SYSTEM AND METHOD FOR WEIGHT-BASED ALIGNMENT OF POSITION SENSORS - Patent application

Abstract

Systems and methods are provided for weight-based alignment of position sensors. In one aspect, the system includes an instrument and a processor configured to provide a first set of commands for driving the instrument along a first branch of a lumen network, the first branch being off-path to a target in a model. The processor is also configured to track one or more sets of alignment parameters while driving the instrument along the first branch and determine that the set of alignment parameters meets an alignment criterion. The processor is further configured to determine an alignment between a position sensor coordinate system and a model coordinate system based on position data received from the set of position sensors while driving the instrument along the first branch and the second branch.

Description

[Technical field]

[0001] (CROSS REFERENCE TO RELATED APPLICATIONS) This application claims the benefit of U.S. Provisional Application No. 62 / 894,639, filed Aug. 30, 2019, which is incorporated by reference in its entirety.

[0002] FIELD OF THEINVENTION SUMMARY OF THE DISCLOSURE Systems and methods disclosed herein relate to systems and methods for alignment of a position sensor, and more particularly, to weighting the alignment of a position sensor coordinate system to another coordinate system. [Background technology]

[0003] Medical procedures such as endoscopy (e.g., bronchoscopy) may involve the insertion of medical implements into a patient's luminal network (e.g., airways) for diagnostic and / or therapeutic purposes. A surgical robotic system may be used to control the insertion and / or manipulation of the medical implements during the medical procedure. The surgical robotic system may comprise at least one robotic arm including a manipulator assembly that may be used to control the positioning of the medical implement before and during the medical procedure. The surgical robotic system may further comprise a position sensor configured to generate position data indicative of a position of a distal end of the medical implement relative to a position sensor coordinate system.

[0004] The surgical robotic system may further utilize a model of the patient's lumen network, which may be defined relative to the model coordinate system. The position sensor coordinate system may not be aligned to the model coordinate system, and thus the system may perform a process to achieve alignment between the position sensor coordinate system and the model coordinate system, thereby allowing the system to determine the position of the distal end of the medical instrument relative to the model using position data received from the position sensor. Summary of the Invention [Means for solving the problem]

[0005] The systems, methods, and devices of the present disclosure each have several innovative aspects, no single one of which is solely responsible for the desirable attributes disclosed herein.

[0006] In one aspect, a system is provided that includes an instrument having a set of one or more position sensors, the set of position sensors configured to generate position data indicative of a position of the set of position sensors within a position sensor coordinate system; a set of instrument manipulators configured to control movement of a distal end of the instrument; a set of processors; and at least one computer-readable memory in communication with the set of processors that stores a model of a patient's luminal network, the model including a target and a path to the target in the model coordinate system. The memory may further store computer executable instructions to cause the set of processors to provide a first set of commands to the set of instrument manipulators to drive the instrument along a first branch of the lumen network, the first branch being outside of a path to the target; tracking one or more sets of alignment parameters while driving the instrument along the first branch and determining that the set of alignment parameters meets an alignment criterion; providing a second set of commands to the set of instrument manipulators to return the instrument to the path and drive the instrument along a second branch, the second branch being part of the path to the target; and determining an alignment between the position sensor coordinate system and the model coordinate system based on position data received from the set of position sensors while driving the instrument along the first branch and the second branch.

[0007] In another aspect, a non-transitory computer readable storage medium that, when executed, causes at least one computing device to provide a first set of commands to a set of instrument manipulators to drive an instrument along a first branch of a lumen network, the instrument including one or more sets of position sensors, the set of position sensors configured to generate position data indicative of a position of the set of position sensors in a position sensor coordinate system, the set of instrument manipulators configured to control movement of a distal end of the instrument, a memory storing a model of the patient's lumen network, the model including a target and a path to the target in the model coordinate system, the first branch being outside of the path to the target. a set of one or more alignment parameters while driving the instrument along the first branch; determining that the set of alignment parameters meets an alignment criterion; providing a second set of commands to a set of instrument manipulators to return the instrument to the path and drive the instrument along a second branch, the second branch being part of a path to the target; and determining an alignment between the position sensor coordinate system and a model coordinate system based on position data received from a set of position sensors while driving the instrument along the first branch and the second branch.

[0008] In yet another aspect, a method of aligning one or more sets of position sensors includes providing a first set of commands to a set of instrument manipulators to drive an instrument along a first branch of a lumen network, the instrument including a set of position sensors, the set of position sensors configured to generate position data indicative of a position of the set of position sensors in a position sensor coordinate system, the set of instrument manipulators configured to control movement of a distal end of the instrument, a memory storing a model of the patient's lumen network, the model including a target and a path to the target in the model coordinate system, the first branch being positioned outside the path to the target. A method is provided that includes: providing, tracking a set of one or more alignment parameters while driving the instrument along a first branch, determining that the set of alignment parameters meet an alignment criterion, providing a second set of commands to a set of instrument manipulators to return the instrument to the path and drive the instrument along a second branch, the second branch being part of a path to a target, and determining an alignment between a position sensor coordinate system and a model coordinate system based on position data received from a set of position sensors while driving the instrument along the first branch and the second branch.

[0009] In yet another aspect, a system is provided that includes a set of one or more processors and at least one computer readable memory in communication with the set of processors and storing a model of a patient's luminal network, the model including a target in a model coordinate system and a path to the target, the memory providing instructions to the set of processors for displaying the luminal network via a display device, receiving an indication of a location of the target in the model coordinate system, and identifying a first branch and a second branch in the luminal network, the first branch being outside the path to the target and the second branch being outside the path to the target. The instrument further stores computer-executable instructions for: identifying a branch that is part of a path to the target; generating a set of instructions for driving the distal end of the instrument along the first branch, returning the branch from the first branch back onto the path, and driving along the second branch, where position data received from a set of one or more position sensors while driving the instrument in accordance with the instructions facilitates alignment between a position coordinate system of the position data and a model coordinate system; and determining an alignment criterion for one or more alignment parameters that are tracked while driving the instrument along the first branch.

[0010] In yet another aspect, a non-transitory computer readable storage medium provides instructions that, when executed, cause at least one computing device to display a lumen network via a display device, the lumen network being stored in the non-transitory computer readable storage medium, the model including a target and a path to the target in a model coordinate system; receiving an indication of a location of the target in the model coordinate system; and identifying a first branch and a second branch in the lumen network, the first branch being outside of the path to the target and the second branch being part of the path to the target. A non-transitory computer-readable storage medium is provided, further storing instructions for: identifying; generating a set of instructions for driving a distal end of the instrument along a first branch, returning the distal end of the instrument from the first branch back onto the path, and driving along a second branch, where position data received from a set of one or more position sensors while driving the instrument in accordance with the instructions facilitates alignment between a position coordinate system of the position data and a model coordinate system; and determining alignment criteria for one or more alignment parameters that are tracked while driving the instrument along the first branch.

[0011] In another aspect, a method of pre-operative planning is provided comprising: providing instructions for displaying a luminal network via a display device, the luminal network being stored in a non-transitory computer readable storage medium, the model including a target and a path to the target in a model coordinate system; receiving an indication of a position of the target in the model coordinate system; identifying a first branch and a second branch in the luminal network, the first branch being outside of the path to the target and the second branch being part of the path to the target; generating a set of instructions to drive a distal end of an instrument along the first branch, return from the first branch to the path, and drive along the second branch, wherein position data received from a set of one or more position sensors while driving the instrument in accordance with the instructions facilitates alignment between a position coordinate system of the position data and the model coordinate system; and determining an alignment criterion of one or more alignment parameters tracked while driving the instrument along the first branch. [Brief description of the drawings]

[0012] The disclosed aspects are hereinafter described in conjunction with the accompanying drawings, which illustrate, by way of example only, and not by way of limitation, the disclosed aspects, and in which like designations refer to like elements. [Figure 1] 1 illustrates an embodiment of a cart-based robotic system deployed for a diagnostic and / or therapeutic bronchoscopy procedure. [Diagram 2] 2 is a further embodiment of the robotic system of FIG. 1. [Diagram 3] 2 illustrates an embodiment of the robotic system of FIG. 1 positioned for ureteroscopy. [Figure 4] 2 illustrates an embodiment of the robotic system of FIG. 1 positioned for a vascular procedure. [Diagram 5] 1 illustrates an embodiment of a table-based robotic system positioned for a bronchoscopy procedure. [Figure 6] FIG. 6 is an alternative view of the robotic system of FIG. [Figure 7]1 is an exemplary system configured to store a robotic arm. [Figure 8] 1 is an embodiment of a table-based robotic system configured for a ureteroscopy procedure. [Figure 9] 1 is an embodiment of a table-based robotic system configured for laparoscopic procedures. [Figure 10] FIG. 10 is an embodiment of the table-based robotic system of FIGS. 5-9 with pitch or tilt adjustment. [Figure 11] FIGS. 5-10 provide detailed illustrations of the interface between the table and column of the table-based robotic system. [Figure 12] 1 is an exemplary instrument driver. [Figure 13] 1 is an exemplary medical instrument with a pair of instrument drivers. [Figure 14] 13 shows an alternative design of the instrument driver and instrument, where the axis of the drive unit is parallel to the axis of the elongated shaft of the instrument. [Figure 15] FIG. 15 is a block diagram illustrating a localization system that estimates the position of one or more elements of the robotic system of FIGS. 1-10, such as the position of the instrument of FIGS. 13 and 14, in accordance with an exemplary embodiment. [Figure 16A] FIG. 1 illustrates an example operating environment for implementing one or more aspects of the disclosed navigation systems and techniques. [Figure 16B] 16B is an exemplary luminal network that can be navigated in the surgical environment of FIG. 16A. [Figure 16C] FIG. 16C illustrates an exemplary robotic arm of a robotic system for guiding the movement of an instrument through the lumen network of FIG. 16B. [Figure 17] 1 illustrates an exemplary command console that may be used, for example, as a command console in an exemplary surgical environment. [Figure 18] 16A-16C depict the distal end of an exemplary instrument having imaging and EM sensing capabilities as described herein, for example, the instrument of FIGS. 16A-16C. [Figure 19] FIG. 1 illustrates an exemplary lumen network in which position sensor alignment may be performed in accordance with aspects of the present disclosure. [Figure 20A] 1 is a flow chart illustrating an exemplary method operable by a surgical robotic system or components thereof for aligning a position sensor coordinate system to a contralateral side in accordance with aspects of the present disclosure. [Figure 20B] 1 is a flowchart illustrating an exemplary method operable by a surgical robotic system or components thereof for determining whether sufficient position data has been received to facilitate contralateral registration, in accordance with aspects of the present disclosure. [Figure 21] FIG. 13 illustrates position data for a model of a lumen network, according to aspects of the present disclosure. [Figure 22] FIG. 13 illustrates an example of alignment of position data without preforming the contralateral registration process, according to aspects of the present disclosure. [Diagram 23] 1 is a flow chart illustrating an exemplary method operable by a surgical robotic system or components thereof for pre-operative planning in accordance with aspects of the present disclosure. [Figure 24] 5 is a flowchart illustrating an example method for determining alignment between a sensor coordinate system and a model coordinate system. [Diagram 25] 13 illustrates an example in which the sensor location points and the model location points are superimposed on the model in the model coordinate system. [Figure 26] 13 shows one embodiment for determining a weight proportional to distance. [Figure 27] 13 illustrates another embodiment for determining binary weights based on distance. [Figure 28] 13 illustrates yet another embodiment for determining binary weights based on distance. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0013] 1.Overview Aspects of the present disclosure may be integrated into a robotic-enabled medical system capable of performing a variety of medical procedures, including both minimally invasive procedures such as laparoscopy, and non-invasive procedures such as endoscopic procedures. Among endoscopic procedures, the system may perform bronchoscopy, ureteroscopy, gastroscopy, etc.

[0014] In addition to performing a wide range of procedures, the system can provide additional benefits such as enhanced imaging and guidance to assist the physician. Additionally, the system can provide the physician with the ability to perform procedures from an ergonomic position without requiring awkward arm movements and postures. Still further, the system can provide the physician with the ability to perform procedures with improved ease of use, such that one or more of the instruments of the system can be controlled by a single user.

[0015] Various embodiments are described below in conjunction with the drawings for purposes of explanation. It should be understood that many other implementations of the disclosed concepts are possible, and that various advantages may be achieved in the disclosed implementations. Headings are included herein for reference and to aid in locating the various sections. These headings are not intended to limit the scope of the concepts described therein. Such concepts may have applicability throughout this specification.

[0016] A. Robot System - Cart Robot-enabled medical systems can be configured in a variety of ways depending on the particular procedure. FIG. 1 illustrates an embodiment of a cart-based robot-controllable system 10 arranged for a diagnostic and / or therapeutic bronchoscopy procedure. During a bronchoscopy procedure, the system 10 can include a cart 11 having one or more robotic arms 12 for delivering a medical instrument, such as a steerable endoscope 13, which can be a procedure-specific bronchoscope for bronchoscopy, to a natural orifice access point (i.e., the patient's mouth, which in this example is positioned on a table) for delivering the diagnostic and / or therapeutic tools. As shown, the cart 11 can be positioned adjacent to the patient's upper torso to provide access to the access point. Similarly, the robotic arms 12 can be actuated to position the bronchoscope relative to the access point. The arrangement of FIG. 1 can also be utilized when performing a gastrointestinal (GI) procedure with a gastroscope (a specialized endoscope for GI procedures). FIG. 2 depicts an exemplary embodiment of the cart in more detail.

[0017] With continued reference to FIG. 1, once the cart 11 is properly positioned, the robotic arm 12 can insert the steerable endoscope 13 into the patient robotically, manually, or a combination thereof. As shown, the steerable endoscope 13 may include at least two nested parts, such as an inner leader portion and an outer sheath portion, each portion coupled to a separate instrument driver from a set of instrument drivers 28, with each instrument driver coupled to the distal end of an individual robotic arm. This linear arrangement of the instrument drivers 28, which facilitates coaxial alignment of the leader portion with the sheath portion, creates a "virtual rail" 29 that can be repositioned in space by manipulating one or more robotic arms 12 to different angles and / or positions. The virtual rails described herein are shown in the figures using dashed lines, and thus do not indicate the physical structure of the system. Translation of the instrument driver 28 along the virtual rail 29 nests the inner leader portion relative to the outer sheath portion or advances or retracts the endoscope 13 from the patient. The angle of the virtual rail 29 may be adjusted, translated, and pivoted based on clinical application or physician preference. For example, in bronchoscopy, the angle and position of the virtual rail 29 as shown represents a compromise that provides the physician access to the endoscope 13 while minimizing friction from bending the endoscope 13 into the patient's mouth.

[0018] After insertion, the endoscope 13 may be directed down the patient's trachea and lungs using precise commands from the robotic system until the target destination or surgical site is reached. To enhance navigation through the patient's pulmonary network and / or to reach a desired target, the endoscope 13 may be steered to telescope the inner leader portion out from the outer sheath portion for enhanced articulation and a larger bend radius. The use of a separate instrument driver 28 also allows the leader portion and sheath portion to be driven independently of one another.

