Search Filters

Search Results

Found 16 results

510(k) Data Aggregation

    K Number
    K202948
    Device Name
    EzOrtho
    Date Cleared
    2020-10-22

    (22 days)

    Product Code
    Regulation Number
    892.2050
    Reference & Predicate Devices
    Why did this record match?
    Applicant Name (Manufacturer) :

    Ewoo Soft Co., Ltd.

    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    EzOrtho is a software indicated for use by dentists who provide orthodontic treatment for image analysis, simulation, profilogram, VTO/STO and patient consultation. Results produced by the software's diagnostic, treatment planning and simulation tools are dependent on the interpretation of trained and licensed practitioners or dentists.

    Device Description

    EzOrtho is a 2D orthodontic analysis and simulation program developed by Ewoosoft. EzOrtho manages patient information and images for orthodontic analysis. This software also assists in orthodontic treatment by providing accurate image analysis, profilograms, superimpositions, and VTO (visualised treatment objective) and STO (surgical treatment objective) simulations. The analyzed results are saved in chart format so that the user can easily store and track the treatment and records of each patient.

    EzOrtho is designed to provide a simple and straightforward user interface.

    • Managing Patients and Registering Images ● EzOrtho offers features for making schedules and managing patient appointments. In addition. EzOrtho enables the users to import images from EzDent-i made by our company, Explorer, or a scanner, and easily calibrate the size of the image or arrange multiple film/photo images.
    • . Analyzing and Tracing Images The Landmark Voice Guide and the improved Landmark Input Interface features support easier tracing.
    • Establishing Treatment Plans ● The Morphing feature enables the user to predict how the treatment plan established may affect the face of a patient. In addition, the Compare feature enables the user to establish a treatment plan by comparing photos before and after the treatment.
    • Assisting with Patient Consultation ● EzOrtho provides features to facilitate understanding and communication between doctors and patients during consultation. For example, the Superimposition feature displays after surgery changes visually, and the Gallery feature plays a slide show with multiple images of patients.
    AI/ML Overview

    The provided text is a 510(k) summary for the medical device EzOrtho. It describes the device, its intended use, and its substantial equivalence to a predicate device. However, it does not contain any performance data from a specific study that demonstrates the device meets particular acceptance criteria. The "Performance Data" section only states that "Verification, validation and testing activities were conducted to establish the performance, functionality and reliability characteristics of the modified devices. The device passed all of the tests based on pre-determined Pass/Fail criteria." This is a general statement and does not provide the specific details required to answer your questions about acceptance criteria and a study proving their fulfillment.

    Therefore, I cannot populate the table or provide the detailed information requested regarding sample size, data provenance, expert involvement, adjudication methods, MRMC studies, standalone performance, or ground truth establishment based on the provided document.

    To answer your questions, I would need a section detailing a specific clinical or performance study, including:

    • Specific performance metrics and their acceptance thresholds.
    • The actual results of the device against those metrics.
    • Details about the dataset used (size, type, origin).
    • Information about the ground truth establishment process (number/qualifications of experts, adjudication).

    Without this specific performance study data, I can only provide general information based on the document's structure, which states that performance, functionality, and reliability characteristics were verified and validated, and all tests passed their pre-determined criteria.

    Ask a Question

    Ask a specific question about this device

    K Number
    K202116
    Date Cleared
    2020-08-21

    (22 days)

    Product Code
    Regulation Number
    892.2050
    Reference & Predicate Devices
    Why did this record match?
    Applicant Name (Manufacturer) :

    Ewoo soft Co., Ltd.

    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    EzDent-i is dental imaging software that is intended to provide diagnostic tools for maxillofacial radiographic imaging. These tools are available to view and interpret a series of DICOM compliant dental radiology images and are meant to be used by trained medical professionals such as radiologist and dentist.

    EzDent-i is intended for use as software to acquire, view, save 2D image files, and load DICOM project files from panorama, cephalometric, and intra-oral imaging equipment.

    Device Description

    EzDent-i is a device that provides various features to acquire, transfer, edit, display, store, and perform digital processing of medical images. EzDent-i is a patient & image management software specifically for digital dental radiography. It also provides server/client model so that the users upload and download clinical diagnostic images and patient information from any workstations in the network environment.

    EzDent-i supports general image formats such as JPG and BMP for 2D image viewing as well as DICOM format. For 3D image management, it provides uploading and downloading support for dental CT Images in DICOM format. It interfaces with a 3D imaging software made by our company, the Ez3D-i (K131616 & K150761 & K163533 & K173863 & K190791) but the EzDent-i itself does not view, transfer or process 3D radiographs.

    EzDent-i supports the acquisition of dental images by interfacing with OpenCV library to import the intra-oral camera images. It also supports the acquisition of CT/Panoramic/Cephalo/Intra-Oral Sensor images by interfacing with X-ray capture software.

    EzDent-i makes it easier to diagnose and analyze 2D dental images with simple and convenient user interface. EzDent-i's main functions are;

    • · Easy and convenient data search function for patient information and clinical images
    • · Various image viewing format for 2D dental images
    • Various image processing functions including adjustment of brightness and contrast for images
    • · Measurement function of length and angle for 2D images
    • · Dental implant simulation for treatment planning and effective patient consultation
    • · Crown simulation for more effective patient consultation
    • · Print function supporting various viewing output format
    AI/ML Overview

    The provided text is a 510(k) summary for the EzDent-i/E2/Prora View/Smart M Viewer dental imaging software. While it states that performance data was collected and the device "passed all of the tests based on pre-determined Pass/Fail criteria," it does not provide specific details about the acceptance criteria, the study itself, or the quantitative performance metrics.

    Therefore, I cannot populate the table or answer the specific questions about sample sizes, ground truth establishment, expert qualifications, or MRMC studies. The document focuses on demonstrating substantial equivalence to a predicate device based on similar intended use and technical characteristics, with modifications described as "additional features for user convenience" that "do not raise the questions of safety or effectiveness."

