|
View Edit Delete |
PER-17 |
1. Discriminative models are trained to learn the boundaries between classes. They model the conditional probability of a target variable Y (class), given an observation x: P(Y|X=x) (“probability of Y given X=x”). Discriminative models describe the probability for classifying a given example x into a classy E Y. Discriminative models include, for example, logistic regression, conditional random fields, support vector machines, neural networks, random forests, or perceptrons. |
96 |
Added by DJM Jan 2024 |
1/6/24, 10:05 PM |
|
View Edit Delete |
PER-17 |
Generative models model the distribution of individual classes. They can generate data and provide a statistical model of the joint probability distribution on X×Y, P(X,Y)=P(X|Y)*P(Y), for an observable variable X and a target variable Y. Generative models include, for example, naïve Bayes models and Bayes networks, hidden Markov models, Boltzmann machines, variational autoencoders or generative adversarial networks (GAN). |
97 |
Added by DJM Jan 2024 |
1/6/24, 10:05 PM |
|
View Edit Delete |
PER-17 |
In some embodiments, the computer system can use a trained artificial neural network (ANN) to determine the treatment plan. The ANN can implement a discriminative model. A discriminative model can be trained to classify the input data, i.e. the preoperative and/or intraoperative data and/or postoperative data, into different classes, wherein each class can represent a different treatment plan. |
98 |
Added by DJM Jan 2024 |
1/6/24, 10:05 PM |
|
View Edit Delete |
PER-17 |
In some embodiments, the ANN can implement a generative model. Instead of assigning preoperative and/or intraoperative input data and/or postoperative data to an existing class, a generative model is trained to generate the treatment plan steps based on the input data. |
99 |
Added by DJM Jan 2024 |
1/6/24, 10:05 PM |
|
View Edit Delete |
PER-17 |
In some embodiments, a generative and a discriminative network model can be combined into a generative adversarial network (GAN) to generate a treatment plan. Using a training data set of existing recorded treatment plans for a number of preoperative and/or intraoperative input data and/or postoperative data sets, in this situation, the generative network can be trained to generate a preferred treatment plan from the preoperative and/or intraoperative input data. The discriminative network can be trained to evaluate the generated treatment plan and to distinguish the generated treatment plan from the actual treatment plan of the training case. Thus, the discriminative network can force the generative network to improve its results. (See US Patent 11,278,413 Para. 80-91). |
100 |
Added by DJM Jan 2024 |
1/6/24, 10:05 PM |
|
View Edit Delete |
PER-17 |
"Instruction" refers to a direction or order. (Search "instruction" on wordhippo.com. WordHippo, 2023. Web. Accessed 2 June 2023.) In certain embodiments, an instruction refers to one or more commands in a set of commands that direct a processor of a computing device to perform logic operations, input operations, output operations, or the like. Such instructions may exist in machine-readable and/or human readable formats. Examples of code include binary code, machine code, scripts, compiled code, virtual machine code, and the like. In certain embodiments, one or more instructions may be issued to a processor in response to a user action in relation to an item on a user interface. |
101 |
Added by DJM Jan 2024 |
1/6/24, 10:05 PM |
|
View Edit Delete |
PER-17 |
"Instrument" refers to any apparatus, device, or object that can be used by a user. An instrument may be used for a specific or a generic purpose. An instrument may also be referred to as instrumentation. Instrumentation may refer to a single instrument and/or a plurality of instruments. An instrument may be specifically designed, constructed or fabricated for use by a specific user and/or for a single use. A patient specific instrument is one example of an instrument. |
102 |
Added by DJM Jan 2024 |
1/6/24, 10:05 PM |
|
View Edit Delete |
PER-17 |
"Step" refers to a measure or action, especially one of a series taken for a given purpose or goal. (Search "step" on wordhippo.com. WordHippo, 2023. Web. Accessed 2 June 2023.) |
103 |
Added by DJM Jan 2024 |
1/6/24, 10:05 PM |
|
View Edit Delete |
PER-17 |
As used herein, "segmentation" or "image segmentation" refers to the process of partitioning an image into different meaningful segments. These segments may correspond to different tissue classes, organs, pathologies, bones, or other biologically relevant structures. Medical image segmentation accommodates imaging ambiguities such as by low contrast, noise, and other imaging ambiguities. |
104 |
Added by DJM Jan 2024 |
1/6/24, 10:05 PM |
|
View Edit Delete |
PER-17 |
Certain computer vision techniques can be used or adapted for image segmentation. For example, the techniques and or algorithms for segmentation may include, but are not limited to: Atlas-Based Segmentation: For many applications, a clinical expert can manually label several images; segmenting unseen images is a matter of extrapolating from these manually labeled training images. Methods of this style are typically referred to as atlas-based segmentation methods. Parametric atlas methods typically combine these training images into a single atlas image, while nonparametric atlas methods typically use all of the training images separately. Atlas-based methods usually require the use of image registration in order to align the atlas image or images to a new, unseen image. |