[0019] For example, the endoscope 13 may be directed to deliver a biopsy needle to a target, such as a lesion or nodule in the patient's lung. The needle may be deployed down a working channel that spans the length of the endoscope to obtain a tissue sample that is analyzed by a pathologist. Depending on the results of the pathology, additional tools may be deployed down the working channel of the endoscope for additional biopsies. After identifying the nodule as malignant, the endoscope 13 may endoscopically deliver an instrument to resect the potential cancerous tissue. In some cases, diagnostic and therapeutic procedures may need to be delivered in separate procedures. In these situations, the endoscope 13 may also be used to deliver fiducials to "mark" the location of the target nodule. In other examples, diagnostic and therapeutic procedures may be delivered during the same procedure.

[0020] The system 10 may also include a movable tower 30 that may be connected to the cart 11 via a support cable to provide support for control, electronics, fluidics, optics, sensors, and / or power to the cart 11. Locating such functionality within the tower 30 allows for a smaller form factor cart 11 that can be more easily adjusted and / or repositioned by the operating physician and his / her staff. Additionally, the division of functionality between the cart / table and the support tower 30 reduces clutter in the operating room and promotes improved clinical workflow. The cart 11 may be placed in close proximity to the patient, while the tower 30 may be stored in a remote location to keep it out of the way during the procedure.

[0021] In support of the robotic system described above, the tower 30 may include computer-based control system components that store computer program instructions in a non-transitory computer-readable storage medium, such as, for example, a persistent magnetic storage drive, a solid-state drive, or the like. Execution of these instructions, whether execution occurs in the tower 30 or the cart 11, may control the entire system or subsystems thereof. For example, when executed by a processor in the computer system, the instructions may cause the robotic system components to actuate associated carriages and arm mounts, operate a robotic arm, and control a medical instrument. For example, in response to receiving control signals, motors in the joints of the robotic arm may position the arm in a particular pose.

[0022] The tower 30 may also include pumps, flow meters, valve controls, and / or fluid access to provide controlled irrigation and aspiration capabilities to a system that may be deployed through the endoscope 13. These components may also be controlled using the computer system of the tower 30. In some embodiments, irrigation and aspiration capabilities may be delivered directly to the endoscope 13 through separate cables.

[0023] The tower 30 may include voltage and surge protection designed to provide filtered and protected power to the cart 11, thereby avoiding the need to place power transformers and other auxiliary power components within the cart 11 and making the cart 11 smaller and more mobile.

[0024] The tower 30 may also include support equipment for sensors deployed throughout the robotic system 10. For example, the tower 30 may include optoelectronic equipment for detecting, receiving, and processing data received from optical sensors or cameras throughout the robotic system 10. In combination with a control system, such optoelectronic equipment may be used to generate real-time images for display in any number of consoles located throughout the system, including in the tower 30. Similarly, the tower 30 may also include electronic subsystems for receiving signals from deployed electromagnetic (EM) sensors and processing the received signals. The tower 30 may also be used to house and position EM field generators for detection by EM sensors in or on the medical instrument.

[0025] The tower 30 may also include a console 31 in addition to other consoles available to the rest of the system, for example a console mounted on top of a cart. The console 31 may include a user interface for the operator physician and a display screen, such as a touch screen. The consoles in the system 10 are generally designed to provide both pre-operative and real-time information of the procedure, such as robotic control, and navigation and localization information for the endoscope 13. If the console 31 is not the only console available to the physician, the console 31 may be used by a second operator, such as a nurse, to monitor the health or vital signs of the patient and the operation of the system, as well as provide procedure-specific data, such as navigation and localization information.

[0026] The tower 30 may be coupled to the cart 11 and endoscope 13 via one or more cables or connections (not shown). In some embodiments, support functions from the tower 30 may be provided to the cart 11 through a single cable, simplifying and decluttering the operating room. In other embodiments, certain functions may be coupled with separate wiring and connections. For example, power may be provided to the cart through a single power cable, while support for control, optics, fluidics, and / or navigation may be provided through separate cables.

[0027] FIG. 2 provides a detailed view of an embodiment of a cart from the cart-based robotic controllable system shown in FIG. The cart 11 generally includes an elongated support structure 14 (often referred to as a "column"), a cart base 15, and a console 16 at the top of the column 14. The column 14 may include one or more carriages, such as a carriage 17 (alternatively an "arm support") for supporting the deployment of one or more robotic arms 12 (three are shown in FIG. 2). The carriage 17 may include an individually configurable arm mount that rotates along a vertical axis to adjust the base of the robotic arm 12 for better positioning relative to the patient. The carriage 17 also includes a carriage interface 19 that allows the carriage 17 to translate vertically along the column 14.

[0028] The carriage interface 19 is connected to the column 14 through slots, such as slots 20 positioned on either side of the column 14 to guide the vertical translation of the carriage 17. The slots 20 include vertical translation interfaces for positioning and holding the carriage at various vertical heights relative to the cart base 15. The vertical translation of the carriage 17 allows the cart 11 to adjust the reach of the robotic arm 12 to meet various table heights, patient sizes, and physician preferences. Similarly, an individually configurable arm mount on the carriage 17 allows the robotic arm base 21 of the robotic arm 12 to be angled in various configurations.

[0029] In some embodiments, a slot cover may be added to the slot 20 that is flush and parallel with the slot surface to prevent dirt and fluids from entering the interior chamber of the column 14 and the vertical translation interface as the carriage 17 translates vertically. The slot cover may be deployed through a pair of spring spools that are positioned near the vertical top and bottom of the slot 20. The cover is coiled within the spools until it is deployed to extend and retract from the coil as the carriage 17 translates vertically up and down. The spring loading of the spools provides the force to retract the cover into the spool as the carriage 17 translates towards the spool, while also maintaining a seal as the carriage 17 translates away from the spool. The cover may be connected to the carriage 17 using, for example, a bracket within the carriage interface 19 to ensure that the cover properly extends and retracts as the carriage 17 translates.

[0030] Column 14 may include mechanisms therein, such as gears and motors, designed to use a vertically aligned leadscrew to mechanically translate carriage 17 in response to control signals generated in response to user input, such as input from console 16.

[0031] The robotic arm 12 may generally include a robotic arm base 21 and an end effector 22 separated by a series of links 23 connected by a series of joints 24, each joint including an independent actuator, each actuator including an independently controllable motor. Each independently controllable joint represents an independent degree of freedom available to the robotic arm. Each of the arms 12 has seven joints, thus providing seven degrees of freedom. A large number of joints results in a large number of degrees of freedom, allowing for "redundant" degrees of freedom. The redundant degrees of freedom allow the robotic arms 12 to position their respective end effectors 22 at specific positions, orientations, and trajectories in space using different articulation positions and joint angles. This allows the system to position and orient the medical instrument from a desired point in space, while at the same time allowing the physician to move the arm joints to a clinically advantageous position away from the patient to create better access while avoiding arm collisions.

[0032] The cart base 15 balances the weight of the column 14, carriage 17, and arm 12 on the floor. Thus, the cart base 15 houses the heavier parts such as electronics, motors, power supplies, and components that allow the cart to be either mobile and / or immobilized. For example, the cart base 15 includes casters 25 in the form of rollable wheels that allow the cart to be easily moved around the room before a procedure. After reaching the proper position, the casters 25 may be immobilized using wheel locks to hold the cart 11 in place during a procedure.

[0033] The console 16 positioned at the vertical end of the column 14 allows for both a user interface and a display screen (or dual-purpose device, e.g., touch screen 26) for receiving user input to provide both pre-operative and intra-operative data to the physician user. Potential pre-operative data on the touch screen 26 may include pre-operative planning, navigation and mapping data derived from a pre-operative computed tomography (CT) scan, and / or notes from a pre-operative patient interview. Intra-operative data on the display may include optical information provided by tools, sensor and coordinate information from sensors, and vital patient statistics such as respiration, heart rate, and / or pulse. The console 16 may be positioned and angled to allow the physician to access the console from the side of the column 14 opposite the carriage 17. From this position, the physician can view the console 16, the robotic arm 12, and the patient while operating the console 16 from behind the cart 11. As shown, the console 16 also includes a handle 27 to aid in maneuvering and stabilizing the cart 11.

[0034] FIG. 3 illustrates an embodiment of the robotically controllable system 10 arranged for ureteroscopy. In a ureteroscopy procedure, the cart 11 may be positioned to deliver a ureteroscope 32, a procedure-specific endoscope designed to traverse the patient's urethra and ureters, to the patient's lower abdominal region. In a ureteroscopy, it may be desirable for the ureteroscope 32 to be directly aligned with the patient's urethra to reduce friction and forces on sensitive anatomical structures in the region. As shown, the cart 11 may be aligned to the table leg to allow the robotic arm 12 to position the ureteroscope 32 for direct linear access to the patient's urethra. From the table leg, the robotic arm 12 may insert the ureteroscope 32 along a virtual rail 33 directly through the urethra and into the patient's lower abdomen.

[0035] After insertion into the urethra using control techniques similar to those in bronchoscopy, the ureteroscope 32 may be navigated to the bladder, ureters, and / or kidneys for diagnostic and / or therapeutic applications. For example, the ureteroscope 32 may be directed to the ureter and kidney to break up formed kidney stones using a laser or ultrasonic lithotripsy device deployed down the working channel of the ureteroscope 32. After the lithotripsy is completed, the resulting stone fragments may be removed using a basket deployed down the ureteroscope 32.

[0036] FIG. 4 shows an embodiment of a similarly arranged robotic controllable system for a vascular procedure. In a vascular procedure, the system 10 can be configured such that the cart 11 can deliver a medical instrument 34, such as a steerable catheter, to an access point in the femoral artery in the patient's leg. The femoral artery presents both a larger diameter for navigation and a relatively circuitous and less tortuous path to the patient's heart, simplifying navigation. As in a ureteroscopy procedure, the cart 11 may be positioned toward the patient's leg and lower abdomen, allowing the robotic arm 12 to provide a virtual rail 35 with direct linear access to the femoral artery access point in the patient's thigh / hip region. After insertion into the artery, the medical instrument 34 may be oriented and inserted by translating the instrument driver 28. Alternatively, the cart may be positioned around the patient's upper abdomen to reach alternative vascular access points, such as the carotid and brachial arteries near the shoulder and wrist.

[0037] B. Robot System - Table An embodiment of a robot-enabled medical system may also incorporate a patient table. The incorporation of a table reduces the amount of capital equipment in the operating room by eliminating carts and allows greater access to the patient. FIG. 5 shows one embodiment of such a robot-controllable system arranged for a bronchoscopy procedure. The system 36 includes a support structure or column 37 for supporting a platform 38 (shown as a "table" or "bed") above the floor. As with cart-based systems, the end effector of the robotic arm 39 of the system 36 includes an instrument driver 42 designed to manipulate an elongated medical instrument, such as the bronchoscope 40 of FIG. 5, through or along a virtual rail 41 formed from a linear alignment of the instrument driver 42. In practice, a C-arm for providing fluoroscopic imaging may be positioned above the upper abdominal region of the patient by placing emitters and detectors around the table 38.

[0038] FIG. 6 provides an alternative view of the system 36 without the patient and medical instruments for discussion purposes. As shown, the column 37 may include one or more carriages 43, illustrated as a ring shape in the system 36, which may be the base for one or more robotic arms 39. The carriages 43 may translate along a vertical column interface 44 that spans the length of the column 37 to provide different vantage points where the robotic arms 39 may be positioned to reach the patient. The carriages 43 may rotate around the column 37 using mechanical motors positioned within the column 37 to allow the robotic arms 39 to have access to multiple sides of the table 38, such as both sides of the patient. In embodiments with multiple carriages, the carriages may be individually positioned on the column and may translate and / or rotate independently of the other carriages. The carriages 43 do not have to surround the column 37 or even be circular, but the ring shape as illustrated facilitates the carriages 43 to rotate around the column 37 while maintaining structural balance. Rotation and translation of carriage 43 enables the system to align medical instruments such as endoscopes and laparoscopes to different access points on the patient.

[0039] The arm 39 may be attached to the carriage via a set of arm mounts 45 that comprise a series of joints that may individually rotate and / or telescope to provide additional configurability to the robotic arm 39. Additionally, the arm mounts 45 may be positioned on the carriage 43 such that when the carriage 43 is appropriately rotated, the arm mounts 45 may be positioned either to one side of the table 38 (as shown in FIG. 6), to both sides of the table 38 (as shown in FIG. 9), or to adjacent sides of the table 38 (not shown).

[0040] The column 37 structurally provides support for the table 38 and a path for the vertical translation of the carriage. Internally, the column 37 may be equipped with a lead screw for guiding the vertical translation of the carriage, and a motor for mechanizing the translation of said carriage based on the lead screw. The column 37 may also transmit power and control signals to the carriage 43 and the robotic arm 39 mounted thereon.

[0041] The table base 46 serves a similar function as the cart base 15 of the cart 11 shown in FIG. 2, housing the heavier components to counterbalance the table / bed 38, column 37, carriage 43, and robotic arm 39. The table base 46 may also incorporate rigid casters to provide stability during a procedure. The casters, which deploy from the bottom of the table base 46, extend in opposite directions on either side of the base 46 and may be retracted when the system 36 needs to be moved.

[0042] Continuing with FIG. 6, the system 36 may also include a tower (not shown) that divides the functions of the system 36 between the table and the tower to reduce the form factor and bulk of the table. As with the previously disclosed embodiments, the tower may provide various support functions to the table, such as processing, computing, and control capabilities, power, fluidics, and / or optical and sensor processing. The tower may also be movable to be positioned away from the patient to improve physician access and reduce clutter in the operating room. Additionally, locating components within the tower allows for more storage space within the table base for potential storage of a robotic arm. The tower may also include a console that provides both a user interface for user input, such as a keyboard and / or pendant, and a display screen (or touch screen) for pre-operative and intra-operative information, such as real-time imaging, navigation, and tracking information.

[0043] In some embodiments, the table base may house and store the robotic arm when not in use. FIG. 7 shows a system 47 for housing the robotic arm in one embodiment of a table-based system. In the system 47, the carriage 48 may be translated vertically into the base 49 to store the robotic arm 50, arm mount 51, and carriage 48 therein. The base cover 52 may be translated and retracted to open to position the carriage 48, arm mount 51, and arm 50 about the column 53, and closed to house and protect them when not in use. The base cover 52 may be sealed with a membrane 54 along the edge of its opening to prevent dirt and fluid ingress when closed.

[0044] FIG. 8 illustrates one embodiment of a robotically controllable table-based system configured for a ureteroscopy procedure. For ureteroscopy, the table 38 may include a swivel portion 55 for positioning the patient off-angle from the column 37 and table base 46. The swivel portion 55 may rotate or pivot about a pivot point (e.g., positioned below the patient's head) to position the bottom of the swivel portion 55 away from the column 37. For example, pivoting the swivel portion 55 allows a C-arm (not shown) to be positioned above the patient's lower abdomen without competing for space with the column (not shown) below the table 38. By rotating the carriage 35 (not shown) about the column 37, the robotic arm 39 may insert the ureteroscope 56 directly into the patient's groin area along the virtual rail 57 to reach the urethra. In ureteroscopy, stirrups 58 may be secured to a swivel portion 55 of table 38 to support the position of the patient's legs during the procedure and allow clear access to the patient's groin area.