    Here's a breakdown of what can be extracted and what information is missing:

    1. Table of Acceptance Criteria and Reported Device Performance:

    Acceptance CriteriaReported Device Performance
    Not specified in the document. The document states: "The device passed all of the tests based on pre-determined Pass/Fail criteria."Not specified quantitatively in the document. The document states: "Verification, validation and testing activities were conducted to establish the performance, functionality and reliability characteristics of the modified devices."

    2. Sample size used for the test set and the data provenance:

    • Sample Size for Test Set: Not specified.
    • Data Provenance: Not specified. (The applicant is based in Republic of Korea, but this does not confirm the data origin).
    • Retrospective or Prospective: Not specified.

    3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

    • Not specified. The document indicates that the software's tools are "meant to be used by trained medical professionals such as radiologist and dentist" and that "Results produced by the software's diagnostic, treatment planning and simulation tools are dependent on the interpretation of trained and licensed radiologists, clinicians and referring physicians as an adjunctive to standard radiology practices for diagnosis." However, this pertains to the intended clinical use, not the ground truth establishment for software validation.

    4. Adjudication method for the test set:

    • Not specified.

    5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:

    • Not specified. The device is described as "dental imaging software that is intended to provide diagnostic tools" and offers "various image processing functions." It is not presented as an AI-powered diagnostic aid that would typically undergo an MRMC study to show human reader improvement with AI assistance. It is classified as "Picture archiving and communications system" (PACS).

    6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:

    • Not explicitly stated. Given its classification as PACS software with "diagnostic tools" and "image processing functions," some standalone performance tests would be expected (e.g., accuracy of measurement tools, image processing fidelity), but no details are provided.

    7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):

    • Not specified.

    8. The sample size for the training set:

    • Not applicable as this documentation describes a PACS/imaging software, not an AI/ML algorithm that requires a separate training set. The changes described are primarily feature additions and graphical updates.

    9. How the ground truth for the training set was established:

    • Not applicable for the same reason as above.

    In summary, the provided 510(k) letter focuses on demonstrating substantial equivalence to a predicate device, primarily through a comparison of intended use and technical specifications. It makes a general statement about performance data collected and tests passed, but it lacks the detailed quantitative information that would typically be available for a device with specific performance claims, especially for AI/ML-driven diagnostics.

    Ask a Question

    Ask a specific question about this device

    K Number
    K192888
    Device Name
    EzOrtho
    Date Cleared
    2020-03-13

    (155 days)

    Product Code
    Regulation Number
    892.2050
    Reference & Predicate Devices
    Why did this record match?
    Applicant Name (Manufacturer) :

    Ewoo Soft Co., Ltd.

    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    EzOrtho is a software indicated for use by dentists who provide orthodontic treatment for image analysis, simulation, profilogram, VTO/STO and patient consultation. Results produced by the software's diagnostic, treatment planning and simulation tools are dependent on the interpretation of trained and licensed practitioners or dentists.

    Device Description

    EzOrtho is a 2D orthodontic analysis program developed by Ewoosoft. EzOrtho manages patient information and images for orthodontic analysis. This software also assists in orthodontic treatment by providing accurate image analysis, profilograms, superimpositions, and VTO (visualised treatment objective) and STO (surgical treatment objective). The analyzed results are saved in chart format so that you can easily store and track the treatment and records of each patient.

    EzOrtho is designed to provide a simple and straightforward user interface.

    • Managing Patients and Registering Images EzOrtho offers powerful features related to making schedules and managing patient appointments. In addition, EzOrtho enables you to import images from EzDenti(K190087, K172364, K163533, K161117, K150747), Explorer, or a scanner and easily calibrate the size of the image or arrange multiple film/photo images.
    • . Analyzing and Tracing Images The Landmark Voice Guide and the improved Landmark Input Interface support more accurate and easier tracing.
    • . Establishing Treatment Plans The Morphing feature enables you to predict how the treatment plan established may affect the face of a patient. In addition, the Compare feature enables you to establish a treatment plan by comparing photos before and after the treatment.
    • . Assisting with Patient Consultation EzOrtho provides features to facilitate understanding and communication between doctors and patients during consultation. For example, the Superimposition feature displays the changes visually due to the treatment and the Gallery feature plays a slide show with multiple images of patients.
    AI/ML Overview

    The EzOrtho device's acceptance criteria and the study proving it meets them are described below:

    1. Table of Acceptance Criteria and Reported Device Performance

    The provided document focuses on establishing substantial equivalence to a predicate device (OrthoVision v2.1) rather than defining granular acceptance criteria for specific performance metrics of the new features. However, for the newly added "automatic cephalometric tracing feature," a validation test was performed to evaluate its accuracy.

    Acceptance Criteria (Implied for Automatic Cephalometric Tracing):

    FeatureAcceptance Criteria (Implied)Reported Device Performance
    Automatic Cephalometric TracingThe automatic cephalometric tracing feature should demonstrate acceptable accuracy.The validation test concluded that the auto feature demonstrates accuracy. (Specific performance metrics like mean absolute error or agreement rates are not provided in this summary.)
    Overall Software PerformanceThe device passed all tests based on pre-determined Pass/Fail criteria for software verification/validation and measurement accuracy.The device passed all of the tests.

    2. Sample Size Used for the Test Set and Data Provenance

    • Test Set Sample Size: The document does not specify the exact sample size (number of images or cases) used for the "validation test to evaluate the accuracy of this auto feature."
    • Data Provenance: Not specified in the document.

    3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts

    Not specified in the document.

    4. Adjudication Method for the Test Set

    Not specified in the document.

