{
    "matter": "71212.157.USU1",
    "document_type": "Patent terminology definitions",
    "definitions": [
        {
            "term": "Analyzer",
            "definition": "“Analyzer” refers to any hardware, software, firmware, circuitry, component, module, logic, device, apparatus, or the like, configured, programmed, designed, arranged, or engineered to process, analyze, examine, and/or review data, including but not limited to digital images, radiographic images, fluoroscopic images, video data, patient information, and the like, and to generate outputs such as annotated images, annotated video sequences, anatomic data for a patient, and the like.\r\n\r\nThe analyzer may be implemented in whole or in part in software, hardware, or any combination thereof. In certain embodiments, the analyzer may include one or more software modules, each of which may carry out specific operations such as image preprocessing, feature extraction, annotation generation, or simulation of corrected anatomy.\r\n\r\nIn additional embodiments, the analyzer may employ one or more artificial intelligence systems, machine learning models, deep learning models, large language models (LLMs), or the like, trained or configured to recognize anatomical landmarks, predict surgical outcomes, generate annotations, or provide recommendations for planned procedures. Such models may be executed locally, remotely, or in distributed form across multiple computing environments."
        },
        {
            "term": "Anatomy Plane",
            "definition": "“Anatomy Plane” refers to a geometric plane in three-dimensional space associated with an anatomical region of interest. Examples include, without limitation, a plane approximating the level of selected anatomical structures (e.g., metatarsal heads), a plantar reference plane, a sagittal or coronal plane, or the like. An anatomy plane may be defined explicitly from landmarks, fitted to points or contours, or inferred from acquisition geometry including the positions and/or orientations of imaging emitters and sensors (e.g., X-ray source and detector, fluoroscope C-arm, camera or mobile-device camera), and may be modeled as coincident with, parallel to, or at a known or estimated offset from a detector plane or display plane. An anatomy plane may also be estimated computationally. As used herein, “at an anatomy plane” denotes that a measurement or calibration corresponds to the physical scale at that anatomical level; where the anatomy is not perfectly planar, the term includes a representative plane within an acceptable tolerance. In one embodiment, the anatomy plane is used for patient-plane calibration to compute a pixel-to-length conversion in millimeters per pixel."
        },
        {
            "term": "Annotated image",
            "definition": "“Annotated Image” refers to any digital image, radiographic image, fluoroscopic image, video frame, video sequence, three-dimensional rendering, or the like, that includes one or more annotations, markings, overlays, augmentations, or the like. Annotations may include, without limitation, landmarks, lines, curves, indicators, measurements, text, predictive markings, graphical objects, or the like, and may be static, dynamic, interactive, or generated in response to user input. An annotated image may depict any projection or view, including anterior–posterior (AP), lateral (LAT), oblique, axial, weight-bearing, non-weight-bearing, or the like. In one embodiment, an “annotated AP image” is an annotated image depicting an AP projection or view (including dorsoplantar (DP) equivalents). In one embodiment, an “annotated LAT image” is an annotated image depicting a lateral projection or view. The annotated image may be structured in various ways, including as an original image with an overlay, as an original image with metadata defining the placement of annotations and/or measurements, or as a combined data file that integrates both image data and annotation data, or the like.\r\nThe annotated image may be generated in whole or in part by computational techniques, including software modules, artificial intelligence systems, machine learning models, deep learning models, large language models (LLMs), or the like. The annotated image may represent anatomic data, predictive data, or simulation data, and may be displayed, stored, transmitted, or further processed in various permutations, including single images, video sequences, interactive user interfaces, or the like. In one embodiment, annotated AP images and annotated LAT images are generated from radiographs, fluoroscopic frames, reconstructed projections or views, or digital photographs of displayed radiographic images, and the like."
        },
        {
            "term": "Annotation",
            "definition": "“Annotation” refers to any information, marking, modification, or graphical element superimposed on, integrated into, or otherwise associated with an image, video frame, video sequence, three-dimensional rendering, or the like. Examples of annotations include, without limitation, indicators, symbols, text, highlights, outlines, lines, segments, planes, points, overlays, predictive markings, or the like.\r\n\r\nAn annotation may serve to identify, highlight, classify, label, or designate an anatomical structure, landmark, axis, plane, region, or characteristic, and may further include quantitative or qualitative information, such as measurements of distances, ratios, angles, areas, volumes, densities, or the like.\r\n\r\nAn annotation may be presented as a line, arrow, curve, circle, polygon, surface, numeric value, descriptive text, color overlay, dynamic indicator, or any combination thereof, and the like, and may function as a static, dynamic, interactive, predictive, or simulated indicator to draw attention to, describe, or characterize features of the underlying data."