[0045] In a laparoscopic procedure, minimally invasive instruments (elongated in shape to accommodate the size of the incision or incisions) may be inserted into the patient's anatomy through small incision(s) in the patient's abdominal wall. After distension of the patient's abdominal cavity, the instruments, often referred to as laparoscopes, may be oriented to perform surgical tasks such as grasping, cutting, ablation, suturing, etc. FIG. 9 illustrates an embodiment of a robotically controllable table-based system configured for a laparoscopic procedure. As shown in FIG. 9, the carriage 43 of the system 36 may be rotated and vertically adjusted to position a pair of robotic arms 39 on either side of the table 38 such that a laparoscope 59 may be positioned using arm mounts 45 to pass through minimal incisions on either side of the patient to reach the patient's abdominal cavity.

[0046] To accommodate laparoscopic procedures, the robotic-enabled table system may also tilt the platform to a desired angle. FIG. 10 shows an embodiment of a robotically controllable medical system with pitch or tilt adjustment. As shown in FIG. 10, the system 36 can accommodate the tilt of the table 38 to position one side of the table at a greater distance from the floor than the other side. Additionally, the arm mount 45 may rotate to match the tilt so that the arm 39 maintains the same planar relationship with the table 38. To accommodate steeper angles, the column 37 may also include a nesting portion 60 that allows the column 37 to extend vertically to prevent the table 38 from contacting the floor or colliding with the base 46.

[0047] FIG. 11 provides a detailed illustration of the interface between the table 38 and column 37. The pitch rotation mechanism 61 may be configured to change the pitch angle of the table 38 relative to the column 37 in multiple degrees of freedom. The pitch rotation mechanism 61 may be enabled by the positioning of orthogonal axes 1, 2 at the column-table interface, each actuated by a separate motor 3, 4 in response to an electrical pitch angle command. Rotation along one screw 5 allows tilt adjustment in one axis 1, and rotation along the other screw 6 allows tilt adjustment along the other axis 2.

[0048] For example, pitch adjustment is particularly useful when attempting to position the table in Trendelenburg position, i.e., positioning the patient's lower abdomen higher off the floor than the patient's lower abdomen for lower abdominal surgery. The Trendelenburg position allows gravity to slide the patient's internal organs toward their upper abdomen, emptying the abdominal cavity for entry of minimally invasive tools to perform lower abdominal surgical procedures such as laparoscopic prostatectomy.

[0049] C. Instrument Drivers and Interfaces The end effector of the robotic arm of the system includes (i) an instrument driver (alternatively called an "instrument drive mechanism" or "instrument device manipulator") that incorporates electromechanical means for actuating the medical instrument, and (ii) a removable or detachable medical instrument that may lack any electromechanical components such as a motor. This dichotomy may be based on the need to sterilize medical instruments used in medical procedures, their complex mechanical assemblies and delicate electronics making it impossible to adequately sterilize expensive capital equipment. Thus, medical instruments can be designed to be detached, removed, and replaced from the instrument driver (and thus the system) for individual sterilization or disposal by the physician or physician's staff. In contrast, instrument drivers do not need to be replaced or sterilized and can be draped for protection.

[0050] FIG. 12 illustrates an exemplary instrument driver. The instrument driver 62, located at the distal end of the robotic arm, includes one or more drive units 63 arranged with parallel axes to provide a controlled torque to the medical instrument via a drive shaft 64. Each drive unit 63 includes an individual drive shaft 64 for interacting with the instrument, a gear head 65 for converting the rotation of the motor shaft to a desired torque, a motor 66 for generating the drive torque, an encoder 67 for measuring the speed of the motor shaft and providing feedback to the control circuit, and a control circuit 68 for receiving the control signal and operating the drive unit. Each drive unit 63 is independently controlled and motorized, and the instrument driver 62 may provide multiple (four as shown in FIG. 12) independent drive outputs to the medical instrument. In operation, the control circuit 68 receives the control signal, sends a motor signal to the motor 66, compares the resulting motor speed measured by the encoder 67 to a desired speed, and modulates the motor signal to generate the desired torque.

[0051] For procedures requiring a sterile environment, the robotic system may incorporate a drive interface, such as a sterile adapter connected to a sterile drape, located between the instrument driver and the medical instrument. The primary purpose of the sterile adapter is to transmit angular motion from the drive shaft of the instrument driver to the drive input of the instrument while maintaining physical separation, and therefore sterility, between the drive shaft and the drive input. Thus, an exemplary sterile adapter may be comprised of a set of rotational inputs and outputs intended to mate with the drive shaft of the instrument driver and a drive input to the instrument. The sterile drape, which is connected to the sterile adapter, is comprised of a thin flexible material, such as a transparent or translucent plastic, and is designed to cover the instrument driver, the robotic arm, and capital equipment, such as a cart (in a cart-based system) or a table (in a table-based system). The use of the drape allows the capital equipment to be placed in close proximity to the patient while still being positioned in an area that does not require sterility (i.e., the non-sterile field). On the other side of the sterile drape, the medical instrument may interface with the patient in an area that requires sterility (i.e., the sterile field).

[0052] D. Medical equipment FIG. 13 illustrates an exemplary medical instrument with a paired instrument driver. Similar to other instruments designed for use with a robotic system, the medical instrument 70 includes an elongated shaft 71 (or elongated body) and an instrument base 72. The instrument base 72, also referred to as an "instrument handle" due to its design intended for manual interaction by a physician, may generally include a rotatable drive input 73, e.g., a receptacle, pulley, or spool, designed to mate with a drive output 74 that extends through a drive interface on an instrument driver 75 at the distal end of a robotic arm 76. When physically connected, latched, and / or coupled, the mated drive input 73 of the instrument base 72 may share a rotational axis with the drive output 74 in the instrument driver 75 to enable the transfer of torque from the drive output 74 to the drive input 73. In some embodiments, the drive output 74 may include a spline designed to mate with a receptacle on the drive input 73.

[0053] The elongated shaft 71 is designed to be delivered through either an anatomical opening or lumen, for example, as in an endoscope, or a minimally invasive incision, as in a laparoscopy. The elongated shaft 66 may be flexible (e.g., with properties similar to an endoscope), rigid (e.g., with properties similar to a laparoscope), or may include a customized combination of both flexible and rigid portions. If designed for laparoscopy, the distal end of the rigid elongated shaft may be connected to an end effector including a jointed wrist formed from a clevis with an axis of rotation, and a surgical tool, for example, a grasper or scissors, that may be actuated based on forces from tendons as the drive input rotates in response to torque received from the drive output 74 of the instrument driver 75. If designed for endoscopy, the distal end of the flexible elongated shaft may include a steerable or controllable bend that may articulate and bend based on torque received from the drive output 74 of the instrument driver 75.

[0054] Torque from the instrument driver 75 is transferred down the elongated shaft 71 using tendons within the shaft 71. These individual tendons, such as pull wires, may be individually secured to individual drive inputs 73 within the instrument handle 72. From the handle 72, the tendons are directed down one or more pull lumens within the elongated shaft 71 and are anchored to a distal portion of the elongated shaft 71. In laparoscopy, these tendons may be coupled to a distally attached end effector, such as a wrist, grasper, or scissors. Under such a configuration, torque exerted on the drive inputs 73 transfers tension to the tendons, thereby actuating the end effector in some manner. In laparoscopy, the tendons can rotate a joint about an axis, thereby moving the end effector in either direction. Alternatively, the tendons may be connected to one or more jaws of a grasper at the distal end of the elongated shaft 71, with tension from the tendons causing the grasper to close.

[0055] In endoscopy, the tendons may be coupled to a flex or articulating section positioned along the elongated shaft 71 (e.g., at the distal end) via adhesive, control ring, or other mechanical fixation. If fixedly attached to the distal end of the flex, torque exerted on the drive input 73 is transferred downstream of the tendon, bending or articulating the softer flex (sometimes referred to as the articulatable section or region). Along the non-flexing portion, it may be advantageous to thread or spiral the individual tendons into individual pull lumens that point along (or inwardly) the wall of the endoscope shaft to counterbalance radial forces resulting from tension in the pull wires. The angle of thread and / or spacing between these may be altered or designed for a particular purpose, with narrower threads exhibiting less shaft compression under load forces, while lesser amounts of threads result in greater shaft compression under load forces, but also exhibiting flexion limitations. At the other end of the spectrum, the pull lumen may be oriented parallel to the longitudinal axis of elongate shaft 71, allowing for desired bending or controlled articulation at the articulatable portion.

[0056] In endoscopy, the elongated shaft 71 houses several components that aid in robotic procedures. The shaft may include a working channel for deploying surgical tools, irrigation, and / or suction to the surgical area at the distal end of the shaft 71. The shaft 71 may also house wires and / or optical fibers for transmitting signals to and from an optical assembly at the distal tip, which may include an optical camera. The shaft 71 may also house optical fibers for carrying light from a proximally located light source, such as a light emitting diode, to the distal end of the shaft.

[0057] At the distal end of the instrument 70, the distal tip may include a working channel opening for delivering tools to the surgical site for diagnosis and / or treatment, irrigation, and aspiration. The distal tip may also include a port for a camera, such as a fiberscope or digital camera, to capture images of the internal anatomical space. Relatedly, the distal tip may also include a port for a light source to illuminate the anatomical space when a camera is used.

[0058] 13, the drive shaft axis, and therefore the drive input axis, is orthogonal to the axis of the elongated shaft. However, this arrangement complicates the ability of the elongated shaft 71 to roll. Allowing the elongated shaft 71 to roll along its axis while holding the drive input 73 stationary can result in undesirable entanglement of tendons as they extend from the drive input 73 and enter the pull lumen within the elongated shaft 71. Such resulting entanglement of tendons can destroy any control algorithm intended to predict the movement of a flexible elongated shaft during an endoscopic procedure.

[0059] FIG. 14 shows an alternative design of the instrument driver and instrument, in which the axis of the drive unit is parallel to the axis of the elongated shaft of the instrument. As shown, a circular instrument driver 80 includes four drive units with parallel aligned drive outputs 81 at the end of a robotic arm 82. The drive units and their respective drive outputs 81 are housed in a rotating assembly 83 of the instrument driver 80, which is driven by one of the drive units in the assembly 83. In response to torque provided by the rotating drive units, the rotating assembly 83 rotates along a circular bearing connecting the rotating assembly 83 to a non-rotating portion 84 of the instrument driver. Power and control signals may be transmitted to the rotating assembly 83 from the non-rotating portion 84 of the instrument driver 80 through electrical contacts and may be maintained through rotation by a brushed slip ring connection (not shown). In other embodiments, the rotating assembly 83 may be responsive to a separate drive unit that is integrated into the non-rotatable portion 84 and thus not parallel to the other drive units. The rotation mechanism 83 enables the instrument driver 80 to rotate the drive units and their respective drive outputs 81 as a single unit about the instrument driver axis 85 .

[0060] Similar to the previously disclosed embodiments, the instrument 86 may include an elongated shaft 88 and an instrument base 87 (shown with a transparent exterior skin for purposes of discussion) that includes a number of drive inputs 89 (such as receptacles, pulleys, and spools) configured to receive the drive output 81 in the instrument driver 80. Unlike the previously disclosed embodiments, the instrument shaft 88 extends from the center of the instrument base 87 with an axis that is substantially parallel to the axis of the drive inputs 89, rather than orthogonal as in the design of FIG.

[0061] When coupled to the rotation assembly 83 of the instrument driver 80, the medical instrument 86, including the instrument base 87 and the instrument shaft 88, rotates with the rotation assembly 83 about the instrument driver axis 85. Because the instrument shaft 88 is positioned at the center of the instrument base 87, the instrument shaft 88 is coaxial with the instrument driver axis 85 when attached. Thus, rotation of the rotation assembly 83 causes the instrument shaft 88 to rotate about its own longitudinal axis. Furthermore, as the instrument base 87 rotates with the instrument shaft 88, any tendons connected to the drive input 89 in the instrument base 87 do not become entangled during rotation. Thus, the parallelism of the axes of the drive output 81, drive input 89, and instrument shaft 88 allows for shaft rotation without entangling the control tendons.

[0062] E. Navigation and Control. Traditional endoscopy may involve the use of fluoroscopy (e.g., as may be delivered through a C-arm) and other forms of radiation-based imaging modalities to provide intraluminal guidance to the operator-physician. In contrast, the robotic system contemplated by the present disclosure may provide non-radiation-based navigation and localization means to reduce the physician's exposure to radiation and reduce the amount of equipment in the operating room. As used herein, the term "localization" may refer to determining and / or monitoring the position of an object in a reference coordinate system. Techniques such as pre-operative mapping, computer vision, real-time EM tracking, and robot command data may be used individually or in combination to achieve a radiation-free operating environment. In other cases where radiation-based imaging modalities are still used, pre-operative mapping, computer vision, real-time EM tracking, and robot command data may be used individually or in combination to improve the information obtained solely by radiation-based imaging modalities.

[0063] 15 is a block diagram illustrating a localization system 90 for estimating the position of one or more elements of a robotic system, such as the position of an instrument, according to an exemplary embodiment. The localization system 90 may be a set of one or more computing devices configured to execute one or more instructions. The computing devices may be embodied by a processor (or processors) and computer readable memory in one or more of the components discussed above. By way of example, and not by way of limitation, the computing devices may be in the tower 30 shown in FIG. 1, may be a cart shown in FIGS. 1-4, may be a bed shown in FIGS. 5-10, or the like.

[0064] As shown in FIG. 15, the localization system 90 may include a localization module 95 that processes the input data 91-94 to generate location data 96 of the distal tip of the medical instrument. The location data 96 may be data or logic that represents the location and / or orientation of the distal end of the instrument relative to a frame of reference. The frame of reference may be a frame of reference relative to a known object such as the patient's anatomy or an EM field generator (see below discussion of EM field generators). The location data 96 may also be referred to herein as "state data" that describes the current state of the distal tip of the medical instrument relative to a model of the patient's anatomy (e.g., a skeletal model). The state data may include information such as the position and orientation of the distal tip of the medical instrument over a given sample period. For example, if the patient's anatomy is modeled using a skeletal model based on the midpoint of the lumen network, the location may take the form of a segment ID and a depth along the segment.

[0065] The various input data 91-94 will now be described in more detail. Pre-operative mapping can be accomplished utilizing the acquisition of low-dose CT scans. The pre-operative CT scans are reconstructed into three-dimensional (3D) images that are visualized, for example, as cutaway "slices" of the patient's internal anatomy. When analyzed as a whole, an image-based model can be generated for the anatomical cavities, spaces, and structures of the patient's anatomy, such as the patient's pulmonary network. Techniques such as centerline geometry can be determined and approximated from the CT images to generate a 3D volume of the patient's anatomy, referred to as pre-operative model data 91. The use of centerline geometry is discussed in U.S. Patent Application Serial No. 14 / 523,760, the contents of which are incorporated herein in their entirety. Network topological models may also be derived from CT images and are particularly suited for bronchoscopy.

[0066] In some embodiments, the instrument may be equipped with a camera to provide visual data 92. The localization module 95 may process the visual data to enable one or more vision-based location tracking. For example, pre-operative model data may be used along with the visual data 92 to enable computer vision-based tracking of a medical instrument (e.g., an endoscope, or an instrument advancing through the working channel of the endoscope). For example, using the pre-operative model data 91, the robotic system may generate a library of predicted endoscopic images from the model based on the expected path of travel of the endoscope, with each image linked to a location in the model. During surgery, this library may be referenced by the robotic system to compare real-time images captured by a camera (e.g., a camera at the distal end of the endoscope) to those in the image library to assist with localization.