    5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and the Effect Size of How Much Human Readers Improve with AI vs Without AI Assistance

    No, an MRMC comparative effectiveness study involving human readers with and without AI assistance was not explicitly mentioned or described for the EzOrtho device. The focus of the performance data section is on the device's own accuracy and software validation.

    6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done

    Yes, a standalone performance evaluation of the "automatic cephalometric tracing feature" was done. The document states: "We performed the validation test to evaluate the accuracy of this auto feature." This implies an assessment of the algorithm's performance on its own. It also states that "The users can still adjust the points manually when necessary," indicating that while standalone performance was evaluated, the device is ultimately intended for human-in-the-loop use.

    7. The Type of Ground Truth Used (Expert Consensus, Pathology, Outcomes Data, etc.)

    For the "automatic cephalometric tracing feature," the type of ground truth used is not explicitly stated. However, given the context of cephalometric analysis, it is highly probable that the ground truth would have been established by:

    • Expert Tracings/Measurements: Manual tracings and measurements performed by one or more qualified orthodontic experts.

    8. The Sample Size for the Training Set

    Not specified in the document. The document details a 510(k) submission for a software device, and while it mentions an "auto feature," it does not provide details about model training or the size of any training sets.

    9. How the Ground Truth for the Training Set Was Established

    Not specified in the document. As no information on a training set is provided, the method for establishing its ground truth is also not mentioned.

    Ask a Question

    Ask a specific question about this device

    K Number
    K190087
    Date Cleared
    2019-02-27

    (41 days)

    Product Code
    Regulation Number
    892.2050
    Reference & Predicate Devices
    Why did this record match?
    Applicant Name (Manufacturer) :

    EWOO SOFT Co., Ltd.

    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    EzDent-i is dental imaging software that is intended to provide diagnostic tools for maxillofacial radiographic imaging. These tools are available to view and interpret a series of DICOM compliant dental radiology images and are meant to be used by trained medical professionals such as radiologist and dentist.

    EzDent-i is intended for use as software to acquire, view, save 2D image files, and load DICOM project files from panorama, cephalometric, and intra-oral imaging equipment.

    Device Description

    EzDent-i is a device that provides various features to acquire, transfer, edit, display, store, and perform digital processing of medical images. EzDent-i is a patient & image management software specifically for digital dental radiography. It also provides server/client model so that the users upload and download clinical diagnostic images and patient information from any workstations in the network environment.

    EzDent-i supports general image formats such as JPG and BMP for 2D image viewing as well as DICOM format. For 3D image management, it provides uploading and downloading support for dental CT Images in DICOM format. It interfaces with a 3D imaging software made by our company, the Ez3D-i (K131616 & K150761 & K163533 & K173863) but the EzDent-i itself does not view, transfer or process 3D radiographs.

    EzDent-i supports the acquisition of dental images by interfacing with OpenCV library to import the intra-oral camera images. It also supports the acquisition of CT/Panoramic/Cephalo/Intra-Oral Sensor images by interfacing with X-ray capture software.

    EzDent-i makes it easier to diagnose and analyze 2D dental images with simple and convenient user interface. EzDent-i's main functions are;

    • · Easy and convenient data search function for patient information and clinical images
    • · Various image viewing format for 2D dental images
    • · Various image processing functions including adjustment of brightness and contrast for images
    • · Measurement function of length and angle for 2D images
    • · Dental implant simulation for treatment planning and effective patient consultation
    • · Crown simulation for more effective patient consultation
    • · Print function supporting various viewing output format
    AI/ML Overview

    The provided text is a 510(k) summary for the EzDent-i / E2 / Prora View dental imaging software. Based on the information given, here's an analysis addressing your questions:

    1. A table of acceptance criteria and the reported device performance

    The document states:

    • "Verification, validation and testing activities were conducted to establish the performance, functionality and reliability characteristics of the modified devices. The device passed all of the tests based on pre-determined Pass/Fail criteria."
    • "The subject device and the unmodified device are substantially equivalent, having the same indications for use and functionalities like operation software, computer platform, picture archiving and communication format, image format, image processing features, windowing. image edit, measurements and manipulation."
    • "The differences are that the subject device has changes in PC System Requirement Information Change, Settings upgrade (Annotation, Privacy Policy, adding Help Document, VIEWER tab upgrade (Export Image with Overlay, Saving as IO Sensor Image) and adding SERVICE tab. These differences are not significant since they are additional features for user convenience and do not raise the questions of safety or effectiveness."

    Crucially, this 510(k) summary does not provide a specific table of quantitative acceptance criteria or detailed performance metrics. The core of this submission is to demonstrate substantial equivalence to a previously cleared device (EzDent-i / E2 / ProraView, K172364). The "performance data" section only states that testing was done and passed pre-determined criteria, but it does not specify what those criteria were (e.g., minimum accuracy, sensitivity, specificity for a diagnostic task). The changes appear to be primarily related to software features, user interface, and system compatibility, rather than fundamental diagnostic algorithm performance.

    Therefore, a table of acceptance criteria and reported device performance specific to diagnostic accuracy (e.g., AUC, sensitivity, specificity) cannot be extracted from this document because it's not a de novo submission or a significant change that would necessitate such detailed performance validation for diagnostic claims.

    2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

    The document does not specify the sample size used for any test set or the provenance of the data (country of origin, retrospective/prospective). Given that the submission focuses on substantial equivalence based on feature updates rather than new diagnostic claims, it's unlikely a large-scale diagnostic performance study with specific sample sizes was conducted. The testing likely focused on functional verification and validation of the new software features.

    3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)

    This information is not provided in the document. Since the submission is not focused on validating a new diagnostic algorithm's performance against ground truth, there's no mention of expert-established ground truth or expert qualifications used for such a test.

    4. Adjudication method (e.g. 2+1, 3+1, none) for the test set

    This information is not provided in the document.