        },
        {
            "term": "AP images or views",
            "definition": "“AP” (anterior–posterior) refers to any projection, view, or representation in which an anatomical region is depicted in an anterior-to-posterior orientation. AP includes images acquired by X-ray with the beam directed generally from an anterior or dorsal aspect toward a posterior or plantar aspect with the detector opposite the source; reconstructed or simulated AP projections/views derived from volumetric or other data; and depictions of AP imagery captured from displays or prints, including photographs, screenshots, video frames, or the like. When used as a modifier with any image term (e.g., image, digital photograph, radiographic image, X-ray image, view, or the like), AP denotes the AP projection, view, or representation including minor variations in beam angle, source-to-detector distance, subject positioning, camera viewpoint, or reconstruction parameters that do not materially alter the AP depiction. In the context of the foot, AP includes dorsoplantar (DP) projections/views and the like."
        },
        {
            "term": "Artificial Neural Network (ANN)",
            "definition": "“Artificial Neural Network (ANN)” refers to a parameterized computational architecture comprising layers of interconnected units (neurons) that apply learned weights and nonlinear activation functions to input data. ANNs may be trained by backpropagation (optionally with stochastic gradient methods) and may include components such as convolutional layers, pooling, normalization, attention, and skip connections. ANN families include feedforward, convolutional, recurrent, and transformer-based networks."
        },
        {
            "term": "Capturing",
            "definition": "“Capturing” refers to acquiring, recording, receiving, ingesting, or otherwise obtaining data—including, without limitation, digital photographs, images, radiographic or fluoroscopic images, video frames or sequences, animations, three-dimensional data, patient information, and the like—for storage, processing, display, export, or transmission.\r\n\r\nCapturing may be performed by exposing a sensor (e.g., CCD, CMOS, flat-panel X-ray detector, ultrasound probe, depth or time-of-flight sensor, or the like), by scanning or digitizing physical media (e.g., film, prints), by screen capture (screenshot) or photographing a display, by importing/receiving files or streams from local storage, PACS/DICOM systems, or networks, by exporting or downloading files and/or streams from local storage, PACS/DICOM systems, or networks. Capturing may occur under weight-bearing or non-weight-bearing conditions for the object, patient, body part, imaged region, and may be synchronous or asynchronous, real-time or buffered, local or remote, automated, semi-automated, or user-initiated.\r\n\r\nCapturing may include associated control or acquisition operations such as triggering, exposure control, gating, buffering, demosaicing, format conversion, compression/decompression, high-dynamic-range compositing, burst acquisition, or the like, and may store metadata (e.g., timestamps, orientation, calibration, geolocation, device settings) linked to the captured data. In one embodiment, a single frame extracted from a video or fluoroscopic stream, a screenshot of on-screen imagery, or a photograph of a displayed radiographic image constitutes capturing. In one embodiment, capturing multiple items (e.g., AP and LAT views) within a defined interval may constitute a single acquisition session."
        },
        {
            "term": "Constructed Reference",
            "definition": "\"Constructed Reference” refers to a derived geometric construct computed from landmarks or anatomic data, including points, centroids, axes, lines, rays, curves, planes, regions, tolerance bands, or the like, used for measurement, registration, planning, guidance, or assessment. Constructed references may be rendered as annotations and/or stored as data."
        },
        {
            "term": "Consultation",
            "definition": "“Consultation” refers to any clinical encounter between a licensed healthcare professional (e.g., physician, surgeon, podiatrist, dentist, advanced practice provider, therapist, orthotist/prosthetist, or the like) and a patient (and/or caregiver or representative) to evaluate a condition, obtain history, perform or confirm an examination, review available data (including images, measurements, reports, or the like), discuss assessments and potential treatment options (including non-operative, operative, interventional, rehabilitative, pharmacologic, or the like), address questions, and establish or update a plan of care. \r\nA consultation may include, without limitation, ordering or reviewing diagnostic tests, capturing or reviewing images, documenting findings, discussing risks/benefits/alternatives, obtaining or preparing elements of informed consent, providing instructions, and scheduling follow-up or procedures. Consultations may occur in person or by telehealth (video or audio), may involve single-clinician or multidisciplinary participation, and may be conducted as a single session or a series of sessions, with preparatory and follow-up communications as appropriate.\r\n\r\nTypical consultation duration is context-dependent and varies with complexity, acuity, and institutional practice. By way of illustration and without limitation, routine or follow-up consultations may take about 10–30 minutes, while consultations in which a procedure (e.g., surgical or interventional) is discussed, recommended, or prescribed may take about 20–60 minutes or longer, including time for shared decision-making, imaging review, counseling, and consent. In certain cases, consultation time may exceed 60 minutes or be staged across multiple encounters. Durations are approximate and non-limiting."
