Computer-assisted surgery planning

Abstract

To provide a technique concerning a computerized surgical planning system.SOLUTION: The method comprises: obtaining, by a computing system, one or more surgeon preference parameters specifying values of one or more surgical parameters, in which the surgical parameters include one or more positioning parameters for a glenoid implant to be attached to a glenoid of a patient during a surgery; determining, by the computing system, one or more suggested surgical options based on one or more anatomical parameters of the patient and the surgeon preference parameters, in which each of the surgical options corresponds to a different combination of the positioning parameters for the glenoid implant and a type of the glenoid implant; and outputting, by the computing system, the one or more suggested surgical options for display.SELECTED DRAWING: Figure 5

Description

Cross - reference to related applications

[0001]

[0001] This application claims the priority of U.S. Provisional Patent Application No. 63 / 146,278, filed on February 5, 2021, the entire content of which is incorporated herein by reference.

Background Art

[0002]

[0002] Shoulder arthroplasty is a complex type of orthopedic surgery. However, shoulder arthroplasty has become increasingly common because it can relieve pain and restore range of motion in many patients. The complexity of shoulder arthroplasty has become an obstacle for many surgeons, especially those who do not perform shoulder arthroplasty frequently, to perform shoulder arthroplasty. Therefore, computerized surgical planning systems have been developed to assist surgeons in planning complex surgeries such as shoulder arthroplasty.

Summary of the Invention

[0003]

[0003] This disclosure describes various techniques for improving a computerized surgical planning system. One issue related to the implementation of a computerized surgical planning system is how to ensure that the computerized surgical planning system generates a surgical plan for shoulder arthroplasty that matches the preferences of individual surgeons. For example, a computerized surgical planning system may use a machine learning (ML) model to generate multiple predictions regarding various surgical options for shoulder arthroplasty. Generally, a large number of training datasets (e.g., data regarding individual surgeries) may be required to train an ML model. Due at least to the number of cases required to train the ML model, it may be impractical to train a separate ML model for each individual surgeon to generate predictions based on the preferences of the individual surgeon. This may be particularly true for surgeons who do not perform shoulder arthroplasty frequently, simply because such surgeons have not performed enough shoulder arthroplasties to adequately train an ML model. This disclosure can address this problem and will describe techniques that enable a surgical planning system to generate surgical proposals tailored to the preferences of individual surgeons, along with the associated benefits of reduced memory requirements and reduced utilization of computing resources.

[0004]

[0004] In one embodiment, the present disclosure obtains, by a computing system, one or more surgeon preference parameters that specify values of one or more surgical parameters, where the surgical parameters include one or more positioning parameters for a glenoid implant to be attached to a patient's glenoid fossa during surgery, determines, by the computing system, one or more suggested surgical options based on the patient's one or more anatomical parameters and the surgeon preference parameters, where each of the surgical options corresponds to a different combination of positioning parameters for the glenoid implant and the type of glenoid implant, and outputs, by the computing system, the one or more suggested surgical options, and describes a method comprising the above.

[0005]

[0005] In another embodiment, the present disclosure describes a computing system comprising a memory configured to store one or more surgeon preference parameters that specify values of one or more surgical parameters, where the surgical parameters include one or more positioning parameters for a glenoid implant to be attached to a patient's glenoid fossa during surgery, and one or more processors implemented within a circuit, the one or more processors being configured to determine one or more suggested surgical options based on the patient's one or more anatomical parameters and the surgeon preference parameters, where each of the surgical options corresponds to a different combination of positioning parameters for the glenoid implant and the type of glenoid implant, and output the one or more suggested surgical options for display.

[0006]

[0006] In other embodiments, the present disclosure describes a computing system comprising means for performing the method of the present disclosure, and a computer-readable storage medium storing instructions that, when executed, cause one or more processors of the computing system to perform the method of the present disclosure.

[0007]

[0007] The details of various embodiments of the present disclosure are described in the accompanying drawings and the following description. Various features, objectives, and advantages will become apparent from the description, the drawings, and the claims.

Brief Description of the Drawings

[0008]

Figure 1

[0008] A block diagram of a surgical assistance system according to one or more techniques of the present disclosure.

Figure 2

[0009] A block diagram illustrating exemplary details of a surgical planning system according to one or more techniques of the present disclosure.

Figure 3

[0010] A conceptual diagram illustrating an exemplary surgical planning user interface according to one or more techniques of the present disclosure.

Figure 4A

[0011] A conceptual diagram illustrating an exemplary surgical planning user interface for selecting surgeon preference parameters for an anatomical shoulder arthroplasty according to one or more techniques of the present disclosure.

Figure 4B

[0012] A conceptual diagram illustrating an exemplary surgical planning user interface for selecting surgeon preference parameters for a reverse shoulder arthroplasty according to one or more techniques of the present disclosure.

Figure 5

[0013] A conceptual diagram illustrating an exemplary surgical planning user interface showing a surgical proposal for an anatomical shoulder arthroplasty according to one or more techniques of the present disclosure.

Figure 6

[0014] A conceptual diagram illustrating an exemplary surgical planning user interface showing a surgical proposal for a reverse shoulder arthroplasty according to one or more techniques of the present disclosure.

Figure 7

[0015] A flowchart illustrating exemplary operations of a surgical planning system according to one or more techniques of the present disclosure.

Figure 8

[0016] A flowchart illustrating an exemplary operation of a parameter prediction unit for determining one or more proposed surgical options for a glenoid implant according to one or more techniques of the present disclosure.

Best Mode for Carrying Out the Invention

[0009]

[0017] Specific embodiments of the present disclosure will be described with reference to the accompanying drawings, where like reference numerals indicate like elements. However, it should be understood that the accompanying drawings merely illustrate various implementations described herein and are not intended to limit the scope of the various techniques described herein. The drawings show and describe various embodiments of the present disclosure. In the following description, numerous details are set forth. However, one of ordinary skill in the art will understand that the invention can be practiced without these details and that numerous variations or modifications from the described embodiments are possible.

[0010]

[0018] The present disclosure describes systems and methods related to planning a surgery. In other words, the present disclosure describes techniques for automatic planning of a surgery. A surgical plan, such as a surgical plan generated by the BLUEPRINT™ system manufactured by Wright Medical Group NV or another surgical planning platform, may include various information regarding the surgery. For example, the surgical plan may include information regarding steps to be performed on a patient by a user, such as a surgeon. Exemplary steps may include, for example, steps for preparation of bone or tissue, and / or steps for selection, modification, and / or placement of implant components, such as prosthetics, and related hardware or media. Further, the information within the surgical plan may, in various embodiments, include dimensions, shapes, angles, surface contours, and / or orientations of implant components to be selected or modified by a user, dimensions, shapes, angles, surface contours, and / or orientations to be defined in bone or tissue by a user in a bone or tissue preparation step, and / or positions, axes, planes, angles, and / or entry points that define placement of implant components by a user with respect to a patient's bone or tissue. Information such as dimensions, shapes, angles, surface contours, and / or orientations of a patient's anatomical features may be derived from analysis of imaging (e.g., X-ray, CT, MRI, ultrasound, or other images), direct observation, or other techniques.

[0011]

[0019] As described herein, a computing system may obtain one or more surgeon preference parameters that specify values of one or more surgical parameters. The surgical parameters may include one or more positioning parameters for a glenoid implant that is to be attached to a patient's glenoid fossa during surgery. Further, the computing system may determine one or more proposed surgical options for attaching a glenoid implant to a patient's glenoid fossa during surgery based on one or more anatomical parameters of the patient and the surgeon preference parameters. Each of the surgical options corresponds to a different combination of values of the surgical parameters. The computing system may output one or more proposed surgical options for display.

[0012]

[0020] FIG. 1 is a block diagram illustrating an exemplary surgical assistance system 100 according to one or more techniques of the present disclosure. In the embodiment of FIG. 1, the surgical assistance system 100 includes a computing system 102 that is an example of a computing system configured to perform one or more exemplary techniques described in the present disclosure. The computing system 102 may include various types of computing devices, such as a server computer, a personal computer, a smartphone, a tablet computer, a laptop computer, and other types of computing devices. The computing system 102 includes a processing circuit 104, a memory 106, a display 108, and a communication interface 110. The display 108 may be optional in embodiments where the computing system 102 comprises a server computer. Further, in the embodiment of FIG. 1, the surgical assistance system 100 includes a local device 112 and a communication network 114.