    5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance

    No such study (MRMC or otherwise demonstrating human reader improvement with AI assistance) is mentioned or implied in this 510(k) summary. The device's purpose is "to provide diagnostic tools" and is "meant to be used by trained medical professionals such as radiologist and dentist" for viewing and interpreting images. It is not described as an AI-powered diagnostic aid that assists human readers.

    6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done

    This document does not indicate that a standalone algorithm performance study was conducted. The device is described as software that provides tools for human interpretation, not an autonomous diagnostic algorithm.

    7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)

    Since the document does not detail a diagnostic performance study, the type of ground truth used is not specified.

    8. The sample size for the training set

    This information is not provided. The device is described as "dental imaging software," and it's unclear if it even employs machine learning/AI models that would require a "training set" in the conventional sense for diagnostic tasks. The changes described are primarily software features and compatibility updates.

    9. How the ground truth for the training set was established

    Not applicable, as no information about a training set or its ground truth establishment is provided.

    Summary of what's provided for acceptance criteria and proof of meeting them:

    The 510(k) submission for EzDent-i / E2 / Prora View (K190087) focuses on demonstrating substantial equivalence to its predicate device (K172364) following software updates. The acceptance criteria described are primarily functional:

    • The device retains the same indications for use.
    • The device maintains the same functionalities as the predicate, including image acquisition, viewing, saving, loading DICOM files, image processing features (brightness, contrast, measurement), and simulation tools.
    • New features (PC system requirement changes, settings upgrades, viewer tab upgrades, service tab) are deemed "additional features for user convenience" and do not raise new questions of safety or effectiveness.
    • "Verification, validation and testing activities were conducted to establish the performance, functionality and reliability characteristics of the modified devices. The device passed all of the tests based on pre-determined Pass/Fail criteria."

    The proof of meeting those criteria is presented as the statement that "the device passed all of the tests based on pre-determined Pass/Fail criteria" and the FDA's ultimate determination of substantial equivalence. The document does not disclose the specific quantitative criteria or the detailed results of those tests (e.g., specific error rates, precision, or recall for any diagnostic task). This is typical for a 510(k) submission based on substantial equivalence for software updates, where the primary concern is that the changes do not adversely affect existing validated functionality and safety.

    Ask a Question

    Ask a specific question about this device

    K Number
    K173863
    Device Name
    Ez3D-i /E3
    Date Cleared
    2018-02-23

    (65 days)

    Product Code
    Regulation Number
    892.2050
    Reference & Predicate Devices
    Why did this record match?
    Applicant Name (Manufacturer) :

    Ewoo Soft Co., Ltd.

    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    Ez3D-i is dental imaging software that is intended to provide diagnostic tools for maxillofacial radiographic imaging. These tools are available to view and interpret a series of DICOM compliant dental radiology images and are meant to be used by trained medical professionals such as radiologist and dentist.

    Ez3D-i is intended for use as software to load, view and save DICOM images from CT, panorama, cephalometric and intraoral imaging equipment and to provide 3D visualization, 2D analysis, in various MPR (Multi-Planar Reconstruction) functions.

    Device Description

    Ez3D-i is 3D viewing software for prompt and accurate diagnosis dental CT images in DICOM format with a host of useful functions including MPR, 2-dimensional analysis and 3dimensional image reformation. It provides advanced simulation functions such as Implant Simulation, Drawing Canal, and Implant Environ Bone Density, etc for the benefit of effective doctor and patient communication and precise treatment planning. Ez3D-i is a useful tool for an easier diagnosis and analysis by processing a 3D image with simple and convenient user interface. Ez3D-i's main functions are;

    • · Image adaptation through various rendering methods such as Teeth/Bone/Soft tissue/MIP
    • · Versatile 3D image viewing via MPR Rotating, Curve mode
    • · "Sculpt" for deleting unnecessary parts to view only the region of interest.
    • · Implant Simulation for efficient treatment planning and effective patient consultation
    • · Canal Draw to trace alveolar canal and its geometrical orientation relative to teeth.
    • · "Bone Density" test to measure bone density around the site of an implant(s)
    • · Various utilities such as Measurement, Annotation, Gallery, and Report
    • · 3D Volume function to transform the image into 3D Panorama and the Tab has been optimized for Implant Simulation.
    • . Provides the Axial View of TMJ, the Condyle/Fossa images in 3D and the Section images, and supports functions to separate the Condyle/Fossa and display the bone density
    • STO/VTO Simulation to predict orthodontic treatment/ surgery results with 3D Photo image.
    • · Segmentation function to get tooth segmentation data from CT, label each segmented tooth data as an object and utilize them in simulation such as tooth extraction, implant simulation, etc.
    AI/ML Overview

    The provided text is a 510(k) summary for the Ez3D-i / E3 dental imaging software. While it states that performance data exists and the device passed tests based on pre-determined criteria, it does not provide any specific quantitative acceptance criteria or the detailed results of a study to demonstrate that the device meets those criteria.

    Therefore, I cannot fulfill your request for:

    1. A table of acceptance criteria and reported device performance.
    2. Effect size of MRMC study (as no such study is described).
    3. Description of a standalone performance study.

    However, I can extract the following information:

    2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

    • Sample Size: Not specified.
    • Data Provenance: Not specified. The document only mentions that the software loads, views, and saves DICOM images from various dental imaging equipment.

    3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)

    • Not specified. The document only states that the device is "meant to be used by trained medical professionals such as radiologist and dentist."

    4. Adjudication method (e.g. 2+1, 3+1, none) for the test set

    • Not specified.

    7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)

    • Not specified. The document mentions that the software provides "diagnostic tools" and "advanced simulation functions" and that "Results produced by the software's diagnostic, treatment planning and simulation tools are dependent on the interpretation of trained and licensed radiologists, clinicians and referring physicians as an adjunctive to standard radiology practices for diagnosis." This implies reliance on expert interpretation, but the specific type of ground truth used for testing is not detailed.