[0067] Other computer vision based tracking techniques use tracking functions to determine the motion of the camera and therefore the endoscope. Some features of the localization module 95 may identify circular geometric shapes in the pre-operative model data 91 that correspond to anatomical lumens and track changes in those geometries to determine which anatomical lumens have been selected and the relative rotational and / or translational motion of the camera. The use of a phase map may further enhance vision based algorithms or techniques.

[0068] Optical flow, another computer vision based technique, may analyze the displacement and translation of image pixels in a video sequence in the visual data 92 to infer camera movement. Examples of optical flow techniques may include motion detection, object segmentation calculations, luminance, motion compensated coding, stereo disparity measurements, etc. By comparing multiple frames over multiple iterations, the movement and position of the camera (and therefore the endoscope) can be determined.

[0069] The localization module 95 can use real-time EM tracking to generate a real-time location of the endoscope in a global coordinate system that can be registered to the patient's anatomy represented by the pre-operative model. In EM tracking, an EM sensor (or tracker), consisting of one or more sensor coils embedded in a medical instrument (e.g., an endoscopic instrument) at one or more positions and orientations, measures the variations in an EM field generated by one or more static EM field generators positioned at known locations. The position information detected by the EM sensor is stored as EM data 93. The EM field generator (or transmitter) can be placed in close proximity to the patient to generate a low-intensity magnetic field that can be detected by the embedded sensor. The magnetic field induces a small current in the sensor coil of the EM sensor, which can be analyzed to determine the distance and angle between the EM sensor and the EM field generator. These distances and orientations can be "registered" intraoperatively to the patient's anatomy (e.g., the pre-operative model) to determine a geometric transformation that aligns a single position in the coordinate system with a position in the pre-operative model of the patient's anatomy. Once registered, an EM tracker embedded at one or more locations on the medical instrument (e.g., the distal tip of an endoscope) can provide a real-time indication of the medical instrument's progression through the patient's anatomy.

[0070] The robotic commands and kinematic data 94 may also be used by a localization module 95 to provide localization data 96 for the robotic system. The device pitch and yaw resulting from the articulation commands can be determined during pre-operative calibration. Intraoperatively, these calibration measurements can be used in combination with known insertion depth information to estimate the position of the instrument. Alternatively, these calculations may be analyzed in combination with EM, vision, and / or phase modeling to estimate the position of the medical instrument within the network.

[0071] As Fig. 15 illustrates, several other input data can be used by the localization module 95. For example, although not shown in Fig. 15, an instrument that utilizes shape sensing fibers can provide shape data that the localization module 95 can use to determine the position and shape of the instrument.

[0072] The localization module 95 may use a combination of the input data 91-94. In some cases, such a combination may use a probabilistic approach in which the localization module 95 assigns a confidence weight to the location determined from each of the input data 91-94. Thus, if the EM data is unreliable (such as when EM interference is present), causing the location determined by the EM data 93 to be less reliable, the localization module 95 may rely more heavily on the vision data 92 and / or the robot command and kinematic data 94.

[0073] As discussed above, the robotic systems discussed herein can be designed to incorporate one or a combination of two or more of the above-mentioned techniques. The computer-based control system of the tower, bed, and / or cart-based robotic system may store, for example in a non-transitory computer-readable storage medium, such as a persistent magnetic storage drive, solid-state drive, etc., computer program instructions that, when executed, cause the system to receive and analyze sensor data and user commands, generate system-wide control signals, and display navigation and localization data, such as instrument position within a global coordinate system, anatomical maps, etc.

[0074] 2. Overview of position sensor alignment Embodiments of the present disclosure relate to systems and techniques for aligning a coordinate system used by one or more position sensors with another coordinate system, such as a coordinate system used by an anatomical model. Alignment may refer to a transformation that can be applied to position sensor data to map the position sensor data to the coordinate system of the anatomical model. Thus, alignment may be used by the system to determine the position of one or more position sensors relative to the anatomical model based on the position sensor data. The position sensor may be used to locate the distal end of an instrument to an anatomical location during a medical procedure. The position sensor may be positioned at or near the distal end of the instrument, or may be positioned away from the distal end of the instrument. Examples of position sensors that may be positioned at or near the distal end of the instrument include EM sensors, vision-based position sensors (e.g., cameras), shape-sensing fibers, etc. Examples of position sensors that may be positioned away from the distal end of the instrument include fluoroscopic imaging devices, robotic data used to control the position of the instrument via one or more instrument manipulators, etc.

[0075] The position sensor may be configured to generate position data indicative of a position of the distal end of the instrument relative to a position sensor coordinate system. When the position sensor is juxtaposed with the distal end of the instrument, the position data may represent a position of the position sensor itself, which may be used to determine the position of the distal end of the instrument. In certain embodiments, the position sensor coordinate system may include a set of axes and origins, which may be defined based on the particular technology used to implement the position sensor.

[0076] For example, an EM sensor located in or on an instrument may be configured to measure an EM field generated by an EM field generator. The properties of the EM field, and therefore the EM values ​​measured by the EM sensor, may be defined with respect to the position and orientation of the EM field generator. Thus, the positioning of the EM field generator may affect the values ​​measured by the EM sensor, and may also define the position and orientation of an EM coordinate system.

[0077] As mentioned above, the patient's luminal network can be preoperatively mapped using, for example, a low-dose CT scan to generate a model of the luminal network. Because the model may be generated via a different technique than that used to locate the distal end of the instrument, the model coordinate system may not be aligned with the position sensor coordinate system. Thus, to track the position of the instrument relative to the model using the position sensor coordinate system, certain aspects of the present disclosure relate to "registering" the position sensor coordinate system to the model coordinate system. This registration may include, for example, translations and / or rotations that can be applied to the position data to map the position data from the position sensor coordinate system to the model coordinate system.

[0078] Since the model of the luminal network provides a mapping of the luminal network of the patient, the model coordinate system is "fixed" or defined with respect to the patient. That is, the frame of reference for the model coordinate system is based on the position and / or orientation of the patient during the procedure. One challenge in aligning the position sensor coordinate system to the model coordinate system is that the frame of reference for the position sensor coordinate system may not be "fixed" or predefined with respect to the patient. For example, when the position sensor is embodied as an EM sensor, the frame of reference for the EM coordinate system may be the EM field generator. However, in certain implementations, the EM field generator may be freely positioned within a certain region such that the EM field generator may be positioned out of the path of other elements of the robotic surgical system (e.g., robotic arm, C-arm, etc.). Because the position of the EM field generator, and therefore the frame of reference for the EM coordinate system, is not predefined, a process may be configured to perform to align the EM coordinate system to the model coordinate system.

[0079] One technique for aligning the EM coordinate system to the model coordinate system may include a pre-operative step of identifying multiple locations in a pre-operative model and an intra-operative step of providing instructions to a user to drive an instrument to each of these locations. The system may rely on other forms of navigation (e.g., camera feedback) to instruct the user to drive the instrument to each of the locations, and the system may be further configured to receive input from the user confirming when the instrument is located at each of the identified locations. Using the confirmation received from the user, the EM data, and the identified locations in the model, the system may determine an alignment that maps the EM data to the identified locations. This alignment may then be used to map the EM data representing the location of the distal end of the instrument to the model for the remainder of the procedure.

[0080] However, the above alignment process may be complicated and time-consuming for the user. For example, to provide a sufficiently robust alignment, the system may be required to identify a relatively large number of positions (e.g., six or more positions) that are spatially diverse (e.g., the identified positions may need to be at least a certain distance apart from each other). Therefore, certain aspects of the present disclosure relate to systems and techniques that can provide alignment between a position sensor coordinate system and a model coordinate system through a simplified process.

[0081] A.EM navigation-guided bronchoscope. Position sensor alignment is described below with respect to embodiments of EM sensor alignment for use in EM navigation-guided bronchoscopic procedures, however aspects of the disclosure may also be applied to other position sensors capable of generating position data within a corresponding position sensor coordinate system, as well as other medical types of medical procedures.

[0082] A bronchoscope may include a light source and a small camera that allows a physician to inspect a patient's trachea and airways. If the exact position of the bronchoscope in the patient's airways is not known, patient trauma may occur. To verify the position of the bronchoscope, an image-based bronchoscope guidance system may use data from the bronchoscope camera to perform local registration (e.g., registration at a specific location in the lumen network) at the bifurcation of the patient's airways, and thus may be advantageously less susceptible to positional errors due to the patient's respiratory motion. However, image-based guidance methods rely on bronchoscope video and may be affected by artifacts in the bronchoscope video caused by the patient's coughing or mucus blockage, etc.

[0083] EM navigation-guided bronchoscopy is a type of bronchoscopy procedure that implements EM techniques to locate and guide an endoscopic tool or catheter through the bronchial passages of the lungs. EM navigation-guided bronchoscopy systems can use an EM field generator that emits a variable EM field of low intensity and establishes the position of a tracking volume around the luminal network of the patient. An EM field is a physical field generated by a charged object that affects the behavior of the charged object in the vicinity of the electric field. An EM sensor attached to the instrument when positioned within the generated electric field can be used to track the position and orientation of the instrument within the EM field. Small currents are induced in the EM sensor by the various EM fields. The characteristics of these electrical signals depend on the distance and angle between the sensor and the EM field generator. Thus, an EM navigation-guided bronchoscopy system can include an EM field generator, a steerable instrument having one or more EM sensors at or near its distal tip, and a guidance computing system. The EM field generator generates an EM field around the luminal network of the patient to be navigated, for example, the airway, gastrointestinal tract, or circulatory pathway. The steerable channel is inserted through the working channel of the bronchoscope and tracked within the EM field via the EM sensor.

[0084] Prior to the start of an EM navigation-guided bronchoscopy procedure, a virtual 3D bronchial model can be obtained for a patient's particular airway structure, for example, from a pre-operative CT chest scan. Using the model and the EM navigation-guided bronchoscopy system, the physician can navigate to a desired location in the lung for a biopsy lesion, stage lymph nodes, and insert markers to guide radiation therapy or guide a brachytherapy catheter. For example, an alignment can be performed at the start of the procedure to generate a mapping between the EM coordinate system and the model coordinate system. Thus, when an instrument is tracked during bronchoscopy, the position of the instrument in the model coordinate system is nominally known based on position data from the EM sensor.

[0085] Figure 16A illustrates an exemplary operating environment 100 for implementing one or more aspects of the disclosed navigation systems and techniques. The operating environment 100 includes a patient 101, a platform 102 supporting the patient 101, a surgical or medical robotic system 110 for guiding the movement of an instrument 115, a command center 105 for controlling the operation of the robotic system 110, an EM controller 135, an EM field generator 120, and EM sensors 125, 130. Figure 16A also illustrates an outline of a region of a lumen network 140 within the patient 101, which is shown in more detail in Figure 16B.

[0086] The system 110 may include one or more robotic arms for positioning and guiding the movement of the instrument 115 through the lumen network 140 of the patient 101. The command center 105 may be communicatively coupled to the robotic system 110 to receive position data and / or provide control signals from a user. As used herein, "communicatively coupled" refers to any wired and / or wireless data transfer medium, including, but not limited to, a wireless wide area network (WWAN) (e.g., one or more cellular networks), a wireless local area network (WLAN) (e.g., configured for one or more standards such as IEEE 802.11 (Wi-Fi)), Bluetooth, a data transfer cable, and / or the like. The robotic system 110 may be any of the systems described above in connection with FIGS. 1-15. An embodiment of the system 110 is discussed in more detail with respect to FIG. 16C, and the command center 105 is discussed in more detail with respect to FIG. 17.

[0087] The instrument 115 may be a tubular, flexible surgical instrument that is inserted into a patient's anatomy to capture images of the anatomy (e.g., body tissue) and provide a working channel for inserting other medical instruments into a target tissue site. As described above, the instrument 115 may be a procedure-specific endoscope, such as a bronchoscope, gastroscope, or ureteroscope, or may be a laparoscope or a vascular steerable catheter. The instrument 115 may include one or more imaging devices (e.g., cameras or other types of optical sensors) at its distal end. The imaging device may include one or more optical components, such as optical fibers, fiber arrays, photosensitive substrates, and / or lens(es). The optical components move with the tip of the instrument 115, such that movement of the tip of the instrument 115 results in a corresponding change in the field of view of the image captured by the imaging device. The distal end of the instrument 115 may be provided with one or more EM sensors 125 for tracking the position of the distal end within the EM field generated around the lumen network 140. The distal end of the instrument 115 is further described with reference to FIG. 18 below.

[0088] The EM controller 135 can control the EM field generator 120 to generate various EM fields. The EM fields can be time-varying and / or spatially-varying depending on the embodiment. In some embodiments, the EM field generator 120 can be an EM field generator board. Some embodiments of the disclosed patient navigation system can use an EM field generator board positioned between the patient and the platform 102 supporting the patient, and the EM field generator board can incorporate a thin barrier that minimizes any tracking distortion caused by conductive or magnetic materials located below it. In other embodiments, the EM field generator board can be mounted on a robotic arm, for example, similar to that shown in the robotic system 110, which can provide flexible setup options around the patient.

[0089] FIG. 16B illustrates an exemplary luminal network 140 that may be navigated within the surgical environment 100 of FIG. 16A. The luminal network 140 includes a branching structure of the airway 150 of the patient 101, a trachea 154 that leads to a main carina 156 (typically the first branch encountered during bronchoscopy navigation), and a nodule (or lesion) 155 that may be accessed as described herein for diagnosis and / or treatment. As illustrated, the nodule 155 is located at a distal end of the airway 150. The instrument 115 may include a sheath 141 having a first diameter such that the distal end of the sheath 141 cannot be positioned through the smaller diameter airway around the nodule 155. Thus, the scope 145 extends from the working channel of the instrument 115 the entire remaining distance to the nodule 155. The scope 145 may have a lumen through which an instrument, such as a biopsy needle, a cytological brush, and / or a tissue sampling forceps, may be passed to a target tissue site in the nodule 155. In such an embodiment, both the distal end of the sheath 141 and the distal end of the scope 145 may be provided with EM sensors for tracking their respective positions within the airway 150.

[0090] In some embodiments, a 2D representation of a 3D luminal network model described herein, or a cross-section of the 3D model, may resemble Figure 16B. Estimated position information may be overlaid onto such a representation.

[0091] Figure 16C illustrates an exemplary robotic arm 175 of the robotic system 110 for guiding movement of an instrument through the lumen network 140 of Figure 16B. The robotic arm 175 can include the robotic arms 12, 39 described above in some embodiments and is coupled to a base 180 which can include a cart base 15, column 37 or ceiling-based mount of a patient platform 38 in various embodiments. As described above, the robotic arm 175 includes multiple arm segments 170 coupled to linkages 165 that provide the robotic arm 175 with multiple degrees of freedom.