[0013]

[0021] Examples of processing circuit 104 include one or more microprocessors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), hardware, or any combination thereof. Generally, processing circuit 104 can be implemented as a fixed function circuit, a programmable circuit, or a combination thereof. A fixed function circuit refers to a circuit that provides a specific function and is preset with respect to the operations it can perform. A programmable circuit refers to a circuit that can be programmed to perform various tasks and provide a flexible function in terms of the operations it can perform. For example, a programmable circuit can execute software or firmware that operates the programmable circuit in a manner defined by software or firmware instructions. A fixed function circuit can execute software instructions (e.g., to receive or output parameters), but the type of operations performed by the fixed function circuit is generally invariant. In some embodiments, one or more units may be separate circuit blocks (fixed function or programmable), and in some embodiments, one or more units may be integrated circuits.

[0014]

[0022] Processing circuit 104 may include an arithmetic logic unit (ALU), an elementary function unit (EFU), digital circuits, analog circuits, and / or a programmable core formed from a programmable circuit. In embodiments where the operations of processing circuit 104 are performed using software executed by the programmable circuit, memory 106 may store the object code of the software that processing circuit 104 receives and executes, or another memory (not shown) within processing circuit 104 may store such instructions. Examples of software include software designed for surgical planning. Processing circuit 104 may perform actions attributed to computing system 102 in the present disclosure.

[0015]

[0023] Memory 106 can store various types of data used by processing circuit 104. For example, memory 106 can store data related to one or more surgical plans. Memory 106 can be formed by any of various memory devices such as dynamic random access memory (DRAM) including synchronous dynamic random access memory (SDRAM), magnetoresistive RAM (MRAM), resistive RAM (RRAM (registered trademark)), hard disk drive, optical disk, or other types of non-transitory computer-readable media. Examples of display 108 can include a liquid crystal display (LCD), plasma display, organic light emitting diode (OLED) display, or another type of display device.

[0016]

[0024] Further, in the embodiment of FIG. 1, the memory 106 may include computer-readable instructions that, when executed by the processing circuit 104, cause the computing system 102 to provide the surgical planning system 116. In some embodiments, some or all of the instructions of the surgical planning system 116 are stored on the local device 112 and / or executed by the processing circuit of the local device 112. In other embodiments, some or all of the instructions of the surgical planning system 116 are stored on the computing system 102 and / or executed by the processing circuit of the computing system 102. In some embodiments, the local device 112 may be or include a mixed reality (MR) visualization device. For ease of explanation, the present disclosure simply describes the actions performed by the computing system 102 and / or the local device 112 when the processing circuit of the processing circuit 104 and / or the local device 112 executes the instructions of the surgical planning system 116 as being performed by the surgical planning system 116, understanding that the processing operations may be performed by the processing circuit of the computing system 102, the local device 112, or a combination of both, or by other processing circuits including the processing circuits associated with one or more cloud servers and / or one or more other remote computing devices, or in combination therewith. In the embodiment of FIG. 1, the memory 106 may also include surgical planning data 117, medical image data 119, and surgeon preference parameters 121.

[0017]

[0025] The communication interface 110 enables the computing system 102 to output data and instructions to and receive data and instructions from the local device 112 and / or other devices via the network 114. The communication interface 110 may include hardware circuitry that enables the computing system 102 to communicate (e.g., wirelessly or using wires) with other computing systems and devices such as the MR visualization device 112. The network 114 may include various types of communication networks including one or more wide area networks such as the Internet, and local area networks. In some embodiments, the network 114 may include wired and / or wireless communication links.

[0018]

[0026] The local device 112 can be a computing device used by the user 118. In other embodiments, the user 118 can directly use the computing device of the computing system 102. In such embodiments, the user 118 can view the content displayed on the display 108. In some embodiments, the local device 112 is a personal computer, a smartphone, a tablet computer, a laptop computer, or another type of computing device. In some embodiments, the local device 112 is a mixed reality (MR) visualization device. The MR visualization device can use various visualization techniques to display image content to the user 118, who can be a surgeon. For example, the MR visualization device can include a holographic projector or other types of devices for presenting an MR scene. In some embodiments where the local device 112 is an MR visualization device, the local device 112 can be a Microsoft HOLOLENS (trademark) headset available from Microsoft Corporation, Redmond, Washington, United States of America, or a similar device such as a similar MR visualization device including a waveguide, for example. The HOLOLENS (trademark) device can be used to present 3D virtual objects through a holographic lens or waveguide while enabling the user 118 to view actual objects in the real-world scene, i.e., the real-world environment, through the holographic lens.

[0019]

[0027] As described above, memory 106 may include computer-readable instructions that, when executed by processing circuitry 104, cause computing system 102 to provide surgical planning system 116. Surgical planning system 116 is configured to assist a surgeon in planning a surgery such as an anatomical shoulder replacement or a reverse shoulder replacement. In an anatomical shoulder replacement, the surgeon implants a cup-shaped glenoid implant into the glenoid fossa of the patient's scapula and a ball-shaped humeral implant into the proximal end of the patient's humerus. In a reverse shoulder replacement, the surgeon implants a ball-shaped glenoid implant into the glenoid fossa of the patient's scapula and a cup-shaped humeral implant into the proximal end of the patient's humerus.

[0020]

[0028] For either an anatomical shoulder replacement or a reverse shoulder replacement, the surgeon can select from among a variety of different types of glenoid implants and humeral implants. For example, the surgeon can select from among a glenoid implant having a keel, a glenoid implant having a peg, or other types of glenoid implants. Further, the surgeon can select from among a variety of sizes within each type of glenoid implant. Additionally, the surgeon can select from among a stemmed humeral implant, a stemless humeral implant, or other types of humeral implants. Similarly, the surgeon can select from among a variety of sizes within each type of humeral implant. For any one glenoid implant or humeral implant, the surgeon can select from among a variety of placement parameters for the glenoid implant or humeral implant. For example, the surgeon can select from among a variety of angles at which to place the glenoid implant or humeral implant. In some embodiments, the surgeon can select from among a variety of bone preparation angles, depths, and positions.

[0021]

[0029] Considering that there are multiple types of implants and various available placement parameters, it may be difficult for a surgeon to select which type of implant and which placement parameters should be used for a specific patient. Therefore, the surgical planning system 116 can generate proposed surgical options regarding the type of implant and placement parameters to be used for the patient when the surgeon is planning a shoulder replacement for a specific patient. When planning a shoulder replacement, the surgeon may select from among the proposed surgical options generated by the surgical planning system 116, or may select other types of implants and / or surgical parameters. In other words, the surgeon is not limited to the proposed surgical options generated by the surgical planning system 116.

[0022]

[0030] Individual surgeons may have specific preferences regarding the type of implant and placement parameters. For example, a surgeon may prefer to always use a peg-type glenoid implant instead of a keel-type glenoid implant because the surgeon feels that the revision rate for the patient is lower when using a peg-type glenoid implant than a keel-type glenoid implant. In another example, a surgeon may prefer to set the post-implant twist angle of the glenoid implant to 10° or less.

[0023]

[0031] Ignoring the surgeon's preferences, the surgical planning system 116 may result in generating proposed surgical options that the surgeon will not use. In any case, this significantly limits the usefulness of the surgical planning system 116 that generates the proposals. One approach to addressing this problem is to train a machine learning (ML) model based on surgeries performed according to the preferences of individual surgeons. However, surgeons may not have completed enough surgeries to have sufficient training data to train an ML model for the surgeon. Without sufficient training data, the ML model for the surgeon may generate inadequate proposals. Furthermore, implementing different ML models for different surgeons may consume significant processing power and memory space.