    8. The sample size for the training set

    • Not specified.

    9. How the ground truth for the training set was established

    • Not specified.

    Additional Information from the Document:

    • Device Type: Dental Imaging Software (Ez3D-i / E3)
    • Intended Use: "to provide diagnostic tools for maxillofacial radiographic imaging... to view and interpret a series of DICOM compliant dental radiology images and are meant to be used by trained medical professionals such as radiologist and dentist." Also intended "to load, view and save DICOM images from CT, panorama, cephalometric and intraoral imaging equipment and to provide 3D visualization, 2D analysis, in various MPR (Multi-Planar Reconstruction) functions."
    • Predicate Device: Ez3D-i / E3 (K163539) by EWOO SOFT Co., Ltd.
    • Safety and Effectiveness Claim: The submission claims substantial equivalence to the predicate device because "The new device and the predicate device are substantially equivalent in the areas of technical characteristics, general function, application, and intended use. The new device does not introduce a fundamentally new scientific technology, and the nonclinical tests demonstrate that the device is safe and effective."
    • New Features in Subject Device: "additional features such as tooth segmentation function and orthodontic simulation function using 3D Photo and segmented data from CT including bone model and tooth model data. Its file import menu and MPR tab also have been upgraded."
    • Justification for Equivalence despite new features: "These differences are not significant since they do not raise any new or potential safety risks to the user or patient and questions of safety or effectiveness."
    • Performance Data Statement: "Verification, validation and testing activities were conducted to establish the performance, functionality and reliability characteristics of the modified devices. The device passed all of the tests based on pre-determined Pass/Fail criteria." (However, the criteria and results are not listed).
    Ask a Question

    Ask a specific question about this device

    K Number
    K173094
    Device Name
    OrthoVision
    Date Cleared
    2017-10-26

    (27 days)

    Product Code
    Regulation Number
    892.2050
    Reference & Predicate Devices
    Why did this record match?
    Applicant Name (Manufacturer) :

    Ewoo Soft Co., Ltd.

    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    Otrho Vision software is indicated for use by orthodontists for image analysis, simulation, profilogram, growth forecast, VTO/STO and patient consultation. Results produced by the software's diagnostic, treatment planning and simulation tools are dependent on the interpretation of trained and licensed practitioners or dentists.

    Device Description

    OrthoVision is a 2D orthodontic analysis and simulation program created by EWOOSOFT. OrthoVision manages patient information and images during orthodontic analysis. This software also assists in orthodontic treatment by providing accurate image analysis, growth forecasts, profilograms, superimpositions, and VTO/STO simulations. The analyzed results are saved in chart format so that you can easily store and track treatment and records of each patient.

    AI/ML Overview

    The provided text is a 510(k) summary for the OrthoVision software. It asserts substantial equivalence to a previous version of the same device. As such, it does not contain the detailed study information typically found in a De Novo or full PMA submission where a new device's performance is rigorously tested against acceptance criteria.

    The document states that "Verification, validation and testing activities were conducted to establish the performance, functionality and reliability characteristics of the modified devices. The device passed all of the tests based on pre-determined Pass/Fail criteria." However, it does not specify what those acceptance criteria were, what tests were conducted, or the results of those tests in a quantifiable manner.

    Therefore, the requested information, specifically acceptance criteria and a study proving the device meets them, is not present in the provided text.

    Here's a breakdown of the specific points missing:

    1. A table of acceptance criteria and the reported device performance: This is not provided. The document only states that tests were conducted and passed.
    2. Sample sized used for the test set and the data provenance: Not provided.
    3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not provided.
    4. Adjudication method: Not provided.
    5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance: Not provided. This type of study is typically done for AI/CAD devices aiming to improve human performance. OrthoVision is described as an "image analysis, simulation, profilogram, growth forecast, VTO/STO and patient consultation" software, whose results are "dependent on the interpretation of trained and licensed practitioners or dentists," suggesting it's a tool for practitioners rather than a direct diagnostic AI that would be subject to MRMC studies demonstrating improvement over human readers.
    6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not provided. Given its description, a standalone performance study in the context of a new diagnostic algorithm is not explicitly relevant here as it's an analysis and simulation tool for interpretation by a human.
    7. The type of ground truth used: Not provided.
    8. The sample size for the training set: Not provided.
    9. How the ground truth for the training set was established: Not provided.
    Ask a Question

    Ask a specific question about this device

    K Number
    K172364
    Date Cleared
    2017-08-22

    (18 days)

    Product Code
    Regulation Number
    892.2050
    Reference & Predicate Devices
    Why did this record match?
    Applicant Name (Manufacturer) :

    Ewoo Soft Co., Ltd.

    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    EzDent-i is dental imaging software that is intended to provide diagnostic tools for maxillofacial radiographic imaging. These tools are available to view and interpret a series of DICOM compliant dental radiology images and are meant to be used by trained medical professionals such as radiologist and dentist.

    EzDent-i is intended for use as software to acquire, view, save 2D image files, and load DICOM project files from panorama, cephalometric, and intra-oral imaging equipment.

    Device Description

    EzDent-i is a device that provides various features to acquire, transfer, edit, display, store, and perform digital processing of medical images. EzDent-i is a patient & image management software specifically for digital dental radiography. It also provides server/client model so that the users upload and download clinical diagnostic images and patient information from any workstations in the network environment.

    EzDent-i supports general image formats such as JPG and BMP for 2D image viewing as well as DICOM format. For 3D image management, it provides uploading and downloading support for dental CT Images in DICOM format. It interfaces with a 3D imaging software made by our company, the Ez3D-i (K131616 & K150761 & K163533) but the EzDent-i itself does not view, transfer or process 3D radiographs.

    EzDent-i supports the acquisition of dental images by interfacing with OpenCV library to import the intra-oral camera images. It also supports the acquisition of CT/Panoramic/Cephalo/Intra-Oral Sensor images by interfacing with X-ray capture software.

