SURGICAL ROBOTIC SYSTEM AND METHOD
FOR INTEGRATED CONTROL OF 3D MODEL DATA
CROSS-REFERENCE TO RELATED APPLICATION
[0001] This application claims the benefit of U.S. Provisional Patent Application Serial No. 63/590,077, filed October 13, 2023, the entire content of which is incorporated herein by reference.
BACKGROUND
[0002] Surgical robotic systems are currently being used in a variety of surgical procedures, including minimally invasive medical procedures. Some surgical robotic systems include a surgeon console controlling a surgical robotic arm and a surgical instrument having an end effector (e.g., forceps or grasping instrument) coupled to and actuated by the robotic arm. In operation, the robotic arm is moved to a position over a patient and then guides the surgical instrument into a small incision via a surgical port or a natural orifice of a patient to position the end effector at a work site within the patient’s body.
[0003] Minimally invasive surgery (MIS) and robotic assisted surgery (RAS) require the surgeon to have situational awareness during the surgical procedure. This can be accomplished by providing access to pre-operative imaging scans and 3D model derived from those. There is an unmet need for presenting the 3D model as an augmented reality (AR) overlay on 3D displays that are used during robotic surgical procedure.
SUMMARY
[0004] The present disclosure provides an innovative solution for intra-operative navigational assistance by semi-automatically registering a pre-operative 3D model with endoscope images intra-operatively. The system and method reduce surgical workflow disruptions by providing user interfaces that effectively minimize time spent in visualizing the 3D model registered with intra-operative endoscope images.
[0005] According to one embodiment of the present disclosure, a surgical robotic system is disclosed. The surgical robotic system includes a robotic arm having an instrument and a surgeon console including a display screen and a handle controller for receiving input to move the instrument via the robotic arm. The system further includes a laparoscopic camera for imaging a surgical site and the instrument and generating a video feed. The system additionally includes a controller for: receiving a 3D model of a portion of the surgical site, the 3D model including a plurality of anatomical landmarks; displaying the 3D model as an augmented reality overlay in the video feed on the display screen; receiving input through the handle controller to contact the surgical site with the instrument at a location corresponding to one or more anatomical landmarks with the instrument; analyzing the video feed to determine whether the instrument touched the location; associating the location with one or more anatomical landmarks; automatically registering the 3D model to the surgical site based on the associated location; and displaying the registered 3D model as the augmented reality overlay in the video feed on the display screen.
[0006] Implementations of the above embodiment may include one or more of the following features. According to one aspect of the above embodiment, the 3D model may be based on a plurality of preoperative images. The controller may receive calibration data for the laparoscopic camera. The controller may also render the 3D model based on the calibration data to match the video feed. The controller may also receive kinematic data pertaining to the laparoscopic camera and the robotic arm. The controller may further track the 3D model on the video feed by tracking position and orientation of the laparoscopic camera based on the kinematic data. The controller may additionally generate a dense depth map from the video feed and a point cloud based on the dense depth map. The controller may also track the instrument contact with one or more anatomical landmarks using the point cloud.
[0007] According to another embodiment of the present disclosure, a method for imaging a surgical site during robotically assisted surgery is disclosed. The method includes imaging, with a laparoscopic camera, a surgical site and an instrument coupled to a robotic arm to generate a video feed and receiving a 3D model of a portion of the surgical site, the 3D model including a plurality of anatomical landmarks. The method also includes displaying, on the display screen of a surgeon console, the 3D model as an augmented reality overlay in the video feed on the display screen. The method further includes receiving, at a controller, input through a handle controller of a surgeon console to contact the surgical site with the instrument at a location corresponding to one or more anatomical landmarks with the instrument. The method also includes analyzing, at the controller, the video feed to determine whether the instrument touched the location and associating, at the controller, the location with one or more anatomical landmarks. The method additionally includes automatically registering, at the controller, the 3D model to the surgical site based on the associated location and displaying, on the display screen of the surgeon console, the registered 3D model as an augmented reality overlay in the video feed. [0008] Implementations of the above embodiment may include one or more of the following features. According to one aspect of the above embodiment, the 3D model may be based on a plurality of preoperative images. The method may include receiving calibration data for the laparoscopic camera and rendering the 3D model based on the calibration data to match the video feed. The method may also include receiving kinematic data pertaining to the laparoscopic camera and the robotic arm and tracking the 3D model on the video feed by tracking position and orientation of the laparoscopic camera based on the kinematic data. The method may further include generating a dense depth map from the video feed and a point cloud based on the dense depth map and tracking the instrument contact with one or more anatomical landmarks using the point cloud.
[0009] According to a further embodiment of the present disclosure, a surgical robotic system is disclosed. The surgical robotic system includes a robotic arm including an instrument and a surgeon console including a display screen and a handle controller for receiving movement input to move the instrument via the robotic arm. The system also includes a laparoscopic camera for imaging a surgical site and the instrument and generating a video feed. The system further includes a controller for: receiving a 3D model of a portion of the surgical site, the 3D model including a plurality of model landmarks; registering the 3D model to the surgical site based on association of the plurality of model landmarks with a plurality of anatomical landmarks of the surgical site; displaying the registered 3D model as an augmented reality overlay in the video feed on the display screen; receiving manipulation input through the handle controller to manipulate the 3D model relative to the video feed; modifying the 3D model based on the manipulation input; and displaying the modified 3D model as the augmented reality overlay in the video feed on the display screen.
[0010] Implementations of the above embodiment may include one or more of the following features. According to one aspect of the above embodiment, the controller may receive the manipulation input from the handle controller to change transparency of the modified 3D model. The controller may also receive manipulation input from the handle controller to transform the modified 3D model. The laparoscopic camera may be stereoscopic and the controller may further receive calibration data for the laparoscopic camera and display the modified 3D model as a stereoscopic augmented reality overlay.