[0024]

[0032] The techniques of the present disclosure can address this problem. As described herein, the surgical planning system 116 can obtain one or more surgeon preference parameters 121 that specify a range of surgical parameters, such as the type and positioning parameters of a glenoid implant to be attached to the patient's glenoid fossa during surgery. Further, the surgical planning system 116 can determine one or more proposed surgical options based on one or more anatomical parameters and surgeon preference parameters of the patient. The proposed surgical options can correspond to different combinations of positioning parameters for the implant and the type of glenoid implant.

[0025]

[0033] An example of how the surgical planning system 116 can perform automatic planning to determine proposed surgical options based on one or more anatomical parameters and surgeon preference parameters is described in detail below. The surgical planning system 116 can output one or more proposed surgical options for display. In some embodiments, the surgical planning system 116 can receive an indication of user input from the surgeon to select one of the proposals or to select an alternative implant type or placement parameters. The surgical planning system 116 can store the selected implant type and / or placement parameters in the surgical planning data 117.

[0026]

[0034] Figure 2 is a block diagram illustrating exemplary details of a surgical planning system 116 according to one or more techniques of the present disclosure. In the example of Figure 2, the surgical planning system 116 includes a surgical prediction unit 200, a preference acquisition unit 202, an anatomical parameter unit 204, a parameter prediction unit 206, a range of motion (RoM) unit 208, and a plan presentation unit 210. In other examples, the surgical planning system 116 may include more, fewer, or different units. The surgical prediction unit 200, the preference acquisition unit 202, the anatomical parameter unit 204, the parameter prediction unit 206, the RoM unit 208, and the plan presentation unit 210 may be implemented in software executed by a programmable processing circuit. In some examples, one or more of the surgical prediction unit 200, the preference acquisition unit 202, the anatomical parameter unit 204, the parameter prediction unit 206, the RoM unit 208, and the plan presentation unit 210 may be at least partially implemented using dedicated hardware. The surgical prediction unit 200, the preference acquisition unit 202, the anatomical parameter unit 204, the parameter prediction unit 206, and the RoM unit 208 may cooperate to generate computer-assisted predictions.

[0027]

[0035] The surgical prediction unit 200 may generate a prediction as to whether an anatomical shoulder arthroplasty or a reverse shoulder arthroplasty should be performed. For example, the surgical prediction unit 200 may generate a first confidence value indicating the level of confidence (e.g., an estimated probability) that a set of reference surgeons would select an anatomical shoulder arthroplasty for a patient, and a second confidence value indicating the level of confidence that the set of reference surgeons would select a reverse shoulder arthroplasty for the patient. In this example, the surgical prediction unit 200 may output an indication as to which of the anatomical shoulder arthroplasty and the reverse shoulder arthroplasty has a greater confidence score.

[0028]

[0036] The surgical prediction unit 200 can be implemented in one of various ways. For example, the surgical prediction unit 200 can be implemented using one or more artificial intelligence systems, such as a combination of one or more artificial neural networks, support vector machines (SVMs), decision tree networks, random forests, and naive Bayes networks. The surgical prediction unit 200 can generate a prediction as to whether an anatomical shoulder arthroplasty or a reverse shoulder arthroplasty should be performed based on a set of input data. Exemplary types of input data for the surgical prediction unit 200 can include patient data such as the patient's age, diagnosis of the patient's symptoms (e.g., severe rotator cuff tear, osteoarthritis, etc.), patient's gender, orientation of the patient's glenoid fossa, glenoid ball radius of the patient, glenoid version of the patient, glenoid inclination of the patient, humeral subluxation of the patient, direction of the patient's glenoid fossa, area of the patient's glenoid fossa, and / or other types of data regarding the patient.

[0029]

[0037] The preference acquisition unit 202 is configured to acquire surgeon preference parameters for a surgeon. The preference acquisition unit 202 can store the acquired surgeon preference parameters as surgeon preference parameters 121. In some embodiments, the surgeon preference parameters can be specific to a particular patient's surgery. In some embodiments, the surgeon preference parameters can be common across all patients treated by that surgeon. The preference acquisition unit 202 can output a user interface for selecting surgeon preference parameters. FIG. 4A, which is detailed below, illustrates an exemplary user interface for selecting surgeon preference parameters for an anatomical shoulder arthroplasty. FIG. 4B, which is detailed below, illustrates an exemplary user interface for selecting surgeon preference parameters for a reverse shoulder arthroplasty.

[0030]

[0038] In connection with the embodiment of FIG. 2, the anatomical parameter unit 204 is configured to determine the anatomical parameters of a patient. In some embodiments, the anatomical parameter unit 204 is configured to determine one or more anatomical parameters of a patient based on an indication of an input of anatomical parameters from the user 118. In some embodiments, the anatomical parameter unit 204 is configured to determine one or more anatomical parameters of a patient based on the medical image data 119. The medical image data 119 may include, for example, X-ray images, computed tomography (CT) images, and magnetic resonance imaging (MRI) images. Exemplary types of anatomical parameters of a patient may include glenoid ball radius, glenoid orientation, reverse shoulder angle, critical shoulder angle, glenoid rotation angle, coracoid process angle, subglenoid tubercle angle, acromion index, acromion-humeral space, humeral subluxation rate, humeral head radius, humeral orientation, humeral direction, distance from the center of the humeral head to the center of the glenoid, Giannotti cortical bone index of the humerus, Tingart cortical bone thickness of the humerus, proximal diaphyseal bone density value of the humerus, metaphyseal cancellous bone density value of the humerus, metaphyseal cortical bone density value of the humerus, bone density value of the scapula, glenoid anteroposterior twist, glenoid tilt, humeral subluxation, and / or other types of information regarding the anatomical structure of the patient.

[0031]

[0039] In some embodiments, to determine one or more of the patient's anatomical parameters based on the medical image data 119, the anatomical parameter unit 204 may generate a three-dimensional (3D) model of the patient's bone (e.g., scapula, humerus, etc.) based on the medical image data 119. Further, the anatomical parameter unit 204 may perform a process to identify specific landmarks in the 3D model of the bone. A landmark is a position in 3D space that is on or within the 3D model of the bone. The anatomical parameter unit 204 may then use the position of the landmark in 3D space to calculate one or more of the anatomical parameters. For example, to calculate the critical shoulder angle, the anatomical parameter unit 204 may determine the angle between (i) a line from the uppermost point of the edge of the patient's glenoid fossa (i.e., the first landmark) to the lowermost point of the edge of the patient's glenoid fossa (i.e., the second landmark), and (ii) a line from the lowermost point of the edge of the patient's glenoid fossa to the outermost point of the acromion of the patient's scapula (i.e., the third landmark). The anatomical parameter unit 204 may use one or more types of algorithms to identify the landmarks. For example, the anatomical parameter unit 204 may use a hill climbing algorithm to identify specific landmarks such as points on the edge of the patient's glenoid fossa.

[0032]

[0040] The parameter prediction unit 206 can determine one or more proposed surgical options based on one or more anatomical parameters and surgeon preference parameters of the patient. The proposed surgical options can correspond to different combinations of glenoid implants, positioning parameters, and / or bone preparation parameters of the glenoid implant. The parameter prediction unit 206 can perform a process for determining the proposed surgical options, including several stages. In the first stage, the parameter prediction unit 206 can filter the glenoid implant type based on the surgeon preference parameters. In the second stage, the parameter prediction unit 206 can determine the size of the glenoid implant. In the third stage, the parameter prediction unit 206 can use a cost function to determine the cost value for the trial vectors. Each trial vector is a set of surgical parameter values such as positioning parameters and / or glenoid implant type. FIG. 8, which will be detailed below, illustrates an exemplary process for determining the proposed surgical options for the glenoid implant.

[0033]

[0041] The RoM unit 208 can determine the range of motion (RoM) of the patient's shoulder for one or more of the proposed surgical options. The RoM unit 208 can use the combined 3D model of the patient's scapula, humerus (with the humeral implant), and the glenoid implant attached to the patient's scapula along with the surgical parameters corresponding to the proposed surgical options to determine the range of motion for the proposed surgical options. Next, the RoM unit 208 can move the 3D model of the humerus along one or more axes of motion with respect to the 3D models of the scapula and the glenoid implant. Then, for each axis of motion, the RoM unit 208 can detect the angle at which the model of the humerus collides with the model of the scapula. These collisions represent the outermost ends of the range of motion for the axis of motion.