        },
        {
            "term": "Convolutional Neural Network (CNN)",
            "definition": "“Convolutional Neural Network (CNN)” refers to a neural network employing convolutional operations (optionally with pooling and up/down-sampling) suited to images or grid-structured data. Examples include U-Net and U-Net-derived encoder–decoder architectures with skip connections. CNNs may be used for segmentation, detection, classification, denoising, super-resolution, and the like."
        },
        {
            "term": "Corrected Anatomy Image",
            "definition": "“Corrected Anatomy Image” refers to any image, video frame, video sequence, three-dimensional rendering, or the like that depicts an anatomical region after performance of a correction procedure, including intraoperative fluoroscopic frames, post-operative radiographs, clinical photographs, or the like, with or without annotations, overlays, or measurements."
        },
        {
            "term": "Correction Procedure",
            "definition": "“Correction Procedure” refers to any method, technique, workflow, treatment, operation, intervention, or the like that is intended to produce a correction. Examples include, without limitation, surgical procedures (e.g., osteotomy, arthrodesis, soft-tissue balancing), minimally invasive or percutaneous techniques, intraoperative adjustments, image-guided manipulations, external fixation adjustments, orthotic or prosthetic fitting, bracing, casting, physical therapy protocols, rehabilitation regimens, pharmacologic or biologic interventions, staged or combined approaches, and the like. A correction procedure may be performed on one or more parts of a foot and/or ankle and may include invasive surgical procedures and/or minimally invasive surgical procedures.\r\n\r\nFoot and ankle examples of correction procedures include, without limitation, Lapidus procedures (first tarsometatarsal arthrodesis), metatarsus adductus corrections (including metatarsal base osteotomies or soft-tissue balancing), Akin osteotomy, Chevron (Austin) distal metatarsal osteotomy, Scarf osteotomy, proximal metatarsal osteotomy, Weil osteotomy, Cotton osteotomy (medial cuneiform opening wedge), Evans lateral column lengthening, medial displacement calcaneal osteotomy (MDCO), Dwyer or other calcaneal closing-wedge osteotomies, first metatarsophalangeal arthrodesis, cheilectomy, bunionette correction, hammertoe correction (PIP arthrodesis or arthroplasty), gastrocnemius recession, Achilles tendon lengthening, plantar fascia release, spring-ligament repair, posterior tibial tendon procedures (including Kidner), Lisfranc arthrodesis, tarsal coalition resection, lateral ligament reconstruction (Broström), subtalar arthrodesis, arthrodesis, and the like. \r\n\r\nMinimally invasive surgery (MIS) examples of correction procedures include, without limitation, percutaneous or arthroscopically assisted techniques such as MICA/PECA (minimally invasive/percutaneous Chevron-Akin bunion correction), DMMO (distal minimally invasive metatarsal osteotomy) for lesser metatarsals, percutaneous Akin osteotomy, percutaneous distal or proximal metatarsal osteotomies, percutaneous bunionette osteotomy, minimally invasive or percutaneous Lapidus arthrodesis, minimally invasive cheilectomy, endoscopic or percutaneous gastrocnemius recession, percutaneous Achilles tendon lengthening, endoscopic plantar fasciotomy, arthroscopic Broström lateral ligament repair, endoscopic calcaneoplasty for Haglund deformity, percutaneous MDCO or Dwyer calcaneal osteotomy, minimally invasive subtalar arthrodesis, arthroscopically assisted Lisfranc reduction/arthrodesis, percutaneous hammertoe correction (including PIP arthrodesis with intramedullary fixation), percutaneous screw fixation of fractures or osteotomies, and the like. \r\n\r\nA correction procedure may be planned, simulated, rehearsed, or executed in one or multiple stages, may use instruments, devices, implants, or software, and may be performed manually, robotically, or via computer-assisted systems, and the like. A correction procedure may include procedures that comport to conventional standard of care, as well as standard of care procedures that have certain measurements, corrections, a planned change in measurements, a correction intended to produce different measurements, adjustments, edits, or changes applied. These modifications may be based on surgeon discretion, user preferences, patient preferences, institutional protocols, system-generated recommendations, software-generated recommendations, colleague input, or other factors. In certain embodiments, a correction procedure may be tailored to optimize clinical outcomes, patient satisfaction, workflow efficiency, or procedural safety, or the like."