    EzDent-i makes it easier to diagnose and analyze 2D dental images with simple and convenient user interface. EzDent-i's main functions are;

    • · Easy and convenient data search function for patient information and clinical images
    • · Various image viewing format for 2D dental images
    • · Various image processing functions including adjustment of brightness and contrast for images
    • · Measurement function of length and angle for 2D images
    • · Dental implant simulation for treatment planning and effective patient consultation
    • · Crown simulation for more effective patient consultation
    • · Print function supporting various viewing output format
    AI/ML Overview

    Based on the provided text, the device in question is the EzDent-i / E2 / ProraView dental imaging software.

    Here's the information regarding its acceptance criteria and the study that proves it:

    1. Table of Acceptance Criteria and Reported Device Performance

    The provided text does not explicitly state specific quantitative acceptance criteria (e.g., specific accuracy, sensitivity, or specificity thresholds) for the EzDent-i software. Instead, it refers to general performance and safety verification.

    Acceptance Criteria CategoryAcceptance Criteria (as implied)Reported Device Performance
    FunctionalityDevice functions as intended for acquiring, viewing, saving 2D images, loading DICOM files, editing, displaying, storing, and performing digital processing of medical images."The device passed all of the tests based on pre-determined Pass/Fail criteria."
    Technical CharacteristicsMaintain technical characteristics similar to the predicate device, including operation software, computer platform, picture archiving and communication format, image format, image processing features, windowing, image edit, measurements, and manipulation."EzDent-i v2.2 described in this 510(k) has the same intended use and the same technical characteristics as the unmodified device." "The new device and predicate device are substantially equivalent in the areas of technical characteristics, general function, application, and intended use."
    Safety and EffectivenessModifications do not raise questions of safety or effectiveness. Not introduce a fundamentally new scientific technology."These differences [additional features] are not significant since they are additional features for user convenience and do not raise the questions of safety or effectiveness." "The new device does not introduce a fundamentally new scientific technology, and the modifications are validated through system level test."

    2. Sample Size Used for the Test Set and Data Provenance

    The document does not specify a sample size for a test set in terms of patient cases or images. It mentions "verification, validation and testing activities" but does not detail the nature or size of these tests.

    The data provenance (country of origin, retrospective/prospective) is not provided in the text.

    3. Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications

    The document does not provide any information about the number of experts used to establish ground truth or their qualifications.

    4. Adjudication Method for the Test Set

    The document does not specify any adjudication method for a test set.

    5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

    The document does not mention a Multi-Reader Multi-Case (MRMC) comparative effectiveness study, nor does it discuss the effect size of AI assistance on human readers.

    6. Standalone Performance Study

    The document describes a standalone performance assessment of the software's functionality and technical characteristics. It states: "Verification, validation and testing activities were conducted to establish the performance, functionality and reliability characteristics of the modified devices. The device passed all of the tests based on pre-determined Pass/Fail criteria." This indicates that the algorithm/software itself was tested for its intended functions. However, it does not provide quantitative results in terms of diagnostic metrics.

    7. Type of Ground Truth Used

    The document does not explicitly state the type of ground truth used for any testing. Given it's a dental imaging software for viewing and interpreting DICOM images, the "ground truth" for its functionality testing would likely involve verification against expected image displays, processing outcomes, and measurement accuracy, but no specific method like "expert consensus" or "pathology" is detailed for a diagnostic evaluation.

    8. Sample Size for the Training Set

    The document does not provide any information about the sample size used for a training set. This is consistent with the device being primarily an image management and viewing software rather than one performing automated diagnostic interpretations with AI/ML that typically require large training datasets.

    9. How Ground Truth for the Training Set Was Established

    Since no training set is mentioned in the context of AI/ML, the document does not describe how ground truth for a training set was established.

    Ask a Question

    Ask a specific question about this device

    K Number
    K163533
    Date Cleared
    2017-01-12

    (27 days)

    Product Code
    Regulation Number
    892.2050
    Reference & Predicate Devices
    Why did this record match?
    Applicant Name (Manufacturer) :

    EWOO SOFT CO., LTD.

    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    EzDent-i is dental imaging software that is intended to provide diagnostic tools for maxillofacial radiographic imaging. These tools are available to view and interpret a series of DICOM compliant dental radiology images and are meant to be used by trained medical professionals such as radiologist and dentist.

    EzDent-i is intended for use as software to acquire, view, save 2D image files, and load DICOM project files from panorama, cephalometric, and intra-oral imaging equipment.

    Device Description

    EzDent-i is a device that provides various features to acquire, transfer, edit, display, store, and perform digital processing of medical images. EzDent-i is a patient & image management software specifically for digital dental radiography. It also provides server/client model so that the users upload and download clinical diagnostic images and patient information from any workstations in the network environment.

    EzDent-i supports general image formats such as JPG and BMP for 2D image viewing as well as DICOM format. For 3D image management, it provides uploading and downloading support for dental CT Images in DICOM format. It interfaces with a 3D imaging software made by our company, the Ez3D-i (K131616, K150761, K161246) but the EzDent-i itself does not view, transfer or process 3D radiographs.

    EzDent-i supports the acquisition of dental images by interfacing with OpenCV library to import the intra-oral camera images. It also supports the acquisition of CT/Panoramic/Cephalo/Intra-Oral Sensor images by interfacing with X-ray capture software.