BRIEF DESCRIPTION OF THE DRAWINGS
[0011] Various embodiments of the present disclosure are described herein with reference to the drawings wherein: [0012] FIG. 1 is a perspective view of a surgical robotic system including a control tower, a console, and one or more surgical robotic arms each disposed on a mobile cart according to an embodiment of the present disclosure;
[0013] FIG. 2 is a perspective view of a surgical robotic arm of the surgical robotic system of FIG. 1 according to an embodiment of the present disclosure;
[0014] FIG. 3 is a perspective view of a mobile cart having a setup arm with the surgical robotic arm of the surgical robotic system of FIG. 1 according to an embodiment of the present disclosure;
[0015] FIG. 4 is a schematic diagram of a computer architecture of the surgical robotic system of FIG. 1 according to an embodiment of the present disclosure;
[0016] FIG. 5 is a plan schematic view of the surgical robotic system of FIG. 1 positioned about a surgical table according to an embodiment of the present disclosure;
[0017] FIG. 6 is a schematic diagram of a system for determining phases of a surgical procedure according to an embodiment of the present disclosure;
[0018] FIG. 7 is a perspective view of a handle controller according to one embodiment of the present disclosure;
[0019] FIG. 8 is a flow chart of a method for integrated control of 3D model data according to one embodiment of the present disclosure;
[0020] FIG. 9 is an image of a 3D model generated according to one embodiment of the present disclosure;
[0021] FIG. 10 shows a screen of the surgeon console displaying another 3D model as an AR overlay according to one embodiment of the present disclosure;
[0022] FIG. 11 is an image a dense depth map of a surgical site according to one embodiment of the present disclosure;
[0023] FIG. 12 is an image of a live surface 3D point cloud generated from the dense depth map of FIG. 11 ; and
[0024] FIG. 13 is an image of a stereoscopic 3D model according to one embodiment of the present disclosure.
DETAILED DESCRIPTION
[0025] Embodiments of the presently disclosed surgical robotic system are described in detail with reference to the drawings, in which like reference numerals designate identical or corresponding elements in each of the several views. As used herein the term “coupled to” denotes a connection between components, which may be direct or indirect(i.e., through one or more components) and may be electronic, electrical, mechanical, or combinations thereof. [0026] With reference to FIG. 1, a surgical robotic system 10 includes a control tower 20, which is connected to all the components of the surgical robotic system 10 including a surgeon console 30 and one or more mobile carts 60. Each of the mobile carts 60 includes a robotic arm 40 having a surgical instrument 50 removably coupled thereto. The robotic arms 40 also couple to the mobile carts 60. The robotic system 10 may include any number of mobile carts 60 and/or robotic arms 40.
[0027] The surgical instrument 50 is configured for use during minimally invasive surgical procedures. In embodiments, the surgical instrument 50 may be configured for open surgical procedures. In further embodiments, the surgical instrument 50 may be an electrosurgical or ultrasonic instrument, such as a forceps configured to seal tissue by compressing tissue between jaw members and applying electrosurgical current or ultrasonic vibrations via an ultrasonic transducer to the tissue. In yet further embodiments, the surgical instrument 50 may be a surgical stapler including a pair of jaws configured to grasp and clamp tissue while deploying a plurality of tissue fasteners, e.g., staples, and cutting stapled tissue. In yet further embodiments, the surgical instrument 50 may be a surgical clip applier including a pair of jaws configured apply a surgical clip onto tissue. The system also includes an electrosurgical generator 57 configured to output electrosurgical (e.g., monopolar or bipolar) or ultrasonic energy in a variety of operating modes, such as coagulation, cutting, sealing, etc. Suitable generators include a Valleylab™ FT10 Energy Platform available from Medtronic of Minneapolis, MN.
[0028] One of the robotic arms 40 may include a laparoscopic camera 51 configured to capture video of the surgical site. The laparoscopic camera 51 may be a stereoscopic camera configured to capture two side-by-side (i.e., left and right) images of the surgical site to produce a video stream of the surgical scene. The laparoscopic camera 51 is coupled to an image processing device 56, which may be disposed within the control tower 20. The image processing device 56 may be any computing device configured to receive the video feed from the laparoscopic camera 51 and output the processed video stream.
[0029] The surgeon console 30 includes a first, i.e., surgeon, screen 32, which displays a video feed of the surgical site provided by camera 51 of the surgical instrument 50 disposed on the robotic arm 40, and a second screen 34, which displays a user interface for controlling the surgical robotic system 10. The first screen 32 and second screen 34 may be touchscreens allowing for displaying various graphical user inputs. The first screen 32 may be a 3D screen. [0030] The surgeon console 30 also includes a plurality of user interface devices, such as foot pedals 36 and a pair of hand controllers 38a and 38b which are used by a user to remotely control robotic arms 40. The surgeon console further includes an armrest 33 used to support clinician’s arms while operating the hand controllers 38a and 38b.
[0031] The control tower 20 includes a screen 23, which may be a touchscreen, and outputs on the graphical user interfaces (GUIs). The control tower 20 also acts as an interface between the surgeon console 30 and one or more robotic arms 40. In particular, the control tower 20 is configured to control the robotic arms 40, such as to move the robotic arms 40 and the corresponding surgical instrument 50, based on a set of programmable instructions and/or input commands from the surgeon console 30, in such a way that robotic arms 40 and the surgical instrument 50 execute a desired movement sequence in response to input from the foot pedals 36 and the hand controllers 38a and 38b. The foot pedals 36 may be used to enable and lock the hand controllers 38a and 38b, repositioning camera movement and electrosurgical activation/deactivation. In particular, the foot pedals 36 may be used to perform a clutching action on the hand controllers 38a and 38b. Clutching is initiated by pressing one of the foot pedals 36, which disconnects (i.e., prevents movement inputs) the hand controllers 38a and/or 38b from the robotic arm 40 and corresponding instrument 50 or camera 51 attached thereto. This allows the user to reposition the hand controllers 38a and 38b without moving the robotic arm(s) 40 and the instrument 50 and/or camera 51. This is useful when reaching control boundaries of the surgical space.
