Apparatus for guiding a surgical access device - Patent Application 20070122997

Abstract

A system for facilitating a medical procedure includes an access device / trocar having a trocar body and first and second sensors supported by the trocar body. The first and second sensors are configured to sense at least one of a position of the trocar, an orientation of the trocar, a characteristic of tissue adjacent to the trocar, and a distance from the tissue and the trocar. A processor is configured to overlay a graphical representation of the sensor data on a display as the trocar is advanced toward a target anatomical site.

Description

[Technical Field]

[0001] The present disclosure relates generally to systems and methods for facilitating implantation of an anatomical implant at a target surgical location, and more particularly to systems and methods for facilitating implantation of an intervertebral implant into an intervertebral space through Kambin's triangle. [Background technology]

[0002] Perioperative nerve injury is a known complication associated with elective spine surgery. Nerve injury can occur when contact with neural structures occurs during the surgical procedure. Some examples of perioperative neurological complications that can result from spinal surgery include vascular injury, durotomy, nerve root injury, and direct mechanical compression of the spinal cord or nerve roots during spinal instrumentation. Wide variability in patient anatomy can make it difficult to accurately predict or identify the location of neural structures in a particular patient's spinal region.

[0003] According to data from the National Institute of Science, the incidence of perioperative neurological injuries resulting from elective spine surgery increased 54.4%, from 0.68% to 1%, between 1999 and 2011. In addition, perioperative neurologic complications in elective spine surgery were associated with longer hospital stays (9.68 days vs. 2.59 days), higher total costs ($110,326.23 vs. $48,695.93), and increased in-hospital mortality (2.84% vs. 0.13%).

[0004] Minimally invasive spine surgery (MISS) has many known benefits. However, multiple study analyses of patient outcome data for lumbar spine surgery have shown that MISS has a significantly higher rate of nerve root injury (2%–23.8%) compared with traditional “open” surgical techniques (0%–2%). In MISS procedures, accessing the spine or target surgical site often involves navigating surgical instruments through the patient's anatomy, including muscle, fatty tissue, and neural structures. Current intraoperative imaging devices do not adequately depict neural structures in the surgical area. For example, computed tomography (CT) and cone beam computed tomography (CBCT) imaging techniques are often used intraoperatively to visualize musculoskeletal structures within the surgical area of ​​the patient's anatomy. However, CT and CBCT images do not depict neural structures. Furthermore, current clinical practice uses CT imaging for preoperative planning of surgical approaches. Because neural structures are not visible in CT image volumes, surgical approaches cannot be optimized to avoid or reduce contact with neural structures. Magnetic resonance imaging (MRI) imaging shows both the musculoskeletal and neural structures of the scanned patient's anatomy, but MRI imaging is typically used only to diagnose the patient and not for preoperative surgical planning or intraoperative use.

[0005] Although the incidence of perioperative neurological injury in MISS procedures is higher than in traditional open surgical techniques, MISS remains an attractive treatment option for spinal disorders requiring surgery. Advantages of MISS include shorter recovery time, less postoperative pain, and smaller incisions compared to open surgery.

[0006] Therefore, there is a need for systems and methods for reducing the incidence of neurological complications in spinal surgery, and in particular for reducing the incidence of neurological complications in minimally invasive spinal surgery.

[0007] During MISS procedures, even experienced physicians have difficulty identifying anatomical structures, so multiple techniques are often utilized. CT noninvasive scans involve X-rays to create detailed three-dimensional (3D) images of a region of interest (ROI) in a body or patient (e.g., a human or animal). MRI involves the noninvasive use of magnets to create strong magnetic fields and pulses to create a 3D image of the target or region of interest. Endoscopes provide real-time visual information about the surgical site. CT and MRI scans can be overlaid on camera images, and visualization can be performed via augmented reality (AR) or virtual reality (VR). Summary of the Invention [Means for solving the problem]

[0008] In one example, a surgical system includes a trocar having a trocar body and a first sensor and a second sensor supported by the trocar body, each of the first sensor and the second sensor configured to sense at least one of a position of the trocar, an orientation of the trocar, a property of tissue proximate to the trocar, and a distance from the tissue and the trocar. The surgical system can further include a display and a processor in communication with the plurality of sensors and the display. The processor can be configured to overlay a graphical representation of data from each of the sensors on the display as the trocar is advanced toward the target anatomical site. [Brief explanation of the drawings]

[0009] Details of particular implementations are set forth in the accompanying drawings and the following description. Like reference numerals may refer to like elements throughout the specification. Other features will become apparent from the drawings and the following description, including the claims. However, the drawings are for the purposes of illustration and description only and are not intended as a definition of the limits of the present disclosure. [Figure 1A] FIG. 1 is a lateral elevation view of a portion of the spinal column. [Figure 1B] FIG. 1B is a posterior elevational view of the spinal column of FIG. 1A. [Figure 1C] FIG. 1C is a plan view of the vertebrae of the spinal column of FIG. 1B. [Figure 2] FIG. 1 is a schematic side view of the Kambin triangle. [Figure 3A] 1 is a perspective view of a trocar constructed in accordance with one example. [Figure 3B] FIG. 3B is an enlarged side elevational view of a portion of the trocar of FIG. 3A. [Figure 3C] FIG. 3B is an enlarged, exploded side elevational view of a portion of the trocar of FIG. 3A. [Figure 3D] FIG. 3B is an enlarged side elevational view of a portion of the trocar of FIG. 3A in another example. [Figure 3E] 3B is an enlarged side elevational view of a portion of the trocar of FIG. 3A in yet another example. [Figure 3F] 3B is a perspective enlarged view of a portion of the trocar of FIG. 3A in yet another example. [Figure 4A] 1 is a preoperative image of the patient's anatomy before surgical procedure according to Kambin's triangle. [Figure 4B] 4B is a real-time image from the camera of the trocar of FIG. 3A overlaid with the image of FIG. 4A. [Figure 5A] 3B is a perspective view of an access assembly including the trocar of FIG. 3A and a flexible surgical access port removably coupled to the trocar. [Figure 5B] FIG. 10 is another perspective view of the flexible surgical access port. [Figure 6A] 4 is a perspective view of the flexible surgical access port of FIG. 3, constructed in accordance with one example. [Figure 6B] FIG. 6B is a perspective view of the flexible surgical access port of FIG. 6A conforming to irregular shapes. [Figure 6C] FIG. 6B is a perspective view of the flexible surgical access port of FIG. 6A adapted to fit alternative irregular shapes. [Figure 7] 5C is a perspective view of one embodiment of a spinal fusion cage aligned for insertion into the intervertebral space through the flexible distal access port of FIG. 5B. FIG. [Figure 8A] 1 illustrates a surgical system for assisting minimally invasive spinal surgery, according to one or more embodiments. [Figure 8B] 8B further illustrates an example of the surgical system of FIG. 8A. [Figure 9] 1 illustrates a process for improving the accuracy of a medical procedure, according to one or more embodiments. [Figure 10] 1 illustrates a process for facilitating situation-aware medical treatment, according to one or more embodiments. DETAILED DESCRIPTION OF THE INVENTION

[0010] Certain embodiments disclosed herein will be discussed in the context of intervertebral implants and spinal fusion, as the devices and methods have applicability and utility in such fields. The devices may be used for fusion, for example, in situations where a ruptured or otherwise damaged intervertebral disc has been present, by inserting an intervertebral implant to properly space adjacent vertebrae. "Adjacent" vertebrae may include vertebrae initially separated only by an intervertebral disc, or vertebrae separated by an intervening vertebra and an intervertebral disc. Accordingly, such embodiments may be used to create appropriate disc height and spinal curvature as needed to restore normal anatomical position and distance. However, it is contemplated that the teachings and embodiments disclosed herein may be beneficially implemented in a variety of other surgical settings, both for spinal surgery and otherwise.

[0011] As used throughout this application, the word "may" is used in a permissive sense (i.e., meaning having the possibility of doing something) rather than an obligatory sense (i.e., meaning required). Words such as "include," "including," and "includes" mean including but not limited to. As used herein, the singular forms "a," "an," and "the" include plural referents unless the context clearly dictates otherwise. As used herein, the term "number" shall mean one or an integer greater than one (i.e., plural).

[0012] As used herein, a statement that two or more parts or components are "coupled" shall mean that the parts are joined or operate together directly or indirectly, i.e., through one or more intermediate parts or components, to the extent that a link occurs. As used herein, "directly coupled" means that the two elements are in direct contact with one another. Directional language used herein, such as, for example and without limitation, top, bottom, left, right, upper, lower, front, back, and derivatives thereof, relates to the orientation of the elements as shown in the drawings and does not limit the scope of the claims unless expressly stated therein.

[0013] The drawings may not be drawn to scale, may not precisely reflect the structure or performance characteristics of any given embodiment, and should not be construed as defining or limiting the range of values ​​or characteristics encompassed by example embodiments.

[0014] Unless specifically stated otherwise, as will be apparent from the discussion, throughout this specification discussions utilizing terms such as "processing," "computing," "calculating," "determining," etc. will be understood to refer to the actions or processes of a particular apparatus, such as a special purpose computer or similar special purpose electronic processing / computing device.

[0015] Certain exemplary embodiments will now be described to provide an overall understanding of the principles of the structure, function, manufacture, and use of the devices, systems, and methods disclosed herein. One or more examples of these embodiments are illustrated in the accompanying drawings. Those skilled in the art will recognize that the devices, systems, and methods described in detail herein and illustrated in the accompanying drawings are non-limiting exemplary embodiments. Features illustrated or described in connection with one exemplary embodiment may be combined with features of other embodiments. Such modifications and variations are intended to be within the scope of the present disclosure.

[0016] Additionally, to the extent that linear or circular dimensions are used in describing the disclosed devices and methods, such dimensions are not intended to limit the types of shapes that may be used with such devices and methods. Those skilled in the art will recognize that equivalent dimensions to such linear and circular dimensions can be readily determined for any geometric shape. Furthermore, the size and shape of a device and its components may depend at least on the anatomy of the subject with whom the device will be used, the size and shape of the components with which the device will be used, and the method and procedure with which the device will be used.

[0017] As a context for the methods and devices described herein, Figures 1A-1C illustrate different views of a spinal column 10, including a series of alternating vertebrae 11 with vertebral bodies 13 and an intervertebral disc space 14 containing fibrous intervertebral discs that provide axial support and movement to the upper body. The spinal column typically includes 33 vertebrae 11, with seven cervical vertebrae (C1-C7), twelve thoracic vertebrae (T1-T12), five lumbar vertebrae (L1-L5), five fused sacral vertebrae (S1-S5), and four fused coccygeal vertebrae. Intervertebral discs 12 are positioned within the intervertebral spaces between adjacent vertebral bodies and provide axial support and movement to the upper body. At times, it is desirable to remove the intervertebral discs 12 and insert an intervertebral implant into the disc space to restore vertebral height and alignment.

[0018] FIG. 2 is a schematic diagram of Kambin's triangle 24. This region 20 is the site of posterolateral access for spinal surgery. It can be defined as a right triangle on the intervertebral disc 12 viewed from the dorsal side. The hypotenuse is the exiting nerve 21, the base is the superior edge of the inferior vertebra 22, and the elevation is the transverse nerve root 23. In some instances, the disc space 14, and therefore the disc 12, can be accessed by performing a foraminoplasty, which involves removing a portion of the superior articular process (SAP) 53 of the inferior vertebra 22 so that surgical instruments, such as surgical instruments or implants, can be introduced through Kambin's triangle 24. The disc space 14 is defined by the vertebrae of the inferior vertebra 22 and the superior vertebra 27 opposite the inferior vertebra 22. The portion of the inferior vertebra 22 that is removed can be defined by the superior articular process of the inferior vertebra 22. In such procedures, it is often desirable to protect the exiting nerve and the transverse nerve root. Devices and methods for accessing the intervertebral disc through Kambin's triangle 24 may involve performing an endoscopic foraminoplasty procedure with nerve protection, and are discussed in more detail below. Utilizing foraminoplasty to access the intervertebral disc 12 through Kambin's triangle 24 can have several advantages (e.g., less or reduced trauma to the patient) compared to accessing the disc from a posterior or anterior perspective, as is typically done in the art.

[0019] In particular, surgical procedures involving posterior access often require removal of a facet joint. For example, transforaminal interbody lumbar fusion (TLIF) typically involves removal of one facet joint to create an enlarged access pathway to the intervertebral disc. Facet joint removal can be very painful for the patient and is associated with increased recovery time. In contrast, accessing the disc through Kambin's triangle 24 advantageously avoids the need to remove a facet joint.

[0020] As described in more detail below, endoscopic foraminoplasty can provide expanded access to the intervertebral disc without removing the facet joints. Preserving the facet joints can reduce patient pain and blood loss associated with surgical procedures. In addition, preserving the facet joints can advantageously allow the use of certain posterior fixation devices (e.g., transfacet screws, transpedicular screws, and / or pedicle screws) that utilize the facet joints for support. In this manner, such posterior fixation devices can be used in combination with interbody devices inserted through Kambin's triangle 24.

[0021] As described now with reference to FIGS. 3A-3E , a surgical system 25 can include a trocar 30 configured to be driven through anatomy along a trajectory toward Kambin's triangle 24 to form a pathway to Kambin's triangle. The trocar 30 can be further driven along a trajectory through Kambin's triangle 24 to a target surgical location, which can be defined by a desired intervertebral disc space or vertebra. While reference is made herein to a trocar, it should be understood that the embodiments disclosed herein can be used with any access device configured to be driven through anatomy along a trajectory toward a target anatomy to form a pathway to the target anatomy. The access device can be further driven through the target anatomy along the trajectory to the target surgical location. In one example, the access device can be defined by the trocar 30, the target anatomy can be defined by Kambin's triangle, and the target surgical location can be defined by an intervertebral disc space. The target surgical location can also be referred to as the target anatomy. Additionally, in some instances, for example, when a portion of the superior articular process is removed to enlarge Kambin's triangle, Kambin's triangle can be referred to as the target surgical location.

