Computer-aided surgical planning

Abstract

A method includes obtaining, by a computing system, one or more surgeon preference parameters that specify values for 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 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, each of the surgical options corresponding 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.

Description

[0001] This application claims the benefit of U.S. Provisional Patent Application 63 / 146,278, filed February 5, 2021, the entire contents of which are incorporated herein by reference. Background Technology

[0002] Shoulder replacement surgery is a complex type of orthopedic surgery. However, it is becoming increasingly common because it can reduce pain and restore range of motion in many patients. The complexity of shoulder replacement surgery prevents many surgeons from performing it, especially those who do not frequently perform the procedure. Therefore, computerized surgical planning systems have been developed to assist surgeons in planning complex surgeries such as shoulder replacement. Summary of the Invention

[0003] This disclosure describes various techniques for improving computerized surgical planning systems. One challenge associated with implementing a computerized surgical planning system is ensuring that it generates surgical plans for shoulder replacement surgeries that are consistent with the preferences of individual surgeons. For example, a computerized surgical planning system may use a machine learning (ML) model to generate multiple predictions about various surgical options for shoulder replacement surgery. Typically, this may require a large training dataset (e.g., data on individual surgeries) to train the ML model. Training a separate ML model for each individual surgeon to generate predictions based on their preferences may be impractical, at least due to the number of cases required to train the ML model. This is especially true for surgeons who do not frequently perform shoulder replacement surgeries, as they simply do not perform enough surgeries to adequately train the ML model. This disclosure describes techniques that can address this problem and allow surgical planning systems to generate surgical recommendations that are adapted to the preferences of individual surgeons, with associated benefits of reduced storage requirements and reduced computational resource utilization.

[0004] In one example, this disclosure describes a method comprising: obtaining, via a computational system, one or more surgeon preference parameters specifying values ​​for one or more surgical parameters, wherein the surgical parameters include one or more positioning parameters for a glenoid implant to be attached to the patient's glenoid fossa during surgery; determining, via the computational system, one or more suggested surgical options based on one or more anatomical parameters of the patient and the surgeon preference parameters, each surgical option corresponding to a different combination of the glenoid implant positioning parameters and the type of glenoid implant; and outputting, via the computational system, one or more suggested surgical options.

[0005] In another example, this disclosure describes a computing system comprising: a memory configured to store one or more surgeon preference parameters specifying values ​​for one or more surgical parameters, wherein the surgical parameters include one or more positioning parameters for a glenoid implant to be attached to the patient's glenoid fossa during surgery; one or more processors implemented in circuitry configured to: determine one or more suggested surgical options based on one or more anatomical parameters of the patient and the surgeon preference parameters, each surgical option corresponding to a different combination of the glenoid implant positioning parameters and the type of glenoid implant; and output the one or more suggested surgical options for display.

[0006] In other examples, this disclosure describes a computing system including means for performing the methods of this disclosure and a computer-readable storage medium having instructions stored thereon, which, when executed, cause one or more processors of the computing system to perform the methods of this disclosure.

[0007] Details of various examples of this disclosure are set forth in the accompanying drawings and the following description. Various features, objects, and advantages will become apparent from the description, drawings, and claims. Attached Figure Description

[0008] Figure 1 This is a block diagram of a surgical assistance system based on one or more technologies disclosed herein.

[0009] Figure 2 This is a block diagram illustrating example details of a surgical planning system according to one or more technologies of this disclosure.

[0010] Figure 3 This is a conceptual diagram illustrating an example surgical planning user interface according to one or more technologies disclosed herein.

[0011] Figure 4A This is a conceptual diagram illustrating an example surgical planning user interface for selecting surgeon preference parameters for anatomical shoulder replacement surgery according to one or more technologies of this disclosure.

[0012] Figure 4B This is a conceptual diagram illustrating an example surgical planning user interface for selecting surgeon preference parameters for reverse shoulder replacement surgery according to one or more technologies of this disclosure.

[0013] Figure 5 This is a conceptual diagram illustrating an example surgical planning user interface for displaying surgical recommendations for anatomical shoulder replacement surgery according to one or more technologies of this disclosure.

[0014] Figure 6This is a conceptual diagram illustrating an example surgical planning user interface for displaying surgical recommendations for reverse shoulder replacement surgery, according to one or more technologies disclosed herein.

[0015] Figure 7 This is a flowchart illustrating an example operation of a surgical planning system according to one or more technologies of this disclosure.

[0016] Figure 8 This is a flowchart illustrating an example operation of a parameter prediction unit that determines one or more suggested surgical options for a glenoid implant according to one or more techniques of this disclosure. Detailed Implementation

[0017] Certain examples of this disclosure are described with reference to the accompanying drawings, wherein similar reference numerals denote similar elements. However, it should be understood that the 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 examples of this disclosure. Numerous details are set forth in the following description. However, those skilled in the art will understand that the invention can be practiced without these details, and various changes or modifications can be made to the described examples.

[0018] This disclosure describes systems and methods associated with surgical planning. In other words, this disclosure describes techniques for automated surgical planning. Surgical planning, such as BLUEPRINT produced by Wright Medical Group NV, is used. TM Surgical plans generated by a system or another surgical planning platform may include various information about the surgery. For example, a surgical plan may include information about the steps a user (e.g., a surgeon) performs on a patient. Example steps may include, for example, bone or tissue preparation steps and / or steps for selecting, modifying, and / or replacing implant components (e.g., prostheses) and associated hardware or media. Furthermore, in various examples, information in the surgical plan may include the size, shape, angle, surface profile, and / or orientation of implant components to be selected or modified by the user; the size, shape, angle, surface profile, and / or orientation to be defined by the user in the bone or tissue preparation steps; and / or the position, axis, plane, angle, and / or entry point of the implant component to be replaced by the user relative to the patient's bone or tissue. For example, information about the size, shape, angle, surface profile, and / or orientation of the patient's anatomical features may be derived from imaging analysis (e.g., X-ray, CT, MRI, ultrasound, or other images), direct observation, or other techniques.

[0019] As described herein, the computational system can obtain one or more surgeon preference parameters specifying values ​​for one or more surgical parameters. Surgical parameters may include one or more positioning parameters for a glenoid implant to be attached to the patient's glenoid fossa during surgery. Furthermore, the computational system can determine one or more suggested surgical options for attaching the glenoid implant to the patient's glenoid fossa during surgery based on one or more anatomical parameters of the patient and the surgeon preference parameters. Each surgical option corresponds to a different combination of values ​​for the surgical parameters. The computational system can output one or more suggested surgical options for display.

[0020] Figure 1 This is a block diagram illustrating an example surgical assistance system 100 according to one or more technologies of this disclosure. Figure 1 In the example, the surgical assistance system 100 includes a computing system 102, which is an example of a computing system configured to perform one or more example technologies described in this disclosure. The computing system 102 may include various types of computing devices, such as server computers, personal computers, smartphones, tablets, laptops, and other types of computing devices. The computing system 102 includes processing circuitry 104, memory 106, a display 108, and a communication interface 110. The display 108 is optional, for example, in the example where the computing system 102 includes a server computer. Furthermore, in... Figure 1 In the example, the surgical assistance system 100 includes a local device 112 and a communication network 114.

