Search Filters

Search Results

Found 4 results

510(k) Data Aggregation

    K Number
    K222304
    Manufacturer
    Date Cleared
    2022-11-08

    (99 days)

    Product Code
    Regulation Number
    884.4160
    Reference & Predicate Devices
    Why did this record match?
    Reference Devices :

    K150533

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

    The Sonata® Transcervical Fibroid Ablation System 2.2 is intended for diagnostic intrauterine imaging and transcervical treatment of symptomatic uterine fibroids, including those associated with heavy menstrual bleeding.

    Device Description

    The Sonata System 2.2 provides radiofrequency (RF) ablation of uterine fibroids using a transcervical approach that is uterine sparing without incisions or material uterine distension. The system enables a clinician to deliver radiofrequency energy to fibroid tissue resulting in thermal fixation and coagulative necrosis of the tissue. The system combines two technologies - ultrasound for visualization, and radiofrequency energy for ablative therapy - in a single integrated handpiece. The Sonata System is comprised of medical equipment, software, and various single-use and reusable instruments. A single-use Radiofrequency Ablation (RFA) Handpiece attaches to a reusable Intrauterine Ultrasound (IUUS) Probe to provide sonography-guided RF ablation. Once connected, the combination is referred to as the "Treatment Device". The RFA Handpiece connects to the Sonata RF Generator and contains the Needle Electrodes that deliver radiofrequency energy to the target tissue. The IUUS Probe connects to the SMART Tablet and provides diagnostic ultrasound imaging and guidance. Ultrasound guidance is used to localize the fibroids from within the uterine cavity, guide placement of the RFA Handpiece Needle Electrodes into a target fibroid and ensure safety with respect to the serosa. When the Needle Electrodes are anchored within tissue, the physician is able to pivot the IUUS Probe transducer around the Needle Electrodes in order to confirm safety of the uterine serosa through multiple ultrasound planes. The Sonata System allows for treatment planning through the use of a graphical interface and automated control of RF energy delivery. Sonata Graphical Guidance Software (GGS) includes the SMART Guide and integrates treatment planning, targeting, and ablation of fibroids. The SMART Guide displays a real-time graphic overlay on the live ultrasound image for targeting and deployment of radiofrequency ablation.

    AI/ML Overview

    The provided document is a 510(k) summary for the Sonata® Transcervical Fibroid Ablation System 2.2. It describes modifications made to an already cleared device and demonstrates substantial equivalence to its predicate. The critical point here is that this submission is for modifications to a previously cleared device, and thus, it largely leverages the safety and effectiveness data of the predicate device (K211535). The performance testing done for this specific submission focuses on verifying the impact of the changes.

    Here's a breakdown of the requested information based on the provided text:

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

    For this specific 510(k) submission (K222304), the performance testing was focused on the modifications to the device (new sterilization instructions for the IUUS Probe and the addition of the IUUS Probe Connector Protector). The document states:

    "In all cases, the verification and validation testing met the acceptance criteria."

    Therefore, the table will reflect the verification of the changes rather than comprehensive performance data of the entire system (as that was covered in the predicate device's clearance).

    Acceptance Criteria (from the document)Reported Device Performance (as stated in the document)
    For Addition of validated sterilization instructions for the IUUS Probe:Met Acceptance Criteria
    - Risk AnalysisDemonstrated no new risks were identified, and the overall risk profile remains unchanged.
    - Sterilization Validation (for STERIS System 1E and STERIS System 1 EXPRESS)Validated; all acceptance criteria met.
    - Residuals TestingValidated; all acceptance criteria met.
    - Impact on IUUS Probe Use LifeValidated; all acceptance criteria met.
    - Impact on IUUS Probe BiocompatibilityValidated; all acceptance criteria met. (The document globally states the device is biocompatible with intended use in compliance with ISO 10993-1, -5, -10, -11).
    - Impact on Human Factors Engineering analysisValidated; all acceptance criteria met. (The modified Sonata System 2.2 continues to rely on HFE validation of Sonata System 2.1).
    - Electrical safety certification (e.g., ANSI/AAMI ES60601-1, IEC 60601-1-2, etc.)The device continues to comply with the listed electrical safety & EMC standards (ANSI/AAMI ES60601-1:2005, IEC 60601-1-2, IEC 60601-1-6, ANSI AAMI IEC 62366-1, IEC 60601-1-8, ANSI/AAMI IEC 60601-2-2, IEC 60601-2-37, IEC 62304).
    For New Accessory: IUUS Probe Connector Protector:Met Acceptance Criteria
    - Risk AnalysisDemonstrated no new risks were identified, and the overall risk profile remains unchanged.
    - Design verificationValidated; all acceptance criteria met.
    - Connector Protector Life testing (including shipping stress & multiple cycles of simulated use, cleaning, disinfection & sterilization with IUUS Probe)Validated; all acceptance criteria met. The new accessory supports reprocessing of the IUUS Probe and provides a water-tight cover for the IUUS Probe electrical connector during liquid reprocessing procedures.
    - Human Factors Engineering AnalysisValidated; all acceptance criteria met. (The modified Sonata System 2.2 continues to rely on HFE validation of Sonata System 2.1).
    Overall Statement:
    Applicable design requirements, FDA recognized standards, and/or methods and criteria used in the predicate device submission."In all cases, the verification and validation testing met the acceptance criteria." and "The modifications... did not raise any new questions of safety and effectiveness." and "The risk analysis demonstrated that no new risks were identified... and the overall risk profile of the device remains unchanged."
    Clinical Trial Acceptance Criteria (from predicate K211535, relied upon by K222304): No specific numerical acceptance criteria are provided in this summary for the clinical endpoints, but the overall conclusion for the predicate implies they were met.Results from IDE G140114 (NCT NCT02228174) with n=147 treated subjects across 22 centers demonstrated the system performs as intended and per specifications, and ablation capability was confirmed with reproducible, discretely demarcated zone of tissue necrosis.