[0022] The trocar 30 may include a trocar body 31 and a camera 51 supported on the trocar body 31. The camera 51 may be an optical camera that acquires images that can be displayed to a user or manipulated by a surgical system to be overlaid in a composite image, as described in more detail below. Alternatively or additionally, the camera 51 may be hyperspectral to identify and distinguish different tissue types (e.g., nerves, muscle tissue, bone, arteries, etc.) in response to different types of light that may be emitted by the trocar 30, and particularly by the camera 51. That is, it is recognized that different tissue types respond differently to different types of light within the hyperspectral light range. Accordingly, the trocar 30, and particularly the camera 51, or any suitable alternative light source, may direct light in the hyperspectral range toward the tissue to be identified. Identification of the tissue type may be determined based on the tissue's response to specific light within the hyperspectral range.

[0023] It is understood, therefore, that camera 51 can be referred to as a non-visible light image sensor such that the processor can distinguish between tissue types (e.g., bone, soft tissue, and nerve) based on images captured by the non-visible light image sensor. Alternatively, or additionally, camera 51 can be configured as a visible light sensor. As described in more detail below, trocar 30 is driven into the anatomical structure toward Kambin's triangle, and the processor can receive images from camera 51 and identify structures within the camera's field of view based on either or both the known location of camera 51 and pre-operative images taken of the patient's anatomy prior to the surgical procedure (see FIG. 4A ). One or more of the pre-operative images can be overlaid on the camera's real-time image, as shown in FIG. 4B , to provide identification of the anatomical structures within the camera's field of view.

[0024] The trocar body 31 can be made from any suitable biocompatible material. The trocar body 31 can include a trocar handle 32 and a trocar shaft 34 extending from the trocar handle 32 along a central axis 45 of the trocar 30. The central axis of the trocar 30 can define the central axis of the trocar shaft 34. The trocar shaft 34 can be solid or cannulated, as desired. The trocar handle 32 can be enlarged relative to the trocar shaft 34 in a cross section perpendicular to the distal direction. The trocar shaft 34 can have a main shaft portion 35 and a distal region 36 extending from the main shaft portion 35. The distal region 36 can be made from a different material than the main shaft portion 35. Alternatively, the distal region 36 can be made from the same material as the main shaft portion 35. The distal region 36 can terminate in a distal tip 37 that defines the distal end of both the trocar shaft 34 and the trocar body 31, and thus the distal end of the trocar 30. The distal end can define a tip for insertion through the anatomy through Kambin's triangle toward the target intervertebral space.

[0025] The distal tip 37 may be disposed on a central axis of the trocar 30. The trocar handle 32 may define a proximal end of the trocar body 31. The distal direction may be defined as the direction from the proximal end to the distal end of the trocar body 31. Thus, the distal region 36 may extend distally relative to the main shaft portion 35. For example, the distal region 36 may extend distally from the main shaft portion 35. The proximal direction, which is opposite the distal direction, may be defined as the direction from the distal end of the trocar 30 to the proximal end of the trocar body 31. The proximal and distal directions may each be defined by the central axis of the trocar 30, which may be oriented along the longitudinal direction L.

[0026] At least a portion of the distal region 36 of the trocar shaft 34 can taper toward the distal tip 37 as it extends distally. For example, the first portion 36a of the distal region 36 can extend along the longitudinal direction L without tapering. The second portion 36b of the distal region 36 can taper toward the distal tip 37 as it extends distally. The second portion 36b of the distal region 36 can extend distally from the first portion 36a of the distal region 36. The first portion 36a of the distal region 36 can extend distally from the main shaft portion 35. In other examples, the entire distal region 36 can taper from the main shaft portion 35 toward the distal tip 37. That is, the entire distal region 36 can be defined as described with respect to the second portion 36b extending from the main shaft portion 35.

[0027] In one example, the second portion 36b of the distal region 36 can be conical. In another example, the second portion 36b of the distal region 36 can define one or more flat surfaces as it extends distally. The flat surfaces can be adjacent to one another to define a structure extending around the central axis of the trocar shaft 34. For example, the second portion 36b of the distal region 36 can be a pyramid, such as a square pyramid, a triangular pyramid, or a hexagonal pyramid. Thus, the distal region 36 can have at least one tapered sidewall 41. In some examples, the tapered sidewall 41 can include multiple tapered sidewalls 41. The distal tip 37 can be, for example, a sharp distal tip defining the apex of a cone or a pyramid. Thus, the second portion 36b of the distal region 36 can be conical. In another example, the distal tip 37 can have an obtuse angle. Thus, in one example, the second portion 36b of the distal region 36 can be frustoconical. A sharp distal tip can be advantageous when penetrating fascia and soft tissue as the trocar is inserted toward the target surgical location, which can be defined, for example, by the intervertebral space accessed through Kambin's triangle.

[0028] Thus, during operation, the trocar 30 can be driven along a desired trajectory through Kambin's triangle to the intervertebral space without contacting the exiting nerve 21 or the transverse nerve root 23. Because the trocar 30 can be the first instrument inserted into or through Kambin's triangle during a surgical procedure, the trocar 30 can establish a trajectory through Kambin's triangle. In some instances, the trocar 30 can be driven distally along a desired trajectory through Kambin's triangle.

[0029] The surgical system 25 can be configured to inform the operator whether the trocar 30 is being driven along a trajectory through Kambin's triangle and into the disc space while avoiding contact with surrounding nerves and other tissue. In particular, the camera 51 can have direct real-time visualization of the anatomical structures within its field of view as the trocar 30 is driven through Kambin's triangle and into the disc space. The camera 51 can provide real-time images of the anatomical structures within its field of view as the trocar 30 is driven toward Kambin's triangle 24. The surgical system 25 can determine the identity of the tissue within the field of view of the camera 51 and determine whether the trocar 30 is on a trajectory through Kambin's triangle. In particular, the images of the anatomical structures from the camera 51 can be provided on a display, as described in more detail below. In some examples, the surgical system 25 can overlay the camera image on one or more preoperative images of the patient's anatomy such that the anatomical structures in the camera image achieve a match with similar anatomical structures in the one or more preoperative images. The pre-operative image may be similar to that of Figure 2. Thus, on the overlaid image, the surgical system 25 can identify anatomical structures within the field of view of the camera 51 relevant to the approach of the trocar 30 to or through Kambin's triangle 24, including the exiting nerves 21, SAP 53, etc. (see Figure 4A). The image may further include, in some instances, the transverse nerve roots 23 (see Figure 2).

[0030] The surgical system 25 can further provide feedback to the operator if it is determined that the actual trajectory of the trocar 30 differs from the desired trajectory or is outside a tolerance of the desired trajectory (collectively referred to as substantially different from the desired trajectory). The feedback can be a visual indicator. Alternatively, or additionally, the feedback can be tactile feedback. For example, if the actual trajectory of the trocar 30 differs substantially from the desired trajectory, the trocar handle 32 can include a vibration actuator 55 (see FIG. 5A).

[0031] Alternatively or additionally, the feedback may be audible feedback along with corrective instructions to change the actual trajectory to the desired trajectory. Any of the above feedback may inform the operator that the actual trajectory of the trocar 30 is the desired trajectory or is within an acceptable range of the desired trajectory.

[0032] In particular, the camera 51 can be in communication with the processor 221 (see FIGS. 8A-8B) and / or can be stored in memory in any manner as desired. For example, a communication cable 38 can extend from the camera 51 to a computing device including the processor 221 and / or memory to facilitate the exchange of data between the camera 51 and the processor 221. For example, image data can be communicated from the camera 51 and imaging instructions can be communicated to the camera 51. The communication cable 38 can extend from the trocar handle 32. Alternatively, the camera 51 can communicate wirelessly with the processor 221 and / or memory.

[0033] The camera 51 can be supported by the trocar body 31 in any suitable manner, as desired. For example, with reference to FIGS. 2-3C , the trocar body 31 can define a lumen 39. The lumen 39 can extend into or through the trocar shaft 34. Alternatively or additionally, the lumen 39 can extend into or through the distal region 36. The lumen 39 can be a central lumen such that a central axis of the trocar body 31 extends through the lumen 39. The camera 51 can be disposed within the lumen 39 and can be supported by either or both the trocar shaft 34 and the distal region 36. Thus, the camera 51 can be disposed on an inner surface of the trocar body 31 that faces the lumen 39 or that partially defines the lumen 39.

[0034] The camera 51 can be centered on the central axis of the trocar 30, and the camera's field of view can be directed distally and substantially centered on the central axis. At least a portion of the distal region 36 can be transparent so that the camera's field of view extends through the distal region 36. The distal region 36 can be made of any suitable material, such as plastic or glass. A sharp distal tip 37 can aid in penetration of soft tissue as the trocar is driven through Kambin's triangle toward the target intervertebral space, while a blunt distal tip 37 can provide better viewing for the camera 51 through the distal tip 37. Of course, it should be understood that the entire distal region 36 can be transparent. The camera's field of view can be centered on the central axis of the trocar 30 and can include data from tissue surrounding and adjacent to the distal region 36. Furthermore, the camera's field of view can be directed distally, which can define the insertion direction of the trocar 30 toward Kambin's triangle. A communication cable 38 can extend proximally out of the trocar handle 32 through the lumen 39. Additionally, at least a portion of the distal region 36 can carry a light source that can be activated to illuminate the field of view of the camera 51. Light source control signals can be communicated via the communication cable 38. The light source can be within the lumen 39 or can be mounted on the exterior of the trocar 30, as desired.

[0035] In addition to the visual indicia transmitted from the camera 51 to the processor 221 and / or memory (see FIGS. 8A-8B), the trocar 30 can also provide a device to facilitate determining the insertion depth of the trocar 30 as it is driven toward Kambin's triangle. In one example, the trocar 30 can include a reference array 40 that can include a reference array body 42 and a plurality of markers 44 supported by the reference array body 42. The reference array body 42 can be attached to the trocar body 31 in any suitable location. In one example, the reference array body 42 extends from the trocar handle 32. The markers 44 can be radiopaque in some examples. The markers 44 can be positionally fixed relative to the reference array body 42 such that, when the markers 44 are coupled to the reference array body 42, movement of the reference body 42 causes corresponding movement of the markers 44. Each marker 104 can have any suitable shape, such as a spherical or partially spherical, as desired. It should be appreciated that the fiducial array 40 , and in particular the markers 44 , provide sensors for determining the location and orientation of the trocar 30 .

[0036] The markers 44 can be detected by the processor 221 and / or memory (see FIGS. 8A-8B ), allowing the position and orientation of the trocar 30 (and thus the movement of the trocar 30) to be determined. In particular, the position of each of the markers 44 can be determined before driving the trocar 30 toward Kambin's triangle (or some other known location). Based on subsequent detection of the position of each of the markers 44, the processor can determine the direction and distance the trocar 30 has moved. The processor can further determine the orientation of the trocar 30 based on the positions of the markers 44 relative to one another. As described in more detail below, the known position and orientation of the trocar 30, along with images generated from the camera 51, can be processed to determine the anatomical structures within the field of view of the camera 51. Determination of the anatomical structures within the field of view of the camera 51 can be augmented by a preoperative scan of the patient's anatomy. For example, images from camera 51 can be overlaid on the preoperative images to provide confidence intervals for various anatomical structures (e.g., SAP, exiting nerves 21, nerve roots 23, Kambin's triangle 24, soft tissue, other bony structures, etc.). The surgical system 25 provides the operator with a real-time output indicating any difference between the desired trajectory through Kambin's triangle and the actual trajectory (taking into account changes in the position and orientation of the trocar 30). This difference can include the distance and direction of the trocar 30 relative to the desired trajectory. The operator can then adjust the actual trajectory of the trocar 30 to match the desired trajectory. The surgical system 25 can provide an output confirming that the actual trajectory matches the desired trajectory when no difference exists between the desired trajectory and the actual trajectory.

[0037] It should be understood that at least one marker 44 can be detected to determine the distance and direction of travel of the trocar 30. Multiple markers 44 can be detected to further determine the orientation of the trocar 30. Each marker 44 can be a passive marker, such as a reflective marker, that can be detected by at least one sensor or camera of the computer-assisted surgery system 25 without actively communicating with the computer of the computer-assisted surgery system 25. Alternatively, each marker 44 can be an active marker configured to actively communicate with a computing device of the computer-assisted surgery system 25.

[0038] As mentioned above, the camera 51 can be supported by the trocar body 31 in any suitable location as desired. For example, referring now to FIG. 3D , the camera 51 can be positioned on the exterior surface of the trocar body 31 opposite the interior surface. In one example, the camera 51 can be positioned at the distal tip 37, defining the tip with respect to insertion through the anatomy through Kambin's triangle toward the target intervertebral space. As mentioned above, the field of view of the camera 51 can face distally and be substantially centered on the central axis of the trocar 30. That is, a two-dimensional representation of the field of view of the camera 51 can be oriented in a plane that is substantially perpendicular to the central axis of the trocar 30 and perpendicular to the direction of movement of the trocar into the target intervertebral space. In this regard, it should be understood that the distal region 36 may be opaque, as desired, particularly if the camera is attached or otherwise secured to the exterior surface of the trocar body 31.

[0039] 3E , in yet another example, the camera 51 can be one or both of: 1) positioned at a location directionally offset from the central axis of the trocar 30; or 2) facing a direction angularly offset relative to the central axis of the trocar 30 and the actual trajectory of the trocar 30. In particular, the camera 51 can be positioned on the exterior surface of the trocar body 31 at a location offset from the distal tip 37. For example, the camera 51 can be mounted or otherwise attached to at least one side wall 41. As described above, the at least one side wall 41 can be tapered relative to the central axis of the trocar 30 so as to define an angle relative to the central axis of the trocar 30. In another example, the trocar 30 can be mounted on the interior surface of at least one side wall 41 within the lumen 39 of the trocar 30. The at least one side wall 41 can be optically transparent in this example. In both Figures 3D and 3E, the camera image is not taken through the distal region 36 of the trocar body 31, so the distal region 36, including the first and second portions 36a and 36b of the distal region, may be opaque.