[0021] Examples of processing circuitry 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. Typically, processing circuitry 104 can be implemented as fixed-function circuitry, programmable circuitry, or a combination thereof. Fixed-function circuitry refers to circuitry that provides a specific function and is pre-defined for the operations it can perform. Programmable circuitry refers to circuitry that can be programmed to perform various tasks and provide flexible functionality in the operations it can perform. For example, programmable circuitry can execute software or firmware, causing the programmable circuitry to operate in a manner defined by the instructions of the software or firmware. Fixed-function circuitry can execute software instructions (e.g., receiving or outputting parameters), but the type of operation performed by fixed-function circuitry is typically immutable. In some examples, one or more units may be different circuit blocks (fixed-function or programmable), and in some examples, one or more units may be integrated circuits.

[0022] Processing circuitry 104 may include an arithmetic logic unit (ALU), an essential function unit (EFU), digital circuitry, analog circuitry, and / or a programmable core formed by programmable circuitry. In an example where the operation of processing circuitry 104 is performed using software executed by programmable circuitry, memory 106 may store the object code of the software received and executed by processing circuitry 104, or another memory (not shown) within processing circuitry 104 may store such instructions. Examples of software include software designed for surgical planning. Processing circuitry 104 may perform the actions attributed to computing system 102 in this disclosure.

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

[0024] In addition, Figure 1 In some examples, memory 106 may include computer-readable instructions that, when executed by processing circuitry 104, cause computing system 102 to provide surgical planning system 116. In some examples, some or all of the instructions for surgical planning system 116 are stored on local device 112 and / or executed by processing circuitry of local device 112. In other examples, some or all of the instructions for surgical planning system 116 are stored on computing system 102 and / or executed by processing circuitry of computing system 102. In some examples, local device 112 may be or may include a mixed reality (MR) visualization device. For ease of explanation, this disclosure may simply describe the actions performed by the computing system 102 and / or the local device 112 when the processing circuitry of processing circuitry 104 and / or the local device 112 executes instructions from the surgical planning system 116. As performed by the surgical planning system 116, it should be understood that processing operations can be performed by the processing circuitry of the computing system 102, the local device 112, or a combination of both, or by other processing circuitry including processing circuitry associated with one or more cloud servers and / or one or more other remote computing devices, or in combination with other processing circuitry. Figure 1 In the example, memory 106 may also include surgical planning data 117, medical imaging data 119, and surgeon preference parameters 121.

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

[0026] Local device 112 can be a computing device used by user 118. In other examples, user 118 can directly use the computing device of computing system 102. In such examples, user 118 can view content displayed on display 108. In some examples, local device 112 is a personal computer, smartphone, tablet, laptop, or another type of computing device. In some examples, local device 112 is a mixed reality (MR) visualization device. MR visualization devices can use various visualization technologies to display image content to user 118 (who could be a surgeon). For example, MR visualization devices can include holographic projectors or other types of devices used to present MR scenes. In some examples, if local device 112 is an MR visualization device, local device 112 can be a Microsoft HoloLens available from Microsoft Corporation, Redmond, Washington, USA. TM Headphones or similar devices, such as waveguide-based MR visualization devices. HOLOLENS TM The device can be used to present 3D virtual objects through holographic lenses or waveguides, while allowing users to view real scenes, i.e. real objects in the real environment, through holographic lenses.

[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 surgeons in planning surgeries, such as anatomical shoulder replacement surgery or reverse shoulder replacement surgery. In anatomical shoulder replacement surgery, the surgeon implants a cup-shaped glenoid implant in the glenoid fossa of the patient's scapula and a ball-shaped humeral implant in the proximal humerus. In reverse shoulder replacement surgery, the surgeon implants a ball-shaped glenoid implant in the glenoid fossa of the patient's scapula and a cup-shaped humeral implant in the proximal humerus.

[0028] In anatomical or reverse shoulder replacement surgery, surgeons can choose from a variety of different types of glenoid and humeral implants. For example, surgeons can choose from keel-type glenoid implants, fixed glenoid implants, or other types of glenoid grafts. Furthermore, surgeons can choose from a variety of sizes within each type of glenoid implant. Similarly, surgeons can choose from stemmed humeral implants, sessile humeral implants, or other types of humeral implants. Likewise, surgeons can choose from a variety of sizes within each type of glenoid implant. For any glenoid or humeral implant, surgeons can choose from a variety of placement parameters. For example, surgeons can choose from a variety of angles that allow the glenoid or humeral implant to be placed. In some examples, surgeons can choose from various bone preparation angles, depths, and positions.

[0029] Given the many types of implants and various available placement parameters, surgeons may find it difficult to select the appropriate implant type and placement parameters for a specific patient. Therefore, when a surgeon plans shoulder replacement surgery for a patient, the surgical planning system 116 can generate recommended surgical options regarding implant type and placement parameters for that specific patient. When planning shoulder replacement surgery, the surgeon can choose from the recommended surgical options generated by the surgical planning system 116, or select other types of implants and / or surgical parameters. In other words, the surgeon is not limited by the recommended surgical options generated by the surgical planning system 116.

[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 fixed glenoid implant rather than a keel glenoid implant because they feel that the revision rate is lower with fixed glenoid implants than with keel glenoid implants. In another example, a surgeon may prefer a glenoid implant with a posterior tilt of no more than 10°.

[0031] Ignoring surgeon preferences may cause the surgical planning system 116 to generate suggested surgical options that the surgeon would not use. This poses a significant limitation to the usability of the surgical planning system 116 that generates suggestions. One approach to this problem is to train a machine learning (ML) model based on surgeries performed according to the individual surgeon's preferences. However, surgeons may not have performed enough surgeries to have sufficient training data to train their ML models. Without sufficient training data, the surgeon's ML model may produce poor suggestions. Furthermore, implementing different ML models for different surgeons can consume considerable processing power and storage space.

[0032] The technology disclosed herein can solve this problem. As described herein, the surgical planning system 116 can obtain one or more surgeon preference parameters 121, which specify a range of surgical parameters, such as the type and positioning parameters of the glenoid implant to be attached to the patient's glenoid during surgery. Furthermore, the surgical planning system 116 can determine one or more suggested surgical options based on one or more anatomical parameters of the patient and the surgeon preference parameters. The suggested surgical options may correspond to different combinations of implant positioning parameters and glenoid implant types.

[0033] Examples of how the surgical planning system 116 can perform automated planning to determine recommended surgical options based on one or more anatomical parameters and surgeon preference parameters will be described in more detail below. The surgical planning system 116 can output one or more recommended surgical options for display. In some examples, the surgical planning system 116 may receive instructions from the surgeon based on user input to select one of the recommendations, or to select an alternative implant type or placement parameters. The surgical planning system 116 may store the selected implant type and / or placement parameters in surgical planning data 117.

[0034] Figure 2 This is a block diagram illustrating example details of a surgical planning system 116 according to one or more technologies of this disclosure. Figure 2 In one example, 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, preference acquisition unit 202, anatomical parameter unit 204, parameter prediction unit 206, RoM unit 208, and plan presentation unit 210 may be implemented by software executed by programmable processing circuitry. In some examples, one or more of the surgical prediction unit 200, preference acquisition unit 202, anatomical parameter unit 204, parameter prediction unit 206, RoM unit 208, and plan presentation unit 210 may be implemented at least partially using dedicated hardware. The surgical prediction unit 200, preference acquisition unit 202, anatomical parameter unit 204, parameter prediction unit 206, and RoM unit 208 may work together to generate computer-aided predictions.