105 |
Added by DJM Jan 2024 |
1/6/24, 10:05 PM |
|
View Edit Delete |
PER-17 |
Image registration is a process of correctly aligning images; Shape-Based Segmentation: Many methods parametrize a template shape for a given structure, often relying on control points along the boundary. The entire shape is then deformed to match a new image. Two of the most common shape-based techniques are Active Shape Models and Active Appearance Models; Image-Based Segmentation: Some methods initiate a template and refine its shape according to the image data while minimizing integral error measures, like the Active contour model and its variations; Interactive Segmentation: Interactive methods are useful when clinicians can provide some information, such as a seed region or rough outline of the region to segment. An algorithm can then iteratively refine such a segmentation, with or without guidance from the clinician. Manual segmentation, using tools such as a paint brush to explicitly define the tissue class of each pixel, remains the gold standard for many imaging applications. Recently, principles from feedback control theory have been incorporated into segmentation, which give the user much greater flexibility and allow for the automatic correction of errors; Subjective surface Segmentation: This method is based on the idea of evolution of segmentation function which is governed by an advection-diffusion model. To segment an object, a segmentation seed is needed (that is the starting point that determines the approximate position of the object in the image). Consequently, an initial segmentation function is constructed. With the subjective surface method, the position of the seed is the main factor determining the form of this segmentation function; and Hybrid segmentation which is based on combination of methods. (Search "medical image computing" on Wikipedia.com June 24, 2021. CC-BY-SA 3.0 Modified. Accessed June 24, 2021.) |
106 |
Added by DJM Jan 2024 |
1/6/24, 10:05 PM |
|
View Edit Delete |
PER-17 |
As used herein, "medical imaging" refers to a technique and process of imaging the interior of a body for clinical analysis and medical intervention, as well as visual representation of the function of some organs or tissues (physiology). Medical imaging seeks to reveal internal structures hidden by the skin and bones, as well as to diagnose and treat disease. Medical imaging may be used to establish a database of normal anatomy and physiology to make possible identification of abnormalities. Medical imaging in its widest sense, is part of biological imaging and incorporates radiology, which uses the imaging technologies of X-ray radiography, magnetic resonance imaging, ultrasound, endoscopy, elastography, tactile imaging, thermography, medical photography, nuclear medicine functional imaging techniques as positron emission tomography (PET) and single-photon emission computed tomography (SPECT). Another form of X-ray radiography includes computerized tomography (CT) scans in which a computer controls the position of the X-ray sources and detectors. Magnetic Resonance Imaging (MRI) is another medical imaging technology. Measurement and recording techniques that are not primarily designed to produce images, such as electroencephalography (EEG), magnetoencephalography (MEG), electrocardiography (ECG), and others, represent other technologies that produce data susceptible to representation as a parameter graph vs. time or maps that contain data about the measurement locations. In certain embodiments bone imaging includes devices that scan and gather bone density anatomic data. These technologies may be considered forms of medical imaging in certain disciplines. (Search "medical imaging" on Wikipedia.com June 16, 2021. CC-BY-SA 3.0 Modified. Accessed June 23, 2021.) Data, including images, text, and other data associated with medical imaging is referred to as patient imaging data. As used herein, "patient imaging data" refers to data identified, used, collected, gathered, and/or generated in connection with medical imaging and/or medical imaging data. Patient imaging data can be shared between users, systems, patients, and professionals using a common data format referred to as Digital Imaging and Communications in Medicine (DICOM) data. DICOM data is a standard format for storing, viewing, retrieving, and sharing medical images. |
107 |
Added by DJM Jan 2024 |
1/6/24, 10:05 PM |
|
View Edit Delete |
PER-17 |
