrument to reach each of the list of cut points; and

generating control signals for configuring a surgical setting for the surgical operation based on the insertion location for the surgical instrument and the base location for the robot.

2. The method of claim 1 , wherein the step of identifying an insertion location comprises:

determining a plurality of candidate insertion locations for inserting the surgical instrument;

determining performance evaluation parameters for each of the candidate insertion locations; and

selecting the insertion location from the candidate insertion locations based on the performance evaluation parameters for each of the candidate insertion locations.

3. The method of claim 2 , wherein the performance evaluation parameters for each of the candidate insertion locations include at least one of:

a first access map obtained by determining an area on the organ that the surgical instrument inserted from the candidate insertion location is able to reach;

a coverage indicating a portion of the list of cut points that that fall within the first access map;

a distance from the candidate insertion location to the surgery trajectory projected on the organ;

an angle between a surface norm associated with one cut point selected from the list of cut points and a line formed between the candidate insertion point and the cut point; and

an indication of any collision with other anatomical structure in reaching any of the cut points from the insertion location.

4. The method of claim 2 , wherein the step of selecting the insertion location is based on an insertion location optimization model obtained via machine learning based on training data collected from past historic surgery data.

5. The method of claim 1 , wherein the step of identifying the base location for the robot with respect to the insertion location comprises:

determining an operating space of the robot based on the optimal insertion location;

creating an operating space grid, according to a resolution, wherein each unit in the operating space grid corresponds to a candidate base location;

determining, for each candidate base location in the operating space grid, evaluation parameters; and

selecting the base location from the candidate base locations based on the evaluation parameters of each of the candidate base locations.

6. The method of claim 5 , wherein the evaluation parameters for each candidate base location include at least one of:

a second access map specifying an area on the organ that the robot stationed at the candidate base location is able to control the surgical instrument to reach;

a coverage indicating a portion of a first access map associated with the optimal insertion location that overlaps with the second access map;

a distance from the candidate base location to the optimal insertion location;

an angle between a surface norm at the optimal insertion location and a line formed between the robot stationed at the candidate base location and the optimal insertion location; and

a proximity to singularity of the robot determined based on kinematic parameter configurations needed for the robot to control the surgical instrument to reach the list of cut points.

7. The method of claim 5 , wherein the step of selecting the base location is based on a robot base location optimization model obtained via machine learning based on training data collected from past historic surgery data.

8. Machine readable and non-transitory medium having information recorded thereon, wherein the information, when read by the machine, causes the machine to perform the following steps:

receiving input related to a surgical operation, including a three-dimensional (3D) model of an organ, wherein the 3D model includes a list of cut points on the organ forming a planned surgical trajectory, wherein a surgical instrument controlled by a robot is used to reach each of the cut points to carry out the surgical operation;

identifying an insertion location on skin of a patient for inserting the surgical instrument, wherein the surgical instrument inserted at the insertion location is controlled by the robot to reach each of the list of cut points;

identifying, with respect to the insertion location, a robot base location, where the robot is to be stationed and operates to control movement of the surgical instrument to reach each of the list of cut points; and

generating control signals for configuring a surgical setting for the surgical operation based on the insertion location for the surgical instrument and the base location for the robot.

9. The medium of claim 8 , wherein the step of identifying an insertion location comprises:

determining a plurality of candidate insertion locations for inserting the surgical instrument;

determining performance evaluation parameters for each of the candidate insertion locations; and

selecting the insertion location from the candidate insertion locations based on the performance evaluation parameters for each of the candidate insertion locations.

10. The medium of claim 9 , wherein the performance evaluation parameters for each of the candidate insertion locations include at least one of:

a first access map obtained by determining an area on the organ that the surgical instrument inserted from the candidate insertion location is able to reach;

a coverage indicating a portion of the list of cut points that that fall within the first access map;

a distance from the candidate insertion location to the surgery trajectory projected on the organ;

an angle between a surface norm associated with one cut point selected from the list of cut points and a line formed between the candidate insertion point and the cut point; and

an indication of any collision with other anatomical structure in reaching any of the cut points from the insertion location.

11. The medium of claim 9 , wherein the step of selecting the insertion location is based on an insertion location optimization model obtained via machine learning based on training data collected from past historic surgery data.

12. The medium of claim 9 , wherein the step of identifying the base location for the robot with respect to the insertion location comprises:

determining an operating space of the robot based on the insertion location;

creating an operating space grid, according to a resolution, wherein each unit in the operating space grid corresponds to a candidate base location;

determining, for each candidate base location in the operating space grid, evaluation parameters; and

selecting the base location from the candidate base locations based on the evaluation parameters of each of the candidate base locations.