[0034]

[0042] FIG. 3 is a conceptual diagram illustrating an exemplary surgical planning user interface 300 according to one or more techniques of the present disclosure. The planning presentation unit 210 (FIG. 2) may generate a user interface 300 for display (e.g., on the display 108 or the local device 112 (FIG. 1)). The user 118 may use the interface 300 as part of the process of planning a shoulder replacement. In the example of FIG. 3, the user interface 300 includes a top view 302, a front view 304, and a bone model 306. In this example, the top view 302 is an X-ray image of the patient's shoulder from a top perspective (i.e., looking down from a top position in a downward direction). In this example, the front view 304 is an X-ray image of the patient's shoulder from a front perspective (i.e., looking back from a front position in a rearward direction). In this example, the model 306 is a three-dimensional model of the bones of the patient's shoulder. The top view 302, the front view 304, and the model 306 may assist the user 118 in visualizing the patient's shoulder for the purpose of planning a shoulder replacement for the patient's shoulder.

[0035]

[0043] Furthermore, the surgical planning interface 300 includes a patient information field 308, a patient anatomical structure field 310, a surgical prediction field 312, an "Anatomical Plan" button 314, and a "Reverse Plan" button 316. The patient information field 308 includes name information, age information, and information regarding whether the surgery is planned for the patient's left shoulder or right shoulder. The patient anatomical structure field 310 includes information regarding the patient's diagnosis, glenoid type, previous surgeries, and the F1 sub-scapularis footprint (F1 sub-scap). The surgical prediction field 312 may include an indication of the type of predicted shoulder arthroplasty for the patient. In the example of FIG. 3, the surgical prediction field 312 indicates that the type of predicted shoulder arthroplasty for the patient is a reverse shoulder arthroplasty with a 66% probability. In other words, considering the information about the patient, most of the surgeons associated with the training data would perform the predicted type of shoulder arthroplasty, and the confidence level of the prediction is 66%. The surgical prediction unit 200 (FIG. 2) may determine the type of predicted shoulder arthroplasty, for example, as described elsewhere in the present disclosure.

[0036]

[0044] User 118 may initiate the process of planning an anatomical shoulder arthroplasty by selecting the "Anatomical Plan" button 314. User 118 may initiate the process of planning a reverse shoulder arthroplasty by selecting the "Reverse Plan" button 316. Note that in some embodiments, User 118 does not need to select the type of shoulder arthroplasty shown in the surgical prediction field 312, i.e., is not required to do so, and instead may select a different type of shoulder arthroplasty that is not shown.

[0037]

[0045] FIG. 4A is a conceptual diagram illustrating an exemplary surgical planning user interface 400 for selecting surgeon preference parameters for an anatomical shoulder arthroplasty according to one or more techniques of the present disclosure. In some embodiments, the preference acquisition unit 202 (FIG. 2) may present the user interface 400 in response to receiving an indication of user input selecting the “Plan Anatomy” button 314 (FIG. 3).

[0038]

[0046] In the example of FIG. 4A, the user interface 400 includes anchorage checkboxes 402A-402C (collectively referred to as “anchorage checkboxes 402”). Anchorage checkbox 402A corresponds to a glenoid implant having a keel-type anchorage. Anchorage checkbox 402B corresponds to a glenoid implant having a peg-type anchorage. Anchorage checkbox 402C corresponds to a glenoid implant having a peg-type anchorage that includes one or more finned pegs. In other embodiments, the anchorage checkboxes 402 may correspond to arrangements of other types of anchorage for the glenoid implant. The user 118 (e.g., a surgeon) may use the anchorage checkboxes 402 to indicate which type of anchorage arrangement for the glenoid implant may be used by the parameter prediction unit 206 to determine a proposed surgical option.

[0039]

[0047] Further, in the embodiment of FIG. 4A, the user interface 400 includes range selection features 404A - 404F (collectively referred to as "range selection features 404"). Range selection feature 404A corresponds to the maximum retroversion angle of the glenoid implant. Range selection feature 404B corresponds to the maximum anteversion angle of the glenoid implant. Range selection feature 404C corresponds to the maximum inferior tilt angle of the glenoid implant. Range selection feature 404D corresponds to the maximum superior tilt angle of the glenoid implant. Range selection feature 404E corresponds to the minimum seating rate of the glenoid implant. The seating rate is the area ratio of the seating surface of the implant that is in contact with (i.e., seated on) the bone. Range selection feature 404F corresponds to the maximum seating rate of the glenoid implant.

[0040]

[0048] FIG. 4B is a conceptual diagram illustrating an exemplary surgical planning user interface 450 for selecting surgeon preference parameters for an anatomical shoulder arthroplasty according to one or more techniques of the present disclosure. In some embodiments, the preference acquisition unit 202 (FIG. 2) may present the user interface 450 in response to receiving an indication of user input selecting the "plan reverse type" button 316 (FIG. 3).

[0041]

[0049] In the embodiment of FIG. 4B, the user interface 450 includes check boxes 452A to 452D (collectively referred to as "check boxes 452"). The check boxes 452 correspond to the types of implants that the surgeon intends to use in reverse shoulder arthroplasty. Check box 452A corresponds to an eccentric glenosphere. Check box 452B corresponds to a glenoid implant having a 135° neck-shaft angle. Check box 452C corresponds to a first type of glenoid implant. Check box 452D corresponds to a second type of glenoid implant. In other embodiments, the check boxes 452 may correspond to other types of implants used in reverse shoulder arthroplasty. The user 118 (e.g., a surgeon) may use the check boxes 452 to indicate to the parameter prediction unit 206 which types of implants may be used to determine the proposed surgical options.

[0042]

[0050] Further, in the embodiment of FIG. 4B, the user interface 450 includes range selection features 454A to 454E (collectively referred to as "range selection features 454"). Range selection feature 454A corresponds to the maximum posterior twist angle of the glenoid implant. Range selection feature 454B corresponds to the maximum anterior twist angle of the glenoid implant. Range selection feature 454C corresponds to the maximum inferior tilt angle of the glenoid implant. Range selection feature 454D corresponds to the maximum superior tilt angle of the glenoid implant. Range selection feature 454E corresponds to the minimum implantation rate of the glenoid implant.

[0043]

[0051] FIG. 5 is a conceptual diagram illustrating an exemplary surgical planning user interface 500 for a surgical proposal for an anatomical shoulder arthroplasty according to one or more techniques of the present disclosure. The planning presentation unit 210 (FIG. 2) can generate a user interface 500 for display (e.g., on the display 108 or the local device 112 (FIG. 1)). In some embodiments, the planning presentation unit 210 can generate the user interface 500 after receiving an indication of user input indicating surgeon preference parameters (e.g., via the user interface 300 (FIG. 3)).

[0044]

[0052] In the example of FIG. 5, the user interface 500 shows surgical proposals 502A, 502B (collectively referred to as "surgical proposal 502") for an anatomical shoulder arthroplasty. Each of the surgical proposals 502 indicates the type of glenoid implant, the type of fixture for the glenoid implant, the size of the glenoid implant, the radius of the ball of the glenoid implant, the augment of the glenoid implant, the anteroposterior twist of the glenoid implant, the inclination of the glenoid implant, and the placement rate of the glenoid implant. The augment of the glenoid implant is a device that compensates for a large anteroposterior twist of the glenoid. In other embodiments, the surgical proposal 502 can indicate more, fewer, or different types of data. For example, in some embodiments, the surgical proposal 502 can indicate the amount of reaming (e.g., in cubic millimeters or millimeters). In some embodiments, the surgical proposal 502 can include two radii of curvature for an augmented glenoid implant and a single radius of curvature for a non-augmented glenoid implant. The user 118 can select one of the surgical proposals 502. In the example of FIG. 5, a black background is used to indicate that the surgical proposal 502A is the selected surgical proposal.