[0040] Thus, the center of the field of view of camera 51 can be directionally offset relative to the central axis of trocar 30. Furthermore, the display of the field of view can be in a plane that is angularly offset relative to a plane perpendicular to the central axis of trocar 30. The display of the field of view can also be angularly offset relative to a plane perpendicular to the actual trajectory of trocar 30. The angle can be compensated for in the manner described above so that the displayed camera image is a corrected image from a viewpoint at distal tip 37 oriented along the actual trajectory of trocar 30. Thus, both the directional offset and the angular offset can be compensated for by processor 221 to generate an image as if the camera were oriented on the actual trajectory of trocar 30, with the field of view centered on the actual trajectory of trocar 30 (see FIGS. 8A-8B). Thus, the display of the corrected image can be in a plane that is perpendicular to the central axis of trocar 30 and also perpendicular to the actual trajectory of trocar 30.

[0041] Referring now to FIG. 3F , the trocar 30 can further include recesses 58 extending into the outer surface of the trocar body 31 toward the central axis of the trocar. The recesses can extend into the outer surface and terminate before extending through the inner surface of the trocar body 31. The recesses 58 can be arranged circumferentially around the trocar body 31 or in any other pattern or arrangement as desired. Furthermore, the recesses 58 can be elongated along the longitudinal direction L as desired. It will be appreciated that contact between the trocar body 31 and the anatomical tissue can cause the anatomical tissue to compress as the trocar 30 is driven toward Kambin's triangle. The recesses 58 can reduce contact between the trocar 30 and the anatomical tissue, thereby resulting in reduced compression of the anatomical tissue. Because more of the anatomical tissue remains uncompressed and therefore undeformed, the surgical system 25 can more reliably identify the tissue.

[0042] Referring again to FIGS. 3A-3B, the trocar 30, and thus the surgical system 25, can include a neuromonitoring system 50. While the neuromonitoring system 50 is shown in connection with the trocar in FIGS. 3A-3B, it should be understood that the neuromonitoring system 50 can be included in any trocar as described herein. The neuromonitoring system 50 can include at least one neuromonitoring electrode 52, which can be supported by the trocar body 31. As described herein, the electrode 52 provides a sensor for detecting proximity to a nerve or the distance between the electrode 52 and the nerve. Because the position of the electrode 52 relative to other locations on the trocar 30 is known, the distance between any location on the trocar 30, such as the distal tip 37, and the nerve can be determined. In one example, the electrode 52 can be positioned in the distal region 36. At least a portion to all of the at least one electrode 52 can be embedded in the trocar body 31. For example, the at least one electrode can be overmolded by the distal region 36 of the trocar body 31. Alternatively or additionally, the at least one electrode 52 can extend at least partially to entirely around the trocar body 31, for example, at the distal end 36. In one example, the at least one electrode 52 can extend along the inner surface of the trocar body 31. Alternatively, the at least one electrode 52 can extend along the outer surface of the trocar body 31. The at least one electrode 52 can be glued or otherwise attached to the trocar body.

[0043] The at least one electrode 52 may be supported, in particular, on either or both of the first portion 36a and the second portion 36b of the distal region 36. Thus, the at least one electrode 52 may be supported at the distal tip 37. In one example, the at least one electrode 52 may be disposed within the lumen 39. For example, the at least one electrode 52 may be supported on the inner surface of the trocar body 31. In another example, the at least one electrode 52 may be embedded in the trocar body 31. In yet another example, the at least one electrode 52 may be supported on the outer surface of the trocar body 31. It should be understood that the at least one electrode 52 may be oriented along the longitudinal direction L. In another example, some or all of the at least one electrode 52 may be oriented to extend toward the central axis of the trocar 30 when extending distally. Alternatively or additionally, some or all of the at least one electrode 52 may be oriented parallel to the central axis of the trocar 30 when extending distally.

[0044] In some examples, the at least one electrode 52 of the neuromonitoring system 50 can include multiple conductive electrodes 52 circumferentially spaced from one another around the trocar body 31. The electrodes 52 can be equidistantly spaced from one another or variably spaced from one another around or within the trocar body 31, as desired. The number of electrodes 52 and the distance between each of the electrodes can be input, stored, and / or otherwise programmed into memory for access by the processor. Each electrode can extend within the trocar body 31, such as in either or both of the first and second portions 36a and 36b of the distal region 36. Thus, at least a portion to all of each of the electrodes 52, for example, in the second portion 36b, can taper toward one another as they extend distally. Furthermore, at least a portion to all of each of the electrodes 52, for example, in the first portion 36a, can extend parallel to the other of the electrodes as they extend distally.

[0045] A respective neural monitoring electrical lead can extend from each electrode 52 to the processor such that each electrode 52 is in electrical communication with the processor. Alternatively, the electrodes 52 can be integral with the lead. Each electrode can comprise a conductive material such as silver, copper, gold, aluminum, platinum, stainless steel, or the like. If desired, a portion of each electrode can be insulated with a dielectric coating to protect the conductive electrode 52. The conductive electrode 52 can define an exposed tip that is not covered by the dielectric extending from the dielectric coating.

[0046] As the trocar 30 advances through tissue, a current can be supplied to each conductive electrode 52. When the distal region 36 of the trocar body 31, and thus each electrode 52, approaches a nerve, the nerve can be stimulated by the current. At a given current, the degree of stimulation of the nerve is related to the distance between the distal tip 37 (and thus each conductive electrode 52) and the nerve. Nerve stimulation may be measured, for example, by visually observing the patient's leg for movement or by measuring muscle activity through electromyography (EMG) or various other known techniques. Once nerve stimulation is observed or otherwise determined, the distance from the distal region 36 to the nerve can be calculated based on the intensity of the current emitted by at least one electrode 52. This measurement can be referred to as time-of-flight mapping. It should be understood that the distance from the distal region 36 to an anatomical structure, as used herein, can apply to the distance from each electrical electrode 52 to the anatomical structure or the distance from the tip 37 to the anatomical structure based on the known distance from each electrical electrode 52 to the tip 37.

[0047] Alternatively or additionally, the surgical system 25 can perform another mapping technique known as signal strength mapping. Under this method, the insertion position of the trocar 30 into the patient's anatomy is known, for example, by monitoring the reference array 40. Accordingly, the position of the at least one electrode 52 or distal portion 36 (including the tip 37) is similarly known based on the known positional relationship between the at least one electrode or distal portion from the reference array 40. At the known position, the current emitted by the at least one electrode 52 can be increased until the nerve is stimulated by the current. As described above, nerve stimulation may be measured, for example, by visually observing the patient's leg for movement or by measuring muscle activity through electromyography (EMG) or various other known techniques. Once nerve stimulation is observed or otherwise determined, the nerve's distance from the distal region 36 to the nerve can be calculated based on the known positions of the electrodes and distal portion 36 and the strength of the current that transitioned the nerve from a non-stimulated to a stimulated state.

[0048] Utilizing the neuromonitoring system 50 can provide the operator with additional guidance for driving the trocar 30 through Kambin's triangle to the desired target anatomical site. With each movement, the operator can be alerted when the tip of the first dilator tube approaches or contacts a nerve. The operator can use this technique alone or in combination with the other positioning aids described herein. The amount of current applied to each electrode 52 can be varied depending on the desired sensitivity. Naturally, the greater the current delivered, the greater the neural stimulation at a given distance from the nerve. In some examples, the current applied to each conductive electrode 52 can be a constant current. In other examples, the current applied to each conductive electrode 52 can be periodic or irregular. Alternatively, current pulses may be provided only upon request from the operator.

[0049] It is understood that the distance from a given conductive electrode 52 (and thus the tip 37) to the nerve can be determined and stored in memory. When the distance is greater than a predetermined threshold, the processor can conclude that the actual trajectory of the trocar 30 differs from the desired trajectory of the trocar 30 extending through Kambin's triangle. Therefore, the system 25 can provide feedback to the operator to modify the actual trajectory of the trocar 30. The feedback can be provided to the feedback device 48, in one example. If the trocar 30 includes multiple conductive electrodes 52, the processor can determine the distance from each of the electrodes 52 to the nerve using any of the techniques described above. Furthermore, the position (including location and orientation) of each of the conductive electrodes 52 is known and can be stored in memory.

[0050] Therefore, based on the distance from the electrodes 52 to the nerve and the known position of each of the electrodes 52 relative to one another, the location of the nerve relative to the trocar 30 can be determined by the processor, for example, by triangulating the distance from each of the electrodes to the nerve based on the known distance of each location of the trocar 30 relative to each of the electrodes 52. Thus, the nerve monitoring or electrical guidance of the system 25, achieved by the conductive electrodes 52 and the processor, can determine the location of the nerve. The location of the nerve can be displayed to the operator in any manner described herein (e.g., see FIG. 4B ). It should be understood that the system 25 can use the nerve monitoring electrodes 52, the camera 51, or a combination of both the camera 51 and the nerve monitoring electrodes 52. Thus, the actual trajectory of the trocar 30 can be guided by the electrical signals from the electrodes 52 rather than by the optical signals from the camera 51. Alternatively, the actual trajectory of the trocar 30 can be guided by the optical signals from the camera 51 rather than by the electrical signals from the electrodes 52. Alternatively, the actual trajectory of the trocar 30 can be guided by both the optical signals from the camera 51 and the electrical signals from the electrodes 52. If desired, the neuromonitoring leads and communication cables 38 can be bundled into a single multi-core cable as desired, which extends from the camera 51 and electrodes 52 out of the trocar and to a processor or other component of a computing device as desired.

[0051] Regardless of the method used to determine the distance between the trocar 30 and a given nerve, the processor can activate the vibration actuator 55 (see FIG. 5A) to vibrate when the trocar 30 is within a predetermined distance of the nerve, thereby alerting the operator to change the trajectory of the trocar 30. The trajectory of the trocar 30 can be changed in real time, or the trocar 30 can be retracted proximally from the anatomy and then advanced distally along the new trajectory.

[0052] As described above, the surgical system 25 can include multiple sensors of different types and configured to sense different parameters. For example, the different parameters can include any one or more, up to all, of the following: trocar position, trocar orientation, characteristics of tissue proximate the trocar (e.g., to identify tissue type), and distance between the target tissue, such as a nerve, and the trocar 30. A processor can be coupled to at least one or more, up to all, of the sensors to determine the parameters and / or overlay a graphical representation of the data from each of the multiple sensors on a display to provide enhanced visualization of the trocar in real time as it is driven toward and / or through Kambin's triangle. The processor can also overlay a pre-operative image of the anatomical structure on a real-time image from the camera of the anatomical structure to provide enhanced visualization of the anatomical structure within the camera's field of view.

[0053] As described above, the surgical system 25 can include at least one feedback device 48 (see FIG. 3A ) in communication with the processor to provide feedback to the operator when the actual trajectory of the trocar 30 is determined to differ from the desired trajectory or a tolerance for the desired trajectory. The feedback device 48 can be in communication with the processor and can be activated, for example, when the actual trajectory of the trocar 30 is determined to not pass through Kambin's triangle. The feedback device 48 can also be activated when the trocar 30 is determined to be within a predetermined distance of or otherwise approaching the exiting nerve 21 or transverse nerve root 23. The feedback device 48 can be positioned anywhere desired. For example, in one embodiment, the feedback device 48 can be carried by the trocar handle 32. In one example, the feedback device 48 can be a tactile feedback device, such as a vibration actuator 55 (see FIG. 5A ), that vibrates when activated. Alternatively or additionally, the feedback device 48 can emit an audible signal. The audible signal can include corrective instructions to change the actual trajectory to the desired trajectory.

[0054] It should be appreciated that both the camera 51 and the neuromonitoring system 50 can provide input of the real-time location of Kambin's triangle and surrounding anatomical structures to the processor, including the structures imaged preoperatively and shown in FIG. 4A . The image of FIG. 4A can be acquired using any suitable preoperative imaging technique of the anatomical structures, for example, using computed tomography (CT), X-ray, magnetic resonance imaging (MRI), etc. As described now with reference to FIG. 4B , the anatomical structures of FIG. 4A can be overlaid on the camera image as the trocar 30 is driven toward and through Kambin's triangle. Furthermore, to assist in trocar guidance, the anatomical structures can be labeled on the display 46 as the trocar 30 is driven toward and through Kambin's triangle. Thus, a user can identify the anatomical structures within the camera's field of view and adjust the trajectory of the trocar 30 as desired. Alternatively or additionally, the locations of the nerves 21 and 23 determined using the neuromonitoring system can be overlaid on the camera image.

[0055] Thus, referring now to FIG. 4B , the feedback device 48 may be in the form of a surgical navigation display 46 of images overlaid on a real-time camera image 49 from the camera 51. Additionally, the anatomical structures provided on the display as a graphical representation of data from one or more of the camera 51 ( FIG. 3A ), the reference array 40 ( FIG. 3A ), and the neuromonitoring system 50 may include highlighted areas of the image captured by the camera indicating the presence of any type of tissue (e.g., muscle, bone, and nerve) and anatomical structures (e.g., any one or more of vertebrae, exiting nerves, and nerve roots). The display 46 may include the anatomical structures from preoperative images of the anatomical structures (e.g., see FIG. 4A ), using, for example, computed tomography (CT), X-ray, magnetic resonance imaging (MRI), etc. Additionally, the processor may receive real-time images of the anatomical structures from the camera 51 as the trocar 30 is driven toward Kambin's triangle. As described herein, the processor can update the display of any one or more, up to all, of the position, size, and shape of the anatomical structures in FIG. 4A and update the display on display 46 in FIG. 4B based on real-time data from camera 51 images of the anatomical structures as the trocar 30 moves toward Kambin's triangle.

[0056] Further, as described herein with continued reference to FIG. 4B , the processor can display on the camera image 49 a graphical representation of the alignment between either or both of the first and second locations of the trocar 30 relative to a desired position of either or both of the first and second locations of the trocar 30. As described above with reference to FIG. 3A , the reference array 40 can provide an orientation of the trocar 30. In one example, the first location can be spaced distally from the second location. For example, the first location can be defined by the tip 27 of the trocar 30, and the second location can be defined by the trocar handle 32. In some examples, the first and second locations of the trocar 30 can be disposed along the central axis 45 of the trocar.