[0035] The surgical prediction unit 200 can generate a prediction about whether to perform anatomical shoulder replacement surgery or reverse shoulder replacement surgery. For example, the surgical prediction unit 200 can generate a first confidence value (e.g., an estimated probability) indicating the level of confidence a group of reference surgeons will choose anatomical shoulder replacement surgery for the patient, and a second confidence value indicating the level of confidence a group of reference surgeons will choose reverse shoulder replacement surgery for the patient. In this example, the surgical prediction unit 200 can output an indication of which of the two surgeries, anatomical shoulder replacement surgery and reverse shoulder replacement surgery, has a higher confidence score.

[0036] The surgical prediction unit 200 can be implemented in one of several ways. For example, the surgical prediction unit 200 can be implemented using one or more artificial intelligence systems, such as combinations of one or more artificial neural networks, support vector machines (SVMs), decision tree networks, random forests, Naive Bayes networks, etc. The surgical prediction unit 200 can generate a prediction about whether to perform anatomical shoulder replacement surgery or reverse shoulder replacement surgery based on a set of input data. Examples of input data for the surgical prediction unit 200 may include patient data, such as the patient's age, diagnosis of the patient's condition (e.g., large rotator cuff tear, osteoarthritis, etc.), the patient's sex, the patient's glenoid orientation, the patient's glenoid ball radius, the patient's glenoid version, the patient's glenoid inclination, the patient's humeral subluxation, the patient's glenoid orientation, the patient's glenoid region, and / or other types of data about the patient.

[0037] The preference acquisition unit 202 is configured to acquire surgeon preference parameters. The preference acquisition unit 202 can store the acquired surgeon preference parameters as surgeon preference parameters 121. In some examples, the surgeon preference parameters may be specific parameters for a particular patient's surgery. In some examples, the surgeon preference parameters may be common parameters for all patients treated by the surgeon. The preference acquisition unit 202 can output a user interface for selecting surgeon preference parameters. (The following...) Figure 4A A sample user interface for selecting surgeon preference parameters for anatomical shoulder replacement surgery is shown in more detail below. Figure 4B A sample user interface for selecting surgeon preference parameters for reverse shoulder replacement surgery is shown in more detail.

[0038] refer to Figure 2For example, anatomical parameter unit 204 is configured to determine a patient's anatomical parameters. In some examples, anatomical parameter unit 204 is configured to determine one or more anatomical parameters of a patient based on input instructions for anatomical parameters from user 118. In some examples, anatomical parameter unit 204 is configured to determine one or more anatomical parameters of a patient based on medical imaging data 119. Medical imaging data 119 may include X-ray images, computed tomography (CT) images, magnetic resonance imaging (MRI) images, and so on. Examples of patient anatomical parameters 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, percentage of humeral subluxation, humeral head radius, humeral orientation, humeral position, distance from the center of the humeral head to the center of the glenoid, Giannotti cortical index of the humerus, Tingart cortical thickness of the humerus, proximal diaphysis bone mineral density of the humerus, metaphyseal cavernous bone mineral density of the humerus, metaphyseal cortical bone mineral density of the humerus, scapular bone mineral density, glenoid version, glenoid inclination, humeral subluxation, and / or other types of information about the patient's anatomy.

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

[0040] The parameter prediction unit 206 can determine one or more suggested surgical options based on one or more anatomical parameters of the patient and surgeon preference parameters. The suggested surgical options may correspond to different combinations of glenoid implants, positioning parameters, and / or bone preparation parameters for the glenoid implant. The parameter prediction unit 206 can perform processing to determine the suggested surgical options, including several stages. In the first stage, the parameter prediction unit 206 can filter glenoid implant types based on 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 of a trial vector. Each trial vector is a set of surgical parameter values, such as positioning parameters and / or glenoid implant type. The following... Figure 8 A sample procedure for determining recommended surgical options for glenoid implants is described in more detail.

[0041] RoM unit 208 can determine the range of motion (RoM) of the patient's shoulder for one or more suggested surgical options. RoM unit 208 can determine the RoM of motion for the suggested surgical options using a combined 3D model of the patient's scapula, humerus (with a humeral implant), and glenoid implant attached to the patient's scapula, utilizing surgical parameters corresponding to the suggested surgical options. RoM unit 208 can then move the 3D model of the humerus relative to the 3D models of the scapula and glenoid implant along one or more motion axes. For each motion axis, RoM unit 208 can then detect the angle of collision between the humeral model and the scapular model. These collisions represent the outermost edge of the range of motion of the motion axis.

[0042] Figure 3 This is a conceptual diagram illustrating an example surgical planning user interface 300 according to one or more technologies of this disclosure. Planning presentation unit 210 ( Figure 2 This can generate data for display (e.g., on monitor 108 or local device 112). Figure 1 The user interface 300 is located on the [surface / top]. User 118 can use interface 300 as part of the process of planning shoulder replacement surgery. Figure 3In this example, the user interface 300 includes a top view 302, a front view 304, and a skeletal model 306. In this example, the top view 302 is an X-ray image of the patient's shoulder from an overhead perspective (i.e., viewed from above). In this example, the front view 304 is an X-ray image of the patient's shoulder from a frontal perspective (i.e., viewed from the front to the rear). 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 help the user 118 visualize the patient's shoulder in order to plan shoulder replacement surgery to be performed on the patient's shoulder.

[0043] In addition, the surgical planning interface 300 includes a patient information field 308, a patient anatomy field 310, a surgical prediction field 312, a "Planned Anatomy" button 314, and a "Plan Reverse" button 316. The patient information field 308 includes name information, age information, and information about whether the surgery is planned on the patient's left or right shoulder. The patient anatomy field 310 includes information about the patient's diagnosis, glenoid type, previous surgeries, and F1 subscapular footprint (F1 subscapular). The surgical prediction field 312 may include an indication of the predicted type of shoulder replacement surgery for the patient. Figure 3 In the example, surgical prediction field 312 indicates that the predicted type of shoulder replacement surgery for the patient is a reverse shoulder replacement surgery with a 66% probability. In other words, given information about the patient, most surgeons associated with the training data will perform the predicted type of shoulder replacement surgery, and the confidence level of the prediction is 66%. Surgical prediction unit 200 ( Figure 2 This can help determine the predicted type of shoulder replacement surgery, for example, as described elsewhere in this disclosure.

[0044] User 118 can initiate the process of planning anatomy for shoulder replacement surgery by selecting the "Planned Anatomy" button 314. User 118 can initiate the process of planning reverse shoulder replacement surgery by selecting the "Reverse Planning" button 316. Note that in some examples, user 118 does not need to, i.e., is not required to, select the type of shoulder replacement surgery indicated in the surgical prediction field 312, but can instead select another type of shoulder replacement surgery that is not indicated.

[0045] Figure 4A This is a conceptual diagram illustrating an example surgical planning user interface 400 for selecting surgeon preference parameters for anatomical shoulder replacement surgery according to one or more technologies of this disclosure. In some examples, preference acquisition unit 202 ( Figure 2 ) can respond to receiving the selection of the "Planned Dissection" button 314 ( Figure 3 The user interface 400 is presented based on the user's input instructions.