        },
        {
            "term": "Deep Learning (DL)",
            "definition": "“Deep Learning (DL)” refers to the use of neural networks with multiple layers (deep neural networks) that learn hierarchical feature representations. Deep learning architectures include, without limitation, convolutional neural networks (CNNs), recurrent networks, and transformers, and may be trained in supervised or unsupervised/self-supervised regimes."
        },
        {
            "term": "Digital Photograph",
            "definition": "“Digital Photograph” refers to any electronically captured still image formed by a sensor (e.g., CCD, CMOS, or the like) and stored as a pixel array, whether captured by a mobile device, camera, or computing device, depicting physical subjects or imagery displayed on a screen (including photographs of radiographic or fluoroscopic images shown on a monitor), prints, documents, or the like. A digital photograph also encompasses a single frame extracted from a video stream, as well as computationally produced captures such as HDR composites, low-light “night mode” images, stitched panoramas, or the like.\r\n\r\nA digital photograph may be encoded in any format, bit depth, or color space (including RAW, JPEG, PNG, HEIF, TIFF, or the like), may include embedded metadata (e.g., EXIF, XMP, geolocation, orientation, timestamps, or the like), and may be cropped, scaled, filtered, denoised, compressed, decompressed, or otherwise transformed without ceasing to be a digital photograph. For the avoidance of doubt, a screen capture (screenshot) of on-screen imagery is treated as a digital photograph for purposes herein."
        },
        {
            "term": "Edit",
            "definition": "“Edit” (or “Editing”) refers to any user-initiated or system-assisted action to create, modify, confirm, reject, reorder, relabel, hide/show, lock/unlock, attach metadata to, or delete one or more items relevant to surgical planning, including without limitation landmarks, constructed references (e.g., a plumbline), annotations, measurements (e.g., distances, angles, ratios), calibration data, views/projections (AP, LAT, oblique, weight-bearing or non-weight-bearing designations), simulation parameters, and elements of a planned or final correction procedure, and the like.\r\n\r\nEditing may include, without limitation: placing or re-placing points; translating/rotating/scaling lines, axes, or regions; snapping to detected edges; redefining or refining a landmark; changing labels or classes; adjusting thresholds or tolerances (e.g., ε for intersect/tangential determinations); recalibrating pixel spacing; converting units; re-measuring or recomputing values; accepting, rejecting, or modifying analyzer-proposed landmarks or measurements; toggling visibility or layering of overlays; cropping, window/level adjustment, or other non-destructive display adjustments; linking a measurement or reference to a planned correction step; and adding notes or rationale.\r\n\r\nEditing may be performed manually, semi-automatically, or automatically, via any input modality including mouse/trackpad, keyboard, stylus, touch, multi-touch gestures, voice, foot pedal, gaze/eye-tracking, or programmatic commands, and the like. In one embodiment, edits trigger real-time re-computation of dependent values (e.g., intermetatarsal angle, PL classification/clearance), updates to anatomic data, regeneration of annotated images or simulated corrected anatomy images, and/or updates to procedure plans. In one embodiment, edits are versioned with timestamps, user identity, and change descriptions, and are non-destructive to the underlying image data unless an explicit destructive operation is selected.\r\n\r\nEditing may occur pre-operative, intra-operative, or post-operative; may be performed locally or remotely (including telehealth); and may be executed by a surgeon or other authorized user under applicable permissions and workflows."
        },
        {
            "term": "Generative Network",
            "definition": "“Generative Network” refers to a model configured to synthesize data samples (e.g., images) from random inputs and/or conditioning signals. Examples include GANs, variational autoencoders (VAEs), diffusion models, autoregressive models, or hybrids. A generative network may be conditioned on pixel-wise representations, masks/label maps, edges, landmarks, text prompts, or other anatomic data."
        },
        {
            "term": "Geometric Rectification",
            "definition": "“Geometric Rectification” refers to processing that transforms a captured image to compensate for perspective and/or lens distortion and to isolate a depiction of an image of interest, including, without limitation, homography or projective warping, undistortion, dewarping, rotation, scaling, cropping, resampling, glare/reflection suppression, and the like."
        },
        {
            "term": "Hallux Valgus Angle (HVA)",
            "definition": "“Hallux Valgus Angle (HVA)” refers to an angular measurement formed between a long axis of the first metatarsal and a long axis of the proximal phalanx of the hallux, typically measured on an anterior–posterior view. HVA may be computed from anatomic data and/or constructed references and may be used to classify deformity severity."