[0057] For at least one or both of the first and second locations of the trocar 30, the display 46 may include visual indicia, such as one or more, up to all of: 1) the location of the trocar 30; 2) the position of the trocar 30 location relative to the anatomical structure; and 3) whether the trocar location is substantially aligned with the desired location of the trocar 30 location. The indicia may further distinguish the first location from the trocar and the second location of the trocar 30. In one example, the first image icon 62 may identify the first location of the trocar, and the second image icon 64, which has different image characteristics from the first image icon, may identify the second location of the trocar. For example, the first image icon 62 and the second image icon 64 may be one or more of a size and a shape. In one example, one of the first image icon and the second image icon (e.g., the first image icon 62) may be configured as a circle, and the other of the first image icon and the second image icon (e.g., the second image icon 64) may be configured as a crosshair. Alternatively, the first image icon and the second image icon may be configured as different colors, different line thicknesses, and the like.

[0058] As the trocar 30 is driven through the anatomy toward and through Kambin's triangle, the first image icon and the second image icon have relative positions on the display that indicate whether the first location is aligned with the second location along the actual trajectory of the trocar 30 as it is driven into the anatomy. For example, when the first location is not aligned with the second location relative to the actual trajectory of the trocar 30, the first image icon is spaced apart from the second image icon on the display 46. Furthermore, the distance by which the first image icon is spaced apart from the second image icon on the display 46 informs the operator of the direction and distance to correct either or both of the first and second locations to achieve alignment of the first and second ends along the actual trajectory. Moving the first location of the trocar 30 correspondingly moves the first image icon 62 on the display 46. Similarly, moving the second location of the trocar 30 correspondingly moves the second image icon 64 on the display 46. The processor can further activate the vibration actuator 55 (see FIG. 5A) to vibrate when the first location of the trocar 30 is not aligned with the second location of the trocar along the actual trajectory of the trocar 30.

[0059] The first image icon and the second image icon can merge when the first location and the second location are aligned with each other along the actual trajectory. For example, a crosshair can be centered inside a circle when the first location and the second location are aligned with each other along the actual trajectory. When the first location and the second location of the trocar 30 are aligned with each other, the actual trajectory of the trocar 30 is along the central axis 45 of the trocar. Furthermore, when the first location and the second location of the trocar 30 are aligned with each other, the center of the display from the camera 51 can be positioned on the trajectory of movement of the trocar 30 when the camera 51 is facing distally about the central axis of the trocar. Thus, the operator can visually inspect the display 46 to assess whether the actual trajectory is aligned with Kambin's triangle or whether the actual trajectory is aligned with anatomical structures other than Kambin's triangle, such as nerves 66 (e.g., exiting nerves 21 or transverse nerve roots 23), bone tissue 68, and soft tissue 70. The operator can then adjust the actual trajectory to the desired trajectory through Kambin's triangle. As described below, the surgical system 25 can compensate for situations where the camera 51 is positioned offset from the trocar's central axis and / or angled relative to the distal direction, such that the display 46 shows the image from the camera 51 as if the camera were positioned on the central axis and facing the distal direction. Additionally, either or both of the first image icon 62 and the second image icon 64 can be a predetermined color when the actual trajectory is at least substantially aligned with the desired trajectory. "Substantially" in this context can mean that the trocar 30 is within a tolerance of the predetermined desired trajectory through Kambin's triangle so that the trocar 30 does not contact any of the nerves 21 and 23 or other tissue with which it is desirable to avoid contact with the trocar 30. For example, either or both of the first image icon 62 and the second image icon 64 can be a first color, such as red, when the actual trajectory is not substantially aligned with the predetermined desired trajectory.Either or both of the first graphical icon 62 and the second graphical icon 64 can be a second color, such as green, when the actual trajectory is substantially aligned with the predetermined desired trajectory. When the first location and the second location are aligned along the actual trajectory and the actual trajectory is substantially aligned with the desired trajectory, the actual trajectory of the trocar 30 passes through Kambin's triangle.

[0060] 5A-7 , the surgical system 25 may further include a flexible surgical access port 130 configured to provide an access pathway to the spine through Kambin's triangle 24. The flexible surgical access port 130 may include a collar 128 and a flexible surgical access body 136 extending generally distally from the collar 128. The collar 128 may be configured as an annulus defining a bore 132 that opens into the flexible body 136. The bore 132 may be cylindrical or alternatively of any desired shape. Additionally, the collar 128 may be rigid or flexible. The flexible body 136 extends from the collar 128 along a central axis 134. The flexible surgical access port 130 may define the central axis 134 extending through the flexible body 136. Flexible body 136 may define a proximal end 138a and a distal end 138b opposite proximal end 138a along central axis 134. Lumen 140 may extend through flexible surgical access port 130 from its proximal end to its distal end. Thus, lumen 140 may extend the entire length of flexible body 136 along central axis 134 from proximal end 138a to distal end 138b.

[0061] The surgical access port 130 can be coupled to the trocar 30 prior to driving the trocar 30 into the patient's anatomy and toward / through Kambin's triangle. Thus, the access assembly 43, including the trocar 30 and the surgical access port 130, can be driven along a desired trajectory to and through Kambin's triangle in the manner described herein. In particular, the trocar 30 is driven toward / through Kambin's triangle, and the surgical access port 130 moves with the trocar 30. In one example, the trocar 30 can be inserted through the surgical access port 130, and the surgical access port 130 can be coupled to the trocar 30. In particular, the distal tip 37, along with the distal region 36 and the trocar shaft 34, can be driven distally through the lumen 140 until the distal tip 37 extends from the distal end 138b of the flexible body 36. In examples where the flexible body 36 extends from the port handle 152 and port grommet 154, the distal end 36 and trocar shaft 34 can be driven distally through the port handle 152 and port grommet 154 and then through the lumen 140 until the port handle 152 abuts or nests with the trocar handle 32. In one example, the trocar 30 can be releasably locked to the surgical access port 130 as the assembly 43 is driven toward and through Kambin's triangle.

[0062] It should be understood that the access assembly 43, including the trocar 30 and the surgical access port 130, may be the first instrument inserted into a patient during a surgical procedure. Once the trocar 30 has been driven through Kambin's triangle and toward the disc space, the trocar 30 is unlocked from the surgical access port 130, and can then be removed from the surgical access port 130, and surgical instruments for performing the surgical procedure within the disc space can be delivered through the lumen 140 of the surgical access port 130.

[0063] The proximal end 138a can be coupled to the collar 128 in any desired manner such that the lumen 140 is in communication with the bore 132 of the collar 128. In particular, the central axis of the bore 132 can be aligned with the central axis 134 of the flexible surgical access port 130. The surgical system 25 can include a handle 142 configured to support the flexible surgical access port 130. In one example, the handle 142 can be coupled to the collar 128 in any suitable manner so as to direct the flexible surgical access port 130 toward a target anatomical site, such as Kambin's triangle 24. Thus, a device, such as a surgical instrument or implant, can be inserted distally through the bore 132 and into the lumen 140 toward the spine. The collar 128 can define the proximal end of the flexible surgical access port 130.

[0064] 6A-6B, the flexible body 136, and thus the flexible surgical access port 130, can be advantageously configured to radially expand from a first configuration having a first cross-sectional dimension to a second or expanded configuration having a second cross-sectional dimension greater than the first cross-sectional dimension. The first and second cross-sectional dimensions can be measured along the same direction, extending through the central axis 134. In some examples, the first and second cross-sectional dimensions can be configured as diameters when the cross-section of the flexible body 136 is circular. The flexible body 136 can define any suitable shape as desired. The flexible body 136, and thus the flexible surgical access port 130, can be woven or nonwoven as desired. If woven, the flexible body 136 can be made from any suitable pattern of woven fibers 144 that define the weave pattern. The description of flexible body 136 herein can be applied with equal force to flexible surgical access port 130. In one example, fibers 144 can be woven to define a mesh. In another example, fibers 144 can define a lattice. Thus, fibers 144 can intersect at respective intersection angles that can change as flexible body 136 expands radially. Thus, one or more of the intersection angles can be measured to determine a quantification of the outer diameter of flexible body 136. In yet another example, fibers 144 can be braided. For example, fibers 144 can be helically wound to define a braid.

[0065] In operation, the flexible body 136 can be folded into a first configuration and biased into a normal, relaxed geometric configuration. In the normal, relaxed geometric configuration, the flexible body 136 is no longer folded, but is not expanded beyond its normal, relaxed geometric shape. For example, when the flexible body 136 is configured as a cylindrical body, the flexible fibers 144 may be folded in the first configuration and thus not define a cylinder. The flexible body 136 can be biased into its normal, relaxed cylindrical geometric shape, if desired. However, the flexible body 136 is not yet expanded. Thus, the first configuration can be either folded or its normal, relaxed geometric shape in the first configuration. The flexible body 136 is configured to expand beyond the first configuration to an extended position, whereby at least a portion of the flexible body is expanded beyond its normal, relaxed geometric configuration. The expansion of the flexible body 136 to the second position may be along a direction perpendicular to the central axis 134 .

[0066] The surgical system 25 can include a surgical instrument 146 configured to be driven distally through the lumen 140. The surgical instrument can have a cross-sectional dimension that is larger than the cross-sectional dimension of the flexible body when the flexible body is in the first configuration. The cross-sectional dimension of the surgical instrument 146 is oriented in the same direction as the cross-sectional dimension of the flexible body 136. Thus, the surgical instrument 146 applies a radially outward force that urges the flexible body 136 to expand into a second configuration beyond its normal relaxed geometric configuration. When the flexible body 136 defines a lattice structure, the surgical instrument can urge the flexible body 136 to change the crossing angle, causing the flexible body 136 to expand into the second configuration. Thus, in some examples, the flexible body 136 can expand into the second configuration without the fibers 144 substantially expanding along their respective lengths. In this regard, the fibers 144 can be substantially rigid along their lengths.

[0067] In other examples, the fibers 144 may be expandable along their length to expand the flexible body 136. For example, the fibers 144 may extend circumferentially around a central axis such that expansion of the fibers 144 along their length causes the flexible body 136 to expand radially. For example, the fibers 144 may be defined by an elastically deformable elastomer, which may define a braid, mesh, lattice structure, or any suitable alternative woven structure, as desired. Thus, elongation of the fibers 144 may contribute to the movement of the flexible body 136 from the first configuration to the second configuration. In other examples, the flexible body 136 may be nonwoven or made from an expandable material. The flexible body 136 may be elastic so that it moves toward or to the first configuration after being expanded to the second configuration. In other examples, the flexible body 136 may be substantially inelastic so that compressive forces from the surrounding anatomical tissue can move the flexible body 136 from the second configuration toward or to the first configuration. The fibers can be made from Nickel-Titanium (NiTi) or any suitable alternative material desired. In one example, the filaments can have shape memory so that once the flexible body is deflected into a desired shape, it remains in the desired shape.

[0068] The terms "substantially," "approximately," and their derivatives, and words of similar import, when used to describe size, shape, spatial relationship, distance, orientation, extension, and other similar parameters, include, in addition to the stated parameter, ranges of up to 10% more and up to 10% less than the stated parameter, such as ranges of up to 5% more and up to 5% less, such as ranges of up to 3% more and up to 3% less, such as ranges of up to 1% more and up to 1% less.

[0069] 4A-4C , surgical instrument 146 can be sized to be inserted through bore 132 (see FIG. 3 ) of collar 128. Furthermore, when flexible body 136 is in a first configuration, a first cross-sectional dimension is smaller than a cross-sectional dimension of bore 132 of collar 128. Thus, when surgical instrument 146 is driven through bore 132 and into lumen 140, in some instances, flexible body 136 expands to a second configuration having a second cross-sectional dimension that is equal to or smaller than the cross-sectional dimension of bore 132. It will be appreciated that in other instances, surgical instrument 146 can be inserted through bore 132 in a first orientation and then cycled within lumen 140 in a second orientation to expand lumen 140 to a second cross-sectional dimension that is larger than the cross-sectional dimension of bore 132. Flexible body 136 can abut at least a portion of or all of the surgical instrument that expanded flexible body 136.

[0070] Thus, in operation, a surgical instrument 146, such as a surgical tool or implant, can be driven through bore 132 and into flexible body 136. Surgical instrument 146 can be sized to fit through bore 132 and can be sized larger than a first cross-sectional dimension of flexible body 136. Thus, when surgical instrument 146 is driven through lumen 140, force from surgical instrument 146 biases a localized region of flexible body 136 to radially expand from a first configuration to a second configuration. The localized region can include an aligned location of flexible body 136 aligned with surgical instrument 146 and a region adjacent to the aligned location that is biased to expand by force from surgical instrument 146 as surgical instrument 146 moves through lumen 140. That is, the region of flexible body 136 that is aligned with surgical instrument 146, or the region of flexible body 136 adjacent to the portion of flexible body 136 that is aligned with surgical instrument 146, can expand outward to enlarge lumen 140 to accommodate a surgical instrument having a larger cross-sectional dimension than the cross-sectional dimension of flexible body 136 when the flexible body is in the first configuration. Typically, the aligned region expands more than the adjacent region. When the force from surgical instrument 146 is removed, for example, when the surgical instrument is moved away from the aligned region, the expanded portion of flexible body 136 can return toward or to the first configuration. The remote region of flexible body 136 away from surgical instrument 146 can be in the first configuration.

[0071] Thus, as the surgical instrument 146 is driven through the lumen 140, the previously expanded region of the surgical instrument 146 can remain in the second configuration or move from the second configuration toward or back to the first configuration as the surgical instrument 146 moves distally along the lumen 140 a sufficient distance such that the portion of the flexible body 136 that previously defined a local region now defines a remote region such that the surgical instrument 146 no longer exerts sufficient force on the remote region to expand it from the first configuration. The local region 136 of the flexible body moves distally as the surgical instrument is advanced distally within the lumen 140. Conversely, the local region 136 of the flexible body 136 moves proximally as the surgical instrument is advanced proximally within the lumen 140. As the surgical instrument 146 moves within the lumen 140, a location of the flexible body 136 that is biased by the surgical instrument 146 to expand to the second configuration can revert to or toward the first configuration when the surgical instrument 146 moves away from the location, such that the location defines a remote region. The natural bias of the flexible body 136 can bias the flexible body 136 toward or toward the first configuration after the surgical instrument 146 has passed. Thus, the surgical instrument 146 biases the flexible body 136 to expand as the surgical instrument 146 selectively moves distally and proximally within the lumen 140. It should be understood that the local expansion of the flexible body 136 can thus be instantaneous, as the local region becomes a remote region and then moves toward or back to the first configuration once the surgical instrument has passed.