[0032] Each of the control tower 20, the surgeon console 30, and the robotic arm 40 includes a respective computer 21, 31, 41. The computers 21, 31, 41 are interconnected to each other using any suitable communication network based on wired or wireless communication protocols. The term “network,” whether plural or singular, as used herein, denotes a data network, including, but not limited to, the Internet, Intranet, a wide area network, or a local area network, and without limitation as to the full scope of the definition of communication networks as encompassed by the present disclosure. Suitable protocols include, but are not limited to, transmission control protocol/intemet protocol (TCP/IP), datagram protocol/intemet protocol (UDP/IP), and/or datagram congestion control protocol (DC). Wireless communication may be achieved via one or more wireless configurations, e.g., radio frequency, optical, Wi-Fi, Bluetooth (an open wireless protocol for exchanging data over short distances, using short length radio waves, from fixed and mobile devices, creating personal area networks (PANs), ZigBee® (a specification for a suite of high level communication protocols using small, low-power digital radios based on the IEEE 122.15.4-1203 standard for wireless personal area networks (WPANs)).
[0033] The computers 21, 31, 41 may include any suitable processor (not shown) operably connected to a memory (not shown), which may include one or more of volatile, non-volatile, magnetic, optical, or electrical media, such as read-only memory (ROM), random access memory (RAM), electrically erasable programmable ROM (EEPROM), non-volatile RAM (NVRAM), or flash memory. The processor may be any suitable processor (e.g., control circuit) adapted to perform the operations, calculations, and/or set of instructions described in the present disclosure including, but not limited to, a hardware processor, a field programmable gate array (FPGA), a digital signal processor (DSP), a central processing unit (CPU), a microprocessor, and combinations thereof. Those skilled in the art will appreciate that the processor may be substituted for by using any logic processor (e.g., control circuit) adapted to execute algorithms, calculations, and/or set of instructions described herein.
[0034] With reference to FIG. 2, each of the robotic arms 40 may include a plurality of links 42a, 42b, 42c, which are interconnected at joints 44a, 44b, 44c, respectively. Other configurations of links and joints may be utilized as known by those skilled in the art. The joint 44a is configured to secure the robotic arm 40 to the mobile cart 60 and defines a first longitudinal axis. With reference to FIG. 3, the mobile cart 60 includes a lift 67 and a setup arm 61, which provides a base for mounting the robotic arm 40. The lift 67 allows for vertical movement of the setup arm 61. The mobile cart 60 also includes a screen 69 for displaying information pertaining to the robotic arm 40. In embodiments, the robotic arm 40 may include any type and/or number of joints.
[0035] The setup arm 61 includes a first link 62a, a second link 62b, and a third link 62c, which provide for lateral maneuverability of the robotic arm 40. The links 62a, 62b, 62c are interconnected at joints 63a and 63b, each of which may include an actuator (not shown) for rotating the links 62b and 62b relative to each other and the link 62c. In particular, the links 62a, 62b, 62c are movable in their corresponding lateral planes that are parallel to each other, thereby allowing for extension of the robotic arm 40 relative to the patient (e.g., surgical table). In embodiments, the robotic arm 40 may be coupled to the surgical table (not shown). The setup arm 61 includes controls 65 for adjusting movement of the links 62a, 62b, 62c as well as the lift 67. In embodiments, the setup arm 61 may include any type and/or number of joints.
[0036] The third link 62c may include a rotatable base 64 having two degrees of freedom. In particular, the rotatable base 64 includes a first actuator 64a and a second actuator 64b. The first actuator 64a is rotatable about a first stationary arm axis which is perpendicular to a plane defined by the third link 62c and the second actuator 64b is rotatable about a second stationary arm axis which is transverse to the first stationary arm axis. The first and second actuators 64a and 64b allow for full three-dimensional orientation of the robotic arm 40.
[0037] The actuator 48b of the joint 44b is coupled to the joint 44c via the belt 45a, and the joint 44c is in turn coupled to the joint 46b via the belt 45b. Joint 44c may include a transfer case coupling the belts 45a and 45b, such that the actuator 48b is configured to rotate each of the links 42b, 42c and a holder 46 relative to each other. More specifically, links 42b, 42c, and the holder 46 are passively coupled to the actuator 48b which enforces rotation about a pivot point “P” which lies at an intersection of the first axis defined by the link 42a and the second axis defined by the holder 46. In other words, the pivot point “P” is a remote center of motion (RCM) for the robotic arm 40. Thus, the actuator 48b controls the angle 0 between the first and second axes allowing for orientation of the surgical instrument 50. Due to the interlinking of the links 42a, 42b, 42c, and the holder 46 via the belts 45a and 45b, the angles between the links 42a, 42b, 42c, and the holder 46 are also adjusted to achieve the desired angle 0. In embodiments, some or all of the joints 44a, 44b, 44c may include an actuator to obviate the need for mechanical linkages.
[0038] The joints 44a and 44b include an actuator 48a and 48b configured to drive the joints 44a, 44b, 44c relative to each other through a series of belts 45a and 45b or other mechanical linkages such as a drive rod, a cable, or a lever and the like. In particular, the actuator 48a is configured to rotate the robotic arm 40 about a longitudinal axis defined by the link 42a.