13. The medium of claim 12 , wherein the evaluation parameters for each candidate base location include at least one of:

a second access map specifying an area on the organ that the robot stationed at the candidate base location is able to control the surgical instrument to reach;

a coverage indicating a portion of a first access map associated with the optimal insertion location that overlaps with the second access map;

a distance from the candidate base location to the optimal insertion location;

an angle between a surface norm at the optimal insertion location and a line formed between the robot stationed at the candidate base location and the optimal insertion location; and

a proximity to singularity of the robot determined based on kinematic parameter configurations needed for the robot to control the surgical instrument to reach the list of cut points.

14. The medium of claim 12 , wherein the step of selecting the base location is based on a robot base location optimization model obtained via machine learning based on training data collected from past historic surgery data.

15. A system, comprising:

a sequential optimization framework implemented by a processor and configured for receiving input related to a surgical operation, including a three-dimensional (3D) model of an organ, wherein the 3D model includes a list of cut points on the organ forming a planned surgical trajectory, wherein a surgical instrument controlled by a robot is used to reach each of the cut points to carry out the surgical operation;

an insertion location optimizer implemented by a processor and configured for identifying an insertion location on skin of a patient for inserting the surgical instrument, wherein the surgical instrument inserted at the insertion location is controlled by the robot to reach each of the list of cut points;

a robot base location optimizer implemented by a processor and configured for identifying, with respect to the insertion location, a robot base location, where the robot is to be stationed and operates to control movement of the surgical instrument to reach each of the list of cut points; and

a surgery setting configuration unit implemented by a processor and configured for generating control signals for configuring a surgical setting for the surgical operation based on the insertion location for the surgical instrument and the base location for the robot.

16. The system of claim 15 , wherein the insertion location optimizer comprises:

a candidate insertion location generator implemented by a processor and configured for determining a plurality of candidate insertion locations for inserting the surgical instrument;

an evaluation parameter determiner implemented by a processor and configured for determining performance evaluation parameters for each of the candidate insertion locations; and

a location optimizer implemented by a processor and configured for selecting the insertion location from the candidate insertion locations based on the performance evaluation parameters for each of the candidate insertion locations.

17. The system of claim 16 , wherein the performance evaluation parameters for each of the candidate insertion locations include at least one of:

a first access map obtained by determining an area on the organ that the surgical instrument inserted from the candidate insertion location is able to reach;

a coverage indicating a portion of the list of cut points that that fall within the first access map;

a distance from the candidate insertion location to the surgery trajectory projected on the organ;

an angle between a surface norm associated with one cut point selected from the list of cut points and a line formed between the candidate insertion point and the cut point; and

an indication of any collision with other anatomical structure in reaching any of the cut points from the insertion location.

18. The system of claim 16 , wherein the location optimizer selects the insertion location is based on an insertion location optimization model obtained via machine learning based on training data collected from past historic surgery data.

19. The system of claim 15 , wherein the robot base location optimizer comprises:

a robot operating space determiner implemented by a processor and configured for determining an operating space of the robot based on the optimal insertion location;

an operating space grid generator implemented by a processor and configured for creating an operating space grid, according to a resolution, wherein each unit in the operating space grid corresponds to a candidate base location;

a grid based evaluation parameter generator implemented by a processor and configured for determining, for each candidate base location in the operating space grid, evaluation parameters; and

an optimal base location selector implemented by a processor and configured for selecting the base location from candidate base locations based on the evaluation parameters of each of the candidate base locations.

20. The system of claim 19 , wherein the evaluation parameters for each candidate base location include at least one of:

a second access map specifying an area on the organ that the robot stationed at the candidate base location is able to control the surgical instrument to reach;

a coverage indicating a portion of a first access map associated with the optimal insertion location that overlaps with the second access map;

a distance from the candidate base location to the optimal insertion location;

an angle between a surface norm at the optimal insertion location and a line formed between the robot stationed at the candidate base location and the optimal insertion location; and

a proximity to singularity of the robot determined based on kinematic parameter configurations needed for the robot to control the surgical instrument to reach the list of cut points.

21. The system of claim 19 , wherein the optimal base location selector selects the base location is based on a robot base location optimization model obtained via machine learning based on training data collected from past historic surgery data.

Assignments (1)

Continuity (1)

References Cited (39)