|
View Edit Delete |
PER-17 |
As used herein, “edge” refers to a structure, boundary, or line where an object, surface, or area begins or ends. An edge can also refer to a boundary or perimeter between two structures, objects, or surfaces. An edge can also refer to a narrow part adjacent to a border. (search "edge" on Merriam-Webster.com. Merriam-Webster, 2021. Web. 03 Aug. 2021. Modified.) In certain embodiments, an edge can be a one dimensional or a two dimensional structure that joins two adjacent structures or surfaces. Furthermore, an edge may be at a perimeter of an object or within a perimeter or boundary of an object. |
149 |
Added by DJM Jan 2024 |
1/6/24, 10:05 PM |
|
View Edit Delete |
PER-17 |
"Bone fragment" refers to a part of a bone that is normally part of another bone of a patient. A bone fragment may be separate from another bone of a patient due to a deformity or trauma. In one aspect, the bone the bone fragment is normally connected or joined with is referred to as a parent bone. |
150 |
Added by DJM Jan 2024 |
1/6/24, 10:05 PM |
|
View Edit Delete |
PER-17 |
"Joint" or "Articulation" refers to the connection made between bones in a human or animal body which link the skeletal system to form a functional whole. Joints may be biomechanically classified as a simple joint, a compound joint, or a complex joint. Joints may be classified anatomically into groups such as joints of hand, elbow joints, wrist joints, axillary joints, sternoclavicular joints, vertebral articulations, temporomandibular joints, sacroiliac joints, hip joints, knee joints, ankle joints, articulations of foot, and the like. (Search "joint" on Wikipedia.com Dec. 19, 2021. CC-BY-SA 3.0 Modified. Accessed Jan 20, 2022.) |
151 |
Added by DJM Jan 2024 |
1/6/24, 10:05 PM |
|
View Edit Delete |
PER-17 |
"Tarso-metatarsal joint" or "TMT joint" refers to a joint of a patient between a metatarsal bone and one or more cuneiform/tarsal/cuboid bones. The TMT joint may also be referred to as a "Lis Franc" or "Lisfranc" joint after a French surgeon Lisfranc. |
152 |
Added by DJM Jan 2024 |
1/6/24, 10:05 PM |
|
View Edit Delete |
PER-17 |
"Cut surface" refers to a surface of an object that is created or formed by the removal of one or more parts of the object that includes the original surface. Cut surfaces can be created using a variety of methods, tools, or apparatuses and may be formed using a variety of removal actions, including, but not limited to, fenestrating, drilling, abrading, cutting, sawing, chiseling, digging, scrapping, and the like. Tools and/or methods used for forming a cut surface can include manual, mechanical, motorized, hydraulic, automated, robotic, and the like. In certain embodiments, the cut surface(s) are planar. |
153 |
Added by DJM Jan 2024 |
1/6/24, 10:05 PM |
|
View Edit Delete |
PER-17 |
"Orientation" refers to a direction, angle, position, condition, state, or configuration of a first object, component, part, apparatus, system, or assembly relative to another object, component, part, apparatus, system, assembly, reference point, reference axis, or reference plane. |
154 |
Added by DJM Jan 2024 |
1/6/24, 10:05 PM |
|
View Edit Delete |
PER-17 |
"Longitudinal axis" or “Long axis” refers to an axis of a structure, device, object, apparatus, or part thereof that extends from one end of a longest dimension to an opposite end. Typically, a longitudinal axis passes through a center of the structure, device, object, apparatus, or part thereof along the longitudinal axis. The center point used for the longitudinal axis may be a geometric center point and/or a mass center point. |
155 |
Added by DJM Jan 2024 |
1/6/24, 10:05 PM |
|
View Edit Delete |
PER-17 |
As used herein, a “drive”, "drive feature", or "drive recess" refers to an apparatus, instrument, structure, member, device, component, system, or assembly structured, organized, configured, designed, arranged, or engineered to receive a torque and transfer that torque to a structure connected or coupled to the drive. At a minimum, a drive is a set of shaped cavities and/or protrusions on a structure that allows torque to be applied to the structure. Often, a drive includes a mating tool, known as a driver. For example, cavities and/or protrusions on a head of a screw are one kind of drive and an example of a corresponding mating tool is a screwdriver that is used to turn the screw, the drive. Examples of a drive include but are not limited to screw drives such as slotted drives, cruciform drives, square drives, multiple square drives, internal polygon, internal hex drives, penta lobular sockets, hex lobular sockets, combination drives, external drives, tamper-resistant drives, and the like. (Search 'list of screw drives' on Wikipedia.com March 12, 2021. Modified. Accessed March 19, 2021.) |
156 |
Added by DJM Jan 2024 |
1/6/24, 10:05 PM |
|
View Edit Delete |
PER-17 |
"Metatarsal base resection guide" refers to a resection guide designed, engineered, fabricated, or intended for use with, one, in, or about a base part, section, surface, portion, or aspect of a metatarsal for one or more steps of a medical procedure. The metatarsal base resection guide may be used to form an osteotomy, to resect a wedge for a closing wedge procedure, resect a bone wedge that preserves a cortical layer of bone opposite the resected bone wedge, form an osteotomy that uniplanar wedge, a biplanar wedge, or a triplane wedge. Various embodiments of a metatarsal base resection guide may be used on a medial surface, a dorsal surface, a lateral surface, or a plantar surface of a single metatarsal. Alternatively, or in addition, various embodiments of a metatarsal base resection guide can be used on two or more metatarsals. |