[0046] exist Figure 4A In the example, user interface 400 includes anchor checkboxes 402A-402C (collectively referred to as "anchor checkbox 402"). Anchor checkbox 402A corresponds to a glenoid implant with a keel-type anchor. Anchor checkbox 402B corresponds to a glenoid implant with a fixed anchor. Anchor checkbox 402C corresponds to a glenoid implant with a fixed anchor including one or more fin studs. In other examples, anchor checkbox 402 may correspond to other types of anchor settings for glenoid implants. User 118 (e.g., a surgeon) can use anchor checkbox 402 to instruct parameter prediction unit 206 which type of anchor setting for glenoid implants can be used to determine the recommended surgical options.

[0047] In addition, Figure 4A In the example, 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 posterior tilt of the glenoid implant. Range selection feature 404B corresponds to the maximum anterior tilt of the glenoid implant. Range selection feature 404C corresponds to the maximum downward tilt of the glenoid implant. Range selection feature 404D corresponds to the maximum upward tilt of the glenoid implant. Range selection feature 404E corresponds to the minimum placement percentage of the glenoid implant. The placement percentage is the percentage of the area of ​​the implant's placement surface in contact with the bone (i.e., placed on the bone). Range selection feature 404F corresponds to the maximum placement percentage of the glenoid implant.

[0048] Figure 4B This is a conceptual diagram illustrating an example surgical planning user interface 450 for selecting surgeon preference parameters for anatomical shoulder replacement surgery according to one or more technologies of this disclosure. In some examples, preference acquisition unit 202 ( Figure 2 ) can respond to receiving the "Reverse Plan" button 316 ( Figure 3 The user interface 450 is presented based on the user's input instructions.

[0049] exist Figure 4BIn this example, user interface 450 includes checkboxes 452A-452D (collectively referred to as "checkbox 452"). Checkbox 452 corresponds to the type of implant the surgeon wishes to use in a reverse shoulder replacement surgery. Checkbox 452A corresponds to an eccentric glenosphere. Checkbox 452B corresponds to a glenosphere implant with a cervical axis angle of 135°. Checkbox 452C corresponds to a first type of glenosphere implant. Checkbox 452D corresponds to a second type of glenosphere implant. In other examples, checkbox 452 may correspond to other types of implants used in a reverse shoulder replacement surgery. User 118 (e.g., a surgeon) can use checkbox 452 to instruct parameter prediction unit 206 which type of implant can be used to determine the recommended surgical options.

[0050] In addition, Figure 4B In the example, user interface 450 includes range selection features 454A-454E (collectively referred to as "range selection features 454"). Range selection feature 454A corresponds to the maximum posterior tilt of the glenoid implant. Range selection feature 454B corresponds to the maximum anterolateral tilt of the glenoid implant. Range selection feature 454C corresponds to the maximum downward tilt of the glenoid implant. Range selection feature 454D corresponds to the maximum upward tilt of the glenoid implant. Range selection feature 454E corresponds to the minimum placement percentage of the glenoid implant.

[0051] Figure 5 This is a conceptual diagram illustrating an example surgical planning user interface 500 according to one or more technologies of this disclosure, displaying surgical recommendations for anatomical shoulder replacement surgery. Planning presentation unit 210 ( Figure 2 This can generate data for display (e.g., on monitor 108 or local device 112). Figure 1 The user interface 500 is on the screen. In some examples, the planning presentation unit 210 can be on the screen after receiving an instruction from the user that indicates the surgeon's preference parameters (e.g., via the user interface 300). Figure 3 Generate user interface 500.

[0052] exist Figure 5In the example, user interface 500 displays surgical recommendations 502A and 502B (collectively, "surgical recommendations 502") for anatomical shoulder replacement surgery. Each surgical recommendation 502 indicates the type of glenoid implant, the type of anchorage for the glenoid implant, the size of the glenoid implant, the ball radius of the glenoid implant, the enlargement of the glenoid implant, the version of the glenoid implant, the inclination of the glenoid implant, and the placement percentage of the glenoid implant. Enlargement of the glenoid implant is a device to compensate for high glenoid inclination. In other examples, surgical recommendations 502 may indicate more, less, or different types of data. For example, in some examples, surgical recommendations 502 may indicate the amount of reaming (e.g., in cubic millimeters or millimeters). In some examples, surgical recommendations 502 may include two radii of curvature for an enlarged glenoid implant and a single radius of curvature for a non-enlarged glenoid implant. User 118 can select one of the surgical recommendations 502. Figure 5 In the example, the black background is used to indicate that surgical recommendation 502A is the selected surgical recommendation.

[0053] In addition, 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 an overhead perspective (i.e., viewed from above). The top view 506 shows the outline 512 of a glenoid implant of the type indicated by the selected surgical recommendation at the selected surgical recommendation location. The front view 508 is an X-ray image of the patient's shoulder from a forward perspective (i.e., viewed from the front to the rear). The front view 508 shows the outline 514 of a glenoid implant of the type indicated by the selected surgical recommendation at the selected surgical recommendation location. The model 510 shows a 3D model of the patient's scapula, with the glenoid fossa 516 highlighted.

[0054] The user interface 500 also includes controls 504A, 504B for switching between the display of surgical recommendations for anatomical shoulder replacement surgery and reverse shoulder replacement surgery.

[0055] Figure 6 This is a conceptual diagram illustrating an example surgical planning user interface 600 according to one or more technologies of this disclosure, displaying surgical recommendations for a reverse shoulder replacement surgery. Planning presentation unit 210 ( Figure 2 This can generate data for display (e.g., on monitor 108 or local device 112). Figure 1 The user interface 600 is on the screen. In some examples, the planning presentation unit 210 can be on the screen after receiving an instruction from the user that indicates the surgeon's preference parameters (e.g., via the user interface 300). Figure 3 Generate user interface 600.

[0056] exist Figure 6 In the example, user interface 600 displays surgical recommendations 602A and 602B (collectively, "surgical recommendations 602") for a reverse shoulder arthroplasty. Each surgical recommendation 602 indicates the type of glenoid implant, the diameter of the glenoid implant, the diameter and type of the glenoid prosthesis ball of the glenoid implant (e.g., centered, off-center, tilted, etc.), the cervical axis angle of the corresponding humeral implant, the glenoid implant tilt, the placement percentage of the glenoid implant, and the pin depth of the glenoid implant. User 118 can select one of the surgical recommendations 602. Figure 6 In the example, the black background is used to indicate that surgical recommendation 602A is the selected surgical recommendation.

[0057] In addition, 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 an overhead perspective (i.e., viewed from above). The top view 606 shows the outline 612 of a glenoid implant of the type indicated by the selected surgical recommendation at the selected surgical recommendation location. The front view 608 is an X-ray image of the patient's shoulder from a forward perspective (i.e., viewed from the front to the rear). The front view 608 shows the outline 614 of a glenoid implant of the type indicated by the surgical recommendation at the selected surgical recommendation location. The model 610 shows a 3D model of the patient's scapula with a virtual image of the glenoid implant.

[0058] The user interface 600 also includes controls 604A, 604B for switching between the display of surgical recommendations for anatomical shoulder replacement surgery and reverse shoulder replacement surgery.

[0059] Despite Figure 6 The example is not shown, but each surgical suggestion 602 may include data indicating the expected range of motion of the surgical suggestion 602. For example, each surgical suggestion 602 may indicate the expected extension angle, the expected flexion angle, the expected abduction angle, and the expected internal rotation angle. The ROM unit 208 may determine these expected ranges of motion, for example, in a manner described elsewhere in this disclosure.