        },
        {
            "term": "Image",
            "definition": "“Image” refers to any digital or analog pictorial representation of data, including but not limited to two-dimensional frames, multi-frame sequences, three-dimensional or four-dimensional volumes, projections, renderings, heatmaps, probability maps, segmentation masks, depth or disparity maps, and the like. An image may depict physical subjects, scenes, or objects; medical or scientific phenomena (e.g., radiographs, CT, MRI, PET, fluoroscopic views, ultrasound, microscopy), documents, screens or displays, or synthetic or simulated content generated by computation, and may be acquired by cameras, scanners, sensors, or produced by reconstruction, simulation, or other computational processes, and the like.\r\n\r\nAn image may be encoded or stored in any format, resolution, bit depth, sampling scheme, or color space (including grayscale, RGB, multispectral, hyperspectral, RAW, JPEG, PNG, HEIF, TIFF, DICOM, or the like), may include embedded metadata (e.g., timestamps, geolocation, orientation, calibration data, or the like), and may be cropped, scaled, resampled, filtered, denoised, compressed, decompressed, enhanced, super-resolved, deblurred, geometrically transformed, fused, or otherwise processed without ceasing to be an image. For the avoidance of doubt, a single frame extracted from a video stream, a screenshot of on-screen imagery, and a computer-generated rendering are each treated as an image for purposes herein."
        },
        {
            "term": "Intermetatarsal Angle (IMA)",
            "definition": "“Intermetatarsal Angle (IMA)” refers to an angular measurement formed between long axes of the first and second metatarsals, typically measured on an anterior–posterior view. IMA may be computed from anatomic data and/or constructed references and may be used to select and/or evaluate correction procedures."
        },
        {
            "term": "Language Model (LM)",
            "definition": "\"Language model\" refers to a computational model that can be configured to process, generate, predict, transform, classify, summarize, or otherwise analyze linguistic or symbolic information. A language model may be implemented using neural network architectures, transformer-based architectures, machine learning systems, or other computational frameworks capable of modeling relationships among tokens, symbols, or representational units, or the like. A language model may operate in generative, discriminative, inferential, or analytical modes. Synonyms include generative model, neural language processor, sequence model, generative AI model, or the like."
        },
        {
            "term": "LAT images or views",
            "definition": "“LAT” (lateral) refers to any projection, view, or representation in which an anatomical region is depicted in profile with a lateral-to-medial or medial-to-lateral orientation. Lateral includes images acquired by X-ray in a lateral projection; reconstructed or simulated lateral projections/views derived from volumetric or other data; and depictions of lateral imagery captured from displays or prints, including photographs, screenshots, video frames, or the like. When used as a modifier with any image term (e.g., image, digital photograph, radiographic image, X-ray image, view, or the like), lateral denotes the lateral projection, view, or representation, including minor variations in rotation, beam angle, subject positioning, camera viewpoint, or reconstruction parameters that do not materially alter the lateral depiction, including “true lateral” and near-lateral views."
        },
        {
            "term": "Lesser-Ray Realignment",
            "definition": "“Lesser-Ray Realignment” refers to any correction of alignment of one or more lesser rays (metatarsals two through five), including, without limitation, osteotomies, arthrodesis, soft-tissue procedures, image-guided manipulations, or the like, performed alone or in combination with other corrections."
        },
        {
            "term": "Machine Learning (ML)",
            "definition": "“Machine Learning (ML)” refers to techniques by which models improve performance from data. ML may be supervised, semi-supervised, self-supervised, unsupervised, or reinforcement learning, and may address tasks such as classification, regression, clustering, dimensionality reduction, and segmentation. Representative models include, without limitation, neural networks, transformers, support-vector machines, decision trees/ensembles, Bayesian models, and clustering algorithms. Models may be trained by minimizing a loss function and evaluated using metrics such as accuracy, precision/recall/F1, ROC/AUC, or the like."
        },
        {
            "term": "Masks",
            "definition": "“Masks” refers to pixel-wise representations of regions or classes in an image, including, without limitation, binary masks, label maps, instance masks, probability maps, heatmaps, run-length–encoded masks, vector contours rasterized to a grid, or the like, at native or resampled resolution."
        },
        {
            "term": "Measurement",
            "definition": "“Measurement” (or “derived parameter”) refers to a quantitative relationship defined between two or more landmarks, including, without limitation, an angle, distance, ratio, offset, or vector. For example, a measurement may include the intermetatarsal angle (IMA) defined between axes of the first and second metatarsals, the distance between two bony prominences, or a ratio of two anatomical lengths, or the like."
        },
        {
            "term": "Metatarsus Adductus (MTA)",
            "definition": "“Metatarsus Adductus (MTA)” refers to medial deviation of the forefoot relative to the midfoot and/or hindfoot in the transverse plane, characterized by adduction of one or more metatarsals toward the foot midline. MTA may be flexible or rigid and may be assessed using angular, axis-based, or categorical measures."