64 |
Added by DJM Jan 2024 |
1/6/24, 10:05 PM |
|
View Edit Delete |
PER-17 |
As used herein, a “guard” refers to an apparatus, instrument, structure, member, device, component, system, or assembly structured, organized, configured, designed, arranged, or engineered to prevent, limit, impede, stop, or restrict motion, action, or movement and/or operation of the another object, member, structure, component, part, apparatus, system, or assembly beyond a certain parameter such as a boundary. Said another way, a "guard" refers to an apparatus, instrument, structure, member, device, component, system, or assembly structured, organized, configured, designed, arranged, or engineered to retain, maintain, hold, keep, or restrict motion, action, or movement and/or operation of the another object, member, structure, component, part, apparatus, system, or assembly within or at one or more parameters such as a boundary. |
65 |
Added by DJM Jan 2024 |
1/6/24, 10:05 PM |
|
View Edit Delete |
PER-17 |
As used herein, "artificial intelligence" refers to intelligence demonstrated by machines, unlike the natural intelligence displayed by humans and animals, which involves consciousness and emotionality. The distinction between artificial intelligence and natural intelligence categories is often revealed by the acronym chosen. 'Strong' AI is usually labelled as artificial general intelligence (AGI) while attempts to emulate 'natural' intelligence have been called artificial biological intelligence (ABI). Leading AI textbooks define the field as the study of "intelligent agents": any device that perceives its environment and takes actions that maximize its chance of achieving its goals. The term "artificial intelligence" can also be used to describe machines that mimic "cognitive" functions that humans associate with the human mind, such as "learning" and "problem solving". (Search "artificial intelligence" on Wikipedia.com June 25, 2021. CC-BY-SA 3.0 Modified. Accessed June 25, 2021.) |
66 |
Added by DJM Jan 2024 |
1/6/24, 10:05 PM |
|
View Edit Delete |
PER-17 |
Artificial Neural Networks |
67 |
Added by DJM Jan 2024 |
1/6/24, 10:05 PM |
|
View Edit Delete |
PER-17 |
Artificial Intelligence can utilize, for example, neural networks. Artificial neural networks (ANNs) can learn tasks based on examples, e.g. without task specific programming. ANNs can be based on a group of connected units or nodes, i.e. artificial neurons. Each connection between artificial neurons can generate a signal to be transmitted to another artificial neuron. One or more artificial neurons can receive the signal and process it and, for example, use it to initiate a task. The signal at a connection between artificial neurons can be a number, and the outputs can be calculated by various functions or algorithms, e.g. non-linear functions. Artificial neurons can have a weight assigned to them, which can amplify or de-emphasize their signal. Artificial neurons can be organized in layers, with different layers performing different kinds of transformations. Artificial neural networks can utilize various techniques, processes and/or algorithms, e.g. backpropagation, parallel distributed processing, max-pooling, Hebbian learning, long term potentiation, support vector machines, and linear classifiers. ANNs can include recurrent neural networks and deep feedforward neural networks. ANNs can perform functions such as, for example, pattern recognition and machine learning. Components of ANNs can include neurons, connections and weights, propagation functions, and learning rules. Neurons can include an activation component, a threshold component, an activation function, and an output function. ANNs can define mathematical and other functions. ANNs can use predefined functions, e.g. hyperbolic tangent function, sigmoid function, softmax function or rectifier function. |
68 |
Added by DJM Jan 2024 |
1/6/24, 10:05 PM |
|
View Edit Delete |
PER-17 |
ANNs can be used for learning. Learning can comprise using a number of observations to find a function which solves a predetermined or desired task in an optimal sense, e.g. an optimal outcome. Learning can be supervised learning, unsupervised learning and reinforcement learning. Supervised learning can use one or more sets of example pairs and the goal can be, for example, to find a function in an allowed class of functions that matches the examples. Pattern recognition, classification, and regression can be part of supervised learning. Supervised learning can use informational fuzzy networks, random forests, nearest neighbor algorithms, logistic model tree, and other algorithms. Supervised learning can use statistical classification, including, for example, decision trees, Bayesian networks, and/or linear classifiers. |
69 |
Added by DJM Jan 2024 |
1/6/24, 10:05 PM |
|
View Edit Delete |
PER-17 |
In unsupervised learning, a set of data can be provided for example along with a cost function to be minimized, which can be a function of the data and the network output. The cost function can be dependent on the task and the properties of the parameters and observed variables or data. Unsupervised learning can be applied, for example, to pattern recognition, classification, and regression, general estimation problems, clustering, the estimation of statistical distributions, compression and filtering. Unsupervised learning can use one or more ANNs, expectation-maximization algorithms, data clustering, and the like. Association rule learning can use a priori algorithms, eclat algorithms, FP-growth algorithms, hierarchical clustering (e.g., single-linkage clustering and conceptual clustering), partitional clustering (e.g., K-means algorithm, fuzzy clustering), reinforcement learning (e.g., Monte Carlo method, Q-learning, temporal difference learning, and combinations thereof. |