[0045]

[0053] Further, the user interface 500 includes a top view 506, a front view 508, and a model 510. The top view 506 shows an X-ray image of the patient's shoulder from a top perspective (i.e., viewed from a top position in a downward direction). The top view 506 shows the outer contour 512 of the glenoid implant of the type indicated by the selected surgical proposal at the position indicated by the selected surgical proposal. The front view 508 shows an X-ray image of the patient's shoulder from a front perspective (i.e., viewed from a front position in a rearward direction). The front view 508 shows the outer contour 514 of the glenoid implant of the type indicated by the surgical proposal at the position indicated by the selected surgical proposal. The model 510 shows a 3D model of the patient's scapula with the glenoid cavity 516 emphasized.

[0046]

[0054] The user interface 500 also includes control units 504A, 504B for switching the display of surgical proposals for anatomic shoulder arthroplasty and reverse shoulder arthroplasty.

[0047]

[0055] FIG. 6 is a conceptual diagram illustrating an exemplary surgical planning user interface 600 for a surgical proposal for reverse shoulder arthroplasty according to one or more techniques of the present disclosure. The planning presentation unit 210 (FIG. 2) may generate a user interface 600 for display (e.g., on the display 108 or the local device 112 (FIG. 1)). In some embodiments, the planning presentation unit 210 may generate the user interface 600 after receiving an indication of user input indicating surgeon preference parameters (e.g., via the user interface 300 (FIG. 3)).

[0048]

[0056] In the embodiment of FIG. 6, the user interface 600 shows surgical proposals 602A, 602B (collectively referred to as "surgical proposals 602") for reverse shoulder arthroplasty. Each of the surgical proposals 602 indicates the type of glenoid implant, the diameter of the glenoid implant, the diameter and type of the glenosphere of the glenoid implant (e.g., centered, eccentric, angled, etc.), the neck-shaft angle of the corresponding humeral implant, the anteroposterior twist of the glenoid implant, the implantation rate of the glenoid implant, and the peg depth of the glenoid implant. The user 118 may select one of the surgical proposals 602. In the embodiment of FIG. 6, a black background is used to indicate that surgical proposal 602A is the selected surgical proposal.

[0049]

[0057] Further, the user interface 600 includes a top view 606, a front view 608, and a model 610. The top view 606 shows an X-ray image of the patient's shoulder from a top perspective (i.e., viewed from a top position in a downward direction). The top view 606 shows the outer contour 612 of a glenoid implant of the type indicated by the selected surgical proposal at the position indicated by the selected surgical proposal. The front view 608 shows an X-ray image of the patient's shoulder from a front perspective (i.e., viewed from a front position in a rearward direction). The front view 608 shows the outer contour 614 of a glenoid implant of the type indicated by the surgical proposal at the position indicated by the selected surgical proposal. The model 610 shows a 3D model of the patient's scapula with a phantom image of the glenoid implant.

[0050]

[0058] The user interface 600 also includes control units 604A, 604B for switching the display of surgical proposals for anatomic shoulder arthroplasty and reverse shoulder arthroplasty.

[0051]

[0059] Although not shown in the embodiment of FIG. 6, each of the surgical proposals 602 may include data indicating the expected range of motion for the surgical proposal 602. For example, each of the surgical proposals 602 may indicate an expected extension angle, an expected flexion angle, an expected abduction angle, and an expected internal rotation angle. The RoM unit 208 may determine these expected ranges of motion, for example, in the manner described elsewhere in the present disclosure.

[0052]

[0060] FIG. 7 is a flowchart illustrating an exemplary operation of a surgical planning system 116 according to one or more techniques of the present disclosure. In the embodiment of FIG. 7, the surgical planning system 116 (e.g., the preference acquisition unit 202 (FIG. 2)) may acquire one or more surgeon preference parameters that specify values of one or more surgical parameters (700). The surgical parameters may indicate a range of positioning parameters for a glenoid implant that is to be attached to the glenoid fossa of the patient during surgery. For example, the surgical planning system 116 may acquire the surgeon preference parameters via a user interface such as the user interface 400 (FIG. 4A) or the user interface 450 (FIG. 4B).

[0053]

[0061] Further, in the embodiment of FIG. 7, the surgical planning system 116 (e.g., the parameter prediction unit 206) may determine one or more proposed surgical options (702) based on one or more anatomical parameters and surgeon preference parameters of the patient. Each of the surgical options corresponds to a different combination of the positioning parameters of the glenoid implant and the type of glenoid implant. FIG. 8, which will be detailed below, is a flowchart illustrating an exemplary operation of the parameter prediction unit 206 for determining one or more proposed surgical options for the glenoid implant. In some embodiments, as part of determining one or more proposed surgical options, the parameter prediction unit 206 may filter the proposed surgical options (e.g., the proposed surgical options determined using the operations of FIG. 8) to remove invalid proposed surgical options. For example, the parameter prediction unit 206 may exclude a proposed surgical option that includes a glenoid implant having a fixture that penetrates the boundary of the scapula on the opposite side of the glenoid.

[0054]

[0062] In some embodiments, the surgical planning system 116 may acquire medical image data of the patient's glenoid. For example, the surgical planning system 116 may acquire medical image data from a memory such as the memory 106 (FIG. 1), from a medical imaging machine (e.g., an X-ray machine, a CT machine, etc.). The medical image data may include a medical image and / or a model of the patient's shoulder. The surgical planning system 116 (e.g., the anatomical parameter unit 204) may determine one or more anatomical parameters of the patient based on the medical image data.

[0055]

[0063] In the embodiment of FIG. 7, the surgical planning system 116 (e.g., the planning presentation unit 210 (FIG. 2)) may output one or more proposed surgical options (704). For example, the surgical planning system 116 may output one or more proposed surgical options to a user interface such as the user interface 500 (FIG. 5) or the user interface 600 (FIG. 6). In some embodiments, the surgical planning system 116 may output one or more proposed surgical options for display in MR visualization. In some embodiments, the surgical planning system 116 may output one or more proposed surgical options for display on a conventional monitor or screen. In some embodiments, the surgical planning system 116 may output the proposed surgical options audibly.

[0056]

[0064] FIG. 8 is a flowchart illustrating an exemplary operation of the parameter prediction unit 206 for determining one or more proposed surgical options for a glenoid implant according to one or more techniques of the present disclosure. In the embodiment of FIG. 8, the parameter prediction unit 206 may filter the glenoid implant type based on the surgeon preference parameters (800). In other words, the parameter prediction unit 206 may exclude the glenoid implant type based on the surgeon preference parameters to determine a set of one or more remaining glenoid implant types. When filtering the glenoid implant type, the parameter prediction unit 206 may start with a set of glenoid implants including all available glenoid implant types. For example, the glenoid implant types may include glenoid implants with keel-type fixtures, glenoid implants with peg-type fixtures, and glenoid implants with peg-type fixtures including one or more finned pegs. Further, in this embodiment, if the surgeon preference parameters indicate that the surgeon does not want to use a glenoid implant with a keel-type fixture, the parameter prediction unit 206 may exclude (e.g., remove) all glenoid implants with keel-type fixtures from the list of available glenoid implants.

[0057]

[0065] Further, in the embodiment of FIG. 8, the parameter prediction unit 206 may determine the size of the glenoid implant based on the patient's anatomical parameters (802). For example, the parameter prediction unit 206 may determine the glenoid region size (i.e., the anatomical parameter) of the patient's glenoid fossa. In this embodiment, the glenoid region size of the glenoid fossa is a two-dimensional region included inside the edge of the glenoid fossa. Next, the parameter prediction unit 206 may compare the glenoid region size of the glenoid fossa with a set of one or more threshold values. The threshold values may correspond to the sizes of the glenoid implants in the list of available glenoid implants. In some embodiments, the parameter prediction unit 206 may determine the glenoid region size, the length of the major axis of the glenoid fossa, and the length of the minor axis of the glenoid fossa. The major axis and the minor axis of the glenoid fossa are defined by an ellipse corresponding to the boundary of the glenoid fossa. The parameter prediction unit 206 may determine the size of the glenoid implant based on the glenoid region size, the length of the major axis of the glenoid fossa, and the length of the minor axis of the glenoid fossa. For example, the parameter prediction unit 206 may look up the size of the glenoid implant in a table that maps a combination of the glenoid region size, the length of the major axis of the glenoid fossa, and the length of the minor axis of the glenoid fossa to the size of the glenoid implant.