[0092] The robotic arm 175 may be coupled to an instrument manipulator 190, such as the instrument manipulator 62 described above, using, for example, a mechanism changer interface (MCI) 160. The instrument manipulator 190 can be removed and replaced with a different type of instrument manipulator, for example, a first type of instrument manipulator configured to operate an endoscope or a second type of instrument manipulator configured to operate a laparoscope. The MCI 160 includes connectors for transmitting air pressure, power, electrical signals, and optical signals from the robotic arm 175 to the instrument driver 190. The MCI 160 can be a set screw or a base plate connector. The instrument manipulator 190 manipulates instruments, such as the instrument 115, using techniques including direct drive, harmonic drive, gear drive, belt and pulley, magnetic drive, etc. The MCI 160 is interchangeable based on the type of instrument manipulator 190 and can be customized for a particular type of surgical procedure. The robot 175 arm can include joint level torque sensors and a wrist at the distal end.

[0093] The robotic arm 175 of the robotic system 110 can manipulate the instrument 115 using tendons as described above to deflect the tip of the instrument 115. The instrument 115 can exhibit non-linear behavior in response to forces applied by the elongated motion members. The non-linear behavior can be based on the stiffness and compressibility of the instrument 115, as well as slack or stiffness variability between different elongated motion members.

[0094] The base 180 can be positioned such that the robotic arm 175 has access to perform or assist in a surgical procedure on a patient, while a user, such as a physician, can control the robotic system 110 from the comfort of a command console. The base 180 can be communicatively coupled to the command console 105 shown in FIG. 16A.

[0095] The base 180 may include a power source 182, a pneumatic source 186, control and sensor electronics 184 (including components such as a central processing unit, a data bus, control circuits, and memory), and associated actuators (such as motors for moving the robotic arm 175). The electronics 184 may implement the navigation control techniques described herein. The electronics 184 in the base 180 may also process and transmit control signals communicated from a command console. In some embodiments, the base 180 includes wheels 188 for transporting the robotic system 110 and wheel locks / brakes (not shown) for the wheels 188. The mobility of the robotic system 110 helps to accommodate space constraints in a surgical room and facilitates proper positioning and movement of surgical equipment. Furthermore, this mobility allows the robotic arm 175 to be configured so that it does not interfere with the patient, physician, anesthesiologist, or any other equipment. During surgery, a user may control the robotic arm 175 using a control device, such as a command console.

[0096] 17 illustrates an exemplary command console 200 that can be used, for example, as the command console 105 in the exemplary surgical environment 100. The command console 200 can include a console base 201, one or more displays 202 (e.g., monitors), and one or more control modules (e.g., keyboard 203 and joystick 204). In some embodiments, one or more of the functions of the command module 200 can be integrated into the base 180 of the robotic system 110 or another system communicatively coupled to the surgical robotic system 110. A user 205, for example, a physician, uses the command console 200 to remotely control the robotic system 110 from an ergonomic position.

[0097] The console base 201 may include a central processing unit, memory unit, data bus, and associated data communication ports responsible for interpreting and processing signals, such as camera imaging data and tracking sensor data from the instrument 115 shown in FIGS. 16A-16C. In some embodiments, both the console base 201 and the base 180 perform signal processing for load balancing. The console base 201 may also process commands and instructions provided by the user 205 through the control modules 203 and 204. In addition to the keyboard 203 and joystick 204 shown in FIG. 17, the control modules may include other devices, such as controllers, such as a computer mouse, trackpad, trackball, control pad, handheld remote controller, and sensors (e.g., motion sensors or cameras) that capture hand and finger gestures. The controller may include a set of user inputs (e.g., buttons, joystick, directional pad, etc.) that map to or are linked to the instrument's motion (e.g., articulation, actuation, irrigation, etc.).

[0098] The display 202 may include an electronic monitor (e.g., liquid crystal display, LED display, touch-sensitive display), a virtual reality viewing device (e.g., goggles or glasses), and / or other display devices. In some embodiments, the display module 202 is integrated into the control module, for example, as a tablet device with a touch screen. In some embodiments, one of the displays 202 may display a 3D model of the patient's luminal network and virtual navigation information (e.g., a virtual representation of the end of the endoscope in the model based on the position of the EM sensor), while the other of the displays 202 may display image information received from a camera or another sensing device at the end of the instrument 115. In some implementations, the user 205 may both view data and input commands to the system 110 using the integrated display 202 and control module. The display 202 may display 2D renderings of the 3D image and / or the 3D image using a stereoscopic device, for example, a visor or goggles. The 3D image provides an "end view" (i.e., an endoscopic view), which is a computer 3D model showing the patient's anatomy. The "end view" provides a virtual environment of the patient's interior and the expected location of the instrument 115 within the patient. The user 205 compares the "end view" model with the actual image captured by the camera to help mentally orient and ensure that the instrument 115 is in the correct (or approximately correct) location within the patient's body. The "end view" provides information about the shape of the anatomical structures around the distal end of the instrument 115, such as the patient's airway, circulatory vessels, or intestines or colon. The display module 202 can simultaneously display a 3D model and a CT scan of the anatomical structures around the distal end of the instrument 115. Additionally, the display module 202 can overlay an already determined navigation path of the instrument 115 onto the 3D model and the CT scan image.

[0099] In some embodiments, a model of the instrument 115 is displayed along with the 3D model to help show the status of the surgical procedure. For example, a CT scan identifies lesions in the anatomy that may require a biopsy. During operation, the display module 202 can show a reference image captured by the instrument 115 that corresponds to the current position of the instrument 115. The display module 202 can automatically display different views of the model of the instrument 115 depending on user settings and the particular surgical procedure. For example, the display module 202 shows an overhead x-ray perspective of the instrument 115 during the navigation process as the instrument 115 approaches the surgical area of ​​the patient.

[0100] Figure 18 illustrates the distal end 300 of an exemplary instrument having imaging and EM sensing capabilities as described herein, such as the instrument 115 of Figures 16A-16C. In Figure 18, the distal end 300 of the instrument includes an imaging device 315, an illumination source 310, and an end of an EM sensor coil 305. The distal end 300 further includes an opening to the working channel 320 of the endoscope, through which surgical instruments such as biopsy needles, cytological brushes, and forceps can be inserted along the endoscope shaft, allowing access to areas near the endoscope tip.

[0101] The EM coils 305 located on the distal tip 300 can be used in conjunction with an EM tracking system to detect the position and orientation of the distal tip 300 of the endoscope while it is positioned within the anatomical system. In some embodiments, the coils 305 may be angled to provide sensitivity to EM fields along different axes, giving the disclosed navigation system the ability to measure a full six degrees of freedom (three positional and three angular degrees of freedom). In other embodiments, only a single coil may be located on or within the distal tip 300, with its axis oriented along the endoscope shaft of the instrument. Due to the rotational symmetry of such a system, it is insensitive to roll about its axis, and only five degrees of freedom may be detected in such embodiments.

[0102] B. Techniques for Position Sensor Alignment As described above, a position sensor can be used to track the position of a portion of an instrument (e.g., the distal end of the instrument) relative to a model of the patient's anatomy against which the instrument is driven during a medical procedure. It should be understood that the model may be generated based on pre-operative measurements and the position sensor may function based on an independent coordinate system. To accurately determine the position of the instrument using the position sensor, the position sensor coordinate system is aligned to the model coordinate system, which provides a transformation that can be applied to measurements from the position sensor to arrive at a corresponding position in the model coordinate system. FIG. 17 illustrates an exemplary command console 200 that can be used, for example, as the command console 105 in the exemplary operating environment 100. The command console 200 can include a console base 201, one or more displays 202 (e.g., monitors), and one or more control modules (e.g., keyboard 203 and joystick 204). In some embodiments, one or more of the functions of the command module 200 can be integrated into the base 180 of the robotic system 110 or another system communicatively coupled to the surgical robotic system 110. A user 205, e.g., a physician, uses the command console 200 to remotely control the robotic system 110 from an ergonomic position.

[0103] In certain implementations, the position sensor coordinate system can be aligned to the model coordinate system based on position sensor data taken while the instrument is driven within the patient's anatomy. The amount and type of data required to align the position sensor coordinate system to the coordinate system of the model of the anatomy may depend on the shape of a given anatomy. For example, one technique for aligning the position sensor coordinate system to the model coordinate system involves maintaining a history of data received from the position sensor and matching the shape formed by the position data history to a candidate path that the instrument can move based on the model of the anatomy. This technique may be more successful in finding an alignment between the position sensor coordinate system and the model coordinate system for anatomy that has a certain amount of asymmetry.

[0104] FIG. 19 illustrates an exemplary lumen network in which position sensor alignment may be performed according to aspects of the disclosure. In the embodiment of FIG. 19, the illustrated lumen network 400 corresponds to a patient's airway and includes a primary airway 405 (e.g., trachea) that branches at a main carina 410 into two secondary airways 415 and 420 (e.g., primary bronchi). Also illustrated is a target 425 (e.g., a lesion or nodule in the lumen network 400) to which the system can drive an instrument during a medical procedure. The target path 430 provides a planned path along which the instrument may be driven to reach the target 425. Depending on the embodiment, the system may automatically generate the target path 425 based on a preoperatively scanned model of the lumen network 400 and the location of the target 425. In other embodiments, the target path 425 may be selected by a user during preoperative planning. The system may display an illustration of the target path 430 relative to the model on a display to provide the user with an indication of the direction in which to drive the instrument to reach the target 425. In certain embodiments, the target pathway 430 may include only a direct pathway to the target 425 that does not traverse the same portion of the lumen network more than once (i.e., traversing the target pathway 425 does not involve advancing down a segment of the lumen network and retracting the instrument along the same segment).

[0105] As will be appreciated, the airways defined by the second branches 415 and 420 may not be symmetrical, but may instead have different lengths and form different angles with the first airway 405. In one particular alignment technique according to the present disclosure, so-called contralateral alignment, exploits this asymmetry between the branches 415 and 420 to improve alignment of the instrument. Embodiments may exploit the asymmetry by driving the instrument along the contralateral pathway 435, which may include driving the instrument to the second airway 415 that is contralateral to the airway on the target pathway 430, pulling it back to the first airway 405, and then driving it to the second airway on the pathway 430. As discussed below, embodiments may additionally include features that facilitate contralateral alignment, such as automatically detecting the contralateral branch 415 and automatically determining when the distance traversed by the instrument along the contralateral branch 415 is sufficient.

[0106] To better illustrate the use of the contralateral pathway 435, the paths or traces defined by the data output from the position sensors during the registration process (including the contralateral pathway 435) can be compared to various shapes defined by the model of the lumen network 400. Due to the asymmetric shape formed by the lumen network 400, the paths defined by the position sensor data during the registration process may uniquely correspond to the shapes defined by a single portion of the model of the lumen network 400, namely, each of the first and second airways 405 and 415 and 420. Thus, the registration between the position sensor coordinate system and the model coordinate system may be defined based on a transformation between the paths or traces defined by the position sensor data (e.g., the contralateral pathway 435) during the registration process and the shapes defined by each of the first and second airways 405 and 415 and 420.

[0107] 19 provides an example of a patient's airway as an embodiment of a lumen network, however aspects of the present disclosure may also be applied to alignment of position sensors used to navigate other lumen networks, particularly lumen networks that are at least partially asymmetric. For example, aspects of the present disclosure may be applied to gastrointestinal networks, urinary tracts, vascular networks, etc. Thus, aspects of the present disclosure relate to alignment of a position sensor based on position data received while driving an instrument along at least a portion of an asymmetric path within a lumen network.

[0108] FIGURE 20A is a flow chart illustrating an exemplary method operable by a surgical robotic system or components thereof for aligning a position sensor coordinate system to the contralateral side, according to aspects of the present disclosure. It should be understood that the steps of method 500 illustrated in FIGURE 20A may be performed by a processor of the surgical robotic system. For convenience, method 500 is described as being performed by a processor of the system. When relevant to the description of the various steps of method 500, reference is made to the lumen network 400 illustrated in FIGURE 19 for describing one embodiment of method 500 below.

[0109] The processor may be included as part of a system including an instrument having a set of one or more position sensors. The set of position sensors may be configured to generate position data indicative of a position of the set of position sensors in a position sensor coordinate system. The position sensors may be located at or near a distal end of the instrument (see, e.g., FIG. 18 ), such that the position data may indicate a position of the distal end of the instrument. The system may further include a set of instrument manipulators configured to control movement of the distal end of the instrument, and at least one computer readable memory in communication with the processor and having stored therein a model of the patient's luminal network. The model may include targets and paths to the targets in the model coordinate system. The memory may further store computer executable instructions for causing the set of processors to perform the method 500.

[0110] The method 500 starts at block 501. At block 505, the processor provides a first set of commands to a set of instrument manipulators to drive an instrument along a first branch (e.g., the contralateral branch 415) of the lumen network. In some embodiments, the first set of commands may be generated based on user input received from a set of one or more user input devices. Thus, the processor can provide user instructions to a user, including instructions to follow a set of movements associated with the alignment process (e.g., to drive the instrument along a first portion of the contralateral alignment path 435). The system can then receive user input corresponding to the user instructions and generate a first set of commands for the movement of the instrument along the first branch. As shown in FIG. 19, the first branch 415 is located at the target 430 outside the target path 430. Thus, the first set of commands can cause the instrument manipulators to drive the instrument down the contralateral branch 415 along the first portion of the contralateral alignment path 435.

[0111] In block 510, the processor tracks a set of one or more alignment parameters while driving the instrument along the first branch. The alignment parameters may be any data that can be tracked by the system and used to determine whether sufficient data has been collected by the system to perform alignment between the position sensor coordinate system and the model coordinate system. In block 515, the processor determines that the set of alignment parameters meets the alignment criteria. The alignment parameters that meet the alignment criteria may indicate the instrument moving a sufficient distance along the contralateral branch 415, and the alignment process can continue with the instrument retracting back to the target path 430. A more detailed embodiment for tracking the alignment parameters and determining whether the alignment parameters meet the alignment criteria is provided below in connection with FIG. 20B.

[0112] In block 520, the processor provides a second set of commands to the set of instrument manipulators to return the instrument to the target path 430 and drive the instrument along a second branch (e.g., side branch 420). As shown in FIG. 19, the branch 420 is located along the target path 430 to the target 425. The processor may drive the instrument along the remaining portion of the contralateral alignment path 435, which continues down the side branch 420.

[0113] At block 525, the processor determines an alignment between the position sensor coordinate system and the model coordinate system based on position data received from the set of position sensors while driving the instrument along the first branch and the second branch (e.g., along the contralateral alignment path 435). By verifying that the alignment parameters meet the alignment criteria at block 515 before providing a command to retract the instrument into the side branch 420, the processor can ensure that sufficient position data is collected to determine alignment. The method 500 ends at block 530.

[0114] In certain embodiments, the alignment between the position sensor coordinate system and the model coordinate system may be further based on the first command set referenced in step 505 and the second command set from step 520. That is, the first and second command sets may be robotic data provided to the instrument manipulator to control the movement of the instrument. Because the first and second command sets are used to control the movement of the instrument, the processor may determine the position of the instrument when moved based on the first and second command sets. Thus, the processor may determine the position of the distal end of the instrument relative to the model based on the robotic data used to drive the instrument. As an example, if the distal end of the instrument is located at or near the keel (see keel 410 shown in FIG. 19 ) and is positioned to drive below the first branch (e.g., the contralateral branch 415), after providing an insert command to the instrument, the processor may determine that the distal end of the instrument has been inserted into the first branch by the amount indicated in the insert command.