        },
        {
            "term": "Metatarsus Adductus Metric",
            "definition": "“Metatarsus Adductus Metric” refers to any quantitative or categorical representation of MTA, including, without limitation, angles, distances, ratios, scores, thresholds, or a categorical indicator derived from one or more constructed references, and the like."
        },
        {
            "term": "Mobile Device",
            "definition": "“Mobile Device” refers to any portable computing or communication device capable of capturing, processing, storing, or transmitting data, including but not limited to smartphones, tablets, wearable devices, smart glasses, AR/VR headsets, portable media players, handheld scanners, body-worn cameras, and the like."
        },
        {
            "term": "Mobile Device Camera",
            "definition": "“Mobile Device Camera” refers to any image-capture component integrated into, attached to, controlled by, or operably associated with a mobile device, including front-facing or rear-facing cameras, multi-sensor camera arrays, depth sensors, time-of-flight modules, LiDAR, thermal or multispectral sensors, external or peripheral cameras connected via wired or wireless interfaces (e.g., USB, Wi-Fi, Bluetooth), and the like. A mobile device camera may capture still images or video, may employ computational photography (e.g., HDR, denoising, super-resolution), and may be used to capture imagery of scenes, subjects, documents, displays, or the like."
        },
        {
            "term": "Patient-Plane Calibration",
            "definition": "“Patient-Plane Calibration” refers to determining a scale factor that converts pixel measurements to physical dimensions at the anatomical plane of interest. In one embodiment, calibration is obtained using a calibration object of known size positioned at the anatomy plane; in another embodiment, calibration is computed from imaging geometry and/or metadata."
        },
        {
            "term": "Pixel-to-Length Conversion",
            "definition": "“Pixel-to-Length Conversion” refers to a mapping from pixel units to physical units (e.g., millimeters per pixel) applicable to an image or region thereof. The conversion may be a scalar, vector, or spatially varying function and may be derived from patient-plane calibration, metadata, or geometric correction."
        },
        {
            "term": "Pixel-Wise Representations",
            "definition": "“Pixel-Wise Representations” refers to data in which values are defined per pixel (or voxel), including, without limitation, masks, label maps, probability maps, heatmaps, distance transforms, or the like, used to represent anatomy, landmarks, or other features."
        },
        {
            "term": "PL Status",
            "definition": "“PL Status” refers to a classification associated with a plumbline (PL) constructed reference, the status being positive when the PL intersects a region of the second metatarsal head and negative when the PL is tangential to, or does not intersect, the second metatarsal head. In some embodiments, a proximity tolerance ε is applied for borderline cases."
        },
        {
            "term": "Plumbline",
            "definition": "As used herein, \"Plumbline (PL)\" refers to a radiographic assessment reference construct and/or anatomic data representing forefoot alignment, used to evaluate whether space exists to align the first ray relative to a longitudinal foot axis without requiring lesser-ray realignment. In one embodiment, a PL is a constructed reference. In an AP projection or view (including dorsoplantar (DP) equivalents), the PL is constructed from landmarks associated with the medial cuneiform and the first tarsometatarsal (TMT) joint and extended distally toward the lesser metatarsals. A ‘positive PL’ indicates that the PL intersects the second metatarsal head (or shaft), suggesting metatarsus adductus (MTA) of a degree that may impede complete first-ray correction; a ‘negative PL’ indicates that the PL is tangential to, or does not intersect, the second metatarsal, suggesting sufficient clearance for first-ray correction. Minor variations in beam angle, source-to-detector distance, patient positioning, camera viewpoint, or reconstruction that do not materially alter the assessment are included. In some embodiments, a proximity tolerance ε is used to classify borderline cases as intersecting or tangential. McAleer, J. P., DeCarbo, W. T., D’Antonio, P. C., & Hatch, D. J. (2024). \"A Simplified Preoperative Radiographic Assessment for Metatarsus Adductus Associated With Hallux Valgus.\" Foot & Ankle Orthopaedics, 9(2). https://doi.org/10.1177/24730114241246830[]"
        },
        {
            "term": "Processing",
            "definition": "“Processing” refers to any operation or series of operations performed on data—including, without limitation, digital photographs, images, radiographic or fluoroscopic images, video frames or sequences, patient information, and the like—to transform, analyze, interpret, generate, derive, enhance, measure, simulate, store, transmit, or otherwise act upon such data, and the like.