[0072] As a result, the anatomical tissue surrounding the flexible body 136 experiences only momentary compression due to the momentary expansion of the flexible body 136 from the first configuration to the second configuration. In some areas surrounding the flexible body 136, the surrounding anatomical tissue may include the patient's fatty and muscular tissue. In other areas of the flexible body 136, the surrounding tissue may include nerves, such as the exiting nerve 21 and / or transverse nerve root 23, which partially define Kambin's triangle. Advantageously, large surgical instruments 146 can pass through the flexible body 136 while causing only momentary contact between the flexible body 136 and the nerve. In contrast, a rigid conduit sized to accommodate a large surgical instrument will compress the nerve as long as the conduit is in place during the surgical procedure. Thus, the surgical system 25 prevents prolonged compression of the nerve during spinal surgery.

[0073] 6C , flexible body 136 can also be configured to deflect along a direction perpendicular to central axis 134. Thus, when surgical instrument 146 is inserted into lumen 140 with a curvature, surgical instrument 146 can impart a curvature to flexible body 136 accordingly. Thus, central axis 134 can extend along one or more curved paths. When surgical instrument 146 is removed from lumen 140, flexible body 136 can move toward or return to the first configuration. Alternatively, or additionally, a surgical instrument 146 inserted into lumen 140 along a direction angularly offset in a selected direction relative to central axis 134 can correspondingly deflect at least a portion of central axis 134 and / or the distal end of flexible body 136 in the selected direction. Thus, the surgical instrument 146 can change the trajectory of the lumen, defined by the direction separating the proximal end 138a and the distal end 138b, from a first trajectory to a second trajectory. The first trajectory can be a trajectory through Kambin's triangle as defined by the trocar 30. Moving from the first trajectory to the second trajectory can be advantageous when it is desired to perform one or more procedures on different regions of the spine. The flexible body 136 can define the first trajectory when in the first configuration. The distal end 138b of the flexible body 136 can also define the distal end of the flexible surgical access port 130.

[0074] Referring now to FIG. 5A , as described above, the surgical instrument 146 of the surgical system 25 can include a trocar 30 or any suitable alternative access member that can be configured to establish a trajectory to a target anatomical site. In some examples, the trocar 30 can extend through the lumen 140 while the flexible body 136 remains in a first configuration. In other examples, the trocar 30 can expand the flexible body 136 beyond the first configuration to a second configuration. While the trocar 30 extends through the lumen 140, the trocar 30 can be driven through the patient's anatomy toward the target anatomical site, for example, through Kambin's triangle along a desired trajectory in the manner described above. The trocar shaft 34 can be sized to extend through the bore 132 of the collar 128 of the flexible surgical access port 130 (see FIG. 5B ) and can be defined by either or both of the port handle 152 and the proximal port grommet 154 of the flexible surgical access port 130. The flexible body 136 can extend distally from the proximal port grommet 154. The proximal port grommet 154 can have an inner cross-sectional dimension, such as a diameter, equal to the expanded cross-sectional dimension of the flexible body 136. The flexible surgical access port 130 can further include a distal port grommet, the distal port grommet extending distally from the flexible body 136 and having an inner cross-sectional dimension equal to the inner cross-sectional dimension of the proximal port grommet 154. The distal region 36 of the trocar body 31 and the trocar shaft 34 can be driven distally through the port handle 152 and the proximal port grommet 154 and through the lumen 140, causing the tapered distal portion 136b of the trocar shaft 34 to extend distally beyond the distal end of the flexible body 136. In one example, the target anatomical site is defined by a target surgical location, which can be defined by a superior articular process. Alternatively or additionally, the target surgical site may be defined by an intervertebral disc space. The trocar handle 32 may seat against or be removably coupled to the port handle 152 when the trocar shaft 34 is fully driven through the flexible body 136.The distal tip 37 of the trocar 30 can extend distally of the surgical access port 130 when the trocar 30 is fully inserted into the access port.

[0075] The trocar 30 may be detached and removed from the surgical access port by moving the trocar 30 proximally relative to the surgical access port until the trocar 30 is removed. The lumen of the surgical access port 130 may then provide a working channel to the intervertebral disc space. The surgical access port 130 may be docked to one or both of the vertebral bodies defining the intervertebral space either before or after the trocar 30 is detached and removed from the surgical access port 130. The surgical access port 130 may include any desired suitable docking structure that may be releasably secured to the vertebra(s).

[0076] In another example (see FIG. 7 ), a surgical system can include a first surgical access port 136a and a second surgical access port 136b. The trocar 30 can guide the first surgical access port 136a into Kambin's triangle and can be removed from the first surgical access port 136a so that the lumen of the first surgical access port 136a provides a working channel to Kambin's triangle. After a surgical step is performed through the working channel of the first surgical access port 136a, the second surgical access port 136b can be inserted distally through the lumen of the first surgical access port 136a, through Kambin's triangle, and into the intervertebral disc space. The lumen of the second surgical access port 136b thereby defines a working channel to the intervertebral disc space.

[0077] 7 , in some examples, the surgical instrument of the surgical system 25 that may be driven through the lumen of the surgical access port 130 into the intervertebral space may include an intervertebral implant 156 sized to be driven distally through the lumen 140. The intervertebral implant 156 may be configured as a spinal fusion cage. Accordingly, the flexible body 136 may be configured to receive the intervertebral implant 156. The intervertebral implant 156 may be moved through the lumen 140 into the intervertebral disc space. The intervertebral implant 156 may expand the flexible body 136 from a first configuration to a second configuration as the intervertebral implant 156 moves distally through the lumen 140. The implant 156 expands the flexible body 136 140 in an area adjacent to the implant 156 as the implant 156 moves distally through the lumen 140. The region of the flexible body 136 can move toward or return to the first configuration after the intervertebral implant 156 has passed distally. Thus, any nerves that become compressed due to the expansion of the flexible body 136 are only momentarily compressed until the implant 156 has passed distally.

[0078] It should be understood that various surgical instruments of surgical system 25 can radially expand flexible body 136 different amounts from the first configuration, and all such degrees of expansion can define a second configuration. The maximum second cross-sectional dimension can be approximately four times the first cross-sectional dimension. By way of example, flexible body 136 can define a first cross-sectional dimension of approximately 4 mm when in the first configuration and a maximum second cross-sectional dimension of approximately 15 mm when expanded. Surgical access port 130 and the first and second surgical access ports are described in U.S. Patent Application No. 17 / 510,709, filed October 26, 2021, the disclosure of which is incorporated herein by reference as if set forth in its entirety.

[0079] Although the illustrated embodiments and accompanying description are directed to applications in spinal surgical procedures, particularly minimally invasive spinal surgery, the devices, systems, and methods described herein are not limited to these applications.

[0080] In some embodiments, intraoperative feedback may be received from at least one surgical instrument regarding the positioning of the identified neural structures, and the patient-specific surgical access plan may be updated.

[0081] In some embodiments, real-time positioning of at least one of the identified neural structures, the surgical instrument, and the patient position may be displayed.

[0082] 8A-10, the terms artificial neural network (ANN) and neural network may be used interchangeably herein. An artificial neural network may be configured to determine a classification (e.g., type of object) based on an input image or other sensed information. An artificial neural network is a network or circuit of artificial neurons or nodes and may be used for predictive modeling.

[0083] The predictive model may be and / or may include one or more neural networks (e.g., deep neural networks, artificial neural networks, or other neural networks), other machine learning models, or other predictive models.

[0084] Disclosed implementations of artificial neural networks may transform input data by applying weights and applying functions, which are neural layers. The functions may be linear or, more preferably, nonlinear activation functions such as the logistic sigmoid function, the Tanh function, or the rectified linear unit (ReLU) function. The intermediate output of one layer may be used as input to the next layer. Neural networks learn through iterative transformations, with multiple layers that may be combined into a final layer that makes predictions. This learning (i.e., training) may be performed by varying weights or parameters to minimize the difference between predictions and expectations. In some embodiments, information may be fed forward from one layer to the next. In these or other embodiments, neural networks may have, for example, memory or feedback loops that form the neural network. Some embodiments may adjust parameters, for example, via backpropagation.

[0085] An artificial neural network is characterized by its model features, which include activation functions, loss or cost functions, learning algorithms, optimization algorithms, etc. The structure of an artificial neural network can be determined by several factors, including the number of hidden layers, the number of hidden nodes in each hidden layer, input feature vectors, target feature vectors, etc. Hyperparameters can include various parameters that need to be initially set for training, as well as initial values ​​of model parameters. Model parameters can include various parameters that are to be determined through training. Hyperparameters can be set before training, and model parameters can be set through training to specify the architecture of an artificial neural network.

[0086] The learning rate and accuracy of an artificial neural network depend not only on the structure of the artificial neural network and the learning optimization algorithm, but also on its hyperparameters. Therefore, to obtain a good learning model, it is important to select not only the appropriate structure and learning algorithm for the artificial neural network, but also the appropriate hyperparameters.

[0087] The hyperparameters may include initial values ​​of inter-node weights and biases, a mini-batch size, the number of iterations, a learning rate, etc. Furthermore, the model parameters may include inter-node weights, inter-node biases, etc.

[0088] Typically, an artificial neural network is first trained by experimentally setting the hyperparameters to various values, and based on the results of the training, the hyperparameters can be set to optimal values ​​that provide a stable learning rate and accuracy.

[0089] Some embodiments of the model 264 in the system 25 shown in FIG. 8B may include a convolutional neural network (CNN). A convolutional neural network may include an input layer, an output layer, and multiple hidden layers. The hidden layers of a convolutional neural network typically include a series of convolutional layers that convolve with multiplication or other dot products. The activation function is typically a ReLU layer, followed by additional convolutions such as pooling layers, fully connected layers, and normalization layers, which are called hidden layers because the inputs and outputs of these layers are masked by the activation function and the final convolution.

[0090] A convolutional neural network calculates output values ​​by applying a specific function to input values ​​coming from the receptive field of the previous layer. The function applied to the input values ​​is determined by a vector of weights and biases (typically real numbers). Learning in a neural network proceeds by iteratively adjusting these biases and weights. The vector of weights and biases is called a filter and represents a specific feature of the input (e.g., a specific shape).

[0091] In some embodiments, the training of model 264 may be reinforcement, supervised, semi-supervised, and / or unsupervised. For example, there may be a model for a particular prediction that is trained using one of these types, while another model for another prediction may be trained using another of these types.

[0092] Supervised learning is a machine learning task that learns a function that maps inputs to outputs based on example input-output pairs. It can infer the function from labeled training data that contains a set of training examples. In supervised learning, each example is a pair consisting of an input object (typically a vector) and a desired output value (the supervised signal). A supervised learning algorithm analyzes the training data and produces an inference function that can be used to map new examples. The algorithm can also correctly determine the class labels of unseen instances.

[0093] Unsupervised learning is a type of machine learning that looks for previously undetected patterns in datasets that have no existing labels. In contrast to supervised learning, which typically utilizes human-labeled data, unsupervised learning does not rely on principal components (e.g., to preprocess and reduce the dimensionality of high-dimensional datasets while preserving the original structure and relationships in the original dataset) and cluster analysis (e.g., to identify commonalities in the data and react based on the presence or absence of such commonalities in each new piece of data).

[0094] Semi-supervised learning utilizes supervised and unsupervised techniques.

[0095] Model 264 may analyze predictions made on a reference set of data called a validation set. In some use cases, reference outputs resulting from assessment of predictions made on the validation set may be provided as input to a predictive model, which may be utilized to determine whether its predictions are accurate, determine a level of precision or completeness with respect to the validation set data, or make other determinations. Such determinations may be utilized by the predictive model to improve the precision or completeness of its predictions. In another use case, accuracy or completeness metrics for the predictive model's predictions may be provided to the predictive model, which may then utilize the accuracy or completeness metrics to improve the precision or completeness of its predictions with respect to the input data. For example, a labeled training dataset may enable model improvement. That is, a training model may use a validation set of data to iterate through model parameters until arriving at a final set of parameters / weights for use in the model.

[0096] In some embodiments, the training component 232 depicted in FIG. 8B may implement an algorithm for building and training one or more deep neural networks. The models used may have already been trained on data according to this algorithm. In some embodiments, the training component 232 may train a deep learning model on the training data 262 after successful tests with these or other algorithms have been performed and after the model has been provided with a sufficiently large data set, providing even greater accuracy.

[0097] Models implementing neural networks can be trained using training data in storage / database 262. The training data can include many anatomical attributes. For example, this training data obtained from prediction database 260 can include hundreds, thousands, or millions of pieces of information (e.g., images, scans, or other sensed data) describing parts of cadavers or living bodies to provide a sufficient representation of a patient population or other group. The dataset can be split between training, validation, and test sets in any suitable manner. For example, some embodiments may use approximately 60% or 80% of the images or scans for training or validation, and another approximately 40% or 20% for validation or testing. In another example, training component 232 can randomly split the labeled images, with the exact ratio of training data to test data varying throughout. When a satisfactory model is found, training component 232 can train it on 95% of the training data and further validate it on the remaining 5%.

[0098] The validation set may be a subset of the training data that is kept hidden from the model to test its accuracy. The test set may be a dataset that is new to the model to test its accuracy. The training dataset used to train the predictive model 64 may utilize SQL Server and a Pivotal Greenplum database for data storage and retrieval purposes via the training component 232.