[0039] With reference to FIG. 2, the holder 46 defines a second longitudinal axis and configured to receive an instrument drive unit (IDU) 52 (FIG. 1). The IDU 52 is configured to couple to an actuation mechanism of the surgical instrument 50 and the camera 51 and is configured to move (e.g., rotate) and actuate the instrument 50 and/or the camera 51. IDU 52 transfers actuation forces from its actuators to the surgical instrument 50 to actuate components an end effector 49 of the surgical instrument 50. The holder 46 includes a sliding mechanism 46a, which is configured to move the IDU 52 along the second longitudinal axis defined by the holder 46. The holder 46 also includes a joint 46b, which rotates the holder 46 relative to the link 42c. During laparoscopic procedures, the instrument 50 may be inserted through a laparoscopic access port 55 (FIG. 3) held by the holder 46. The holder 46 also includes a port latch 46c for securing the access port 55 to the holder 46 (FIG. 2).
[0040] The robotic arm 40 also includes a plurality of manual override buttons 53 (FIG. 1) disposed on the IDU 52 and the setup arm 61, which may be used in a manual mode. The user may press one or more of the buttons 53 to move the component associated with the button 53. [0041] With reference to FIG. 4, each of the computers 21, 31, 41 of the surgical robotic system 10 may include a plurality of controllers, which may be embodied in hardware and/or software. The computer 21 of the control tower 20 includes a controller 21a and safety observer 21b. The controller 21a receives data from the computer 31 of the surgeon console 30 about the current position and/or orientation of the hand controllers 38a and 38b and the state of the foot pedals 36 and other buttons. The controller 21a processes these input positions to determine desired drive commands for each joint of the robotic arm 40 and/or the IDU 52 and communicates these to the computer 41 of the robotic arm 40. The controller 21a also receives the actual joint angles measured by encoders of the actuators 48a and 48b and uses this information to determine force feedback commands that are transmitted back to the computer 31 of the surgeon console 30 to provide haptic feedback through the hand controllers 38a and 38b. The safety observer 21b performs validity checks on the data going into and out of the controller 21a and notifies a system fault handler if errors in the data transmission are detected to place the computer 21 and/or the surgical robotic system 10 into a safe state.
[0042] The controller 21a is coupled to a storage 22a, which may be non-transitory computer- readable medium configured to store any suitable computer data, such as software instructions executable by the controller 21a. The controller 21a also includes transitory memory 22b for loading instructions and other computer readable data during execution of the instructions. In embodiments, other controllers of the system 10 include similar configurations.
[0043] The computer 41 includes a plurality of controllers, namely, a main cart controller 41a, a setup arm controller 41b, a robotic arm controller 41c, and an instrument drive unit (IDU) controller 41d. The main cart controller 41a receives and processes joint commands from the controller 21a of the computer 21 and communicates them to the setup arm controller 41b, the robotic arm controller 41c, and the IDU controller 4 Id. The main cart controller 41a also manages instrument exchanges and the overall state of the mobile cart 60, the robotic arm 40, and the IDU 52. The main cart controller 41a also communicates actual joint angles back to the controller 21a.
[0044] Each of joints 63a and 63b and the rotatable base 64 of the setup arm 61 are passive joints (i.e., no actuators are present therein) allowing for manual adjustment thereof by a user. The joints 63a and 63b and the rotatable base 64 include brakes that are disengaged by the user to configure the setup arm 61. The setup arm controller 41b monitors slippage of each of joints 63a and 63b and the rotatable base 64 of the setup arm 61, when brakes are engaged or can be freely moved by the operator when brakes are disengaged, but do not impact controls of other joints. The robotic arm controller 41c controls each joint 44a and 44b of the robotic arm 40 and calculates desired motor torques required for gravity compensation, friction compensation, and closed loop position control of the robotic arm 40. The robotic arm controller 41c calculates a movement command based on the calculated torque. The calculated motor commands are then communicated to one or more of the actuators 48a and 48b in the robotic arm 40. The actual joint positions are then transmitted by the actuators 48a and 48b back to the robotic arm controller 41c.
[0045] The IDU controller 4 Id receives desired joint angles for the surgical instrument 50, such as wrist and jaw angles, and computes desired currents for the motors in the IDU 52. The IDU controller 4 Id calculates actual angles based on the motor positions and transmits the actual angles back to the main cart controller 41a.
[0046] With reference to FIG. 5, the surgical robotic system 10 is set up around a surgical table 90. The system 10 includes mobile carts 60a-d, which may be numbered “1” through “4.” During setup, each of the carts 60a-d are positioned around the surgical table 90. Position and orientation of the carts 60a-d depends on a plurality of factors, such as placement of a plurality of access ports 55a-d, which in turn, depends on the surgery being performed. Once the port placement is determined, the access ports 55a-d are inserted into the patient, and carts 60a-d are positioned to insert instruments 50 and the laparoscopic camera 51 into corresponding ports 55a-d.
[0047] During use, each of the robotic arms 40a-d is attached to one of the access ports 55a-d that is inserted into the patient by attaching the latch 46c (FIG. 2) to the access port 55 (FIG. 3). The IDU 52 is attached to the holder 46, followed by the SIM 43 being attached to a distal portion of the IDU 52. Thereafter, the instrument 50 is attached to the SIM 43. The instrument 50 is then inserted through the access port 55 by moving the IDU 52 along the holder 46. The SIM 43 includes a plurality of drive shafts configured to transmit rotation of individual motors of the IDU 52 to the instrument 50 thereby actuating the instrument 50. In addition, the SIM 43 provides a sterile barrier between the instrument 50 and the other components of robotic arm 40, including the IDU 52. The SIM 43 is also configured to secure a sterile drape (not shown) to the IDU 52.
[0048] A surgical procedure may include multiple phases, and each phase may include one or more surgical actions. As used herein, the term “phase” represents a surgical event that is composed of a series of steps (e.g., closure). A “surgical action” may include an incision, a compression, a stapling, a clipping, a suturing, a cauterization, a sealing, or any other such actions performed to complete a phase in the surgical procedure. A “step” refers to the completion of a named surgical objective (e.g., hemostasis). During each step, certain surgical instruments 50 (e.g., forceps) are used to achieve a specific objective by performing one or more surgical actions.