\r\n\r\nProcessing may include, without limitation: acquiring or receiving data; decoding, parsing, or converting formats (e.g., RAW, JPEG, PNG, HEIF, TIFF, DICOM, or the like); compression or decompression; normalization, calibration, white balance, flat-fielding, shading correction, or gain correction; geometric correction, rectification, undistortion, dewarping, perspective correction, or registration; resampling, resizing, cropping, rotating, or reformatting; denoising, deblurring, sharpening, contrast adjustment, dynamic-range expansion, high-dynamic-range compositing, super-resolution, or enhancement; segmentation, detection, tracking, feature extraction, keypoint or landmark identification, pose or axis estimation, measurement of distances, angles, areas, volumes, ratios, or the like; generation of annotations, overlays, indicators, text, or graphical objects; simulation, prediction, or estimation of anatomy or outcomes (including simulated corrected anatomy, projected alignments, or the like); fusion or compositing of multiple sources; rendering, visualization, or preparation for display or storage; artifact reduction, de-identification, quality assessment, or the like.\r\n\r\nProcessing may be implemented in software, hardware, firmware, circuitry, rules-based logic, statistical or signal-processing methods, computer-vision algorithms, and/or one or more artificial intelligence or machine-learning models (including deep learning models, large language models, or the like), executed locally, remotely, or in distributed form; may operate in real time or batch; may be automated, semi-automated, or interactive; and may occur in a single stage or multiple stages, iteratively or in any order, and the like.\r\n\r\nFor the avoidance of doubt, processing does not require every operation listed; any subset or combination of the foregoing, performed in any reasonable order, constitutes processing, including processing of an image of another image (e.g., a photograph of a displayed radiograph), and the like."
        },
        {
            "term": "Radiographic Image or Radiograph",
            "definition": "“Radiographic Image” or \"Radiograph\" refers to any image generated using X-ray radiation, including but not limited to projection radiographs, fluoroscopic images or frames, tomosynthesis images, reconstructed or reformatted views derived from X-ray data, and the like. Radiographic images may depict any projection or view (e.g., anterior–posterior, posterior–anterior, lateral, oblique, weight-bearing, non-weight-bearing, or the like) of any anatomical region.\r\n\r\nA radiographic image may be digital or analog (film), may be stored or transmitted in any format or container (including DICOM, JPEG, PNG, TIFF, or the like), and may include embedded metadata (e.g., timestamps, orientation, calibration data, or the like). A radiographic image may be windowed/leveled, cropped, scaled, resampled, filtered, denoised, compressed, decompressed, annotated, rendered, reformatted, or otherwise transformed without ceasing to be a radiographic image.\r\n\r\nFor the avoidance of doubt, a radiographic image may be displayed on a screen, printed, exported, or otherwise reproduced, and depictions captured from such displays or prints (including screenshots, scans, photographs, video frames, or the like) constitute representations of the underlying radiographic image."
        },
        {
            "term": "Rectified Digital Photograph",
            "definition": "“Rectified Digital Photograph” refers to a digital photograph that has undergone geometric rectification to compensate for perspective and/or lens distortion and to isolate and normalize a depiction of an image of interest for subsequent analysis."
        },
        {
            "term": "Screen",
            "definition": "“Screen” refers to any physical or virtual surface or region on which visual images and/or video are presented to a user, including emissive panels (e.g., LCD, OLED, microLED), reflective or transmissive surfaces (e.g., projection screens, walls, curtains, or light-box viewing surfaces for radiographic films), touchscreens, near-eye microdisplays, and virtual screens in augmented, mixed, or virtual reality environments, and the like. For the avoidance of doubt, content is deemed “displayed on a screen” whether produced by a panel integrated in a device or by a projector illuminating a separate surface."
        },
        {
            "term": "Selection",
            "definition": "“Selection” refers to any user-initiated or programmatically initiated designation of one or more items, controls, regions, text spans, images, annotations, menu options, or the like as the current target(s) for an action in a graphical user interface. Selection may be single, multiple, range-based, toggle/additive/subtractive, persistent or transient, and may apply to list items, buttons, checkboxes, radio buttons, tabs, icons, canvas regions, form fields, sliders, toolbar commands, or the like. A selection may be indicated by visual or state changes such as highlight, focus, check state, pressed/active state, outline, opacity change, badge, or the like, and may be exposed via properties, events, or accessibility semantics (e.g., selected, checked, pressed, or the like).\r\n\r\nSelection may be effected by any input modality, including but not limited to mouse or trackpad clicks, double-clicks, context-clicks, drags, marquee/rubber-band selection, keyboard focus and shortcut keys, touch taps, long-presses, multi-touch gestures, stylus input, game controllers, remote controls, voice commands, gaze/eye-tracking, switch devices, or the like. Selection may be explicit (user action), implicit (default/preselected), or programmatic (set by the system or an application workflow), may be undone or redone, and may be persisted, synchronized, or transmitted for further processing, execution, or display, and the like.\r\n\r\nIn certain embodiments, “Selection” includes choosing among alternative simulated corrected anatomy images, planned or final correction procedures, or other outputs/options, via any GUI control or input modality, including toggles, radio buttons, checkboxes, lists, menus, thumbnails, keyboard focus, touch, voice, or programmatic selection."