[0058]

[0066] In some embodiments, rather than the parameter prediction unit 206 automatically determining the size of the glenoid implant, the parameter prediction unit 206 may receive data indicating a user-specified size of the glenoid implant. For example, the parameter prediction unit 206 may receive an indication of a user input of the size of the glenoid implant. In another embodiment, the parameter prediction unit 206 may receive from the user 118 an indication of a set of rules that the parameter prediction unit 206 may use to determine the size of the glenoid implant. In this way, the user 118 may be able to select a smaller-sized implant to achieve a more secure placement of the glenoid implant. In another embodiment, the user 118 may feel that the anatomical parameter unit 204 has determined an incorrect glenoid region size, so the user 118 may select a specific size of the glenoid implant. In another embodiment, the user 118 may select a specific size of the glenoid implant to avoid bone spurs.

[0059]

[0067] Furthermore, the parameter prediction unit 206 may generate a current trial vector (803). The trial vector is a set of surgical parameter values. The surgical parameter values are values of surgical parameters. The surgical parameters may include the type and placement parameters of the glenoid implant. Exemplary placement parameters may include the anteroposterior twist of the glenoid implant, the inclination of the glenoid implant, the anterior position of the glenoid implant, the lateral position of the glenoid implant, and the superior position of the glenoid implant. The type of glenoid implant that may be included in the trial vector may be limited to the type of glenoid implant that is within the set of filtered glenoid implant types (i.e., the remaining glenoid implant types) determined in step 800. In other words, the parameter prediction unit 206 may generate a trial vector such that the trial vector includes only the types of glenoid implants that are within the set of remaining glenoid implant types. In some embodiments, the surgical parameter values may include a glenoid implant size parameter limited to the determined size of the glenoid implant. In other words, the parameter prediction unit 206 may generate a trial vector such that the trial vector includes only glenoid implants having the determined size.

[0060]

[0068] The parameter prediction unit 206 can determine an input value based on the surgical parameter values in the current trial vector (804). The input value can include values that the parameter prediction unit 206 uses in a cost function to determine a cost value for the trial vector. The parameter prediction unit 206 can use a set of one or more functions to calculate the input value based on the surgical parameter values in the trial vector and the anatomical parameters of the patient. In some embodiments, the functions are provided to the parameter prediction unit 206 by a surgeon. In some embodiments, the functions are preconfigured. For example, the surgical parameter value may include the anteroposterior twist angle of the glenoid implant, and the rule may specify a function that converts the anteroposterior twist angle of the glenoid implant to an input value such that a glenoid implant anteroposterior twist angle closer to 0° has a larger value than an angle farther from 0°. For example, in this embodiment, the function may be equal to the maximum anteroposterior twist angle of the glenoid implant minus the absolute value of the anteroposterior twist angle of the glenoid implant.

[0061]

[0069] In another embodiment, the parameter prediction unit 206 determines the amount of bone resorption when the surgical parameters of the trial vector are applied considering the anatomical parameters of the patient, determines the area without contact between the implant and the bone when the surgical parameters of the trial vector are applied considering the anatomical parameters of the patient, determines the area with contact between the implant and the strong part of the bone when the surgical parameters of the trial vector are applied considering the anatomical parameters of the patient, determines the area with contact between the implant and the fragile part of the bone when the surgical parameters of the trial vector are applied considering the anatomical parameters of the patient, determines the radius of the glenoid implant indicated by the surgical parameters of the trial vector considering the anatomical parameters of the patient, and / or can determine other input values based on the surgical parameters.

[0062]

[0070] Further, in the embodiment of FIG. 8, the parameter prediction unit 206 may determine a first preliminary cost value for the current trial vector based on the input values (806). The parameter prediction unit 206 may determine a first preliminary cost value for the trial vector based on a linear combination of the input values, as shown in the following equation (1).

Equation

[0063]

[0071] In one embodiment where the parameter prediction unit 206 determines a first preliminary cost value for the trial vector based on a linear combination of the input values, the parameter prediction unit 206 may determine the first preliminary cost value for the trial vector as follows.

Equation

[0064]

[0072] In Equation (2), P represents a penalty value applied when any of the surgical parameters (or input values) of the trial vector do not match the values preferred by the surgeon. For example, the surgical parameters of the trial vector may include an anteroposterior torsion parameter that can range from -15° (posterior torsion) to 15° (anterior torsion). In this embodiment, the surgeon preference parameter may specify a maximum posterior torsion of 10° (i.e., an anteroposterior torsion of -10°). Thus, in this embodiment, when the surgical parameter of the trial vector includes an anteroposterior torsion parameter of -15°, the parameter prediction unit 206 may set P equal to a penalty value (e.g., 100). Otherwise, when the anteroposterior torsion parameter is not outside the range specified by the surgeon preference parameter, the parameter prediction unit 206 may set P equal to a non-penalty value (e.g., 0).

[0065]

[0073] In Equation (2), V Reamed , A NoSeating , A StrongSeating , and A WeakSeating are based on the patient's anatomical parameters. A portion of the bone may be considered brittle if the bone density is less than a specified threshold. In some embodiments, a portion of the bone may be considered strong if the bone density exceeds the specified threshold.

[0066]

[0074] In addition to determining a first preliminary cost value for a set of input values, the parameter prediction unit 206 may determine a second preliminary cost value for the current trial vector (808). The second preliminary cost value may serve as part of a coherence verification that can ensure that the values of the surgical parameters in the trial vector are within a reasonable range. In some embodiments, the parameter prediction unit 206 may determine a second preliminary cost value for the trial vector based on the difference between the surgical parameters of the trial vector and the typical values of the surgical parameters. For example, the parameter prediction unit 206 may determine a second preliminary cost value for the set of input values as follows. [Number] In the above formula (3), C2 represents the second preliminary cost value, k is the index of the surgical parameter, n represents the number of surgical parameters in the trial vector, a k represents the weight of the surgical parameter k, x k represents the value of the surgical parameter k in the trial vector, mean k represents the average of the values of the surgical parameter k in a collection of cases where the surgery has been previously performed, and stdDev k is the standard deviation of the surgical parameter k in a collection of cases where the surgery has been previously performed. The above formula (3) is calculated on a logarithmic scale. In the above formula (3), each of the surgical parameters in the trial vector is assumed to follow a naive Bayes Gaussian distribution. Therefore, formula (3) may be equivalent to calculating according to the following chain rule, considering the values of the other parameters x1...x k in the trial vector for each surgical parameter V n in the trial vector. [Number]

[0067]

[0075] In other embodiments, it may be assumed that the surgical parameters in the trial vector follow other distributions. In some embodiments, different distributions may be assumed for different surgical parameters. For example, the implantation rate is an example of a surgical parameter. Many surgeons prefer an implantation rate of 100%, but a 100% implantation is often not achievable in some patients. As a result, the average implantation rate across patients (and thus the mean of the distribution for the surgical parameter of the implantation rate) can be less than 100% (e.g., 95%). Therefore, in this embodiment, a distribution different from the distribution directly derived from the implantation rate in the trial vector may be used. For example, a bias term may be used to modify the distribution derived from the implantation rate so that the mean of the distribution is equal to 100%.

[0068]

[0076] Furthermore, in the embodiment of FIG. 8, the parameter prediction unit 206 may determine a cost value for the current trial vector based on the first preliminary cost value and the second preliminary cost value (810). For example, the parameter prediction unit 206 may determine the cost value for the trial vector as follows. C = (C1 + M) * C2 (4) In the above formula (4), C represents the cost value for the trial vector, C1 is the first preliminary cost value, C2 is the second preliminary cost value, and M is a constant that ensures that (C1 + M) and C2 have the same sign.

[0069]

[0077] The parameter prediction unit 206 may determine whether the cost value for the trial vector is less than the cost value for the previous trial vector (812). If the cost value for the trial vector is greater than or equal to the cost value for the previous trial vector (the "NO" branch of 812), the parameter prediction unit 206 may return the trial vector to the previous trial vector (814). If the cost value for the current trial vector is less than the cost value for the previous trial vector (the "YES" branch of 812), or after returning the current trial vector to the previous trial vector, the parameter prediction unit 206 may determine whether a stop condition is satisfied (816). In various embodiments, the stop condition may be one or more of, for example, a specific number of times reaching step (816), a specific number of times after evaluating all of the remaining glenoid implant types in a set of glenoid implant types and no lower cost value is found, etc.