[0049] With reference to FIG. 6, the surgical robotic system 10 may include a machine learning (ML) processing system 310 that processes the surgical data using one or more ML models to identify one or more features, such as surgical phase, instrument, anatomical structure, etc., in the surgical data. The ML processing system 310 includes a ML training system 325, which may be a separate device (e.g., server) that stores its output as one or more trained ML models 330. The ML models 330 are accessible by a ML execution system 340. The ML execution system 340 may be separate from the ML training system 325, namely, devices that “train” the models are separate from devices that “infer,” i.e., perform real-time processing of surgical data using the trained ML models 330.
[0050] System 10 includes a data reception system 305 that collects surgical data, including the video data and surgical instrumentation data. The data reception system 305 can include one or more devices (e.g., one or more user devices and/or servers) located within and/or associated with a surgical operating room and/or control center. The data reception system 305 can receive surgical data in real-time, i.e., as the surgical procedure is being performed.
[0051] The ML processing system 310, in some examples, may further include a data generator 315 to generate simulated surgical data, such as a set of virtual images, or record the video data from the image processing device 56, to train the ML models 330 as well as other sources of data, e.g., user input, arm movement, etc. Data generator 315 can access (read/write) a data store 320 to record data, including multiple images and/or multiple videos.
[0052] The ML processing system 310 also includes a phase detector 350 that uses the ML models to identify a phase within the surgical procedure. Phase detector 350 uses a particular procedural tracking data structure 355 from a list of procedural tracking data structures. Phase detector 350 selects the procedural tracking data structure 355 based on the type of surgical procedure that is being performed. In one or more examples, the type of surgical procedure is predetermined or input by user. The procedural tracking data structure 355 identifies a set of potential phases that may correspond to a part of the specific type of surgical procedure.
[0053] In some examples, the procedural tracking data structure 355 may be a graph that includes a set of nodes and a set of edges, with each node corresponding to a potential phase. The edges may provide directional connections between nodes that indicate (via the direction) an expected order during which the phases will be encountered throughout an iteration of the surgical procedure. The procedural tracking data structure 355 may include one or more branching nodes that feed to multiple next nodes and/or may include one or more points of divergence and/or convergence between the nodes. In some instances, a phase indicates a procedural action (e.g., surgical action) that is being performed or has been performed and/or indicates a combination of actions that have been performed. In some instances, a phase relates to a biological state of a patient undergoing a surgical procedure. For example, the biological state may indicate a complication (e.g., blood clots, clogged arteries/veins, etc.), pre-condition (e.g., lesions, polyps, etc.). In some examples, the ML models 330 are trained to detect an “abnormal condition,” such as hemorrhaging, arrhythmias, blood vessel abnormality, etc.
[0054] The phase detector 350 outputs the phase prediction associated with a portion of the video data that is analyzed by the ML processing system 310. The phase prediction is associated with the portion of the video data by identifying a start time and an end time of the portion of the video that is analyzed by the ML execution system 340. The phase prediction that is output may include an identity of a surgical phase as detected by the phase detector 350 based on the output of the ML execution system 340. Further, the phase prediction, in one or more examples, may include identities of the structures (e.g., instrument, anatomy, etc.) that are identified by the ML execution system 340 in the portion of the video that is analyzed. The phase prediction may also include a confidence score of the prediction. Other examples may include various other types of information in the phase prediction that is output. The predicted phase may be used by the controller 2 la to determine when to enable manipulation of projected 3D model as described below.
[0055] FIG. 7 shows the left-handle controller 38a, which is a mirror copy of the right-handle controller 38b. Each of the handle controllers 38a and 38b includes a handle 371 and a paddle 378 that is pivotally coupled to the handle 371 at one end (e.g., proximal) of the paddle 378. The paddle 378 is configured to control actuation of the end effector of the instrument 50. The paddle 378 may include a finger sensor configured to detect presence or movement of a finger, such as touch sensors, capacitive sensors, optical sensors, and the like. In embodiments, the finger sensor may be disposed on any portion of the handle controllers 38a and 38b. Each of the handle controllers 38a and 38b may also include a trigger 375a and one or more buttons 375b for activating various functions of the instrument 50. In addition, each of the handle controllers 38a and 38b may include a gimbal assembly 376 allowing for movement and rotation of the handle controllers 38a and 38b about three axes (x, y, z). The handle controllers 38a and 38b may also include an infrared proximity sensor 377 configured to detect hand contact with a grip of the handle controllers 38a and 38b. The controller 31a of the surgeon console 30 monitors operator interactions with the handle controllers 38a and 38b and controls the instrument(s) 50 in response to operator inputs. Details of the handle controllers 38a and 38b are provided in U.S. Patent Application Publication No. 2020/0315729, titled “Control arm assemblies for robotic surgical systems”.
[0056] With reference to FIG. 8, a method for integrated control of 3D model data may be embodied as software instructions stored in memory and are executable by a processor, which may be any of the controllers disclosed herein. At step 400, preoperative images of the surgical site are obtained. Preoperative imaging includes any suitable imaging modality such as computed tomography (CT), magnetic resonance imaging (MRI), or any other imaging modality capable of obtaining 3D images. The images may be saved in a picture archiving and communication system (PACS) accessible by the system 10.
[0057] At step 402, a 3D model 500 of the tissue is constructed from preoperative images, which may be done by obtaining a plurality of 2D images and reconstructing a 3D volumetric image therefrom. In embodiments, preoperative images may be provided to any computing device (e.g., outside the operating room) to perform the image processing steps described herein. The 3D model 500 may be a wire mesh model based on the preoperative image as shown in FIG. 9. The 3D model 500 may include a plurality of points or vertices interconnected by line segments based on the segmentations and include a surface texture over the vertices and segments. The 3D model 500 may also be saved in the PACS.