As used herein, "medical image computing" or "medical image processing" refers to systems, software, hardware, components, and/or apparatus that involve and combine the fields of computer science, information engineering, electrical engineering, physics, mathematics and medicine. Medical image computing develops computational and mathematical methods for working with medical images and their use for biomedical research and clinical care. One goal for medical image computing is to extract clinically relevant information or knowledge from medical images. While closely related to the field of medical imaging, medical image computing focuses on the computational analysis of the images, not their acquisition. The methods can be grouped into several broad categories: image segmentation, image registration, image-based physiological modeling, and others. (Search "medical image computing" on Wikipedia.com June 24, 2021. CC-BY-SA 3.0 Modified. Accessed June 24, 2021.) Medical image computing may include one or more processors or controllers on one or more computing devices. Such processors or controllers may be referred to herein as medical image processors. Medical imaging and medical image computing together can provide systems and methods to image, quantify and fuse both structural and functional information about a patient in vivo. These two technologies include the transformation of computational models to represent specific subjects/patients, thus paving the way for personalized computational models. Individualization of generic computational models through imaging can be realized in three complementary directions: definition of the subject-specific computational domain (anatomy) and related subdomains (tissue types); definition of boundary and initial conditions from (dynamic and/or functional) imaging; and characterization of structural and functional tissue properties. Medical imaging and medical image computing enable the translation of models to the clinical setting with both diagnostic and therapeutic applications. (Id.) In certain embodiments, medical image computing can be used to generate a bone model, a patient-specific model, and/or a patent specific instrument from medical imaging and/or medical imaging data. |
108 |
Added by DJM Jan 2024 |
1/6/24, 10:05 PM |
|
View Edit Delete |
PER-17 |
"Medical Imager" refers to any device, system, method, or apparatus configured, designed, or engineered to capture a medical image of a patient. In certain embodiments, a medical imager captures images or data that can be converted into images or internal structures of a body and/or of the anatomy of a patient. A medical imager can capture medical imaging in two or three dimensions. Various technologies can be used to implement a medical imager, including X-ray, such as computed tomography (CAT, CAT), magnetic resonance imaging (MRI), sound waves, such as sonography, and the like. A medical imager may support any biological imaging and may incorporate radiology, which uses the imaging technologies of X-ray radiography, magnetic resonance imaging, ultrasound, endoscopy, elastography, tactile imaging, thermography, medical photography, nuclear medicine functional imaging techniques as positron emission tomography (PET) and single-photon emission computed tomography (SPECT), and the like. A medical imager may support fluoroscopy which is an imaging technique that uses X-rays to obtain real-time moving images of the interior of an object. |
109 |
Added by DJM Jan 2024 |
1/6/24, 10:05 PM |
|
View Edit Delete |
PER-17 |
As used herein, "model" refers to an informative representation of an object, person or system. Representational models can be broadly divided into the concrete (e.g. physical form) and the abstract (e.g. behavioral patterns, especially as expressed in mathematical form). In abstract form, certain models may be based on data used in a computer system or software program to represent the model. Such models can be referred to as computer models. Computer models can be used to display the model, modify the model, print the model (either on a 2D medium or using a 3D printer or additive manufacturing technology). Computer models can also be used in environments with models of other objects, people, or systems. Computer models can also be used to generate simulations, display in virtual environment systems, display in augmented reality systems, or the like. Computer models can be used in Computer Aided Design (CAD) and/or Computer Aided Manufacturing (CAM) systems. Certain models may be identified with an adjective that identifies the object, person, or system the model represents. For example, a "bone" model is a model of a bone, and a "heart" model is a model of a heart. (Search "model" on Wikipedia.com June 13, 2021. CC-BY-SA 3.0 Modified. Accessed June 23, 2021.) As used herein, “additive manufacturing” refers to a manufacturing process in which materials are joined together in a process that repeatedly builds one layer on top of another to generate a three-dimensional structure or object. Additive manufacturing may also be referred to using different terms including additive processes, additive fabrication, additive techniques, additive layer manufacturing, layer manufacturing, freeform fabrication, ASTM F2792 (American Society for Testing and Materials), and 3D printing. Additive manufacturing can build the three-dimensional structure or object using computer-controlled equipment that applies successive layers of the material(s) based on a three-dimensional model that may be defined using Computer Aided Design (CAD) software. Additive manufacturing can use a variety of materials including polymers, thermoplastics, metals, ceramics, biochemicals, and the like. Additive manufacturing may provide unique benefits, as an implant together with the pores and/or lattices can be directly manufactured (without the need to generate molds, tool paths, perform any milling, and/or other manufacturing steps). |