70 |
Added by DJM Jan 2024 |
1/6/24, 10:05 PM |
|
View Edit Delete |
PER-17 |
In reinforcement learning, data can be generated by an agent's interactions with one or more objects, e.g. a surgeon interacting with a patient. The agent, e.g. the surgeon, can perform an action, and the environment, e.g. a target tissue or a surgical site, can generate one or more observations and, for example, a cost according to some dynamics or parameters, e.g. a tissue removal or an infection risk. The objective can be to discover a treatment, treatment algorithm, treatment modification that can reduce or minimize a measure of the cost, e.g. an infection risk, a patient reported outcome measurement, a functional result. The parameters and dynamics of the environment, e.g. a surgical site, can be unknown, but can be estimated. The environment, e.g. a target tissue or a surgical site, can be modeled as a Markov decision process and actions, with possible probability distributions, e.g. a cost distribution, an observation distribution, and one or more transitions, and a policy or algorithm or solution can be defined as a conditional distribution over actions given one or more observations. Dynamic programming can be coupled with ANNs and applied to multi-dimensional nonlinear problems. |
71 |
Added by DJM Jan 2024 |
1/6/24, 10:05 PM |
|
View Edit Delete |
PER-17 |
Learning can utilize one or more cost functions, e.g. the cost being an excellent or a poor clinical outcome. The cost function can yield information of how far a particular solution, e.g. a clinical treatment, treatment sequence or treatment algorithm or surgical technique, is from an optimal outcome, e.g. an excellent score in a patient reported outcome measure. ANNs can find the solution, e.g. a clinical treatment, treatment sequence or treatment algorithm or surgical technique, that yields the lowest cost, e.g. distance or amount away from an optimal outcome or excellent score in a patient reported outcome. The cost can be a function of the observations. The cost can be described as a statistic. A cost can be the mean squared error, which can try to minimize the average squared error between the network's output and one or more target values over example pair(s). A cost function can be selected or predetermined for a particular problem set, e.g. a clinical problem set or clinical observation data, e.g. pre-operative, intra-operative or post-operative data. AI can find and develop one or more optimal cost functions for a set of observational data and AI can refine the cost function as the size of the observational data set increases. (See US Patent 11,278,413 Para. 58-63). |
72 |
Added by DJM Jan 2024 |
1/6/24, 10:05 PM |
|
View Edit Delete |
PER-17 |
Machine Learning |
73 |
Added by DJM Jan 2024 |
1/6/24, 10:05 PM |
|
View Edit Delete |
PER-17 |
Machine learning can comprise supervised learning, semi-supervised learning, active learning, reinforcement learning or unsupervised learning. With supervised learning, the computer can receive example inputs and desired outputs, which can be provided from a database or using a learning tool; the objective is to learn one or more rules that map the inputs to the outputs. Semi-supervised learning can be different in that the computer can be given an incomplete training example input, optionally with some desired outputs missing. With active learning, the computer can only obtain training inputs for a limited set of examples, and the computer can optimize the choice of inputs to acquire labels for. With reinforcement learning, training data, e.g. inputs and desired outputs, can be given only as feedback to the program's actions in a dynamic environment, such as guiding a surgery. With unsupervised learning, no training input and/or output data are provided, leaving the computer and computer processor on its own to find structure in the inputs. |
74 |
Added by DJM Jan 2024 |
1/6/24, 10:05 PM |
|
View Edit Delete |
PER-17 |
Machine learning can use processes such as, for example, classification, regression, clustering, density estimation, dimensionality reduction, and topic modeling. With classification, inputs can be divided into two or more classes, and, for example, the learning system can produce a model that assigns unseen inputs to one or more of these classes. Data can be classified, for example, into “excellent”, “good”, “acceptable” or “poor” outcome, e.g. clinical outcome. Numeric values or ranges of numeric values can be assigned to different classes, for example numeric values or ranges of numeric values from a patient reported outcome measurement, from a clinical reporting system, and/or from one or more electronic measurements. With regression, outputs can be continuous rather than discrete. Regression can be used, for example, when patient outcomes are continuous. With clustering, inputs can be divided into groups. The groups cannot be known beforehand; thus, with clustering learning can be unsupervised. With density estimation, the distribution of inputs in a given space or sample can be determined. With dimensionality reduction, inputs can be simplified by mapping them into a lower-dimensional space. With topic modeling, a machine learning system can be given a list of human language documents and can be tasked to find out which documents cover similar topics. |
75 |
Added by DJM Jan 2024 |
1/6/24, 10:05 PM |