[0058] At step 404, the 3D model 500 is analyzed to identify a plurality of landmarks, which include any unique tissue structure, e.g., blood vessel. A computer vision algorithm may be used to identify the plurality of landmarks. The algorithm may be a machine leaming/artificial intelligence (ML/AI) algorithm trained on a dataset including various landmarks and corresponding images and 3D models of surgical sites. The algorithm may support generalization of landmarks to include “weak” constraints (i.e., less 3D-like features) such as ridges and contours, and “strong” constrains (i.e., more 3D-like features) such as distinct structures and geometries.
[0059] 3D landmarks may be extended to support generalized representations of confidence (e.g., feature covariance) specified by the user or derived automatically from properties of the underlying anatomy and tissue structure. In embodiments, a 3D landmark can be specified at a smooth protrusion along a ridge with a covariance defined to represent high confidence orthogonal to the ridge direction, and weak (but not zero) confidence along the smooth protrusion.
[0060] The identified landmarks may be further modified by a user to keep well-detected landmarks, adjust poorly detected landmarks, add missed landmarks, etc. The landmarks are then tagged or annotated on the 3D model. The annotated 3D model is then saved in the PACS using the Digital Imaging and Communications in Medicine (DICOM) standard.
[0061] At step 406, calibration data for the camera 51 is provided to the image processing device 56. The camera may be a stereoscopic camera that may be calibrated prior to or during use in a surgical setting. Calibration may be performed using a calibration pattern, which may be a checkerboard pattern of black and white squares. The calibration may include obtaining a plurality of images at different poses and orientations and providing the images as input to the image processing device 56, which outputs calibration parameters for use by the camera during user. Calibration parameters may include one or more intrinsic and/or extrinsic parameters including, but not limited to, position of the principal point, focal length, skew, sensor scale, distortion coefficients, rotation matrix, translation vector, and the like. The calibration parameters may be stored in a memory of the camera 51 and loaded by the image processing device 56 upon connecting to the camera 51.
[0062] In embodiments, the calibration process may also be provided on the GUI of the screen 23. The GUI may display a camera calibration verification screen. Stereo calibration is loaded from the camera 51 or any other storage device. The GUI may display rectified images as well as a point cloud map of the scene and requesting that the calibration is verified via a user prompt, e.g., “YES” or “NO” displayed on the GUI. If verification fails, then calibration is required by the image processing device 56. A calibration pattern, such as a custom adapter with 3D targets may be used to calibrate the camera 51. After images of the targets are acquired, stereo calibration is then applied to the camera 51 and the calibration parameters are saved in memory of the camera 51 or memory 22b.
[0063] At step 408, the system 10 loads the annotated 3D model from the PACS or any other suitable storage device. A graphical user interface (GUI) is shown on the screen 23 of the control tower 20 or any of the screens 32 and 34 of the surgeon console 30. The user selects patient information and imports preoperative images as well as the annotated 3D model. The 3D model may be modified to suit specific procedures such that relevant anatomy is shown, e.g., for left partial nephrectomy procedure: left kidney, vena cava, aorta, ureter; for radical prostatectomy: prostate, nerve bundle, bladder, rectum, etc. Surgeon-specific configurations based on user profile may also be used to modify the 3D model. Saved configurations may include the location on the screen 32 where the 3D model is displayed and transparency level for each anatomy or global transparency level for all anatomies in model. The 3D model may also highlight different sized vessels in different shades/saturation values to highlight recommended instrument selection, e.g., 7+ mm vessels - stapler, 6-7 mm vessels - vessel sealing, 5 mm vessels - ultrasonic dissection. In embodiments, additional annotation of the 3D model may be performed at this step by approving, adjusting, or removing anatomical landmarks. In further embodiments, the identification of the landmarks may be performed at this step as well allowing the user to load the 3D model and annotate the same.
[0064] At step 410, the loaded 3D model 502 is displayed on a surgeon’s screen 32 of the surgeon console 30 as shown in FIG. 10. The 3D model 502 may be loaded and displayed with a chroma-keyed background. The 3D scene, upon which the 3D model 502 is displayed, may be created from multiple meshes in 3D model. The 3D model, along with embedded landmarks, is displayed in an AR environment with background matching chroma key of scaler video mixer, which is used to mix the original video signal (3D camera 51 with GUI elements) and the 3D model scene. The output of the video mixer is displayed on the 3D screen 32 of the surgeon console. In particular, the system 10 loads preoperative images (e.g., CT/MRI DICOM from the PACS) and displays the 3D model in picture -in-picture tiled display or on a secondary screen 34 of the console 30. The display of the 3D model in this manner allows for easier configuration without cluttering the main screen 32. The user may adjust contrast, brightness, windowing, and other display parameters using the hand controllers 38a and 38b. In particular, the hand controllers 38a and 38b may be used to move through slices of the 3D model in axial, coronal, and sagittal planes.
[0065] In embodiments, manual registration may also include a semi-automatic alignment interface that allows users to successively refine initial rigid registration in coarse to fine fashion by a “branching strategy” of selecting from one of several renderings of plausible automatic registrations at each stage of refinement. This deformation refinement could be guided by refinement along principal modes of variation similar to a supervised simulated annealing in a “shape space” representation.
[0066] At step 412, semi-automatic registration of the 3D model with the video feed of the camera 51 is performed. Semi-automatic registration uses a plurality of user input confirmations that match a some or all of the previously identified landmarks to the landmarks visible in the video feed. Once provided, the image processing device 56 automatically registers the 3D model to the video feed based on the manually verified landmark locations. [0067] After the 3D model is loaded, the user is instructed to enter in special registration mode. This may be done by displaying a prompt on the GUI and entering the registration with a GUI input or controller input, e.g., via pressing clutch pedal 36. In the registration mode, a list of anatomical landmarks read from 3D model is displayed on one of the screens 32 and 34 of the surgeon console 30. The user then uses the instrument 50 to touch on a surgical site a first landmark of the list. The user may repeat the landmark identification process for multiple landmarks, until a sufficient number of landmarks is identified.