[0060] Figure 7 This is a flowchart illustrating an example operation of a surgical planning system 116 according to one or more technologies of this disclosure. Figure 7 In the example, surgical planning system 116 (e.g., preference acquisition unit 202) Figure 2One or more surgeon preference parameters (700) can be obtained, specifying values ​​for one or more surgical parameters. Surgical parameters can indicate the range of positioning parameters for the glenoid implant to be attached to the patient's glenoid during surgery. For example, the surgical planning system 116 can be accessed via a user interface, such as user interface 400. Figure 4A ) or user interface 450 ( Figure 4B To obtain surgeon preference parameters.

[0061] In addition, Figure 7 In the example, surgical planning system 116 (e.g., parameter prediction unit 206) can determine one or more suggested surgical options (702) based on one or more anatomical parameters of the patient and surgeon preference parameters. Each surgical option corresponds to a different combination of glenoid implant positioning parameters and glenoid implant type. The following... Figure 8 A flowchart of example operation of the parameter prediction unit 206 is shown in more detail to determine one or more suggested surgical options for a glenoid implant. In some examples, as part of determining one or more suggested surgical options, the parameter prediction unit 206 may filter the suggested surgical options (e.g., using...). Figure 8 The operation determines the recommended surgical options to remove invalid recommended surgical options. For example, the parameter prediction unit 206 can filter out recommended surgical options including glenoid implants with anchors that pass through the boundary of the scapula relative to the glenoid.

[0062] In some examples, the surgical planning system 116 can acquire medical imaging data of the patient's glenoid cavity. For example, the surgical planning system 116 can obtain this data from memory (e.g., memory 106). Figure 1 Medical imaging data is acquired by a medical imaging machine (e.g., X-ray machine, CT scanner, etc.). The medical imaging data may include medical images and / or models of the patient's shoulder. The surgical planning system 116 (e.g., anatomical parameter unit 204) can determine one or more anatomical parameters of the patient based on the medical imaging data.

[0063] exist Figure 7 In the example, surgical planning system 116 (e.g., planning presentation unit 210) Figure 2 The surgical planning system 116 can output one or more suggested surgical options (704). For example, the surgical planning system 116 can output one or more suggested surgical options in the user interface 500. Figure 5 ) or user interface 600 ( Figure 6The surgical planning system 116 outputs one or more suggested surgical options to the user interface. In some examples, the surgical planning system 116 can output one or more suggested surgical options to be displayed in an MR visualization. In some examples, the surgical planning system 116 can output one or more suggested surgical options to be displayed on a conventional monitor or screen. In some examples, the surgical planning system 116 can output suggested surgical options via audio.

[0064] Figure 8 This is a flowchart illustrating example operation of a parameter prediction unit 206 according to one or more techniques of this disclosure, which is used to determine one or more recommended surgical options for a glenoid implant. Figure 8 In the example, parameter prediction unit 206 can filter glenoid implant types (800) based on surgeon preference parameters. In other words, parameter prediction unit 206 can filter out glenoid implant types based on surgeon preference parameters to determine a set of one or more remaining glenoid implant types. When filtering glenoid implant types, parameter prediction unit 206 can start with a set of glenoid implants that includes all available glenoid implant types. For example, glenoid implant types can include glenoid implants with keel anchors, glenoid implants with fixed anchors, and glenoid implants with fixed anchors (including one or more fin studs). Furthermore, in this example, if the surgeon preference parameters indicate that the surgeon does not want to use glenoid implants with keel anchors, parameter prediction unit 206 can filter out (e.g., remove) all glenoid implants with keel anchors from the list of available glenoid implants.

[0065] In addition, Figure 8In the example, parameter prediction unit 206 can determine the size of the glenoid implant based on the patient's anatomical parameters (802). For example, parameter prediction unit 206 can determine the glenoid region size of the patient's glenoid fossa (i.e., anatomical parameters). In this example, the glenoid region size of the glenoid fossa is a two-dimensional region contained within the boundaries of the glenoid fossa. Parameter prediction unit 206 can then compare the glenoid region size of the glenoid fossa to a set of one or more thresholds. The thresholds may correspond to the sizes of glenoid implants in a list of available glenoid implants. In some examples, parameter prediction unit 206 can determine the glenoid region size, the length of the glenoid long axis, and the length of the glenoid short axis. The glenoid long axis and glenoid short axis are defined by ellipses corresponding to the boundaries of the glenoid fossa. Parameter prediction unit 206 can determine the size of the glenoid implant based on the glenoid area size, the length of the glenoid long axis, and the length of the glenoid short axis. For example, parameter prediction unit 206 can look up the size of the glenoid implant in a table that maps the combination of the glenoid area size, the length of the glenoid long axis, and the length of the glenoid short axis to the size of the glenoid implant.

[0066] In some examples, the parameter prediction unit 206 may receive data indicating the size of the glenoid implant specified by the user, rather than automatically determining the size of the glenoid implant. For example, the parameter prediction unit 206 may receive user input indicating the size of the glenoid implant. In another example, the parameter prediction unit 206 may receive instructions from the user 118 regarding a set of rules that the parameter prediction unit 206 can use to determine the size of the glenoid implant. In this way, the user 118 can select a smaller implant size for a stronger placement of the glenoid implant. In another example, the user 118 may select a specific size for the glenoid implant because the user 118 may believe that the anatomical parameter unit 204 has determined an incorrect glenoid region size. In yet another example, the user 118 may select a specific size glenoid implant to avoid osteophytes.

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

[0068] The parameter prediction unit 206 can determine the input value (804) based on the surgical parameter values ​​in the current trial vector. The input value may include the value used by the parameter prediction unit 206 in the cost function to determine the cost value of the trial vector. The parameter prediction unit 206 may use one or more functions to compute the input value based on the surgical parameter values ​​in the trial vector and the patient's anatomical parameters. In some examples, these functions are provided to the parameter prediction unit 206 by the surgeon. In some examples, the functions are pre-configured. For example, the surgical parameter values ​​may include the glenoid implant tilt angle, and a rule may specify a function that converts the glenoid implant tilt angle into an input value such that glenoid implant tilt angles close to 0° have larger values ​​than angles far from 0°. For example, in this example, the function may be equal to the maximum glenoid implant tilt angle minus the absolute value of the glenoid implant tilt angle.

[0069] In another example, parameter prediction unit 206 may, given the patient's anatomical parameters, determine the enlargement volume when applying surgical parameters of a trial vector; determine the non-contact area between the implant and bone when applying surgical parameters of a trial vector, given the patient's anatomical parameters; determine the contact area between the implant and the strong portion of the bone when applying surgical parameters of a trial vector, given the patient's anatomical parameters; determine the contact area between the implant and the weak portion of the bone when applying surgical parameters of a trial vector, given the patient's anatomical parameters; determine the radius of the glenoid implant indicated by the surgical parameters of a trial vector, given the patient's anatomical parameters; and / or determine other input values ​​based on the surgical parameters.

[0070] In addition, Figure 8 In the example, parameter prediction unit 206 can determine the first preliminary cost value (806) of the current test vector based on the input values. Parameter prediction unit 206 can determine the first preliminary cost value of the test vector based on a linear combination of the input values, as shown in the following equation (1):

[0071]

[0072] In equation (1) above, C1 indicates the first initial cost value of the test vector, i is the exponent of the input value, m is the number of input values, and a i b is the scaling factor for the input value i. i is the input value i in the combination of input k, and offset is the offset value.