[0070]

[0078] In response to determining that the stop condition is not satisfied (the "NO" branch of 816), the parameter prediction unit 206 may generate a new trial vector (818) and repeat steps (804) to (816). The parameter prediction unit 206 may generate a new trial vector by updating one (or more) of the surgical parameter values of the current (or returned) trial vector. For example, the parameter prediction unit 206 may generate a new trial vector by incrementing or decrementing surgical parameter values such as, for example, the tilt angle, the anteroposterior twist angle, etc. In some embodiments, the parameter prediction unit 206 may increment or decrement different surgical parameters by different amounts when generating a new trial vector. In another embodiment, the parameter prediction unit 206 may generate a new trial vector by changing one glenoid implant type to another glenoid implant type in a set of filtered glenoid implant types.

[0071]

[0079] In this way, the parameter prediction unit 206 can determine whether the current trial vector in the set of trial vectors represents an improvement over the previous trial vector in the set of trial vectors based on a comparison of the cost value for the current trial vector with the cost value of the previous trial vector in the set of trial vectors. Further, based on the current trial vector not representing an improvement over the previous trial vector (e.g., the cost score for the current trial vector being smaller than the cost score for the previous trial vector), the parameter prediction unit 206 can revert the current trial vector to the previous trial vector and update one or more surgical parameters of the current trial vector to determine a new current trial vector in the set of trial vectors. Alternatively, based on the current trial vector representing an improvement over the previous trial vector, the parameter prediction unit 206 does not revert the current trial vector to the previous trial vector. In either case, the parameter prediction unit 206 can generate a new trial vector based on the current trial vector.

[0072]

[0080] After generating a new trial vector, the parameter prediction unit 206 can repeat steps (804) to (816) with the new trial vector serving as the current trial vector. In this way, the parameter prediction unit 206 can act as an amoeba optimizer that loops through combinations of the implant and other surgical parameters. Thus, the parameter prediction unit 206 can learn proposed surgical options that may be optimal for a particular patient based on surgeon preference parameters.

[0073]

[0081] In this way, the parameter prediction unit 206 can generate a set of one or more trial vectors, where each trial vector in the set of trial vectors includes one or more of the surgical parameters. For each trial vector in the set of trial vectors, the parameter prediction unit 206 can determine an input value based on the surgical parameters and anatomical parameters of the trial vector, and can determine a cost value for the trial vector based on the input value.

[0074]

[0082] On the other hand, when the stop condition is satisfied (the "YES" branch of 816), the parameter prediction unit 206 can determine the best trial vector in the set of trial vectors (820). The best trial vector is the trial vector that has the lowest cost value when the stop condition is satisfied.

[0075]

[0083] Each of the evaluated trial vectors in FIG. 8 can correspond to a different proposed surgical option. In some embodiments, the parameter prediction unit 206 can rank the trial vectors based on their cost values and set a specific number of trial vectors having the lowest cost values as the proposed surgical options. In some embodiments, the parameter prediction unit 206 can determine whether to include a trial vector as one of the proposed surgical options based on the cost value for the trial vector. For example, the parameter prediction unit 206 can determine whether to include a trial vector as one of the proposed surgical options based on determining that the cost value for the trial vector exceeds a threshold.

[0076]

[0084] Certain techniques of the present disclosure are described in connection with shoulder arthroplasty, and in particular, in connection with the human scapula. Examples of shoulder arthroplasty include, but are not limited to, reverse arthroplasty, reverse arthroplasty using an augmentation, standard total shoulder arthroplasty, total shoulder arthroplasty using an augmentation, and hemiarthroplasty. However, the present techniques are not so limited, and the visualization system can be used to provide virtual guidance information, including virtual guides in any type of surgery. Other exemplary procedures in which the surgical support system 100 can be used to provide virtual guidance include, but are not limited to, other types of orthopedic surgery, any type of procedure with a suffix of "plasty", "ostomy", "ectomy", "destruction", or "puncture", orthopedic surgery of other joints such as the elbow joint, wrist joint, finger joint, hip joint, knee joint, ankle joint, or toe joint, or any other orthopedic surgery where accurate guidance is desired. For example, the surgical support system 100 can be used to provide a computer-assisted plan for ankle arthroplasty.

[0077]

[0085] The present techniques are disclosed in connection with a limited number of embodiments, but those skilled in the art having the benefit of the present disclosure will understand numerous modifications and variations therefrom. For example, it is contemplated that any suitable combination of the described embodiments can be implemented. The appended claims are intended to cover such modifications and variations as being within the true spirit and scope of the invention. Further, the techniques of the present disclosure are generally described in connection with human anatomical structures. However, the techniques of the present disclosure can also be applied to the anatomical structures of animals in veterinary medicine.

[0078]

[0086] It should be recognized that, depending on the implementation example, the specific operations or events of any of the techniques described herein can be performed in a different order, and can be added, integrated, or completely excluded (e.g., not all of the described operations or events are necessary for the implementation of the technique). Further, in certain implementation examples, the operations or events are not sequential but rather, for example, can be performed simultaneously by multi-threading, interrupt processing, or multiple processors.

[0079]

[0087] In one or more implementation examples, the described functions can be implemented in hardware, software, firmware, or any combination thereof. When implemented in software, these functions can be stored or transmitted on a computer-readable medium as one or more instructions or codes and executed by a hardware-based processing unit. The computer-readable medium can include a computer-readable storage medium corresponding to a tangible medium such as a data storage medium, or a communication medium including any medium that facilitates transfer of a computer program from one location to another, for example, according to a communication protocol. Thus, the computer-readable medium generally can correspond to (1) a tangible computer-readable storage medium that is non-transitory, or (2) a communication medium such as a signal or carrier wave. The data storage medium can be any available medium that can be accessed by one or more computers or one or more processors to search for instructions, codes, and / or data structures for implementation of the techniques described in this disclosure. A computer program product can include a computer-readable medium.

[0080]

[0088] By way of example and not limitation, such a computer-readable storage medium can be RAM, ROM, EEPROM (registered trademark), CD-ROM or other optical disk storage device, magnetic disk storage device, or other magnetic storage device, flash memory, or any other medium that can be used to store the desired program code in the form of data structures or instructions and that can be accessed by a computer. Also, any connection can be properly termed a computer-readable medium. For example, if the instructions are transmitted from a website, server, or other remote source using coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwave, then the coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave are included in the definition of the medium. However, it should be understood that computer-readable storage media and data storage media do not include connections, carrier waves, signals, or other transient media, but instead are directed to non-transitory tangible storage media. Disk and disc, as used herein, include compact disc (CD), laser disc (registered trademark), optical disc, digital versatile disc (DVD), and Blu-ray disc, where disk typically magnetically reproduces data, while disc optically reproduces data using a laser. The above combinations should also be included within the scope of computer-readable media.

[0081]

[0089] The operations described in this disclosure may be performed by one or more processors implemented as fixed-function processing circuits, programmable circuits, or combinations thereof, such as one or more digital signal processors (DSPs), general-purpose microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other equivalent integrated logic circuits or discrete logic circuits. A fixed-function circuit refers to a circuit that provides a specific function and is preset with respect to the operations it can perform. A programmable circuit refers to a circuit that can be programmed to perform various tasks and provide a flexible function in the operations it can perform. For example, a programmable circuit can execute instructions specified by software or firmware that cause the programmable circuit to operate in a manner defined by the instructions of the software or firmware. A fixed-function circuit can execute software instructions (e.g., to receive or output parameters), but the type of operations performed by the fixed-function circuit is generally invariant. Thus, the terms "processor" and "processing circuit" as used herein can refer to either the foregoing structures or any other structure suitable for implementing the techniques described in this specification.