    EzDent-i makes it easier to diagnose and analyze 2D dental images with simple and convenient user interface. EzDent-i's main functions are;

    • Easy and convenient data search function for patient information and clinical images
    • Various image viewing format for 2D dental images
    • Various image processing functions including adjustment of brightness and contrast for images
    • Measurement function of length and angle for 2D images
    • Dental implant simulation for treatment planning and effective patient consultation
    • Crown simulation for more effective patient consultation
    • Print function supporting various viewing output format
    AI/ML Overview

    The provided text describes a 510(k) premarket notification for a dental imaging software called EzDent-i (also referred to as E2 and ProraView). The primary purpose of this submission is to demonstrate substantial equivalence to a legally marketed predicate device. As such, the document focuses on comparing the new device to the predicate device rather than detailing specific performance studies with acceptance criteria for diagnostic accuracy.

    Therefore, based on the provided text, I cannot provide a table of acceptance criteria and reported device performance related to diagnostic accuracy because such information is not present. The document focuses on performance related to functionality and reliability of the software.

    Here's an analysis addressing the other points based only on the provided text:


    1. Table of Acceptance Criteria and Reported Device Performance

    As noted above, the provided text does not contain specific acceptance criteria or reported device performance metrics related to diagnostic accuracy (e.g., sensitivity, specificity, AUC) for the EzDent-i software. The document states:

    "Verification, validation and testing activities were conducted to establish the performance, functionality and reliability characteristics of the modified devices. The device passed all of the tests based on pre-determined Pass/Fail criteria."

    This indicates that internal performance tests were conducted for functionality and reliability, and the device met its own pre-determined pass/fail criteria for these aspects. However, further details on these criteria or the results are not provided.

    2. Sample Size Used for the Test Set and Data Provenance

    The document does not specify any sample size used for a test set (in the context of evaluating diagnostic performance) or the data provenance (e.g., country of origin, retrospective/prospective). The testing mentioned refers to "performance, functionality and reliability characteristics" of the software itself.

    3. Number of Experts Used to Establish Ground Truth and Qualifications

    The document does not mention the use of experts to establish a ground truth for any diagnostic performance test set. The software is described as providing "diagnostic tools," but its own diagnostic accuracy is not explicitly evaluated in the provided text.

    4. Adjudication Method

    No adjudication method is mentioned, as there is no described diagnostic performance study involving human readers or expert panels.

    5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

    A multi-reader multi-case (MRMC) comparative effectiveness study is not mentioned. The document focuses on the software's features and its substantial equivalence to a predicate device, not on how human readers perform with or without AI assistance.

    6. Standalone (Algorithm Only) Performance Study

    A standalone performance study for the algorithm's diagnostic accuracy is not mentioned. The "performance data" refers to the verification, validation, and testing of the software's functionality and reliability.

    7. Type of Ground Truth Used

    No type of ground truth (e.g., expert consensus, pathology, outcomes data) is mentioned, as no diagnostic performance study is described. The "ground truth" for the software's own functionality and reliability would relate to its adherence to design specifications.

    8. Sample Size for the Training Set

    No sample size for a training set (relevant for machine learning algorithms) is mentioned. The description of the device's technological characteristics does not indicate the use of AI/machine learning that requires a training set in the typical sense. It describes features like "image processing functions including adjustment of brightness and contrast" and "measurement function of length and angle," which are generally rule-based or conventional image processing techniques, not typically requiring large training datasets for their core function.

    9. How Ground Truth for Training Set Was Established

    Since no training set is mentioned, the method for establishing its ground truth is also not described.

    Ask a Question

    Ask a specific question about this device

    K Number
    K163539
    Device Name
    Ez3D-i / E3
    Date Cleared
    2016-12-23

    (7 days)

    Product Code
    Regulation Number
    892.2050
    Reference & Predicate Devices
    Why did this record match?
    Applicant Name (Manufacturer) :

    EWOO SOFT Co., Ltd.

    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    Ez3D-i is dental imaging software that is intended to provide diagnostic tools for maxillofacial radiographic imaging. These tools are available to view and interpret a series of DICOM compliant dental radiology images and are meant to be used by trained medical professionals such as radiologist and dentist.

    Ez3D-i is intended for use as software to load, view and save DICOM images from CT, panorama, cephalometric and intraoral imaging equipment and to provide 3D visualization, 2D analysis, in various MPR (Multi-Planar Reconstruction) functions.

    Device Description

    Ez3D-i is 3D viewing software for dental CT images in DICOM format with a host of useful functions including MPR, 2-dimensional analysis and 3-dimensional image reformation. It provides advanced simulation functions such as Implant Simulation. Drawing Canal, and Implant Environ Bone Density, etc..for the benefit of effective doctor and patient communication and precise treatment planning.

    Ez3D-i is a useful tool for diagnosis and analysis by processing a 3D image with simple and convenient user interface. Ez3D-i's main functions are;

    • Image adaptation through various rendering methods such as Teeth/Bone/Soft tissue/MIP
    • Versatile 3D image viewing via MPR Rotating, Curve mode
    • "Sculpt" for deleting unnecessary parts to view only the region of interest.
    • Implant Simulation for efficient treatment planning and effective patient consultation
    • Canal Draw to trace alveolar canal and its geometrical orientation relative to teeth.
    • "Bone Density" test to measure bone density around the site of an implant(s)
    • Various utilities such as Measurement. Annotation. Gallery, and Report
    • 3D Volume function to transform the image into 3D Panorama and the Tab has been optimized for Implant Simulation.
    • Provides the Axial View of TMJ, the Condyle / Fossa images in 3D and the Section images, and supports functions to separate the Condyle / Fossa and display the bone density.
    AI/ML Overview

    Here's an analysis of the provided text regarding the acceptance criteria and study for Ez3D-i / E3, specifically focusing on the aspects requested:

    Device: Ez3D-i / E3 (Dental imaging software)

    1. Table of Acceptance Criteria and Reported Device Performance

    The provided 510(k) summary does not explicitly list specific quantitative acceptance criteria or detailed reported device performance metrics in a table format. Instead, it makes a general statement about the testing performed.