[0068] The controller 21a registers the contact based on torque or other input provided by the system 10 or computer vision analysis of the video feed by the image processing device 56 to determine when the instrument 50 has contacted issue. In order to determine whether contact has been made between the instrument 50 and landmarks, initially, a real-time dense depth map 504 is created as shown in FIG. 11. The depth map may be generated using stereo reconstruction from calibrated stereo cameras using conventional depth map generating algorithms, pyramid stereo matching with double cost volume network (PSMDCNet) algorithm, hierarchical iterative tile refinement network (HitNet), and the like. The dense depth map is then used to create a live textured point cloud 506 as shown in FIG. 12.
[0069] The image processing device 56 also tracks the instrument 50 in 3D using point cloud data. The image processing device 56 stores 3D models of the instrument 50 and loads the 3D model based on the instrument ID. The image processing device 56 then loads instrument 3D model, which may be mesh with embedded keypoints and pre-trained keypoints to mesh vertices mapping. To detect contact, the image processing device 56 detects instrument keypoints in both camera images of stereo pair and instrument mesh is automatically registered with detected keypoints and point cloud.
[0070] Once the tip (e.g., end effector) of the instrument 50 is at the desired landmark, the surgeon may confirm the landmark by pressing buttons 375b on the hand controller 38a or via another input method, e.g., via GUI. The controller 21a notes the 3D point cloud location of the touched intra-operative landmark location and associates the pre-operative 3D model landmark with the intra-operative landmark.
[0071] After a first landmark was verified, system 10 then shows the next anatomical landmark for association read from list of landmarks of the 3D model. The user may skip the association step of an anatomical landmark if the landmark is invisible in intra-operative view, e.g., by clicking button 375b. If the mark is usable, i.e., visible, then system 10 repeats the association process described above with the first mark.
[0072] After a plurality of marks, e.g., 3, have been associated, at step, 414, the controller 21a performs automatic registration based on landmark association. The controller 21a may use iterative closest point algorithm to register the 3D model to the video feed based on the associated landmarks. The controller 21a also performs deformable registration by allowing for manipulation of individual meshes. [0073] After registration is completed, the registered 3D model is displayed on the screen 32 to allow the user to accept or reject the registration without disrupting workflow. Confirmation may be performed via one or more buttons (e.g., “YES” and “NO”) displayed on the screen 32 in response to a prompt (e.g., “Accept Registration?”). In further embodiments, the surgeon console 30 may track the user’s head, eye gaze direction, and/or gestures to accept or reject the registration.
[0074] At step 416, system 10 tracks the 3D model as stereo camera feed changes by using forward kinematics to end effector (i.e., camera 51) pose conversion calculations. Once registration is completed, the user may engage automatic tracking of the 3D model, e.g., by pressing a camera foot pedal 36, GUI, or another input. Tracking is performed by the controller 21a by tracking the position and orientation of the camera 51 via robotic arm kinematics and visual-simultaneous localization and mapping (visual-SLAM) to generate the real-time 3D poses of the camera 51. In particular, the controller 21a parses the real-time data from robotic joint angles, runs the robotic joint angles through forward kinematics pipeline, and then compute the transformation matrix based on the joint movements through the forward kinematics pipeline.
[0075] At step 418, the registered 3D model is displayed as an AR overlay of 3D on the surgeon screen 32. The image processing device 56 also segments the instruments 50 and excludes the AR overlay from regions of the video feed where the instruments 50 are shown. Instrument pose estimation is performed in real-time using known instrument mesh models as described above with respect to registration of instruments 50 during landmark association. The controller 21a executes an AR overlay module, which transforms the viewpoint of the virtual camera rendering the 3D scene with 3D model and chroma-keyed background. The AR overlay module simulates two separate cameras to represent stereo endoscope and uses the calibrated endoscope calibration parameters to customize simulated cameras. The AR module renders two views of the 3D model scene to present stereoscopic 3D model 508 as shown in FIG. 13. Stereoscopic 3D Model rendering is performed using unique endoscope calibration parameters and distortion based on the calibration parameters of the camera 51. This allows the user to view the 3D model in stereoscopic view showing distance of anatomical organs in the same manner as the video feed of the camera 51. The AR overlay module further implements a custom shader module to display the shading, transparency and color saturation of individual mesh vertices as a function of distance from camera allowing user to visualize AR overlay surface and anatomy. [0076] Once registration is performed and the 3D model is being displayed, the user may perform manual updates to the 3D model overlay. To enter the manual registration update mode, the user may press a clutch foot pedal 36 or pressing another button or GUI element. Once in this mode, the system 10 enables the hand controllers 38a to manipulate the AR overlay of 3D model as shown in FIGS. 9 and 10. The user can further move the vertices of the individual meshes to impose strong anatomy deformation constraints while the controller 21a then updates deformable registration based on surgeon inputs. The user may also adjust the display properties of the 3D model to visualize the anatomy under the model and internal meshes obscured by external meshes (e.g., critical structures inside organ capsule as shown in FIG. 9.) To accomplish this, the user may change transparency of each 3D model or mesh, which may be adjusted via changing the dithering of the 3D model overlay.
[0077] Force feedback may also be provided through handle controllers 38a and 38b to guide the user in the most optimal direction of registration. The controller 21a continuously computes registration of the 3D model with intra-operative imaging and as the user moves the 3D model for alignment, the controller 21a applies force feedback through handle controllers 38a and 38b to guide the user, i.e., provide less feedback to make movement easier when the 3D model moved in the right direction and provide more feedback to make movement harder when the 3D model is moved in the wrong direction. The controller 21a, may also provide visual AR overlay arrows to show the direction of optimal alignment.