        },
        {
            "term": "Simulated Corrected Anatomy Image",
            "definition": "“Simulated Corrected Anatomy Image” refers to any image, video frame, video sequence, animation, three-dimensional rendering, or the like that depicts a predicted, hypothetical, or planned post-correction state of an anatomical region associated with a planned correction procedure. Such an image may be generated from pre-correction data (including images, annotated images, anatomic data, or the like) using rigid or non-rigid transformations, morphing, deformable or kinematic models, finite-element or physics-based simulation, statistical or rule-based methods, artificial intelligence or machine-learning models, parametric templates, or the like. A simulated corrected anatomy image may include overlays, annotations, indicators, measurements, or predicted implant or instrument positions; may depict any projection or view (including AP, lateral, oblique, weight-bearing, non-weight-bearing, or the like); and may be displayed, stored, transmitted, or further processed without ceasing to be a simulated corrected anatomy image. Labels such as “first” or “second” simulated corrected anatomy image are identifiers for alternative plans and do not imply any order of operations."
        },
        {
            "term": "Threshold condition",
            "definition": "“Threshold Condition” refers to a rule or set of rules evaluated against one or more measurements or indicators, including, without limitation, a value being greater than or less than a threshold, outside a normative range, satisfying a logical combination of criteria, or matching a model-derived decision boundary, and the like."
        },
        {
            "term": "Toggle Input",
            "definition": "\"Toggle input\" refers to any user-initiated action that causes a change in the state of the display between two or more images, views, or modes, including but not limited to pressing a button, clicking with a mouse, tapping a touchscreen, actuating a keyboard key, or operating a hardware or software switch."
        },
        {
            "term": "U-Net",
            "definition": "“U-Net” refers to a convolutional neural network architecture comprising an encoder–decoder with skip connections configured to process images and generate pixel-wise outputs (e.g., segmentations, denoised images), and may be implemented as software, firmware, or hardware as part of an artificial intelligence system."
        },
        {
            "term": "Viewfinder Overlay",
            "definition": "“Viewfinder Overlay” refers to a graphical element, display aid, or interface presented on a display of a device, such as a mobile device, camera, or imaging system, that assists a user in capturing an image. A viewfinder overlay may provide alignment cues, boundary indicators, targeting reticles, crosshairs, grids, framing boxes, shading, highlighting, or other visual markers, or the like, to guide the positioning of a subject within a field of view. In certain embodiments, a viewfinder overlay may be used during capture of a radiographic image displayed on a screen to ensure that the radiograph is properly aligned, centered, and scaled relative to the device’s camera. A viewfinder overlay may be static or dynamic, may change appearance in response to detected motion or alignment, and may provide visual, auditory, or haptic feedback to the user. Examples include overlays that change color when alignment is achieved, gridlines that indicate perspective or scale, or bounding boxes that indicate when an image of interest is positioned within a capture region, or the like."
        },
        {
            "term": "X-ray Image",
            "definition": "“X-Ray Image” refers to any image generated using X-ray radiation, including but not limited to projection radiographs, fluoroscopic images or frames, tomosynthesis images, reconstructed or reformatted views derived from X-ray data, and the like. An X-ray image may depict any projection or view (e.g., anterior–posterior (AP), lateral (LAT), oblique, axial, or the like) and may be acquired as weight-bearing or non-weight-bearing. In one embodiment, a weight-bearing X-ray image is acquired while the patient applies partial or full body weight to the imaged region (including standing, simulated-standing, or externally load-applied configurations). In one embodiment, a non-weight-bearing X-ray image is acquired without applied load to the imaged region.\r\n\r\nAn X-ray image may be digital or analog (film), may be stored, transmitted, or displayed in any format or container (including DICOM, JPEG, PNG, TIFF, or the like), and may include embedded metadata (e.g., timestamps, orientation, calibration data, or the like). An X-ray image may be windowed/leveled, cropped, scaled, resampled, filtered, denoised, compressed, decompressed, annotated, rendered, reformatted, or otherwise transformed without ceasing to be an X-ray image. In one embodiment, an X-ray image may be displayed on a screen, printed, or otherwise reproduced, and depictions captured from such displays or prints (including screenshots, scans, photographs, video frames, or the like) constitute representations of the underlying X-ray image"
        }
    ]
}