[0073] In one example where the parameter prediction unit 206 determines the first preliminary cost value of the test vector based on a linear combination of input values, the parameter prediction unit 206 can determine the first preliminary cost value of the test vector as follows:

[0074]

[0075] In equation (2) above, C1 represents the first initial cost value of the test vector, and a1 to a7 represent the weight values. Reamed Indicates the reaming volume when the surgical parameters of the experimental vector are applied. A NoSeating Indicates the non-contact area between the implant and bone when the surgical parameters of the test vector are applied. A StrongSeating Indicates the contact area between the implant and the robust portion of the bone when the surgical parameters of the test vector are applied. A WeakSeating Indicates the contact area between the implant and the weak point in the bone when the surgical parameters of the test vector are applied. R implant Indicates the radius of the glenoid implant as indicated by the surgical parameters of the test vector. V AnchoragePerforation This indicates whether the anchor (e.g., a nail) of the scapular implant crosses the boundary of the scapula relative to the glenoid fossa, or is too close to the boundary of the scapula. In some examples, to determine whether the anchor is too close to the boundary of the scapula, the parameter prediction unit 206 can compare the position of the anchor to a scaled-down model of the scapula and determine whether any part of the anchor crosses the boundary of the scaled-down model of the scapula relative to the glenoid fossa. α Version and α Inclination It is a fixed value. α Version and α Inclination It can be determined based on case analysis.

[0076] In equation (2), P indicates the penalty value applied if any surgical parameter (or input value) of the trial vector is inconsistent with the surgeon's preferred value. For example, the surgical parameters of the trial vector include a tilt parameter, which may range from -15° (backward tilt) to 15° (forward tilt). In this example, the surgeon's preference parameter may specify a maximum backward tilt of 10° (i.e., a tilt of -10°). Therefore, in this example, if the surgical parameters of the trial vector include a tilt parameter of -15°, the parameter prediction unit 206 may set P to be equal to the penalty value (e.g., 100). Otherwise, if the tilt parameter is outside the range specified by the surgeon's preference parameter, the parameter prediction unit 206 may set P to be equal to a non-penalty value (e.g., 0).

[0077] In equation (2), V Reamed A NoSeating A StrongSeating and A WeakSeating Based on the patient's anatomical parameters, a portion of the bone can be considered weak if its density is below a specified threshold. In some examples, a portion of the bone can be considered strong if its density is above a specified threshold.

[0078] In addition to determining a first preliminary cost value for a set of input values, parameter prediction unit 206 can also determine a second preliminary cost value (808) for the current trial vector. The second preliminary cost value can be used as part of a conformity verification process that ensures the values ​​of surgical parameters in the trial vector are within reasonable ranges. In some examples, parameter prediction unit 206 can determine the second preliminary cost value of the trial vector based on the difference between the surgical parameters of the trial vector and typical values ​​of the surgical parameters. For example, parameter prediction unit 206 can determine the second preliminary cost value for this set of input values ​​as follows:

[0079]

[0080] In equation (3) above, C2 represents the second preliminary cost value, k is the exponent of the surgical parameters, n represents the number of surgical parameters in the trial vector, and a k The weights of surgical parameter k, x k The mean represents the value of the surgical parameter k in the trial vector. k stdDev represents the average value of the surgical parameter k across a series of cases in which the surgery was previously performed. k It is the standard deviation of the surgical parameter k in a series of previously performed surgeries. Equation (3) above is calculated on a logarithmic scale. In equation (3) above, it is assumed that each surgical parameter in the trial vector follows a Naive Bayes Gaussian distribution. Therefore, for each surgical parameter V in the trial vector kOther parameters x1…x in a given trial vector n When the value is , equation (3) can be equivalent to the calculation according to the following chain rule:

[0081] P(V) = P(x1, ... x) n )

[0082] =P(x1, ... x) n |mean1,...,mean n stdDev1, ..., stdDev n )P(mean1 ， ..., mean n stdDev1,...stdDev n )

[0083] ∝P(x1|mean1,stdDev1)*P(mean1)*P(stdDev1)*...*P(x n |mean n stdDev n )*P(mean n )*P(stdDev n )

[0084] ∝P(x1|mean1,stdDev1)*...*P(x n |mean n stdDev n )

[0085] In other examples, it can be assumed that the surgical parameters in the trial vector follow different distributions. In some examples, different distributions can be assumed for different surgical parameters. For example, placement percentage is an example of a surgical parameter. Many surgeons prefer a 100% placement percentage, but 100% placement is often not achievable in some patients. As a result, the patient's average placement percentage (and the mean of the distribution of the placement percentage surgical parameter derived from it) may be less than 100% (e.g., 95%). Therefore, in this example, a different distribution than that derived directly from the placement percentage in the trial vector can be used. For example, a bias term can be used to modify the distribution derived from the placement percentage so that the mean of the distribution is equal to 100%.

[0086] In addition, Figure 8 In the example, parameter prediction unit 206 can determine the cost value (810) of the current test vector based on a first preliminary cost value and a second preliminary cost value. For example, parameter prediction unit 206 can determine the cost value of the test vector as:

[0087] C = (C1 + M) * C2 (4)

[0088] In equation (4) above, C represents the cost value of the test 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.

[0089] The parameter prediction unit 206 can determine whether the cost value of the trial vector is less than the cost value of the previous trial vector (812). If the cost value of the trial vector is not less than the cost value of the previous trial vector (the "No" branch of 812), the parameter prediction unit 206 can restore the trial vector to the previous trial vector (814). If the cost value of the current trial vector is less than the cost value of the previous trial vector (the "Yes" branch of 812), or after restoring the current trial vector to the previous trial vector, the parameter prediction unit 206 can determine whether a stopping condition (816) is met. In various examples, the stopping condition may be one or more of the following: a specific number of times step (816) has been reached, a specific number of times no lower cost value has been found after evaluating all glenoid implant types in the remaining set of glenoid implant types.

[0090] In response to determining that the stopping condition has not yet been met (the "No" branch of 816), parameter prediction unit 206 can generate a new trial vector (818) and repeat steps (804)-(816). Parameter prediction unit 206 can generate a new trial vector by updating one or more of the surgical parameter values ​​of the current (or recovered) trial vector. For example, parameter prediction unit 206 can generate a new trial vector by incrementing or decrementing surgical parameter values, such as inclination angle, version angle, etc. In some examples, parameter prediction unit 206 can increment or decrement different surgical parameters by different amounts when generating a new trial vector. In another example, parameter prediction unit 206 can generate a new trial vector by changing one glenoid implant type in a filtered set of glenoid implant types to another glenoid implant type.

[0091] In this way, the parameter prediction unit 206 can determine whether the current test vector represents an improvement over the previous test vector based on a comparison of the cost value of the current test vector in the set of test vectors with the cost values ​​of the previous test vectors in the set of test vectors. Furthermore, based on a current test vector that does not represent an improvement over the previous test vector (e.g., the cost score of the current test vector is lower than the cost score of the previous test vector), the parameter prediction unit 206 can revert the current test vector to the previous test vector and update one or more surgical parameters of the current test vector to determine a new current test vector in the set of test vectors. Alternatively, based on a current test vector that represents an improvement over the previous test vector, the parameter prediction unit 206 does not revert the current test vector to the previous test vector. In either case, the parameter prediction unit 206 can generate a new test vector based on the current test vector.