[0099] In some embodiments, training component 232 may be configured to obtain training data from any suitable source, for example, via predictive database 260, electronic storage 222, external resources 224 (which may include, for example, a sensor, scanner, or another device), network 270, and / or user interface device 218. Training data may include captured images, smells, lights / colors, shape sizes, noise or other sounds, and / or other discrete instances of sensed information.

[0100] In some embodiments, the training component 232 may enable one or more predictive models to be trained. Training of the neural network may be performed through several iterations. For each training iteration, the classification predictions of the neural network (e.g., layer outputs) may be determined and compared to corresponding known classifications. For example, sensed data known to capture an enclosed environment containing dynamic and / or static objects may be input to the neural network during training or validation to determine whether the predictive model can properly predict a path for a user to reach or avoid the object. Thus, the neural network is configured to receive at least a portion of the training data as an input feature space. Once trained, the model may be stored in the database / storage device 264 of the prediction database 260, as shown in FIG. 8B, and then used to classify a sample of images or scans based on visual attributes.

[0101] The electronic storage device 222 of FIG. 8B includes an electronic storage medium that electronically stores information. The electronic storage medium of the electronic storage device 222 may comprise a system storage device provided integrally (i.e., substantially non-removably) with the system 25 and / or a removable storage device removably connectable to the system 25 via, for example, a port (e.g., a USB port, a FireWire port, etc.) or a drive (e.g., a disk drive, etc.). The electronic storage device 222 may be a separate component within the system 25 (in whole or in part), or the electronic storage device 222 may be provided integrally (in whole or in part) with one or more other components of the system 25, such as the user interface device 218, the processor 221, etc. As shown in FIG. 8A, the processor 221 may further receive images from a pre-operative imaging device 223, such as a CT scan, an MRI, or an X-ray. The processor 221 may further receive data from either or both the camera electrode and the neuro-monitoring electrode of the trocar 30 and identify the first and second locations using a first icon 62 and a second icon 64. The processor 221 can further provide real-time surgical navigation 227, for example, on the display 46 (see FIG. 4B).

[0102] 8B , in some embodiments, electronic storage 222 may be located in a server with processor 221, in a server that is part of external resource 224, in user interface device 218, and / or elsewhere. Electronic storage 222 may comprise a memory controller and one or more of an optically readable storage medium (e.g., optical disk, etc.), a magnetically readable storage medium (e.g., magnetic tape, magnetic hard drive, floppy drive, etc.), a charge-based storage medium (e.g., EPROM, RAM, etc.), a solid-state storage medium (e.g., flash drive, etc.), and / or other electronically readable storage medium. Electronic storage 222 may store software algorithms, information obtained and / or determined by processor 221, information received via user interface device 218 and / or other external computing systems, information received from external resource 224, and / or other information that enables system 25 to function as described herein.

[0103] External resources 224 may include sources of information (e.g., databases, websites, etc.), external entities participating in system 25, one or more servers external to system 25, networks, electronic storage devices, equipment associated with Wi-Fi technology, equipment associated with Bluetooth technology, data input devices, power sources (e.g., battery-powered or line-powered, such as directly to 110 volts AC or indirectly via AC-to-DC conversion), transmit / receive elements (e.g., antennas configured to transmit and / or receive wireless signals), network interface controllers (NICs), display controllers, graphics processing units (GPUs), and / or other resources. In some implementations, some or all of the functionality attributed herein to external resources 224 may be provided by other components or resources included in system 25. The processor 221, external resources 224, user interface device 218, electronic storage device 222, network, and / or other components of system 25 may be configured to communicate with each other via wired and / or wireless connections, such as a network (e.g., a local area network (LAN), the Internet, a wide area network (WAN), a radio access network (RAN), a public switched telephone network (PSTN), etc.), cellular technology (e.g., GSM, UMTS, LTE, 5G, etc.), Wi-Fi technology, another wireless communication link (e.g., radio frequency (RF), microwave, infrared (IR), ultraviolet (UV), visible light, cm wave, mm wave, etc.), base station, and / or other resources.

[0104] The user interface devices 218 of the system 25 may be configured to provide an interface between one or more users and the system 25. The user interface devices 218 are configured to provide information to and / or receive information from one or more user interface devices 218, including user interfaces and / or other components. The user interfaces may be and / or include graphical user interfaces configured to present views and / or fields configured to receive inputs and / or selections related to particular functions of the system 25, and / or may provide and / or receive other information. In some embodiments, the user interface of the user interface devices 218 may include multiple separate interfaces associated with the processor 221 and / or other components of the system 25. Examples of interface devices suitable for inclusion in the user interface devices 218 include a touchscreen, keypad, touch-sensitive and / or physical buttons, switches, keyboards, knobs, levers, displays, speakers, microphones, indicator lights, audible alarms, printers, and / or other interface devices. The present disclosure also contemplates that the user interface devices 218 may include a removable storage device interface. In this example, information may be loaded into the user interface device 218 from a removable storage device (eg, smart card, flash drive, removable disk) that allows a user to customize the implementation of the user interface device 218.

[0105] In some embodiments, user interface device 218 is configured to provide a user interface, processing power, a database, and / or electronic storage to system 25. As such, user interface device 218 may include processor 221, electronic storage 222, external resources 224, and / or other components of system 25. In some embodiments, user interface device 18 is connected to a network (e.g., the Internet). In some embodiments, user interface device 18 does not include processor 221, electronic storage 222, external resources 224, and / or other components of system 25, but instead communicates with these components via dedicated lines, buses, switches, networks, or other communication means. Communication may be wireless or wired. In some embodiments, user interface device 218 is a laptop, desktop computer, smartphone, tablet computer, and / or other user interface device.

[0106] Data and content may be exchanged between the various components of system 25 through communication interfaces and paths using any one of several communication protocols. In one example, data may be exchanged using protocols used to communicate data over packet-switched internetworks, for example, using the Internet Protocol suite, also known as TCP / IP. Data and content may be delivered from a source host to a destination host using datagrams (or packets) based solely on their addresses. To this end, the Internet Protocol (IP) defines an addressing method and structure for datagram encapsulation. Of course, other protocols may be used. Examples of Internet protocols include Internet Protocol version 4 (IPv4) and Internet Protocol version 6 (IPv6).

[0107] In some embodiments, processor 221 may form part of (e.g., in the same or a separate housing) a user device, a consumer electronic device, a mobile phone, a smartphone, a personal data assistant, a digital tablet / pad computer, a wearable device (e.g., a watch), AR goggles, VR goggles, a reflective display, a personal computer, a laptop computer, a notebook computer, a workstation, a server, a high performance computer (HPC), a vehicle (e.g., an embedded computer in the dashboard or in front of a seat in a car or airplane), a gaming or entertainment system, a set-top box, a monitor, a television (TV), a panel, a spacecraft, or any other device. In some embodiments, processor 221 is configured to provide information processing capabilities in system 25. Processor 221 may comprise one or more of a digital processor, an analog processor, a digital circuit designed to process information, an analog circuit designed to process information, a state machine, and / or other mechanisms for electronically processing information. While processor 221 is shown in FIGS. 8A-8B as a single entity, this is for illustrative purposes only. In some embodiments, processor 221 may comprise multiple processing units, which may be physically located within the same device (e.g., a server), or processor 221 may represent the processing functionality of multiple devices acting in concert (e.g., one or more servers, user interface device 218, devices that are part of external resources 224, electronic storage device 222, and / or other devices).

[0108] 8B, processor 221 is configured to execute one or more computer program components via machine-readable instructions. The computer program components may include one or more of information component 231, training component 232, prediction component 234, annotation component 236, trajectory component 238, and / or other components. Processor 221 may be configured to execute components 231, 232, 234, 236, and / or 238 by software, hardware, firmware, any combination of software, hardware, and / or firmware, and / or other mechanisms for configuring processing power on processor 221.

[0109] Although components 231, 232, 234, 236, and 238 are illustrated as being co-located within a single processing unit, it should be understood that in embodiments in which processor 221 comprises multiple processing units, one or more of components 231, 232, 234, 236, and / or 238 may be located remotely from the other components. For example, in some embodiments, processor components 231, 232, 234, 236, and 238 may each comprise a separate and distinct set of processors. The description of functionality provided by different components 231, 232, 234, 236, and / or 238 described below is for purposes of illustration and not limitation, and any of components 231, 232, 234, 236, and / or 238 may provide more or less functionality than described. For example, one or more of components 231, 232, 234, 236, and / or 238 may be excluded, and some or all of its functionality may be provided by other components 231, 232, 234, 236, and / or 238. As another example, processor 221 may be configured to execute one or more additional components that may perform some or all of the functionality attributed below to one of components 231, 232, 234, 236, and / or 238.

[0110] The disclosed approach relates to an advanced imaging solution and system for augmenting camera images in real time with clinically relevant information, such as nerve and bony structures. The output of the system 25 may be a camera image overlaid with real-time relevant structures. The user can select what level of information / refinement may be required. The overlay may be performed based on a confidence interval of the anatomical region of interest. The confidence interval may be determined based on information available prior to access and then updated to narrow the estimated region of interest as new information becomes available intraoperatively, for example, as the camera is advanced within the port. Figure 4B is an exemplary output that may be displayed on the system monitor.

[0111] In some embodiments, the confidence intervals may be similar to or the same as those described above, and each may encode how confident the system 25 is that the anatomical structure is actually what is predicted to be. For example, the annotation component 236 may overlay a transition zone or margin, or annotate a color-coded bull's-eye, with green indicating the highest confidence. Also, when annotating the presence of Kambin's triangle 24 in a camera image, the boundary of the triangle may become more red as it extends outward. The red portion may still be near Kambin's triangle 24, but may represent a lower degree of confidence that this is the case. The same or similar approach may be implemented when indicating nerve roots or other structures. For example, the annotation component 236 may indicate where the center of the nerve is with 100% confidence, but the boundary may change appearance as it extends outward to indicate increased ambiguity.

[0112] In some embodiments, the annotation component 236 may indicate each pixel in the captured image as to whether it represents a nerve, a Kambin triangle, or other structure. For example, the prediction component 234 may indicate that there is a 90% probability that the pixel represents a Kambin triangle 24 and a 60% probability that the pixel represents a nerve 21. In this example, the annotation component 236 may then take the maximum of these two probabilities when determining to positively annotate that pixel or region as a Kambin triangle. Alternatively, there may be a color code that blends colors (e.g., red and green) to visually represent the level of confidence that the prediction is accurate. Regardless of this annotation approach, the representation may be updated in real time as access is gained and as the camera 51 advances within it.

[0113] In some embodiments, model 264 may be a single convolutional neural network or separate neural networks that output all three of: (i) vertebral bodies and foramina, (ii) nerve roots, and (iii) bony landmarks. In other embodiments, there may be three networks, each outputting one of the three different types of anatomical structures. Thus, semantic segmentation is a contemplated approach. A class probability may be predicted for each of the three different types of structures. For each pixel, there may be a probability that the pixel is a particular anatomical structure. For example, in one example, the probability of a pixel may be 80% Kambin's triangle 24, 10% superior articular process (SAP), and 10% outgoing nerve 21. Based on this prediction, the annotation would indicate that the pixel belongs to Kambin's triangle 24. Detection can be further improved by leveraging shape priors, e.g., pixels representing Kambin's triangles may be grouped to resemble a triangle.

[0114] In some implementations, the pre-operative scans from CT 255 and / or MRI 256 may have been taken some time (e.g., a month) ago, which may be important because the region of interest may have already changed and / or the patient position during surgery may be different than during the scan, making the scan somewhat outdated. And as tools and / or physicians access the scene, the region of interest will be manipulated. Thus, the images captured from camera 51 can provide an anchor that shows the actual real-time region of interest, as opposed to a CT and / or MRI scan that simply shows what is expected in the region of interest.

[0115] In some embodiments, the prediction component 234 may adapt the prediction based on the patient, for example, by predicting using only a CT scan and then adjusting the prediction or re-prediction based on images captured from the camera 51 in real time. Thus, these images may be used along with previously taken scans of the patient. For example, a scan from the CT 255 may help determine the region of interest, and then, when the camera 51 is initiated, the prediction of the location of Kambin's triangle 24 may be updated in real time. In this or another example, orientation may change. Preoperative scans may provide additional information for the processor to identify Kambin's triangle 24 and / or adjust the actual trajectory of the advancing trocar 30.

[0116] In some embodiments, the trajectory component 238 can determine whether the trajectory of advancement of the trocar 30 meets the criteria. Then, in response to determining that the trajectory did not meet the criteria, the trajectory component 238 can provide correction data to the trajectory so that the criteria are met. Thus, the processor can display correction information to adjust the actual trajectory of the trocar 30 to a desired trajectory of the trocar 30 that meets the criteria.

[0117] While embodiments are contemplated herein that recognize or detect anatomical structures from camera images alone, CT and / or MRI scans can be useful by providing more information (e.g., relative orientation and size) that can be used to improve the accuracy of such recognition or detection. For example, nerve roots 21, 23 can be identified using MRI scans corresponding to captured images, and model 264 is trained using training data that includes ground truth, labeled based on nerve root structures identified in previously taken MRI scans.

[0118] In one example, the prediction component 234 can predict the presence of one or more anatomical structures (e.g., Kambin's triangle, nerves, soft tissue, and / or bony structures) using only the camera 51 and a convolutional neural network or U-Net. U-Net is recognized as a (deep) convolutional neural network for use in biomedical image segmentation. In another example, the prediction of the anatomical structures can be performed using at least one pre-operative scan from at least one of an MRI 256 and a CT 255. In yet another example with a navigated camera 51, the prediction can be performed using output from a two-dimensional (2D) CT (e.g., a C-arm 254). The prediction component 234 can identify Kambin's triangle and / or bony landmarks using 2D-to-3D image reconstruction. The annotation component 236 can then overlay a representation of the identifications onto the camera image, as described above with respect to FIG. 4B. Therefore, using a calibration target or a navigated C-arm, Kambin's triangle may be predicted based on an atlas or statistical shape model depending on the patient's phenotype.