[0115] The processor may be further configured to generate the first and second sets of commands to be provided to the instrument manipulator based on user input received from the set of one or more user input devices. Thus, actuation of the instrument may be performed manually based on user input received by the system.

[0116] As described above, the alignment may include a transformation that can map data from the position sensor coordinate system to the model coordinate system. The transformation may include a translation and / or rotation that can be applied to the position sensor data. To assist in determining an alignment that accurately maps data from the position sensor coordinate system to the model coordinate system, the processor can identify known locations in each of the two coordinate systems that can be used as anchors between the position sensor coordinate system and the model coordinate system. With reference to FIG. 19, the keel 410 can be automatically identified from the model of the lumen network, and the user can easily navigate the instrument to the keel 410 and provide feedback to the processor indicating the location of the keel 410.

[0117] In certain embodiments, the system may also generate guidance instructions to determine an anchor point at a known location in each of the position sensor coordinate system and the model coordinate system. The guidance instructions may include instructions to the user to drive the distal end of the instrument to contact the keel 410 and then retract the instrument after touching the keel 410. Based on the user input, the processor may provide commands to drive the instrument to the keel 410 and retract the instrument after reaching the keel 410. Thus, by identifying the position of the instrument immediately prior to retraction, the processor can determine that the identified position in the position sensor coordinate system corresponds to the position of the keel 410. The position of the keel 410 in each of the two coordinate systems can then be used as a piece of data to determine a transformation that maps the position sensor coordinate system to the model coordinate system.

[0118] In another exemplary embodiment, rather than requiring the user to indicate the location of the keel 410 by retracting the instrument, the processor may use a camera included at the distal end of the instrument to determine the location of the instrument relative to the model. The user may use images captured by the camera and provided to a display to navigate through the lumen network. In one embodiment, the images acquired by the camera may be displayed to the user in real time. The processor may be configured to determine the position of the distal end of the instrument based on an analysis of the images received from the camera. Any image processing technique capable of determining internal features of the lumen network may be used to determine the position of the distal end of the instrument relative to the model. The processor may further determine that the distal end of the distal end of the instrument is within a threshold distance from a first location (e.g., the keel 410) based on the determined position of the distal end of the instrument.

[0119] FIGURE 20B is a flow chart illustrating an exemplary method operable by a surgical robotic system or components thereof for determining whether sufficient position data has been received to facilitate contralateral registration, according to aspects of the present disclosure. It should be understood that the steps of method 550 illustrated in FIGURE 20B may be performed by a processor of the surgical robotic system. For convenience, method 550 is described as being performed by a processor of the system. The steps of method 550 may be performed as an embodiment of blocks 510 and 515 of FIGURE 20A.

[0120] The method 550 begins at block 551. At block 555, a processor receives raw position data and status data. As used herein, "raw position data" may refer to position data that indicates a position in a position sensor coordinate system. Thus, "raw position data" may be position data that represents a position in an instrument coordinate frame rather than a model coordinate frame. Prior to performing an alignment process and determining an alignment between the position sensor coordinate system and the model coordinate system, the processor cannot map the position sensor data to the model coordinate system. Thus, it will be understood that position data received prior to completion of the alignment process is unregistered or raw position data.

[0121] State data may refer to data generated by a processor that indicates the position of the instrument within the model. For example, the localization system 90 shown in FIG. 15 may be used to generate position data 96 (also referred to as state data) that can be used in methods 500 and 550. The state data may include depth information, such as the current depth of the instrument within a given segment, or the insertion depth within the anatomical model. The state data may also include the orientation of the distal end of the instrument within the model coordinate frame. In certain embodiments, the processor may receive raw position data and state data through a registration process 500 shown in FIG. 20A.

[0122] At block 560, the processor may store position and status data collected during an alignment process, such as the alignment process performed by method 500. The alignment process may include a choreographed set of instrument movements that may relate to the shape of the lumen network. The set of movements may also be based on a defined target path 430 to a target 425 in the model. The alignment process may include providing a first set of commands to a set of instrument manipulators to drive the instrument along a first branch of the lumen network, the first branch being on the contralateral branch 415 and therefore outside the target path 430 to the target 425. The alignment process may also involve providing commands to return the instrument to the target path 430 to the target site 425 and continue along the path. The choreographed set of movements may include a set of commands required to drive the distal end of the instrument along a path defined by the contralateral alignment path 435. The processor may track a set of one or more alignment parameters, such as depth information, while driving the instrument along the first branch.

[0123] At block 565, the processor may determine whether sufficient position sensor data has been collected as part of the contralateral phase of the alignment process based on the tracked alignment parameters. In one embodiment, the processor may use alignment parameters such as depth information (e.g., the insertion depth of the instrument) to determine whether the instrument has been driven a sufficient distance along the contralateral branch 415 of the contralateral pathway 435. In one particular embodiment, after one alignment criterion is met, the processor may provide a second set of commands to the set of instrument manipulators to return the instrument to the target pathway 430 and to drive the instrument along the second branch toward the target site. As the instrument continues along the target site, the processor may continue to track instrument position and status data for the alignment process.

[0124] By determining whether the instrument has been driven a sufficient distance along the contralateral branch 415, the system can reduce the amount of input required from the user, thereby reducing the opportunity for user error. For example, a particular alignment process may require the user to drive to multiple defined positions and provide an input to the system indicating that the instrument has been driven to the defined positions. By eliminating this type of required user input, aspects of the present disclosure can improve the ease of the alignment process and reduce potential sources of user error.

[0125] At block 570, the processor may use position and state data tracked during the registration process (e.g., position and state data tracked along the contralateral path 435 and the target path 430) to register the position coordinate system to the model coordinate system. As described above, this may include matching the shape of the path taken by the instrument when tracked using the position sensor to the shape of the lumen network defined by the skeletal structure of the model. In certain embodiments, the shape of the model having the lowest difference from the tracked path is selected and used to determine the registration between the position sensor coordinate system and the model coordinate system. It should be appreciated that because the tracked path includes the contralateral branch 415, embodiments may reduce the likelihood that the tracked path will match other candidate paths in the model. The method 550 ends at block 575.

[0126] In determining the alignment, the processor may be further configured to match a shape defined by the history of the position sensor data and the robot data. Thus, in certain embodiments, the processor may be configured to generate a set of position data points representing a position of the distal end of the instrument relative to the position coordinate system while driving the instrument along the contralateral alignment path. The processor may further generate a set of model points representing a position of the distal end of the instrument relative to the model coordinate system while driving the instrument along the contralateral alignment path. The processor may generate the model points based on the history of the robot data and the model. The two sets of points may be used by the processor to determine an alignment between the position coordinate system and the model coordinate system based on determining an alignment that maps the set of position data points in the position coordinate system to a second set of model points in the model coordinate system.

[0127] FIG. 21 is a diagram illustrating positional data for a model of a luminal network, according to an embodiment of the present disclosure. In the example of FIG. 21, the diagram 600 includes a model 602 of a preoperative scan of the luminal network, which may also include a skeleton 605 defined by midpoints or center points along each of the airways defined by the model 602. Specifically, the skeleton 605 includes a series of segments, each located at the midpoint of a corresponding lumen in the luminal network. Also shown is ground truth data 610 representing the actual or true position of the distal end of the instrument during the contralateral registration process relative to the anatomical structure. The ground truth data 610 shown in FIG. 21 may be generated by a test tool that is not normally used during the procedure to highlight the accuracy of the contralateral registration process. In the illustrated example, the target 625 may be located on the left side of the diagram. Thus, during the registration procedure, the instrument may be driven from the first airway 630 into the contralateral second airway 635. The instrument may then be retracted into the primary airway 630 and advanced into a lateral secondary airway 640 located along the path to the target 625 .

[0128] The system may also track state data 615 representing the position of the instrument along the skeleton of the model 605. As described above, the processor may determine the state data based on data received from one or more different data sources of data indicative of the position of the distal end of the instrument (e.g., via the localization module 95 of FIG. 15 ). Once sufficient data is received during the alignment process, an alignment transformation may be applied to the raw position data to generate aligned position data 620. As shown in FIG. 21 , the aligned position data 620 may closely track the ground truth data 610. After the position data is aligned, the processor may use the aligned position data 620 as an input in determining the state data 615.

[0129] 22 illustrates an example of alignment of position data without preforming a contralateral alignment process, according to an aspect of the disclosure. In this example, if the contralateral alignment process is not performed (e.g., the instrument is not driven down the contralateral branch), the raw position data 705 may substantially match two different candidate paths 710 and 715 in the model. That is, each of the two candidate paths 710 and 715 may have a similar shape such that a rotation and / or translation of the raw position data 705 may substantially match both paths 710 and 715. However, because the two paths 710 and 715 diverge, selecting the incorrect path 715 for alignment may cause the position data to provide an inaccurate indication of the position of the instrument when driven through the branch between the two paths 710 and 715. In contrast, by performing a contralateral alignment process according to an embodiment of the present disclosure, the erroneous candidate alignment path 715 may be removed from the set of candidate alignments because the alignment based on the erroneous candidate alignment path 715 does not match the shape along the contralateral path taken by the instrument (see, e.g., FIG. 21 ).

[0130] As described above, the contralateral registration procedure can provide more accurate and more robust registration when the first branch and the second branch are asymmetric (e.g., the second gen segment). Thus, in certain embodiments, the processor may select an asymmetric branch of the lumen network for the contralateral registration procedure. This selection of a location within the lumen network can also reduce the number of possible solutions to the match between the position data and the model, resulting in a more robust registration procedure. In the example of bronchoscopy, driving the instrument to the contralateral branch before proceeding along the path to the target can provide sufficient raw position data to facilitate registration of the position sensor to the model coordinate system. Thus, in certain embodiments, the first branch is located on the contralateral side of the lumen network relative to the target.

[0131] C. Position Sensor Alignment Plan Aspects of the present disclosure also relate to pre-operative planning, which may involve determining instructions and / or criteria related to a position sensor alignment procedure. FIG. 23 is a flow chart illustrating an exemplary method operable by a surgical robotic system or components thereof for pre-operative planning, according to aspects of the present disclosure. A procedure 800 for pre-operative planning may be operable by a surgical robotic system or components thereof for pre-operative planning, according to aspects of the present disclosure. For example, aspects of the method 800 for pre-operative planning may be executed by a command console, such as the command console 200 illustrated in FIG. 17, or may be executed by a processor (or set of processors) of the surgical robotic system, which may be included as part of the command console. For convenience, the method for pre-operative planning is described as being executed by a processor of the system. In certain embodiments, the system may also include at least one computer-readable memory in communication with the set of processors and having stored therein a model of the patient's luminal network. The model includes targets and paths to the targets in the model coordinate system. The memory may also store computer-executable instructions that cause the set of processors to execute the method 800.

[0132] Method 800 begins at block 801. At block 905, a processor provides instructions to display the luminal network via a display device. In particular, the processor may provide instructions to display the luminal network via a display device. This may involve, for example, the processor retrieving a model of the luminal network from a memory and displaying the model for viewing by a user. Displaying the model may include, for example, displaying a 3D model of the luminal network generated based on a pre-operative scan of the luminal network. In other embodiments, displaying the model may involve displaying a skeletal and / or more detailed segmented image generated based on a pre-operative scan of the luminal network (as shown in FIGS. 19, 21, and 22).

[0133] At block 810, the processor receives an indication of a location of a target in the model coordinate system. For example, the processor may receive from a user via a user input device an indication of a target portion of the model where at least a portion of a medical procedure will be performed. The target may be, for example, a desired location in a lung for biopsying a lesion, staging a lymph node, inserting a marker to guide radiation therapy or to guide a brachytherapy catheter. In other embodiments, the system may automatically detect or otherwise determine the target location 425 based on detecting features indicative of a tumor in a pre-operative scan.

[0134] In block 815, the processor identifies a first branch in the lumen network (e.g., a branch located on the contralateral side of the lumen network, such as contralateral branch 415 in FIG. 19 ) and a second branch in the lumen network (a branch located on a lateral side of the lumen network, such as lateral branch 420 in FIG. 19 ). Because the identified first and second branches are located on the contralateral and lateral sides of the lumen network, respectively, with respect to the location of the target, the first branch may be located outside the path to the target and the second branch may be located along the path to the target.

[0135] In certain embodiments, based on the model and the selected target, the processor may automatically identify certain segments of the model that may be traversed by the instrument to assist in aligning the position sensor. This may include the processor identifying the first branch as a branch located on the contralateral side of the lumen network and the second branch as a branch located on the lateral side of the lumen network. In certain embodiments, the first and second branches may be second-generation branches of the lumen network, such as branches 415 and 420 shown in FIG. 19. The processor may be further configured to determine that the shape formed by the first and second branches is sufficiently unique within the lumen network such that when the instrument is driven along the contralateral registration path defined by the second-generation branch, no other shape in the model will match the path taken by the instrument during the contralateral registration process. This determination may be performed by comparing the shapes of the first and second branches with other possible shapes in the model to determine whether any possible discrepancies in the shapes exist.

[0136] As mentioned above, certain registration processes may require the user to drive the instrument to multiple defined locations within the lumen network and provide an indication to the system when the instrument is at the defined location. This technique may also require the user to identify the defined locations during the pre-operative planning stage. However, the processor may automatically identify a contralateral path that can be used for the registration process, thereby reducing the steps required for the user during the pre-operative planning stage.

[0137] In block 820, the processor generates a set of guidance instructions for driving the distal end of the instrument along the first branch, returning from the first branch, and driving along the second branch. The set of instructions may thus define a contralateral alignment path, such as the contralateral alignment path 435 of FIG. 19. The guidance instructions may be stored in a memory that is provided to the user during the medical procedure. During the medical procedure, while driving the instrument according to the instructions, the position data received from the set of one or more position sensors may facilitate alignment between the position coordinate system of the position data and a model coordinate system. The alignment may include at least one of a translation and a rotation between the position coordinate system and the model coordinate system. In block 825, the processor determines an alignment criterion for one or more alignment parameters tracked while driving the instrument along the first branch. The method 800 ends in block 830.

[0138] The alignment criteria may relate to the amount of position data required for alignment of the position sensor coordinate system to the model coordinate system. For example, the criteria may specify the required travel distance of the instrument along the contralateral branch before the instrument can be returned to the pathway from the first branch. The alignment criteria may also depend on the particular shape of the patient's anatomy. For example, some patients' airways may have a greater discrepancy between the shape and angle formed between the first branch and the second branch than other patients. If the difference between the first branch and the second branch is more pronounced, the instrument may not need to travel that far down the first branch to receive enough data for alignment. In other embodiments, the alignment criteria may be set based on a threshold determined to provide sufficient position data for alignment for a majority of patients for the particular procedure being performed.

[0139] The alignment parameters may include an insertion depth of the instrument into the contralateral branch. In this embodiment, the set of alignment parameters meets the alignment criterion in response to an insertion depth into the first branch being greater than a threshold insertion depth. For example, the alignment criterion may include instructions to drive the instrument along at least 50% of the contralateral branch before returning to the first branch on the path. The particular values ​​may vary depending on the particular anatomical structures involved in the medical procedure and / or based on an analysis of variations in the shape of the anatomical structures in the general population.