[0092] After generating a new trial vector, parameter prediction unit 206 can repeat steps (804) to (816), where the new trial vector is used as the current trial vector. In this way, parameter prediction unit 206 can act as an amoeba optimizer, iterating through combinations of implant and other surgical parameters. Therefore, parameter prediction unit 206 can learn potentially optimal surgical options for a specific patient based on surgeon preference parameters.

[0093] In this way, the parameter prediction unit 206 can generate a set of one or more trial vectors, each of which includes one or more surgical parameters. For each trial vector in the set, the parameter prediction unit 206 can determine the input value based on the surgical and anatomical parameters of the trial vector, and determine the cost value of the trial vector based on the input value.

[0094] On the other hand, if the stopping condition is met (the "yes" branch of 816), the parameter prediction unit 206 can determine the optimal test vector (820) from the set of test vectors. The optimal test vector is the test vector that has the lowest cost value when the stopping condition is met.

[0095] Figure 8 Each evaluated trial vector can correspond to a different recommended surgical option. In some examples, the parameter prediction unit 206 can sort the trial vectors based on their cost values ​​and set a specific number of trial vectors with the lowest cost values ​​as recommended surgical options. In some examples, the parameter prediction unit 206 can determine whether to include a trial vector as one of the recommended surgical options based on its cost value. For example, the parameter prediction unit 206 can determine whether to include a trial vector as one of the recommended surgical options based on determining that the cost value of the trial vector exceeds a threshold.

[0096] Some of the techniques disclosed herein are described in relation to shoulder replacement surgery, particularly for the human scapula. Examples of shoulder replacement surgery include, but are not limited to, reverse arthroplasty, augmented reverse arthroplasty, standard total shoulder arthroplasty, augmented total shoulder arthroplasty, and hemiarthroplasty. However, these techniques are not limited thereto, and the visualization system can be used to provide virtual guidance information, including virtual guidance in any type of surgery. Other example procedures in which the surgical assistance system 100 can be used to provide virtual guidance include, but are not limited to: other types of orthopedic surgery; any type of surgery suffixed with “plastic surgery,” “ostomy,” “resection,” “dissection,” or “puncture”; orthopedic surgeries for other joints, such as the elbow, wrist, fingers, hip, knee, ankle, or toe, or any other orthopedic surgery requiring precise guidance. For example, the surgical assistance system 100 can be used to provide computer-aided planning for ankle replacement surgery.

[0097] While these techniques have been disclosed with respect to a limited number of examples, those skilled in the art who benefit from this disclosure will recognize many modifications and variations therein. For example, any reasonable combination of the described examples is contemplated. The appended claims are intended to cover modifications and variations that fall within the true spirit and scope of this disclosure. Furthermore, the techniques of this disclosure have generally been described in relation to human anatomy. However, the techniques of this disclosure can also be applied to animal dissection in veterinary settings.

[0098] It should be recognized that, based on the examples, certain actions or events of any technique described herein may be performed in a different order, and may be added, combined, or omitted entirely (e.g., not all described actions or events are necessary for the practice of the technique). Furthermore, in some examples, actions or events may be performed, for example, through multithreaded processing, interrupt handling, or simultaneous execution by multiple processors, rather than sequentially.

[0099] In one or more examples, the described functionality can be implemented in hardware, software, firmware, or any combination thereof. If implemented in software, these functions can be stored or transmitted as one or more instructions or code on or through a computer-readable medium and executed by a hardware-based processing unit. A computer-readable medium can include a computer-readable storage medium, which corresponds to a tangible medium such as a data storage medium or a communication medium that includes, for example, any medium that facilitates the transfer of a computer program from one place to another according to a communication protocol. In this way, a computer-readable medium can generally correspond to (1) a non-transitory tangible computer-readable storage medium, or (2) a communication medium such as a signal or carrier wave. A data storage medium can be any available medium accessible by one or more computers or one or more processors to retrieve instructions, code, and / or data structures to implement the techniques described in this disclosure. Computer program products can include computer-readable media.

[0100] By way of example and not limitation, such computer-readable storage media may include RAM, ROM, EEPROM, CD-ROM or other optical disc storage devices, magnetic disk storage devices or other magnetic storage devices, flash memory, or any other medium that can be used to store desired program code in the form of instructions or data structures and that can be accessed by a computer. Furthermore, any connection is properly referred to as a computer-readable medium. For example, if 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 technology (e.g., infrared, radio, and microwave), then coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technology (e.g., infrared, radio, and microwave) is included in the definition of medium. However, it should be understood that computer-readable storage media and data storage media do not include connections, carrier waves, signals, or other temporary media, but rather refer to non-temporary tangible storage media. Discs and platters used herein include optical discs (CDs), laser discs, optical discs, digital versatile discs (DVDs), and Blu-ray discs, wherein discs typically reproduce data magnetically, while platters reproduce data optically using lasers. Combinations of the above should also be included within the scope of computer-readable media.

[0101] The operations described in this disclosure can be performed by one or more processors, which can be 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 or discrete logic circuits. A fixed-function circuit is a circuit that provides a specific function and is pre-defined for executable operations. A programmable circuit is a circuit that can be programmed to perform various tasks and provide flexible functionality in executable operations. For example, a programmable circuit can execute instructions specified by software or firmware, causing the programmable circuit to operate in a manner defined by the instructions in the software or firmware. A fixed-function circuit can execute software instructions (e.g., receiving or outputting parameters), but the type of operation performed by a fixed-function circuit is generally immutable. Therefore, the terms "processor" and "processing circuit" as used herein can refer to any of the foregoing structures or any other structure suitable for implementing the techniques described herein.

Claims

1. A method for computer-assisted surgical planning, comprising: One or more surgeon preference parameters are obtained by a calculation system to specify the 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 patient's glenoid socket during surgery; The computational system determines one or more suggested surgical options based on one or more anatomical parameters of the patient and one or more surgeon preference parameters, each of the one or more suggested surgical options corresponding to a different combination of one or more positioning parameters for the glenoid implant and the type of the glenoid implant, wherein determining one or more suggested surgical options includes: Generate 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; and for each trial vector in the set of trial vectors: The input value is determined based on the surgical parameters of the test vector and one or more of the anatomical parameters; Determine the cost value for the test vector based on the input value; and The determination of whether to include the trial vector as one of one or more suggested surgical options is based on the cost value used for the trial vector. Determining the cost value for the test vector includes: A first preliminary cost value for the test vector is determined based on a linear combination of the input values. A second preliminary cost value for the test vector is determined based on the difference between the surgical parameters of the test vector and typical values ​​of the surgical parameters; and The cost value for the test vector is determined based on the first preliminary cost value for the test vector and the second preliminary cost value for the test vector; and The computing system outputs one or more suggested surgical options.

2. The method according to claim 1, wherein, Generating the set of test vectors includes: Based on one or more of the surgeon preference parameters, glenoid implant types are filtered out to determine a set of one or more remaining glenoid implant types; and The test vector is generated such that it includes only one set of remaining glenoid implant types.