Claims

1. obtaining, by a computing system, one or more surgeon preference parameters that specify values of one or more surgical parameters, wherein the surgical parameters include one or more positioning parameters for a glenoid implant to be attached to a glenoid cavity of a patient during surgery, determining, by the computing system, one or more proposed surgical options based on the one or more anatomical parameters of the patient and the surgeon preference parameters, wherein each of the proposed surgical options corresponds to a different combination of the positioning parameters for the glenoid implant and the type of the glenoid implant, outputting, by the computing system, the one or more proposed surgical options, A method comprising the above steps.

2. Determining the one or more proposed surgical options comprises: generating a set of one or more trial vectors, wherein each trial vector in the set of trial vectors includes one or more of the surgical parameters, for each trial vector in the set of trial vectors, determining an input value based on the surgical parameters and the anatomical parameters of the trial vector, determining a cost value for the trial vector based on the input value, determining whether to include the trial vector as one of the proposed surgical options based on the cost value for the trial vector, The method according to claim 1, comprising the above steps.

3. Determining the cost value for the trial vector comprises: determining a first preliminary cost value for the trial vector based on a linear combination of the input values, determining a second preliminary cost value for the trial vector based on a difference between the surgical parameters of the trial vector and standard values of the surgical parameters, determining the cost value for the trial vector based on the first preliminary cost value for the trial vector and the second preliminary cost value for the trial vector, The method according to claim 2, comprising the above steps.

4. Generating the set of trial vectors comprises: Excluding a glenoid implant type based on the surgeon preference parameters to determine one or more sets of remaining glenoid implant types, Generating the trial vector such that the trial vector includes only glenoid implant types within the set of remaining glenoid implant types, The method according to claim 2 or 3, comprising:

5. Generating the set of trial vectors comprises: Determining the size of the glenoid implant based on the anatomical parameters of the patient, Generating the trial vector such that the trial vector includes only glenoid implants having the determined size, The method according to any one of claims 2 to 4, comprising:

6. Generating the set of trial vectors comprises generating a new trial vector in the set of trial vectors by updating one or more surgical parameters of a current trial vector, according to the method of any one of claims 2 to 5.

7. Generating the set of trial vectors comprises: Determining whether the current trial vector represents an improvement over the previous trial vector based on a comparison of the cost value for the current trial vector in the set of trial vectors with the cost value of the previous trial vector in the set of trial vectors; Reverting the current trial vector to the previous trial vector based on the current trial vector not representing an improvement over the previous trial vector; Updating one or more surgical parameters of the current trial vector to determine a new current trial vector in the set of trial vectors, The method according to any one of claims 2 to 6, comprising:

8. Determining whether to include the trial vector as one of the proposed surgical options comprises determining whether the cost value for the trial vector exceeds a threshold, according to the method of any one of claims 2 to 7.

9. Determining the one or more proposed surgical options comprises To determine one or more sets of remaining glenoid implant types, filtering the glenoid implant type based on the surgeon preference parameters; Determining the size of the glenoid implant based on the anatomical parameters of the patient; Generating a current trial vector including one or more surgical parameters, wherein the type of glenoid implant in the current trial vector is limited to the remaining glenoid implant types; Determining an input value based on the surgical parameters and the anatomical parameters of the current trial vector; Determining a first preliminary cost value for the current trial vector based on a linear combination of the input values; Determining a second preliminary cost value for the current trial vector based on the difference between the surgical parameters of the current trial vector and the standard values of the surgical parameters; Determining a cost value for the current trial vector based on the first preliminary cost value for the current trial vector and the second preliminary cost value for the current trial vector; Determining whether the current trial vector represents an improvement over the previous trial vector based on a comparison of the cost value for the current trial vector and the cost value of the previous trial vector; Returning the current trial vector to the previous trial vector based on the current trial vector not representing an improvement over the previous trial vector; Updating one or more surgical parameters of the current trial vector to determine a new current trial vector; The method according to claim 1, comprising.

10. A memory configured to store one or more surgeon preference parameters that specify values of one or more surgical parameters, wherein the surgical parameters include one or more positioning parameters for a glenoid implant to be attached to the glenoid of a patient during surgery; One or more processors implemented within a circuit; Comprising, wherein the one or more processors are Determining one or more proposed surgical options based on the one or more anatomical parameters of the patient and the surgeon preference parameters, wherein each of the proposed surgical options corresponds to a different combination of the positioning parameters for the glenoid implant and the type of glenoid implant, Outputting the one or more proposed surgical options for display, A computing system configured to perform.

11. As part of determining the one or more proposed surgical options, the one or more processors generate a set of one or more trial vectors, where each trial vector in the set of trial vectors includes one or more of the surgical parameters. For each trial vector in the set of trial vectors, Determining an input value based on the surgical parameters of the trial vector and the anatomical parameters, Determining a cost value for the trial vector based on the input value, Based on the cost value for the trial vector, determining whether to include the trial vector as one of the proposed surgical options. The computing system according to claim 10, configured to perform.

12. As part of determining the cost value for the trial vector, the one or more processors determine a first preliminary cost value for the trial vector based on a linear combination of the input values, Determining a second preliminary cost value for the trial vector based on the difference between the surgical parameters of the trial vector and the standard values of the surgical parameters, Based on the first preliminary cost value for the trial vector and the second preliminary cost value for the trial vector, determining the cost value for the trial vector. The computing system according to claim 11, configured to perform.

13. As part of generating the set of trial vectors, the one or more processors ​ ​ To determine one or more sets of remaining glenoid implant types, excluding a glenoid implant type based on the surgeon preference parameters, generating the trial vector such that the trial vector includes only glenoid implant types in the set of the remaining glenoid implant types, The computing system according to claim 11 or 12, which is configured to perform the above.

14. As part of generating the set of trial vectors, the one or more processors determine the size of the glenoid implant based on the anatomical parameters of the patient, generating the trial vector such that the trial vector includes only glenoid implants having the determined size, The computing system according to any one of claims 11 to 13, which is configured to perform the above.

15. Generating the set of trial vectors includes generating a current trial vector by updating one or more surgical parameters of a previous trial vector in the set of trial vectors. The computing system according to any one of claims 11 to 14.

16. As part of generating the set of trial vectors, the one or more processors determine based on a comparison between the cost value for the current trial vector in the set of trial vectors and the cost value of the previous trial vector in the set of trial vectors, whether the current trial vector represents an improvement over the previous trial vector, based on the fact that the current trial vector does not represent an improvement over the previous trial vector, reverting the current trial vector to the previous trial vector, updating one or more surgical parameters of the current trial vector to determine a new current trial vector in the set of trial vectors, The computing system according to any one of claims 11 to 15, which is configured to perform the above.

17. The one or more processors are configured to determine whether a cost value for the trial vector exceeds a threshold as part of determining whether to include the trial vector as one of the proposed surgical options, the computing system according to any one of claims 11-16.

18. As part of determining the one or more proposed surgical options, the one or more processors filtering a glenoid implant type based on the surgeon preference parameters to determine a set of one or more remaining glenoid implant types; determining a size of the glenoid implant based on the anatomical parameters of the patient; generating a current trial vector including one or more surgical parameters, wherein a type of the glenoid implant in the current trial vector is limited to the remaining glenoid implant types; determining an input value based on the surgical parameters and the anatomical parameters of the current trial vector; determining a first preliminary cost value for the current trial vector based on a linear combination of the input values; determining a second preliminary cost value for the current trial vector based on a difference between the surgical parameters of the current trial vector and standard values of the surgical parameters; determining a cost value for the current trial vector based on the first preliminary cost value for the current trial vector and the second preliminary cost value for the current trial vector; determining whether the current trial vector represents an improvement over the previous trial vector based on a comparison of the cost value for the current trial vector and the cost value of the previous trial vector; reverting the current trial vector to the previous trial vector based on the current trial vector not representing an improvement over the previous trial vector; To determine a new current trial vector, updating one or more surgical parameters of the current trial vector; The computing system according to claim 10, configured to perform the above.

19. A computing system comprising means for performing the method according to any one of claims 1 to 9.

20. A computer-readable storage medium storing instructions that, when executed, cause one or more processors of a computing system to perform the method according to any one of claims 1 to 9.

Images