[0140] Depending on the particular medical procedure, the processor may also determine whether the first branch and the second branch are asymmetric. The processor may identify the first and second branches in response to determining that the first and second branches are asymmetric. As described above, the registration process may be more accurate for asymmetric paths and / or asymmetric shaped luminal networks. Thus, the processor may select a branch point in the luminal network that has an asymmetric shape relative to where the registration process is performed. In certain embodiments, such as in the case of an airway, one branch where the registration process may be performed is a branch from the trachea into the main bronchus. Thus, the processor may identify the first branch in response to further determining that the first branch is located on the contralateral side of the luminal network relative to the target.

[0141] In one particular embodiment, the set of instructions includes instructions to drive the instrument to a first position within the lumen network. The first position may be a position identifiable by the user during the medical procedure that can provide a known position within each of the position sensor coordinate system and the model coordinate system. For example, during a bronchoscopy procedure, the first position may correspond to the patient's carina. The carina may be identified within the model based on its location at the bifurcation between the main bronchi, and the user may be able to drive to the carina prior to alignment of the position data. In this embodiment, the first and second bifurcations may correspond to the patient's main bronchi. While the distal end of the instrument is within a threshold distance from the first position, alignment between the position sensor coordinate system and the model coordinate system may be further based on position data received from the set of position sensors. By using the first position as a known reference point between the position coordinate system and the model coordinate system, the number of permutations for alignment may be limited. Additionally, the user instructions may include instructions to retract the instrument after touching the carina. This retraction may be interpreted as an indication of the position of the carina, which may be used as the first position during the alignment procedure.

[0142] D. Overview of Weight-Based Alignment of Position Sensors As discussed above in connection with FIG. 15, certain techniques for locating the distal end of the medical instrument may include combining inputs from different sensors / sources to determine the location of the distal end of the medical instrument. These inputs may include a position sensor (e.g., EM sensor) at the distal end of the instrument, an image sensor (e.g., camera) at the distal end, and / or robotic insertion data (e.g., robotic commands and kinematic data). In one example, the three algorithm modules (e.g., EM-based, robotic-based, and image-based) may output estimated state data for each of the positions of the distal end of the instrument to a sensor fusion module (e.g., localization module 95 of FIG. 15) that combines information from the three algorithm modules to generate an output of the navigation framework. In some implementations, the localization algorithm may provide a probability for the current position of the distal end of the medical instrument (e.g., with reference to a model of the patient's lumen network, which may be defined by segment ID and depth / insertion within the corresponding segment). One example of a model is a skeleton that may be generated based on the centerline of the lumen network. Model position points may be defined along the skeleton such that a representation of the position of the distal end of the medical instrument is along the centerline / skeleton of the corresponding lumen. Additionally, some implementations of the branch prediction algorithm can provide probabilities as to which child lumen of the current lumen the medical instrument is driving toward (e.g., the probability of each child lumen that the medical instrument may enter the corresponding lumen).

[0143] In some implementations, a position sensor alignment algorithm is used to calculate the transformation between the sensor coordinate system (e.g., EM sensor space) and the model coordinate system (e.g., CT / skeleton space). Each of the position sensor localization algorithm module and the position sensor branch prediction algorithm module can determine an aligned pose of the distal end of the medical instrument in the model coordinate system, which can be used by each position sensor algorithm module to determine algorithm output values ​​(e.g., the current position of the distal end of the medical instrument and the probability that the medical instrument will enter each of the child lumens).

[0144] 24 is a flow chart illustrating an example method 900 operable by a surgical robotic system or component(s) thereof to determine alignment between a sensor coordinate system and a model coordinate system, according to aspects of the present disclosure. It should be understood that the steps of the method 900 illustrated in FIG. 24 may be performed by a processor of the surgical robotic system. For convenience, the method 900 is described as being performed by a processor of the system.

[0145] The processor may be included as part of a system including an instrument having a set of one or more position sensors. The set of position sensors may be configured to generate position data indicative of a position of the set of position sensors in a position sensor coordinate system. The position sensors may be located at or near a distal end of the instrument (see, e.g., FIG. 18 ), such that the position data may indicate a position of the distal end of the instrument. The system may further include a set of instrument manipulators configured to control movement of the distal end of the instrument, and at least one computer readable memory in communication with the processor and having stored therein a model of the patient's luminal network. The model may include targets and paths to the targets in the model coordinate system. The memory may further store computer executable instructions for causing the set of processors to perform the method 900.

[0146] The method 900 may begin at block 901. At block 902, a processor receives position data from a set of position sensors and receives status data indicative of a current state of the distal end of the instrument. In certain implementations, the status data may be generated by a sensor fusion module (e.g., localization module 95 of FIG. 15) based on a combination of information from various algorithmic modules (e.g., EM-based, robotic-based, and image-based). In some implementations, the method 900 may include a registration algorithm that may be used to calculate a rigid body transformation (e.g., registration) that represents a homogeneous transformation between a sensor coordinate system of the position sensors (e.g., based on the positions of the field generators when the position sensors include EM sensors) and a model coordinate system. The transformation may then be used to transform any pose of the distal end of the medical instrument from the position sensor coordinate system to the model coordinate system.

[0147] At block 904, the processor performs contralateral registration and maintains skeletal position history (also referred to as model position history) and position sensor position history. For example, the processor may perform contralateral registration according to methods 500 and 550 described in connection with Figures 20A and 20B. Additionally, the processor may maintain skeletal position data by storing state data and maintain position sensor position history by storing position data. In some implementations, the skeletal position history and the position sensor position history may be formatted as a point cloud representing the position of the distal end of the instrument over time.

[0148] The position sensor history point cloud and the corresponding model history point cloud can be used as inputs to determine the registration transformation. Depending on the implementation, various techniques can be used to determine the registration. For example, the registration can be determined using a singular value decomposition (SVD) technique, an iterative closed point (ICP) technique, or any other technique that can determine the registration between two coordinate systems.

[0149] At block 906, the processor determines whether a pre-registration condition has been satisfied. In some implementations, determining whether a pre-registration condition has been satisfied may include determining whether sufficient data has been collected for each of the skeleton position history and the position sensor position history for registration. In some implementations, the processor may determine that sufficient data has been collected in response to one or more of the following conditions being satisfied: the instrument is positioned, for example, in a second generation segment (or a third generation segment, etc.); the instrument has advanced at least a threshold distance (or at a threshold speed) into the second generation segment; and / or the size (e.g., number of data points) of the skeleton position and the position sensor position history is greater than a threshold size (e.g., the size / amount of data of the skeleton position history meets / exceeds a first threshold, the size / amount of data of the position sensor position history meets / exceeds a second threshold, and / or the size / amount of data of the skeleton position history and the position sensor position history meets / exceeds a third threshold).

[0150] At block 908, the processor determines an initial alignment based on the skeletal position history and the position sensor position history. The alignment determination may be performed, for example, as described above in connection with block 525 of FIG. 20A and / or block 570 of FIG. 20B. Using the determined alignment, the system may determine an aligned pose of the distal end of the medical instrument by applying the alignment to the position sensor data. At block 910, the processor determines whether including additional points from the position sensor history point cloud in the alignment would result in an error greater than a threshold error. The determination at block 910 may be performed for each point in the position sensor history point cloud as the instrument advances through the lumen network. In response to the error being greater than the threshold error, the method 900 includes fixing or maintaining the alignment at block 912 and continuing the procedure at block 916.

[0151] However, in response to the error being less than or equal to the threshold error, the method 900 includes updating the registration (or re-determining the registration) based on additional points from the position sensor history point cloud at block 914. In some implementations, the processor may update the registration at block 910 using points from the position sensor history point cloud that result in an error less than or equal to the threshold error.

[0152] For example, some user-driven actions or tendencies, such as the approach of the medical instrument to the luminal wall (e.g., distorting the medical instrument toward the wall, contacting the wall, driving the medical instrument away from or off the centerline of the luminal passageway, and / or otherwise driving the medical instrument along a path displaced from the centerline of the luminal passageway), or bending of the medical instrument, may cause a level of mismatch between the registered position sensor points and the corresponding points on the model. FIG. 25 illustrates an example in which sensor location points and model location points are superimposed on a model in a model coordinate system, according to aspects of the present disclosure. Specifically, in the image of FIG. 25, the sensor location points 1002 and the model location points 1004 are illustrated with respect to a model (e.g., skeleton) 1006. The illustrated sensor location points 1002 are transformed to the model coordinate system based on the initial registration determined in block 908, which in some examples may be completed after the contralateral registration in block 902.

[0153] To improve the accuracy of the registration and robustness against suboptimal driving behaviors such as approaching the airway wall, certain aspects of the disclosure relate to the use of weight-based registration after the contralateral step is completed and the initial registration is calculated. Thus, if the error determined in block 912 is greater than a threshold error, the method 900 includes the processor updating the initial registration in block 914. In some implementations, updating the initial registration includes using a weight-based registration technique described in more detail below. As discussed below, the weight-based registration can include determining and assigning different weights to the position sensor points and model points used during registration. In block 916, the processor continues the procedure using the registration determined by the method 900. The method 900 may begin in block 918.

[0154] E. Exemplary Techniques for Determining Weights to Use in Registration In certain implementations, the initial alignment can be modified (e.g., at block 914 of method 900) by determining and assigning different weights to corresponding sensor and model position points and re-determining the alignment using the weights.

[0155] In certain implementations, the weights may be calculated based on i) the position sensor points 1002 transformed into the model coordinate system after the initial alignment is determined, and ii) the model position points 1004. Figure 25 shows the distance between the transformed position sensor points 1002 and the model position points 1004.

[0156] In one or more embodiments, each of the weights may be set to a value between 0 and 1. There are many different techniques that may be used by the processor to determine the weights. In one embodiment, the processor may determine or assign the weights in proportion to the distance between the location sensor point 1002 and the model location point 1004. For example, the nth weight may be determined using the following formula:

[0157]

number

[0158] In another embodiment, the weights may be binary (e.g., 0 or 1). For example, the processor may determine the weights based on a comparison of the distance to a distance threshold (e.g., 5 mm), where a weighting factor of 0 is assigned to a given point (e.g., sensor location point) if the distance between the sensor location point and the model location point is equal to or greater than 0.5 or another distance threshold, and a weighting factor of 1 is assigned to the given point if the distance between the sensor location point and the model location point is less than the threshold. The distance threshold corresponds to an acceptable level of difference between the sensor location point and the corresponding model location point, and may be set based on clinical requirements and / or user preferences as to what level of difference is considered acceptable. FIG. 27 illustrates another example for determining binary weights based on distance. Specifically, FIG. 27 includes a first graph 1202 of distances between transformed sensor location points and model location points, and a second graph 1204 of corresponding weights.

[0159] 28 illustrates yet another example for determining binary weights based on distance, according to aspects of the disclosure. For example, the processor may assign weights by filtering each intraluminal point based on distance. A percentage of each intraluminal point having a minimum distance may be assigned a weight of 1, and the remaining points may be assigned a weight of 0. This embodiment is illustrated in FIG. 28 with a first set of points 1302 having a weight of 1 and a second set of points 1304 having a weight of 0.

[0160] In some implementations, the processor may calculate distance-based weights once for the contralateral registration points after the initial registration is determined. These weights may be applied to the same points in subsequent cycles of registration (FIG. 24), while the processor may assign a weight of 1 to the remaining points accumulated for further generations (e.g., second generation or more) of registrations.

[0161] In other embodiments, rather than determining the weights just once for the contralateral points, the processor can determine and update the weights iteratively or periodically as the distal end of the medical instrument advances to further generations and the registration is updated. The processor can also determine weights for the registration points that are accumulated for further generations. The processor can maintain a history of weights / distances in memory determined for previous points and can set constraints on how much the weights can change as a result of registrations calculated later during the procedure.

[0162] In some embodiments, the processor may adaptively increase the weighting proportional to the lumen diameter as the medical device is advanced into the lumen network. At early generation points (where the diameter of a given lumen is large), the weighting may be smaller, and at further generation points, the weighting may be larger as smaller diameter lumens are more likely to diverge from the centerline path.

[0163] In certain implementations, rather than using the initial alignment and the distance of the transformed sensor location to the centerline of the model to determine the weights, the processor can use a vision algorithm to evaluate a metric of centerline drive by tracking the contour of the airway as seen from the image captured by the camera of the instrument to determine the weights. The processor can also use the robot joint data as another input to identify the centerline drive of the medical instrument to determine the weights based on the distance of the position sensor point from the centerline. For example, a larger weight can be assigned to corresponding points where the user is driving the distal end of the medical instrument closer to the centerline, and a smaller weight can be assigned to points where the distal end of the medical instrument is not facing the centerline (closer to the lumen wall).

[0164] Aspects of the present disclosure can improve the robustness of registration algorithms associated with continuously aligning sensor positions to model points throughout a procedure. For example, by weighting the position sensor points used in determining the registration, a processor can improve the accuracy of the registration by weighting more heavily points located closer to the skeletal model while reducing the influence or effect of points farther away from the skeleton when determining or performing the registration.

[0165] Aspects of the present disclosure may also be applicable to other techniques for aligning two sets of 3D point clouds (e.g., EM points and skeletal model points), including shape-sensing-based and / or other sensor-based solutions.

[0166] 3. Mounting system and terminology SUMMARY OF THE DISCLOSURE The embodiments disclosed herein provide systems, methods, and apparatus for aligning a position sensor to a model coordinate system.

[0167] It should be noted that, as used herein, the terms "couple," "coupled," "coupled," or other variations of the word couple, may indicate either an indirect connection or a direct connection. For example, when a first component is "coupled" to a second component, the first component may be either indirectly connected to the second component through another component, or directly connected to the second component.

[0168] The functions described herein may be stored as one or more instructions on a processor-readable medium or computer-readable medium. The term "computer-readable medium" refers to any available medium that can be accessed by a computer or processor. By way of example, and not limitation, such media may include random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory, compact disk read-only memory (CD-ROM), or other optical disk storage, magnetic disk storage, or other magnetic storage devices, or any other medium that can be used to store desired program code in the form of instructions or data structures and that can be accessed by a computer. It should be noted that computer-readable media may be tangible and non-transitory. As used herein, the term "code" may refer to software, instructions, code, or data that is executable by a computing device or processor.

[0169] The methods disclosed herein include one or more steps or acts for achieving the described method. Method steps and / or acts may be interchanged with one another without departing from the scope of the claims. In other words, unless a specific order of steps or acts is required for the proper operation of the described method, the order and / or use of specific steps and / or acts may be modified without departing from the scope of the claims.

[0170] As used herein, the term "plurality" refers to two or more. For example, a plurality of components refers to two or more components. The term "determining" encompasses a wide variety of acts, and thus "determining" can include calculating, computing, processing, calculating, investigating, looking up (e.g., looking in a table, database, or another data structure), ascertaining, and the like. "Determining" can also include receiving (e.g., receiving information), accessing (e.g., accessing data in a memory), and the like. "Determining" can also include resolving, selecting, choosing, establishing, and the like.

[0171] The phrase "based on" does not mean "based only on," unless expressly specified otherwise. In other words, the phrase "based on" describes both "based only on" and "based at least on."