[0119] In one or more of these embodiments, an expert or surgeon with prior knowledge may annotate or label images of training data in advance (e.g., which surgeons have already constructed to indicate the location of anatomical structures), and then build upon that, e.g., learning directly from a statistical set of other samples. The annotated images may have various levels of tissue penetration or bioavailability. Once trained, the model 264 of these embodiments may be used to predict the presence of these structures in captured images, each with a corresponding confidence interval around them. As more images become available during access, the boundaries of these structures may be narrowed.

[0120] In some embodiments, the trajectory component 238 may use the camera image and various landmarks to provide orientation information and corrections (e.g., when not being navigated). For example, if the camera orientation is changed during a medical procedure, this component can analyze the rotation of landmarks in the image and maintain a constant orientation of the image to maintain the same field of view, which the user may prefer. As the camera rotates, the prediction component 234 may detect structures elsewhere, and the trajectory component 238 may then infer how much the camera 51 has been rotated to maintain that pose. In embodiments in which the camera is navigated, the trajectory component 238 may already know how much the scene has been rotated in order to perform the appropriate corrections.

[0121] In some embodiments, information component 231 may store and then learn from information about how the region of interest was accessed (e.g., as a model parameter or for hyperparameter tuning). In these or other embodiments, a 3D CT scan may enable the use of previous bony anatomical structure information to train model 264. The convolutional neural network implemented by model 264 may perform segmentation. This segmentation may be of spinal structures via CT scans. Segmentation aids in the detection of certain structures, for example, when Kambin's triangle 24 is suspected to be below or above these structures. Thus, the context of what is in the camera 51 image may be determined, increasing the probability of improved detection of the triangle.

[0122] In some embodiments, patient demographic information (e.g., size, weight, gender, bone health, or another attribute) and which levels may be lumbar (e.g., L1, L2 vs. L4, L5) may be obtained via training component 232 and / or prediction component 234. These attributes may serve as model parameters or in hyperparameter tuning to help improve performance.

[0123] As mentioned above, some embodiments of the convolutional neural network of model 264 may have only camera images as input (i.e., for training and during deployment), e.g., a surgeon performs ground truth annotation. However, other embodiments may have camera images, some high-level information, and CT scans (and possibly even MRI scans) for the input, e.g., using 3D CT scan segmentation results as ground truth. The overlaid output from these embodiments (e.g., as shown in FIG. 4B ) may be similar, but in the latter case, other embodiments have more accurate predictions due to having segmentation information, no longer requiring labeling by the surgeon. In other words, the CT scan may be good enough to automatically detect Kambin's triangle 24 through a convolutional neural network and then transfer that learning using camera images to the convolutional neural network.

[0124] In some embodiments, annotation for learning performed using CT scans can be supervised, unsupervised, or semi-supervised.

[0125] In some embodiments, the annotation component 236 can provide the physician with a user interface showing the location of each anatomical structure (e.g., within the region displayed in the example of FIG. 4B or another region of interest) based on a set (e.g., one or more) of images from the camera 51 taken in real time during the approach to Kambin's triangle 24. In these or other embodiments, the trajectory component 238 can determine (e.g., to inform the physician) what changes need to be made to the actual trajectory of the trocar 30 to achieve an improved trajectory toward Kambin's triangle 24. In any embodiment, the disclosed artificial intelligence implementations can improve the efficiency and safety of surgical instruments through improved accuracy in identifying Kambin's triangle 24. For example, unnecessary and erroneous movements of surgical instruments that cause contact with nerves can be avoided.

[0126] In some embodiments, the trajectory component 238 may determine and continuously update in real time the working distance from the camera 51 (and thus from the trocar 30) to Kambin's triangle. In these or other embodiments, the trajectory component 238 can determine the position of a device, such as the trocar 30, advancing toward Kambin's triangle (including the first and second locations of the trocar 30). Images may be captured via at least one of the camera 51 and a charge coupled device (CCD), such as the electrical electrodes 52 of the neuromonitoring system described above with respect to FIGS. 3A-3F.

[0127] In some embodiments, the annotation component 236 can indicate at least one of the Kambin triangle 24, the SAP 53, and the nerve 21 in near real time. If desired, boundaries between anatomical structures may be indicated by bold lines on the camera image, and text indicating each of these structures may also be annotated thereon. Alternatively, pixels or other marks may be used to distinguish the structures. The user may select, via the user interface device 218, what should be emphasized and how such representative emphasis should be performed. For example, such user-configurable annotation may make the SAP boundary (or nerve or Kambin triangle boundary) and / or corresponding text optional.

[0128] In some embodiments, the trajectory component 238 can identify how to advance a tool toward or through Kambin's triangle 24 without contacting a nerve based on the relative locations of the SAP 53, the superior endplate vertebrae, and / or other structures within the region of interest that may serve as anatomical landmarks. From a CT scan, the presence of the SAP 53, spinal level, and / or other bony landmarks can be predicted, each of which is predicted at a specific set of locations. And from an MRI scan, the nerve roots 21, 23 can be predicted to be present at specific locations. To identify Kambin's triangle 24, for example, the presence of three edges including the nerve 21, the SAP 53, and the superior endplate vertebrae can be predicted.

[0129] In some embodiments, the camera 51 may perform hyperspectral or multispectral imaging (i.e., for wavelengths other than just white light) to visually obtain information about blood supply, arteries, nerves, etc. Overlaying information about these other wavelengths may be an option for the user.

[0130] In some embodiments, the trajectory component 238 can identify the position of the trocar or dilator as it advances towards Kambin's triangle 24 and provide feedback to the physician based on those images. As used herein, physician may refer to human-based surgery, a combination of computer-aided and human surgery, or pure automation.

[0131] As described above, the camera 51 can be attached to the tip 37 of the trocar 30 (see FIGS. 3A-3D), which is configured to establish an access path toward or through Kambin's triangle. The camera 51 can be used to locate or identify anatomical structures, including Kambin's triangle 24, one or more nerves, bony structures, and soft tissue. Thus, the camera 51 can be centered at the distal end of the trocar 30 on the central axis. In other examples, the camera can be positioned or embedded on the sidewall of the trocar 30 between the outer and inner surfaces.

[0132] In one implementation, a particular access device, such as a trocar, can be inserted into the disc space along a trajectory that passes through Kambin's triangle 24. The trocar can establish a trajectory that passes through Kambin's triangle 24. In some examples, as described above, an access port 130 (see FIG. 5A ) can be driven to the disc space along a trajectory that passes through Kambin's triangle. Thus, surgical instruments, such as surgical instruments and / or surgical implants, can be driven through the access port 130 in the manner described above. In other examples, other access devices, such as dilators and access cannulas, can be inserted into Kambin's triangle 24 along a trajectory. In some examples, the dilators and access cannulas can be inserted into, but not through, Kambin's triangle 24. The access device can define a working channel that extends to Kambin's triangle 24. A surgical instrument, such as a disc removal instrument, can be driven through the working channel and through Kambin's triangle to the disc space to remove disc material from the disc space in preparation for insertion of an intervertebral implant.

[0133] In some embodiments, the camera 51 can be navigated (e.g., the CT scan and port / camera are aligned). For example, the navigation of the camera 51 can be tracked in real time for a given known position in the trocar space. That is, the position of the trocar can be registered to the preoperative image so that the positions of the anatomical structures are known relative to one another. As described above, the camera 51 can be located on the access device side. This can be compensated for, knowing that the working channel will be directionally offset from the camera (e.g., by a few millimeters). Furthermore, the sidewalls of the trocar can be angled relative to the actual trajectory of the trocar. Thus, the field of view can be directed in a plane that is angularly offset from the central axis of the trocar and a plane perpendicular to the trocar's actual trajectory, as described above. In one example, the angle is approximately 30 degrees. Alternatively, the camera 51 can be attached to the angled sidewall and oriented parallel to the central axis of the trocar 30.

[0134] It is recognized that there may be some distortion that can be corrected based on a known angle and at least an approximation of the offset distance from the central axis. Thus, the image provided by camera 51 may be based on a skewed camera location such that the center of the image is aligned with the central axis of the trocar, and software correction may be performed via the imaging processing pipeline. In some implementations, when viewed from the side, the user may experience more distortion at the top at that angle the further away the camera 51 is. However, much of this can be corrected. When corrected, the entire image may appear centered relative to the user. If not corrected, there may be a lens effect due to the off-centeredness. This does not cause a loss of information; rather, there are simply different pixels representing different areas. This is known as fisheye distortion and can be corrected.

[0135] In an implementation including a CT scanner 255, the patient may be lying on a table during the scan. Then, at a different time, which may be days or weeks later, on the day of surgery, the patient may be lying in a different position when the camera 51 is inserted into the surgical site in the manner described above. For example, radiopaque markers may be placed near the lumbar region (e.g., the L5-S1 region) and fastened thereto. A CT scan may be performed, and the inserted markers can then be identified in the CT scan. Thus, the patient, image, or device can be registered, for example, by aligning the markers on the image from the camera 51 with the coordinate system from a previous CT scan. Registration may further be performed using the scanner and reference array 40, as described above (see FIG. 3A). The flexible nature of the spine can increase the risk of movement, thereby increasing inaccuracy, making navigation to improve accuracy important.

[0136] In embodiments in which the camera 51 is navigated and 3D CT scans are used, the prediction component 234 may automatically segment the CT scan (e.g., using deep learning) to identify vertebral bodies and foramina. Foramina are open holes that exist in an animal's body to allow muscles, nerves, arteries, veins, or other structures to connect one part of the body with another. From these identifications, the prediction component 234 can estimate Kambin's triangle 24. A representation of Kambin's triangle can then be overlaid on the image from the camera 51, as shown in FIG. 4B . In these or other embodiments, the prediction component 234 can automatically segment the CT scan (e.g., using deep learning trained through a co-acquired MRI CT scan) to identify the exiting nerves 21. The annotation component 236 can then overlay this nerve structure on the image. In these or other embodiments, the prediction component 34 can automatically segment the CT scan (e.g., using deep learning) to identify bony landmarks such as vertebrae, pedicles, transverse processes (TP), spinous processes (SP), and / or SAP 53. The annotation component 236 can then overlay the bony structures onto the camera image. Thus, the annotation component 236 may simultaneously overlay at least one of Kambin's triangle 24, neural structures 21, 23, and bony structures onto the image, with options for the user to refine the amount of information displayed.

[0137] In some embodiments, a machine learning model can be input with 3D scans and predict (via supervised or unsupervised learning) where Kambin's triangle 24 is located for each triangle, and then another machine learning model can be trained using labels based on these predictions, such that the other model uses 2D camera images to make predictions of Kambin's triangle. In other embodiments, human labeling of Kambin's triangle can be used to train a machine learning model, and then both the 2D camera and 3D scans can be input into this model to predict the triangle for the current patient in real time. These embodiments implement distilled learning or student-teacher models.

[0138] In some embodiments, even if a 3D CT scan is available, the camera 51 may not be navigated. For example, deep learning may be performed to identify various bony landmarks directly from 2D camera images, as intraoperative images from the camera 51 are fed into this predictive model in real time. In other embodiments, the user may have to wait a period of time (e.g., 10 seconds) to get a prediction of the identification of Kambin's triangle 24, and may not move during that period. In some implementations, the prediction may not be as fast as the camera feed itself, but may update itself in near real time as things move. For example, a port may be rotated (or a tool may be moved) to view from a particular angle.

[0139] When not navigated, registration with the 3D CT scan can be performed in real time based on the found landmarks. Then, the confidence interval of the Kambin triangle, nerve structures, and bone structures can be overlaid on the camera image. Because no registration is performed, the user may not know where the camera is looking relative to where the CT scanner is looking. When navigated and registered, the user will know exactly where the 2D slice of the camera image is looking within the 3D CT scan. Without a navigated camera, the user knows what the patient's bony anatomy looks like, but has no way to link it to the camera image. Therefore, this non-navigated approach can involve obtaining bone predictions from the camera image and then registering it back to the 3D CT scan, which can also predict the presence of bone and then be used to estimate which 2D slice the user is looking at.

[0140] In some embodiments, the CT 255 is an XT (cone-beam CT). In other embodiments where no CT scan is available, the prediction component 34 can rely on some visual indication. In another example, a nerve locator device or some other means, such as ultrasound or a Sentio™ mechanomyographic (MMG) system, can be used to locate and map the nerve using electrical stimulation of the nerve, thereby providing additional imaging input for overlay on the camera image. The Sentio™ MMG system can be located in the distal region 36, particularly in the second portion 36b of the distal region 36 (see FIG. 3A), to control the trajectory of the trocar 30. In one example, an integrated device can be used to send current through a probe or port to an electrode 52 (see FIGS. 3A-3E) to determine the distance to the nerve or other anatomical structure of interest in the manner described above.

[0141] 9 and 10 illustrate methods 300 and 350 for performing precision surgery using enhanced imaging, according to one or more embodiments. These methods may be performed using a computer system including one or more computer processors and / or other components. The processor is configured with machine-readable instructions for executing computer program components. The operations of these methods presented below are intended to be illustrative. In some embodiments, methods 300 and 350 may each be achieved with one or more additional operations not described and / or without one or more of the operations discussed. Additionally, the order of operations for each of these methods is illustrated in FIGS. 9 and 10. In some embodiments, methods 300 and 350 may each be implemented in one or more processing devices (e.g., digital processors, analog processors, digital circuits designed to process information, analog circuits designed to process information, state machines, and / or other mechanisms for electronically processing information). A processing device may include one or more devices that perform some or all of the operations of these methods in response to instructions electronically stored on an electronic storage medium. A processing device may include one or more devices configured via hardware, firmware, and / or software specifically designed to perform one or more of these operations.

[0142] In operation 302 of method 300, one or more scans corresponding to a region of interest of a patient may be acquired. For example, the acquired patient scans may be unsegmented and correspond to a surgical or planned surgical area. In some embodiments, operation 302 is performed by a processor component the same as or similar to information component 231 (shown in FIG. 8B and described herein) and C-arm 254, CT 255, and / or MRI 256.