110 |
Added by DJM Jan 2024 |
1/6/24, 10:05 PM |
|
View Edit Delete |
PER-17 |
"Repository" refers to any data source or dataset that includes data or content. In one embodiment, a repository resides on a computing device. In another embodiment, a repository resides on a remote computing or remote storage device. A repository may comprise a file, a folder, a directory, a set of files, a set of folders, a set of directories, a database, an application, a software application, content of a text, content of an email, content of a calendar entry, and the like. A repository, in one embodiment, comprises unstructured data. A repository, in one embodiment, comprises structured data such as a table, an array, a queue, a look up table, a hash table, a heap, a stack, or the like. A repository may store data in any format including binary, text, encrypted, unencrypted, a proprietary format, or the like. |
111 |
Added by DJM Jan 2024 |
1/6/24, 10:05 PM |
|
View Edit Delete |
PER-17 |
"Reference” refers to any apparatus, structure, device, system, component, marking, and/or indicator organized, configured, designed, engineered, and/or arranged to serve as a source of information or a point of comparison used to support or establish knowledge, truth, or quality. (© ChatGPT Jan. 9 Version, Modified, accessed chat.openai.com/chat Jan. 28, 2023). In certain embodiments, a reference can serve as a starting point or initial position for one or more steps in a surgical procedure. A reference may be a type of fiducial. In certain embodiments, “reference” can be with a an adjective describing the reference. For example, a “model reference” is a reference within a model such as a computer model. A model reference refers to any feature, aspect, and/or component within a model. Examples of a model reference include, but are not limited to, a point, a plane, a line, a plurality of points, a surface, an anatomical structure, a shape, or the like. An “anatomical reference” is a reference within, on, near, or otherwise associated with an anatomical structure such as a bone. A reference (e.g., model, actual, virtual, and/or real) may also be referred to as a reference feature. |
112 |
Added by DJM Jan 2024 |
1/6/24, 10:05 PM |
|
View Edit Delete |
PER-17 |
“Reference feature” refers to a feature configured for use as a point, plane, axis, or line of reference (aka a reference). A reference or reference feature can be used to position, measure, orient, fixation, couple, engage, and/or align one object or structure with another object or structure. In certain embodiments, a reference or reference feature can serve as a baseline, a ground truth, a waypoint, a control point, a landmark, and/or the like. A reference feature can facilitate moving from one coordinate system or frame of reference in a virtual environment to a position, location, frame of reference, environment, or orientation on, or in, an actual object, structure, device, apparatus, anatomical structure, or the like. Advantageously, a reference feature can coordinate objects, models, or structures in a digital or virtual model or representation with corresponding objects or structures (e.g., anatomical structures) of actual physical objects or structures. Said another way, a reference feature can serve to map from a virtual or modeled object to an actual or physical object. As used herein, "feature" refers to a distinctive attribute or aspect of something. (Search "feature" on google.com. Oxford Languages, 2021. Web. 20 Apr. 2021.) A feature may include one or more apparatuses, structures, objects, systems, sub-systems, devices, or the like. A feature may include a modifier that identifies a particular function or operation and/or a particular structure relating to the feature. Examples of such modifiers applied to a feature, include, but are not limited to, "attachment feature," "alignment feature," "securing feature," "placement feature," "protruding feature," "engagement feature," "disengagement feature," “resection feature”, “guide feature”, "alignment feature," and the like. |
113 |
Added by DJM Jan 2024 |
1/6/24, 10:05 PM |
|
View Edit Delete |
PER-17 |
As used herein, a "marking" or "marker" refers to a symbol, letter, lettering, word, phrase, icon, design, color, diagram, indicator, figure, structure, device, apparatus, surface, component, system, or combination of these designed, intended, structured, organized, configured, programmed, arranged, or engineered to communication information and/or a message to a user receiving, viewing, or encountering the marking. The marking or "marker" can include one or more of a tactile signal, a visual signal or indication, an audible signal, and the like. In one embodiment, a marking may comprise a number or set letters, symbols, or words positioned on a surface, structure, color, color scheme, or device to convey a desired message or set of information. |
114 |
Added by DJM Jan 2024 |
1/6/24, 10:05 PM |
|
View Edit Delete |
PER-17 |
"Set" refers to a collection of objects. A set can have zero or more objects in the collection. Generally, a set includes one or more objects in the collection. |
115 |
Added by DJM Jan 2024 |
1/6/24, 10:05 PM |