3. The method according to claim 1, wherein, Generating the set of test vectors includes: The size of the glenoid implant is determined based on one or more anatomical parameters of the patient; and The test vector is generated such that it includes only glenoid implants of a defined size.

4. The method according to claim 1, wherein, Generating the set of test vectors includes generating new test vectors from the set of test vectors by updating one or more surgical parameters of the current test vector.

5. The method according to claim 1, wherein, Generating the set of test vectors includes: Based on a comparison between the cost value of the current test vector in the set of test vectors and the cost value of the previous test vectors in the set of test vectors, it is determined whether the current test vector represents an improvement on the previous test vector; Based on the current test vector, which does not represent an improvement to the previous test vector, the current test vector is restored to the previous test vector; and Update one or more surgical parameters of the current trial vector to determine a new current trial vector from the set of trial vectors.

6. The method according to claim 1, wherein, Determining whether to include the trial vector as one of one or more suggested surgical options includes determining whether the cost value for the trial vector exceeds a threshold.

7. The method according to claim 1, wherein, Determining one or more of the suggested surgical options includes: Filter glenoid implant types based on one or more of the surgeon preference parameters to determine a set of one or more remaining glenoid implant types; The size of the glenoid implant is determined based on one or more anatomical parameters of the patient. Generate a current trial vector that includes one or more surgical parameters, wherein the type of glenoid implant in the current trial vector is limited to the remaining glenoid implant types; The input value is determined based on the surgical parameters of the current test vector and one or more of the anatomical parameters; A first preliminary cost value for the current test vector is determined based on a linear combination of the input values. A second preliminary cost value for the current test vector is determined based on the difference between the surgical parameters of the current test vector and the typical values ​​of the surgical parameters; and The cost value for the current test vector is determined based on the first preliminary cost value for the current test vector and the second preliminary cost value for the current test vector; Whether the current test vector represents an improvement over the previous test vector is determined based on a comparison between the cost value used for the current test vector and the cost value of the previous test vector; Based on the current test vector, which does not represent an improvement to the previous test vector, the current test vector is restored to the previous test vector; and Update one or more surgical parameters of the current trial vector to determine a new current trial vector.

8. A computing system, comprising: The memory is configured to store one or more surgeon preference parameters that specify values ​​for one or more surgical parameters, wherein the surgical parameters include one or more positioning parameters for a glenoid implant to be attached to the patient's glenoid cavity during surgery; One or more processors implemented in a circuit, said one or more processors being configured to: One or more recommended surgical options are determined based on one or more anatomical parameters of the patient and one or more surgeon preference parameters, each of the one or more recommended surgical options corresponding to a different combination of one or more positioning parameters for the glenoid implant and the type of the glenoid implant. As part of determining one or more of the proposed surgical options, the one or more processors are configured to: Generate 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; and For each of the set of test vectors: The input value is determined based on the surgical parameters of the test vector and one or more of the anatomical parameters; Determine the cost value for the test vector based on the input value; and The determination of whether to include the trial vector as one of one or more suggested surgical options is based on the cost value used for the trial vector. Wherein, as part of determining the cost value for the test vector, the one or more processors are configured to: A first preliminary cost value for the test vector is determined based on a linear combination of the input values. A second preliminary cost value for the test vector is determined based on the difference between the surgical parameters of the test vector and typical values ​​of the surgical parameters; and The cost value for the test vector is determined based on the first preliminary cost value for the test vector and the second preliminary cost value for the test vector; and Output one or more suggested surgical options for display.

9. The computing system according to claim 8, wherein, The one or more processors are configured such that, as part of generating the set of test vectors, the one or more processors: Based on one or more of the surgeon preference parameters, glenoid implant types are filtered out to determine a set of one or more remaining glenoid implant types; and The test vector is generated such that it includes only one set of remaining glenoid implant types.

10. The computing system according to claim 8, wherein, The one or more processors are configured such that, as part of generating the set of test vectors, the one or more processors: The size of the glenoid implant is determined based on one or more anatomical parameters of the patient; and The test vector is generated such that it includes only glenoid implants of a defined size.

11. The computing system according to claim 8, wherein, Generating the set of test vectors includes generating the current test vector by updating one or more surgical parameters of the previous test vectors in the set of test vectors.

12. The computing system according to claim 8, wherein, The one or more processors are configured such that, as part of generating the set of test vectors, the one or more processors: Based on a comparison between the cost value of the current test vector in the set of test vectors and the cost value of the previous test vectors in the set of test vectors, it is determined whether the current test vector represents an improvement on the previous test vector; Based on the current test vector, which does not represent an improvement on the previous test vector, the current test vector is restored to the previous test vector; as well as Update one or more surgical parameters of the current trial vector to determine a new current trial vector from the set of trial vectors.

13. The computing system according to claim 8, wherein, The one or more processors are configured such that, as part of determining whether to include the trial vector as one of the one or more suggested surgical options, the one or more processors determine whether the cost value for the trial vector exceeds a threshold.

14. The computing system according to claim 8, wherein, The one or more processors are configured such that, as part of determining one or more suggested surgical options, the one or more processors: Filter glenoid implant types based on one or more of the surgeon preference parameters to determine a set of one or more remaining glenoid implant types; The size of the glenoid implant is determined based on one or more anatomical parameters of the patient. Generate a current trial vector that includes one or more surgical parameters, wherein the type of glenoid implant in the current trial vector is limited to the remaining glenoid implant types; The input value is determined based on the surgical parameters of the current test vector and one or more of the anatomical parameters; A first preliminary cost value for the current test vector is determined based on a linear combination of the input values. A second preliminary cost value for the current test vector is determined based on the difference between the surgical parameters of the current test vector and the typical values ​​of the surgical parameters; and The cost value for the current test vector is determined based on the first preliminary cost value for the current test vector and the second preliminary cost value for the current test vector; Whether the current test vector represents an improvement over the previous test vector is determined based on a comparison between the cost value used for the current test vector and the cost value of the previous test vector; Based on the current test vector, which does not represent an improvement to the previous test vector, the current test vector is restored to the previous test vector; and Update one or more surgical parameters of the current trial vector to determine a new current trial vector.

15. A computer-readable storage medium having instructions stored thereon, the instructions, when executed, causing one or more processors of a computing system to: One or more surgeon preference parameters that specify one or more surgical parameters, wherein, The surgical parameters include one or more positioning parameters for the glenoid implant to be attached to the patient's glenoid socket during surgery; One or more recommended surgical options are determined based on one or more anatomical parameters of the patient and one or more surgeon preference parameters, each of the one or more recommended surgical options corresponding to a different combination of one or more positioning parameters for the glenoid implant and the type of the glenoid implant. In order to determine one or more suggested surgical options, the instructions cause the one or more processors to: Generate 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; and for each trial vector in the set of trial vectors: The input value is determined based on the surgical parameters of the test vector and one or more of the anatomical parameters; Determine the cost value for the test vector based on the input value; and The determination of whether to include the trial vector as one of one or more suggested surgical options is based on the cost value used for the trial vector. Determining the cost value for the test vector includes: A first preliminary cost value for the test vector is determined based on a linear combination of the input values. A second preliminary cost value for the test vector is determined based on the difference between the surgical parameters of the test vector and typical values ​​of the surgical parameters; and The cost value for the test vector is determined based on the first preliminary cost value for the test vector and the second preliminary cost value for the test vector; and Output one or more suggested surgical options.

Images