[0143] In operation 304 of method 300, images within a region of interest of a patient may be captured in real time. For example, camera 51 may take a set of images of the interior of a body or patient in real time, with the capture of the set of images being performed during a procedure. Method 300 may be performed using one or more images at a time. In some embodiments, operation 304 is performed by the camera 51 and a processor component that is the same as or similar to information component 231.

[0144] In operation 306 of method 300, training data may be obtained, the training data including ground truth labeled structures based on structures identified in previously taken scans and corresponding images captured in real time during previous medical procedures. In some embodiments, operation 306 is performed by a processor component the same as or similar to training component 232 of FIG. 8B.

[0145] In operation 308 of method 300, a model may be trained using the obtained training data. For example, a trained convolutional neural network or another of models 264 may be obtained to perform recognition or detection of anatomical structures in images and / or scans. That is, after training component 232 trains the neural network, the resulting trained model may be stored in model 264 of predictive database 260. In some embodiments, operation 308 is performed by the same or similar processor component as training component 232.

[0146] In operation 310 of method 300, a number of different structures within, near, and / or surrounding the region of interest may be selected (e.g., manually via user interface device 218 or automatically based on a predetermined configuration) from among vertebral bodies and foramina, nerve roots, and bony landmarks. In some embodiments, operation 310 is performed by a processor component the same as or similar to information component 231 (shown in FIG. 8B and described herein).

[0147] At operation 312 of method 300, the Kambin triangle and / or each selected structure may be identified via a machine learning (ML) model trained using the acquired scan and the captured image, where each of the identifications may meet a confidence criterion, and the identification of the Kambin triangle is based on the relative location of the selected structure. For example, the prediction is performed by identifying the presence of at least one neural structure from the unsegmented scan using an image analysis tool that receives the unsegmented scan as input and outputs a labeled image volume that identifies the at least one neural structure. In some embodiments, the prediction component 234 may predict via a U-Net, which may comprise a convolutional neural network and / or a fully convolutional network developed for biomedical image segmentation. In some embodiments, operation 312 is performed by the same or similar processor component as the prediction component 234 (shown in FIG. 8B and described herein).

[0148] At operation 314 of method 300, a representation of the identified triangle and / or each selected structure may be overlaid on the captured image. For example, information that distinguishes, emphasizes, highlights, or otherwise indicates anatomical structures on the path of approach to Kambin's triangle 24 may be overlaid on the image. In some embodiments, operation 314 is performed by a processor component that is the same as or similar to annotation component 236 (shown in FIG. 8B and described herein).

[0149] In operation 316 of method 300, another image within the patient's region of interest may be subsequently captured in real time. In some embodiments, operation 316 is performed by the same or similar processor component as information component 231 and camera 51.

[0150] In operation 318 of method 300, the Kambin triangle may be re-identified via a model trained using the acquired scan and another image. For example, subsequent identification of Kambin triangle 24 may meet improved confidence criteria, for example, for growing a region representing the identified triangle based on subsequently captured images. In some embodiments, operation 318 is performed by the same or similar processor component as prediction component 234.

[0151] At operation 320 of method 300, a confidence metric associated with the re-identified triangle may be updated. For example, the confidence interval may be updated in real time based on the camera 51 feed. In some embodiments, the annotation component 236 may determine the confidence interval, for example, while the camera 51 is in proximity to the region of interest and / or Kambin's triangle 24. The confidence interval may indicate the range within which the anatomical structure is predicted to exist in each of a set of locations (e.g., in 2D, 3D, or another suitable number of dimensions). In some embodiments, the confidence metric may be satisfied by the extent to which known measures improve, resulting in greater assurance that Kambin's triangle 24 is actually in the predicted location (e.g., to progress toward the triangle). In some embodiments, operation 320 is performed by the same or similar processor component as the prediction component 234 or the annotation component 236.

[0152] At operation 322 of method 300, the updated representation of the re-identified triangles may be overlaid on another image. For example, the overlay may be on the same image used to make the prediction, or on a different image. In some embodiments, operation 322 is performed by the same or similar processor component as annotation component 236.

[0153] In operation 352 of method 350 depicted in FIG. 10 , the operating room configuration may be obtained. For example, it may be determined whether outputs from 2D CT, 3D CT, and MRI are available. In this or another example, it may be determined whether camera 51 is navigable or registerable. In implementations where only a patient's CT scan is available, training component 232 may use MRI scans of other patients to train a method capable of detecting nerves from CT scans, as discussed herein. Thus, by knowing where certain bony structures or landmarks are located, prediction component 234 may predict where nerves will be located. The algorithmic approach itself may be determined based on the availability of certain tools and techniques. Thus, for example, system 25 may use certain inputs and / or conditions and then adjust itself to select an appropriate method. In some embodiments, operation 352 is performed by the same or similar processor component as information component 231.

[0154] In operation 354 of method 350, a trained machine learning model may be selected based on the obtained configuration by determining whether the configuration is indicative of navigation and / or a 3D CT scan. In some embodiments, operation 354 is performed by the same or similar processor component as training component 232 or prediction component 234.

[0155] In operation 356 of method 350, in response to determining that the configuration indicates navigation and a 3D CT scan, the 3D CT scan may be registered with the port and / or camera (e.g., by registering between a plurality of different coordinate systems and the captured images) and a 3D CT scan corresponding to the region of the patient may be obtained. In some embodiments, operation 356 is performed by a processor component the same as or similar to trajectory component 238 (shown in FIG. 8B and described herein).

[0156] In operation 358 of method 350, images may be captured in real time.

[0157] In operation 360 of method 350, Kambin's triangle may be identified via the model selected using the acquired 3D CT scan and the captured image. In some embodiments, operation 360 is performed by the same or similar processor component as prediction component 234.

[0158] The techniques described herein may be implemented in digital electronic circuitry, or computer hardware, firmware, software, or combinations thereof. The techniques may also be implemented as a computer program product, i.e., a computer program tangibly embodied in an information carrier, such as a machine-readable storage device, machine-readable storage medium, or computer-readable storage medium, for execution by or to control the operation of a data processing apparatus, e.g., a programmable processor, computer, or multiple computers. The computer program may be written in any form of programming language, including compiled or interpreted languages, and may be deployed in any form, including as a stand-alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment. The computer program may be deployed to be executed on one computer or on multiple computers at one site or distributed across multiple sites and interconnected by a communications network.

[0159] The method steps of the present technique may be performed by one or more programmable processors executing a computer program to perform the functions of the present technique by operating on input data and generating output. The method steps may also be performed by techniques and devices that may be implemented as special purpose logic circuitry, e.g., an FPGA (field programmable gate array) or an ASIC (application-specific integrated circuit). Figures 8B-10 are further described in U.S. Patent Application No. 17 / 390,115, filed July 30, 2021, the disclosure of which is incorporated herein by reference as if set forth in its entirety.

[0160] Processors suitable for the execution of a computer program include, by way of example, both general-purpose and special-purpose microprocessors, and any one or more processors of any kind of digital computer. Generally, a processor receives instructions and data from a read-only memory or a random-access memory, or both. The essential elements of a computer are a processor for executing instructions and one or more memory devices for storing instructions and data. Generally, a computer also includes, or is operatively coupled to receive data from, transfer data to, or both of, one or more mass storage devices for storing data, such as magnetic, magneto-optical, or optical disks. Suitable information carriers for embodying computer program instructions and data include, by way of example, all forms of non-volatile memory, including semiconductor memory devices such as EPROM, EEPROM, and flash memory devices, magnetic disks such as internal hard disks or removable disks, magneto-optical disks, and CD-ROM and DVD-ROM disks. The processor and memory may be supplemented by, or incorporated in, special-purpose logic circuitry. The disclosure of communication between a component and a processor may include direct data communication with the processor or indirect data communication with the processor. In one example, indirect communication with the processor may include communication with a memory for storage to the memory, where the memory is in direct communication with the processor such that the processor can retrieve data stored in the memory.

[0161] Although several embodiments of the present disclosure have been specifically illustrated and / or described herein, it will be understood that modifications and variations are contemplated and are within the purview of the appended claims.

[0162] The disclosure of US Pat. No. 8,518,087 is incorporated herein by reference in its entirety and should be considered a part of this specification.

[0163] It should be understood that the illustration and discussion of the embodiments shown in the figures are for illustrative purposes only and should not be construed as limiting the present disclosure. Those skilled in the art will understand that the present disclosure contemplates a variety of embodiments. Additionally, it should be understood that the concepts described above in connection with the above embodiments may be used alone or in combination with any of the other embodiments described above. It should further be understood that the various alternative embodiments described above with respect to one illustrated embodiment may be applied to all embodiments described herein unless otherwise specified.

[0164] [Embodiment] (1) A surgical system, comprising: a trocar having a trocar body and a first sensor and a second sensor supported by the trocar body, each of the first sensor and the second sensor configured to sense at least one of a position of the trocar, an orientation of the trocar, a property of tissue proximate to the trocar, and a distance from the tissue and the trocar; The display and a processor in communication with the plurality of sensors and the display; The surgical system, wherein the processor is configured to overlay a graphical representation of data from each of the sensors on the display as the trocar is advanced towards a target anatomical site. (2) The system of embodiment 1, wherein one of the plurality of sensors includes a visible light image sensor. (3) The system of embodiment 2, wherein the graphical representation of the data from each of the plurality of sensors is a highlighted area of ​​the image captured by the visible light image sensor indicating the presence of any of certain types of tissue and anatomical structures. (4) The system of embodiment 3, wherein the anatomical structure includes any of bone and nerve. (5) The system of embodiment 1, wherein one of the plurality of sensors is configured to sense the position of the trocar, and the processor is configured to provide on the display a graphical representation of alignment between the actual trajectory of the trocar and the desired trajectory of the trocar.

[0165] (6) The system of embodiment 5, wherein the graphical representation of the alignment between the position of the trocar and the desired insertion trajectory includes a first icon representing a first location position of the trocar and a second icon representing a second location position of the trocar. (7) The system of embodiment 1, wherein one of the plurality of sensors comprises a neural mapping electrode. (8) The system of embodiment 7, wherein the plurality of neural mapping electrodes are spaced around a distal region of the trocar, and the processor is configured to triangulate the location of the nerve based on either time of flight or signal strength detection at two or more of the plurality of neural mapping electrodes. (9) The system of embodiment 7, wherein the plurality of neural mapping electrodes are embedded in the transparent distal tip of the trocar. (10) The system of embodiment 1, wherein one of the plurality of sensors comprises a non-visible light image sensor, and the processor is further configured to distinguish tissue types based on images captured by the non-visible light image sensor.

[0166] (11) The system of embodiment 1, wherein the trocar is configured to deliver tactile feedback to the user based on input from the plurality of sensors. (12) The system of embodiment 1, further comprising a flexible access port, wherein the trocar extends through a lumen of the surgical access port. (13) A surgical system, comprising: a trocar having a trocar body and a camera supported by the trocar body; The display and a processor in communication with the camera and the display; the processor is configured to overlay, on the display, a pre-operative image of an anatomical structure over a real-time image of the anatomical structure from the camera as the trocar is moved toward a target anatomical site. (14) The system of embodiment 13, wherein the anatomical structure includes any of bone and nerve. (15) The surgical system of embodiment 13, wherein the trocar has a transparent tip and the camera views the anatomical structure distal to the trocar through the transparent tip.

[0167] (16) The system of embodiment 13, further comprising an electrode supported by the trocar body and configured to apply an electric current to the nerve to determine the distance between the trocar and the nerve. (17) The system of claim 13, further comprising a position sensor configured to detect a position of the trocar, and wherein the processor is configured to provide, on the display, a graphical representation of an alignment between the position of the trocar and a desired insertion trajectory. (18) The system of embodiment 17, wherein the graphical representation of the alignment between the position of the trocar and a desired insertion trajectory includes a first icon representing a first location position of the trocar and a second icon representing a second location position of the trocar, the first location being distally spaced from the second location. (19) The system of embodiment 13, further comprising a flexible access port having a lumen, the trocar being received within the lumen. (20) The system of embodiment 13, wherein the camera comprises a non-visible light image sensor.

Claims

1. 1. A surgical system comprising: a trocar having a trocar body and a first sensor and a second sensor supported by the trocar body, each of the first sensor and the second sensor configured to sense at least one of a position of the trocar, an orientation of the trocar, a property of tissue proximate the trocar, and a distance from the tissue and the trocar; The display and a processor in communication with the plurality of sensors and the display; The surgical system, wherein the processor is configured to overlay a graphical representation of data from each of the sensors on the display as the trocar is advanced towards a target anatomical site.

2. The system of claim 1 , wherein one of the plurality of sensors includes a visible light image sensor.

3. 3. The system of claim 2, wherein the graphical representation of data from each of the plurality of sensors is a highlighted area of ​​an image captured by the visible light image sensor that indicates the presence of any of certain types of tissue and anatomical structures.

4. The system of claim 3 , wherein the anatomical structure includes one of a bone and a nerve.

5. 2. The system of claim 1, wherein one of the plurality of sensors is configured to sense a position of the trocar, and the processor is configured to provide, on the display, a graphical representation of an alignment between an actual trajectory of the trocar and a desired trajectory of the trocar.

6. 6. The system of claim 5, wherein the graphical representation of the alignment between the position of the trocar and a desired insertion trajectory includes a first icon representing a first location position of the trocar and a second icon representing a second location position of the trocar.

7. The system of claim 1 , wherein one of the plurality of sensors comprises a neural mapping electrode.

8. 8. The system of claim 7, wherein the plurality of neural mapping electrodes are spaced around a distal region of the trocar, and the processor is configured to triangulate a nerve location based on either time-of-flight or signal strength detection at two or more of the plurality of neural mapping electrodes.

9. The system of claim 7 , wherein the plurality of neural mapping electrodes are embedded in the transparent distal tip of the trocar.

10. 10. The system of claim 1, wherein one of the plurality of sensors comprises a non-visible light image sensor, and the processor is further configured to distinguish tissue types based on images captured by the non-visible light image sensor.

11. The system of claim 1 , wherein the trocar is configured to deliver tactile feedback to a user based on input from the plurality of sensors.

12. The system of claim 1 , further comprising a flexible access port, the trocar extending through a lumen of the surgical access port.

Images