    Acceptance CriteriaReported Device Performance
    Not explicitly defined as quantitative metrics. Implied criteria relate to functionality, reliability, and safety."The device passed all of the tests based on pre-determined Pass/Fail criteria."
    Substantial equivalence to predicate device in technical characteristics, general function, application, and intended use.The 510(k) concludes that the subject device is substantially equivalent to the predicate device Ez3D-i/E3 (K161246) based on having the same intended use and technical characteristics.
    Differences in new features (USB Model, Quick Settings, Skin Theme, Implant Guide, Dual monitor, 3D Object Manager functions) do not raise new safety or effectiveness concerns.The document states these differences are "not significant since they do not raise any new or potential safety risks to the user or patient and questions of safety or effectiveness."

    2. Sample Size Used for the Test Set and Data Provenance

    The document does not specify the sample size used for the test set. It also does not mention the data provenance (e.g., country of origin, retrospective or prospective nature of the data).

    3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications

    The document does not provide any information about the number of experts used to establish ground truth or their qualifications.

    4. Adjudication Method for the Test Set

    The document does not mention any adjudication method used for the test set.

    5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and Effect Size

    The document does not indicate that an MRMC comparative effectiveness study was performed. There is no mention of human readers, AI assistance, or effect sizes related to human performance improvement.

    6. If Standalone (Algorithm Only Without Human-in-the-Loop Performance) Was Done

    The document describes Ez3D-i as "dental imaging software that is intended to provide diagnostic tools...These tools are available to view and interpret... and are meant to be used by trained medical professionals such as radiologist and dentist." It also states "Results produced by the software's diagnostic, treatment planning and simulation tools are dependent on the interpretation of trained and licensed radiologists, clinicians and referring physicians as an adjunctive to standard radiology practices for diagnosis."

    This strongly suggests that the device is intended for human-in-the-loop use, where the software provides tools, and the medical professional performs the interpretation and diagnosis. The document does not explicitly describe a standalone (algorithm only) performance evaluation.

    7. The Type of Ground Truth Used

    The document does not explicitly state the type of ground truth used. Given the nature of the device as a viewing and analysis tool for imaging, it is highly likely that the "ground truth" for its verification and validation would involve:

    • Known image datasets: Using existing DICOM image sets where the anatomical structures, pathologies, or features are already well-established (e.g., through prior consensus reads, surgical confirmation, or other clinical information).
    • Software functionality validation: Testing that the software accurately performs its stated functions (e.g., MPR, 3D visualization, measurements, implant simulation) according to expected outputs, rather than a clinical ground truth for disease detection.

    8. The Sample Size for the Training Set

    The document does not provide any information about a training set or its sample size. This is consistent with the device being primarily a viewing and analysis tool rather than a machine learning-based diagnostic algorithm that requires explicit training data.

    9. How the Ground Truth for the Training Set Was Established

    Since no training set is mentioned, there is no information on how its ground truth might have been established.

    Ask a Question

    Ask a specific question about this device

    K Number
    K161246
    Device Name
    Ez3D-i / E3
    Date Cleared
    2016-05-31

    (28 days)

    Product Code
    Regulation Number
    892.2050
    Reference & Predicate Devices
    Why did this record match?
    Applicant Name (Manufacturer) :

    EWOO SOFT CO., LTD.

    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    Ez3D-i is dental imaging software that is intended to provide diagnostic tools for maxillofacial radiographic imaging. These tools are available to view and interpret a series of DICOM compliant dental radiology images and are meant to be used by trained medical professionals such as radiologist and dentist.

    Ez3D-i is intended for use as software to load, view and save DICOM images from CT, panorama, cephalometric and intraoral imaging equipment and to provide 3D visualization, 2D analysis, in various MPR (Multi-Planar Reconstruction) functions.

    Device Description

    Ez3D-i is 3D viewing software for dental CT images in DICOM format with a host of useful functions including MPR, 2-dimensional analysis and 3-dimensional image reformation. It provides advanced simulation functions such as Implant Simulation, Drawing Canal, and Implant Environ Bone Density, etc..for the benefit of effective doctor and patient communication and precise treatment planning.

    Ez3D-i is a useful tool for diagnosis and analysis by processing a 3D image with simple and convenient user interface. Ez3D-i's main functions are;

    • · Image adaptation through various rendering methods such as Teeth/Bone/Soft tissue/MIP
    • · Versatile 3D image viewing via MPR Rotating, Curve mode
    • · "Sculpt" for deleting unnecessary parts to view only the region of interest.
    • Implant Simulation for efficient treatment planning and effective patient consultation
    • · Canal Draw to trace alveolar canal and its geometrical orientation relative to teeth.
    • · "Bone Density" test to measure bone density around the site of an implant(s)
    • · Various utilities such as Measurement, Annotation, Gallery, and Report
    • · 3D Volume function to transform the image into 3D Panorama and the Tab has been optimized for Implant Simulation.
    • · Provides the Axial View of TMJ, the Condyle/Fossa images in 3D and the Section images, and supports functions to separate the Condyle/Fossa and display the bone density
    AI/ML Overview

    The provided text is a 510(k) summary for the Ez3D-i / E3 dental imaging software. It describes the device, its intended use, and its substantial equivalence to predicate devices. However, it does not contain the detailed performance data, acceptance criteria, or study specifics requested in your prompt.

    The document states:

    • "Verification, validation and testing activities were conducted to establish the performance, functionality and reliability characteristics of the modified devices. The device passed all of the tests based on pre-determined Pass/Fail criteria." (Page 5)

    This statement indicates that performance testing was performed and passed, but it does not provide any specific acceptance criteria, reported device performance metrics, sample sizes, data provenance, ground truth establishment, or details about comparative effectiveness studies.

    Therefore, I cannot fulfill your request for the specific acceptance criteria and study details based purely on the provided text. The document is a regulatory submission summary, not a detailed technical report of the validation study.

    Ask a Question

    Ask a specific question about this device

    Page 1 of 2