# US 12,758,353 B2 · Fiducial marker set, a method of determining a position of the same and a control system > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,758,353 B2 - Document ID: US12758353B2 - Status: Granted - Kind: B2 - Application number: 18/574,669 - Filed: 2021-06-28 - Published: 2024-09-26 - Granted: 2026-10-13 - Earliest claimed: 2021-06-28 - Assignees: NDR Medical Technology Private Limited - Applicants: NDR Medical Technology Private Limited - Inventors: Ka Wei Ng; Siang Huei Leong; Jin Quan Goh - Web page: https://patentgrep.com/patent/US12758353B2 ## CPC - A61B 90/39: {Markers, e.g. radio-opaque or breast lesions markers} - A61B 34/32: operating autonomously - A61B 2034/2065: {Tracking using image or pattern recognition} - A61B 2090/3966: {Radiopaque markers visible in an X-ray image} - A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D) ## Abstract A method of determining a position of a fiducial marker set including a plurality of fiducial markers is disclosed. The method includes a step of receiving image slices captured by a 3-dimensional (3D) imaging device. The image slices are processed to identify positions of centre points of the respective fiducial markers. Based on the identified positions of the centre points, a virtual Cartesian geometry associated with the fiducial marker set is identified. The virtual Cartesian geometry is represented by a plurality of virtual Cartesian coordinate axes that meet at a virtual origin. A fiducial marker set and a control system are also disclosed. ## Claims ### Claim 1 A control system comprising: a processor communicatively coupled with a robot and a 3D imaging device, the 3D imaging device configured to capture image slices within an imaging space, wherein the imaging space comprises a 3D space with a first fixed origin; a robot comprising a manipulator including an end effector, wherein the robot is configured to move an elongated tool attached to the end effector within a robot space for aligning the elongated tool with an occluded target, and wherein the robot space comprises a 3-dimensional (3D) space with a second fixed origin; and a fiducial marker set mounted on the manipulator of the robot, the fiducial marker set comprising a plurality of fiducial markers, wherein each of the plurality of fiducial markers has a spherical shape with a centre point and is made of a radiopaque material; wherein the processor is configured to: process image slices captured by the 3D imaging device to identify positions of the centre points of the respective fiducial markers; based on the identified positions of the centre points, identify a virtual Cartesian geometry associated with the fiducial marker set, wherein the virtual Cartesian geometry is represented by a plurality of virtual Cartesian coordinate axes that meet at a virtual origin; based on the virtual Cartesian geometry associated with the fiducial marker set, calibrate the robot by integrating the robot space with the imaging space; based on the calibration of the robot, process a 3D image of a body containing the target captured by the 3D imaging device to obtain location data of the target in the integrated space; and based on the location data of the target in the integrated space, automatically control the robot to align a longitudinal axis of the elongated tool with the target. ### Claim 2 (depends on 1) The control system as claimed in claim 1, wherein the processor is configured to: process the image slices of the fiducial marker set to detect 2-dimensional (2D) circles on the image slices; and calculate centre positions of the 2D circles on the image slices to identify positions of the centre points of the respective fiducial markers. ### Claim 3 (depends on 2) The control system as claimed in claim 2, wherein the processor is configured to: measure sizes of the plurality of fiducial markers; compare the measured sizes of the plurality of fiducial markers and stored actual sizes of the plurality of fiducial markers; and based on the comparison, validate the identified positions of centre points. ### Claim 4 (depends on 1) The control system as claimed in claim 1, wherein the processor is configured to: process the image slices of the fiducial marker set to form a 3D image by combining the image slices from the 3D imaging device; detect 3D spheres on the 3D image; and calculate centre positions of the 3D spheres on the 3D image to identify positions of the centre points of the respective fiducial markers. ### Claim 5 (depends on 1) The control system as claimed in claim 1, wherein the processor is configured to: based on the identified positions of centre points, measure distances between the centre points of the plurality of fiducial markers; and based on the measured distances, identify the virtual origin and virtual Cartesian coordinate axes of the virtual Cartesian geometry. ### Claim 6 (depends on 5) The control system as claimed in claim 5, wherein the processor is configured to: compare the measured distances between the identified positions of the centre points with stored actual distances between the centre points of the plurality of fiducial markers; and based on the comparison, validate the identified positions of the centre points. ### Claim 7 (depends on 1) The control system as claimed in claim 1, wherein the processor is configured to: based on virtual origin of the virtual Cartesian geometry, calculate a first directional vector between the first fixed origin and the virtual origin; combine the first directional vector and a second directional vector between the virtual origin and the second fixed origin of the robot to calculate a resultant vector between the first fixed origin of the 3D imaging device and the second fixed origin of the robot; and based on the calculated resultant vector, determine a common origin to integrate the robot space and the imaging space. ### Claim 8 (depends on 1) The control system as claimed in claim 1, wherein the processor is configured to: process the 3D image of the body to extract position data of the target in the imaging space; and based on the calibration of the robot, convert the position data of the target in the imaging space into the location data of the target in the integrated space.