[0172] The foregoing description of the disclosed implementations is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these implementations will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other implementations without departing from the scope of the present invention. For example, those skilled in the art will recognize that many corresponding alternative and equivalent structural details may be employed, such as equivalent methods of fastening, mounting, coupling, or engaging tool components, equivalent mechanisms for producing specific actuation motions, and equivalent mechanisms for delivering electrical energy. Thus, the present invention is not intended to be limited to the implementations shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0173] [Embodiment] (1) A system comprising: an instrument comprising a set of one or more position sensors configured to generate position data indicative of a position of a distal end of the instrument in a sensor coordinate system; a set of one or more processors; at least one computer readable memory in communication with the set of one or more processors and storing a model of the patient's luminal network with respect to a model coordinate system; the memory further comprising computer-executable instructions stored in the memory, the computer-executable instructions causing the one or more processors to: generating a set of sensor position points in the sensor coordinate system based on the position data generated by the position sensor; determining a set of model position points in the model coordinate system; determining an initial alignment between the sensor coordinate system and the model coordinate system based on the set of sensor location points and the set of model location points; determining a set of weight values ​​corresponding to the set of sensor location points; determining an updated alignment between the sensor coordinate system and the model coordinate system based on the set of sensor location points, the set of model location points, and the set of weight values. system. (2) the model includes a skeleton defined by midpoints along lumens of the lumen network; The computer executable instructions further cause the one or more processors to: Transforming the sensor location points from the sensor coordinate system to the model coordinate system using the initial alignment; determining a distance between each of the transformed sensor location points in the model coordinate system and the skeleton; 2. The system of claim 1, wherein the determination of the weight value is further based on a distance between the transformed sensor position point and the skeleton. (3) The system of embodiment 2, wherein the set of weight values ​​is binary. (4) the computer-executable instructions further cause the one or more processors to: comparing each distance between each of the transformed sensor location points and the skeleton to a distance threshold; A system as described in embodiment 3, further comprising having each of the transformed sensor position points assigned one of the binary weight values ​​based on the comparison. (5) the model further includes diameter values ​​of the lumens of the lumen network; The system of embodiment 1, wherein the determination of the weight value is further based on the diameter value of the lumen.

[0174] (6) the instrument further comprises a camera configured to capture an image of the interior of the lumen network; The computer executable instructions further cause the one or more processors to determine, for each of the sensor location points, a distance between the distal end of the instrument and a centerline of a lumen in which the distal end of the instrument is located based on the captured images; 2. The system of claim 1, wherein the determination of the weight value of the sensor location point is further based on the distance between the distal end of the instrument and the corresponding centerline of the lumen. (7) the model includes a skeleton defined by midpoints along lumens of the lumen network; The computer executable instructions further cause the one or more processors to: selecting the sensor location points based on a distance from each of the sensor location points to the skeleton of a given lumen; 2. The system of claim 1, further comprising: assigning the weights to the sensor location points based on the selected sensor location points. (8) The selection of the sensor position points comprises: 8. The system of embodiment 7, further comprising sorting a defined percentage of the sensor location points having a minimum distance into a first group and sorting the remaining sensor location points into a second group. (9) the set of weight values ​​is binary, and the computer-executable instructions further cause the one or more processors to: assigning a weight value of 1 to each of the sensor location points in the first group; 2. The system of embodiment 1, wherein each of the sensor location points in the second group is assigned a weight value of 0. (10) The set of weight values ​​is binary; a subset of the set of sensor location points corresponds to the distal end of the instrument located in a second production lumen; 2. The system of embodiment 1, wherein the subset of the set of sensor location points is assigned a weight value of 1.

[0175] (11) The computer-executable instructions further cause the one or more processors to: determining an error associated with the initial alignment for a first one of the sensor location points; 2. The system of claim 1, further comprising: fixing the initial alignment in response to the error being greater than a threshold error. (12) The system of embodiment 11, wherein the determination of the updated alignment is further based on the first sensor position point in response to the error being less than or equal to the threshold error. (13) A method for determining alignment between a sensor coordinate system and a model coordinate system, comprising: generating a set of sensor position points in the sensor coordinate system based on position data generated by a position sensor of an instrument, the position data indicating a position of the distal end of the instrument in the sensor coordinate system; determining a set of model position points in the model coordinate system; determining an initial alignment between the sensor coordinate system and the model coordinate system based on the set of sensor location points and the set of model location points; determining a set of weight values ​​corresponding to the set of sensor location points; determining an updated alignment between the sensor coordinate system and the model coordinate system based on the set of sensor location points, the set of model location points, and the set of weighting values; A method comprising: (14) The model includes a skeleton defined by midpoints along lumens of the lumen network; The method further comprising: transforming the sensor location points from the sensor coordinate system to the model coordinate system using the initial alignment; determining a distance between each of the transformed sensor location points in the model coordinate system and the skeleton; Further comprising: 14. The method of claim 13, wherein the determination of the weight value is further based on a distance between the transformed sensor location point and the skeleton. (15) The method of embodiment 14, wherein the set of weight values ​​is binary.

[0176] (16) comparing each distance between each of the transformed sensor location points and the skeleton to a distance threshold; assigning one of the binary weight values ​​to each of the transformed sensor location points based on the comparison; and 16. The method of embodiment 15, further comprising: (17) The model further comprises diameter values ​​of the lumens of the lumen network; 14. The method of claim 13, wherein the determination of the weight value is further based on the diameter value of the lumen. (18) The instrument further comprises a camera configured to capture an image of an interior of the lumen network; the method further comprising determining, for each of the sensor location points, a distance between the distal end of the instrument and a centerline of a lumen in which the distal end of the instrument is located based on the captured images; 14. The method of claim 13, wherein the determination of the weight value of the sensor location point is further based on the distance between the distal end of the instrument and the corresponding centerline of the lumen. (19) The model includes a skeleton defined by midpoints along lumens of the lumen network; The method further comprising: selecting the sensor location points based on a distance from each of the sensor location points to the skeleton of a given lumen; 14. The method of claim 13, further comprising: assigning the weights to the sensor location points based on the sorted sensor location points. (20) The selection of the sensor position points comprises: 20. The method of embodiment 19, comprising sorting a defined percentage of the sensor location points having a minimum distance into a first group and sorting the remaining sensor location points into a second group.

[0177] (21) The set of weight values ​​is binary; The method further comprising: assigning a weight of 1 to the first group of sensor location points; assigning a weight of 0 to the second group of sensor location points; 21. The method of embodiment 20, further comprising: (22) The set of weight values ​​is binary; a subset of the set of sensor location points corresponds to the distal end of the instrument located in a second production lumen; 14. The method of claim 13, wherein the subset of the set of model position points is assigned a value of 1. (23) The method, determining an error associated with the initial alignment for a first one of the sensor location points; Fixing the initial alignment in response to the error being greater than a threshold error; 14. The method of embodiment 13, further comprising: (24) The method of claim 23, wherein the determination of the updated alignment is further responsive to the error being less than or equal to the threshold error to the first sensor position point. (25) A non-transitory computer-readable storage medium having instructions stored thereon that, when executed, cause at least one computing device to: generating a set of sensor position points in the sensor coordinate system based on position data generated by a position sensor of an instrument, the position data indicating a position of a distal end of the instrument in the sensor coordinate system; determining a set of model position points in the model coordinate system; determining an initial alignment between the sensor coordinate system and the model coordinate system based on the set of sensor location points and the set of model location points; determining a set of weight values ​​corresponding to the set of sensor location points; determining an updated alignment between the sensor coordinate system and the model coordinate system based on the set of sensor location points, the set of model location points, and the set of weighting values; To carry out A non-transitory computer-readable storage medium.

[0178] (26) The model includes a skeleton defined by midpoints along lumens of the lumen network; The non-transitory computer-readable storage medium further comprises instructions stored on the non-transitory computer-readable storage medium that, when executed, cause the at least one computing device to: Transforming the sensor location points from the sensor coordinate system to the model coordinate system using the initial alignment; determining a distance between each of the transformed sensor location points in the model coordinate system and the skeleton; 26. The non-transitory computer-readable storage medium of embodiment 25, wherein the determination of the weight value is further based on a distance between the transformed sensor location point and the skeleton. (27) The non-transitory computer-readable storage medium of embodiment 26, wherein the set of weight values ​​is binary. (28) The non-transitory computer-readable storage medium further comprises instructions stored on the non-transitory computer-readable storage medium, the instructions, when executed, causing the at least one computing device to: comparing each distance between each of the transformed sensor location points and the skeleton to a distance threshold; 28. The non-transitory computer-readable storage medium of embodiment 27, further comprising: assigning one of the binary weight values ​​to each of the transformed sensor position points based on the comparison. (29) The model further comprises diameter values ​​of the lumens of the lumen network; 26. The non-transitory computer-readable storage medium of embodiment 25, wherein the determination of the weight value is further based on the diameter value of the lumen. (30) The instrument further comprises a camera configured to capture an image of an interior of the lumen network; The non-transitory computer readable storage medium further comprises instructions stored on the non-transitory computer readable storage medium that, when executed, cause the at least one computing device to determine, for each of the sensor location points, based on the captured images, a distance between the distal end of the instrument and a centerline of a lumen in which the distal end of the instrument is located; 26. The non-transitory computer-readable storage medium of embodiment 25, wherein the determination of the weight value of the sensor location point is further based on the distance between the distal end of the instrument and the corresponding centerline of the lumen.

Claims

1. 1. A system comprising: an instrument comprising a set of one or more position sensors configured to generate position data indicative of a position of a distal end of the instrument in a sensor coordinate system; a set of one or more processors; at least one computer readable memory in communication with the set of one or more processors and storing a model of the patient's luminal network relative to a model coordinate system, the model including a skeleton defined by midpoints along the lumens of the luminal network; the at least one computer readable memory further comprising computer executable instructions stored in the at least one computer readable memory, the computer executable instructions causing the one or more processors to: generating a set of sensor position points in the sensor coordinate system based on the position data generated by the position sensor; determining a set of model position points in the model coordinate system; determining an initial alignment between the sensor coordinate system and the model coordinate system based on the set of sensor location points and the set of model location points; sorting the sensor location points into a first group and a second group based on a distance from each of the sensor location points to the skeleton of a given lumen; determining a set of weight values ​​corresponding to the set of sensor location points; assigning the weight values ​​to the sensor location points based on the selected sensor location points; determining an updated alignment between the sensor coordinate system and the model coordinate system based on the set of sensor location points, the set of model location points, and the set of weight values; a distance between the sensor location points in the first group and the skeleton is less than a distance between the sensor location points in the second group and the skeleton; the weighting values ​​assigned to the sensor location points in the first group are greater than the weighting values ​​assigned to the sensor location points in the second group; system.

2. The computer executable instructions further include causing the one or more processors to: Transforming the sensor location points from the sensor coordinate system to the model coordinate system using the initial alignment; determining a distance between each of the transformed sensor location points in the model coordinate system and the skeleton; The system of claim 1 , wherein the determination of the weight value is based on a distance between the transformed sensor location points and the skeleton.

3. The system of claim 2 , wherein the set of weight values ​​is binary.

4. The computer executable instructions further include causing the one or more processors to: comparing each distance between each of the transformed sensor location points and the skeleton to a distance threshold; The system of claim 3 , further comprising: based on said comparison, causing each of said transformed sensor location points to be assigned one of said weight values ​​that is binary.

5. the model further includes diameter values ​​of the lumens of the lumen network; The system of claim 1 , wherein the determination of the weight value is further based on the diameter value of the lumen.

6. the instrument further comprising a camera configured to capture an image of the interior of the lumen network; The computer executable instructions further cause the one or more processors to determine, for each of the sensor location points, a distance between the distal end of the instrument and a centerline of a lumen in which the distal end of the instrument is located based on the captured images; The system of claim 1 , wherein the determination of the weight value of the sensor location point is further based on a distance between the distal end of the instrument and a corresponding centerline of the lumen.

7. the set of weight values ​​is binary, and the computer executable instructions further include causing the one or more processors to: assigning a weight value of 1 to each of the sensor location points in the first group; The system of claim 1 , further comprising: causing each of the sensor location points in the second group to be assigned a weight value of zero.

8. the set of weight values ​​is binary; a subset of the set of sensor location points corresponds to the distal end of the instrument located in a second production lumen; The system of claim 1 , wherein the subset of the set of sensor location points is assigned a weight value of one.

9. The computer executable instructions further include causing the one or more processors to: determining an error associated with the initial alignment for a first one of the sensor location points; The system of claim 1 , further comprising: fixing the initial alignment in response to the error being greater than a threshold error.

10. The system of claim 9 , wherein the determination of the updated alignment is further based on the first sensor location point in response to the error being less than or equal to the threshold error.

11. A non-transitory computer readable storage medium having instructions stored on the non-transitory computer readable storage medium that, when executed, cause at least one computing device to: generating a set of sensor position points in a sensor coordinate system based on position data generated by a position sensor of the instrument, the position data indicating a position of the distal end of the instrument in the sensor coordinate system; determining a set of model position points in a model coordinate system of a model of a patient's lumen network, the model including a skeleton defined by midpoints along lumens of the lumen network; determining an initial alignment between the sensor coordinate system and the model coordinate system based on the set of sensor location points and the set of model location points; sorting the sensor location points into a first group and a second group based on a distance from each of the sensor location points to the skeleton of a given lumen; determining a set of weight values ​​corresponding to the set of sensor location points; assigning said weight values ​​to said sensor location points based on the selected sensor location points; determining an updated alignment between the sensor coordinate system and the model coordinate system based on the set of sensor location points, the set of model location points, and the set of weighting values; Let them do so, a distance between the sensor location points in the first group and the skeleton is less than a distance between the sensor location points in the second group and the skeleton; the weighting values ​​assigned to the sensor location points in the first group are greater than the weighting values ​​assigned to the sensor location points in the second group; A non-transitory computer-readable storage medium.

12. The non-transitory computer-readable storage medium further comprises instructions stored on the non-transitory computer-readable storage medium that, when executed, cause the at least one computing device to: Transforming the sensor location points from the sensor coordinate system to the model coordinate system using the initial alignment; determining a distance between each of the transformed sensor location points in the model coordinate system and the skeleton; The non-transitory computer-readable storage medium of claim 11 , wherein the determination of the weight value is based on a distance between the transformed sensor location points and the skeleton.

13. The non-transitory computer-readable storage medium of claim 12 , wherein the set of weight values ​​is binary.

14. The non-transitory computer-readable storage medium further comprises instructions stored on the non-transitory computer-readable storage medium that, when executed, cause the at least one computing device to: comparing each distance between each of the transformed sensor location points and the skeleton to a distance threshold; The non-transitory computer-readable storage medium of claim 13 , further comprising: causing each of the transformed sensor location points to be assigned one of the weight values ​​that are binary based on the comparison.

15. the instrument further comprising a camera configured to capture an image of the interior of the lumen network; The non-transitory computer readable storage medium further comprises instructions stored on the non-transitory computer readable storage medium that, when executed, cause the at least one computing device to determine, for each of the sensor location points, based on the captured images, a distance between the distal end of the instrument and a centerline of a lumen in which the distal end of the instrument is located; The non-transitory computer readable storage medium of claim 11 , wherein the determination of the weight value of the sensor location point is further based on a distance between the distal end of the instrument and a corresponding centerline of the lumen.

Images