[0078] Controls for adjusting the 3D model may be mapped to the inputs of the system 10 in any suitable manner and the specific examples provided below are illustrative. As noted above the clutch foot pedal 36 may be used to enable or disable registration mode. The clutch left handle controller 38a may be used for manual transformation of the 3D model, i.e., rotate, move the 3D model on the video feed. The forward and rear buttons 375b of the right handle controller 38b may be used to cycle through individual components of the 3D model for manipulation. The forward and rear buttons 375b of the left handle controller 38a may be used to increase or decrease opacity of the selected component of the 3D model.
[0079] It will be understood that various modifications may be made to the embodiments disclosed herein. Therefore, the above description should not be construed as limiting, but merely as exemplifications of various embodiments. Those skilled in the art will envision other modifications within the scope and spirit of the claims appended thereto.
[0080] The following examples are illustrative of the techniques described herein.
[0081] Example 1. A surgical robotic system comprising: a robotic arm including an instrument; a surgeon console including a display screen and a handle controller for receiving input to move the instrument via the robotic arm; a laparoscopic camera for imaging a surgical site and the instrument and generating a video feed; and a controller for: receiving a 3D model of a portion of the surgical site, the 3D model including a plurality of anatomical landmarks; displaying the 3D model as an augmented reality overlay in the video feed on the display screen; receiving input through the handle controller to contact the surgical site with the instrument at a location corresponding to at least one anatomical landmark of the plurality of anatomical landmarks with the instrument; analyzing the video feed to determine whether the instrument touched the location; associating the location with the at least one anatomical landmark of the plurality of anatomical landmarks; automatically registering the 3D model to the surgical site based on the associated location by deforming the 3D model; and displaying the registered 3D model as the augmented reality overlay in the video feed on the display screen.
[0082] Example 2. The surgical robotic system according to Example 1, wherein the 3D model is based on a plurality of preoperative images.
[0083] Example 3. The surgical robotic system according to Example 1, wherein the controller receives calibration data for the laparoscopic camera.
[0084] Example 4. The surgical robotic system according to Example 3, wherein the controller renders the 3D model based on the calibration data to match the video feed.
[0085] Example 5. The surgical robotic system according to Example 1, wherein the controller receives kinematic data pertaining to the laparoscopic camera and the robotic arm.
[0086] Example 6. The surgical robotic system according to Example 5, wherein the controller tracks the 3D model on the video feed by tracking position and orientation of the laparoscopic camera based on the kinematic data.
[0087] Example 7. The surgical robotic system according to Example 1, wherein the controller generates a dense depth map from the video feed and a point cloud based on the dense depth map.
[0088] Example 8. The surgical robotic system according to Example 7, wherein the controller tracks the instrument contact with the at least one anatomical landmark of the plurality of anatomical landmarks using the point cloud.
[0089] Example 9. A method for imaging a surgical site during robotically assisted surgery, the method comprising: imaging, with a laparoscopic camera, a surgical site and an instrument coupled to a robotic arm to generate a video feed; receiving a 3D model of a portion of the surgical site, the 3D model including a plurality of anatomical landmarks; displaying, on the display screen of a surgeon console, the 3D model as an augmented reality overlay in the video feed on the display screen; receiving, at a controller, input through a handle controller of a surgeon console to contact the surgical site with the instrument at a location corresponding to at least one anatomical landmark of the plurality of anatomical landmarks; analyzing, at the controller, the video feed to determine whether the instrument touched the location; associating, at the controller, the location with the at least one anatomical landmark of the plurality of anatomical landmarks; automatically registering, at the controller, the 3D model to the surgical site based on the associated location by deforming the 3D model; and displaying, on the display screen of the surgeon console, the registered 3D model as an augmented reality overlay in the video feed.
[0090] Example 10. The method according to Example 9, wherein the 3D model is based on a plurality of preoperative images.
[0091] Example 11. The method according to Example 9, further comprising receiving calibration data for the laparoscopic camera.
[0092] Example 12. The method according to Example 11, further comprising rendering the 3D model based on the calibration data to match the video feed.
[0093] Example 13. The method according to Example 9, further comprising receiving kinematic data pertaining to the laparoscopic camera and the robotic arm.
[0094] Example 14. The method according to Example 13, further comprising tracking the 3D model on the video feed by tracking position and orientation of the laparoscopic camera based on the kinematic data.
[0095] Example 15. The method according to Example 9, further comprising generating a dense depth map from the video feed and a point cloud based on the dense depth map.
[0096] Example 16. The method according to Example 15, further comprising tracking the instrument contact with the at least one anatomical landmark of the plurality of anatomical landmarks using the point cloud.
[0097] Example 17. A surgical robotic system comprising: a robotic arm including an instrument; a surgeon console including a display screen and a handle controller for receiving movement input to move the instrument via the robotic arm; a laparoscopic camera for imaging a surgical site and the instrument and generating a video feed; and a controller for: receiving a 3D model of a portion of the surgical site, the 3D model including a plurality of model landmarks; registering the 3D model to the surgical site based on association of the plurality of model landmarks with a plurality of anatomical landmarks of the surgical site; displaying the registered 3D model as an augmented reality overlay in the video feed on the display screen; receiving manipulation input through the handle controller to manipulate the 3D model relative to the video feed; modifying the 3D model based on the manipulation input; and displaying the modified 3D model as the augmented reality overlay in the video feed on the display screen.
[0098] Example 18. The surgical robotic system according to Example 17, wherein the controller receives manipulation input from the handle controller to change transparency of the modified 3D model.
[0099] Example 19. The surgical robotic system according to Example 17, wherein the controller receives the manipulation input from the handle controller to transform the modified 3D model.
[00100] Example 20. The surgical robotic system according to Example 17, wherein the laparoscopic camera is stereoscopic, and the controller receives calibration data for the laparoscopic camera and displays the modified 3D model as a stereoscopic augmented reality overlay.