    2. Sample sizes used for the test set and the data provenance

    • For the modifications assessed in K222304 (sterilization and connector protector):

      • Sample Size: Not explicitly stated for each specific test (e.g., how many IUUS probes were tested for use life or biocompatibility with the new sterilization methods). However, the document indicates that "verification and validation testing met the acceptance criteria" for these changes.
      • Data Provenance: Not specified as a country of origin. This refers to bench testing and design control activities rather than human subject data. The validation was conducted by Gynesonics, Inc. as part of their design control procedures.
      • Retrospective/Prospective: These are likely prospective bench tests performed specifically for this submission.
    • For the underlying clinical safety and effectiveness of the Sonata System (relied upon from predicate K211535):

      • Sample Size: 147 treated patients (n=147).
      • Data Provenance: The study (IDE G140114, NCT NCT02228174) included 22 centers with treated patients. The specific countries are not mentioned in this summary but are typically part of a full clinical study report.
      • Retrospective/Prospective: This was a single-arm cohort study, effectively prospective, where each subject served as their own control for assessing treatment outcomes.

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

    • For the modifications assessed in K222304: This refers to bench testing and design verification/validation. Ground truth would be defined by engineering specifications, recognized standards (e.g., ISO, IEC), and established test protocols. The document does not describe the involvement of external experts for establishing ground truth for these specific non-clinical tests, and it's not typically required for this type of verification.
    • For the underlying clinical safety and effectiveness of the Sonata System (relied upon from predicate K211535): The document does not specify the number or qualifications of experts used to establish ground truth for the clinical outcomes. In clinical trials for this type of device, ground truth for fibroid diagnosis and treatment effect would typically be established by the treating physicians (e.g., gynecologists) and potentially independent assessment committees based on imaging (ultrasound, MRI) and patient-reported outcomes.

    4. Adjudication method for the test set

    • For the modifications assessed in K222304: Adjudication methods are not described for these bench tests. Compliance is determined against pre-defined engineering specifications and standard requirements.
    • For the underlying clinical safety and effectiveness of the Sonata System (relied upon from predicate K211535): The document does not specify an adjudication method for the clinical trial endpoints. Clinical trials often employ independent data monitoring committees or clinical events committees for adjudication, but this detail is not present in the 510(k) summary.

    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 Applicable. The Sonata System 2.2 is a medical device for fibroid ablation, not an AI-powered diagnostic system that relies on human readers interpreting images. While it uses "Sonata Graphical Guidance Software (GGS)" including a "SMART Guide" with "graphical overlay on the live ultrasound image for targeting and deployment," this is an integrated guidance system for the physician performing the procedure, not a standalone AI diagnostic tool requiring MRMC studies to assess reader improvement. The "SMART Guide" provides real-time visual assistance during the procedure.

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

    • Not Applicable. The Sonata System is not a standalone algorithm. It is a physical medical device (ablator) with integrated ultrasound imaging and software guidance, requiring direct human operation (human-in-the-loop) during the transcervical fibroid ablation procedure. The "SMART Guide" is an integral part of the user interface provided to the clinician.

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

    • For the modifications assessed in K222304: The ground truth for these specific changes involves adherence to engineering specifications, validated sterilization protocols, biocompatibility standards, and functional performance criteria in bench testing.
    • For the underlying clinical safety and effectiveness of the Sonata System (relied upon from predicate K211535): The clinical trial (IDE G140114) would have relied on a combination of:
      • Clinical outcomes data: Patient symptoms (e.g., heavy menstrual bleeding), quality of life.
      • Imaging: For fibroid identification, sizing, and assessment of treatment effect (e.g., volume reduction of ablated fibroids).
      • Safety data: Adverse event reporting.

    8. The sample size for the training set

    • Not Applicable. This document describes a medical device with integrated software guidance, not a machine learning or AI model that requires a distinct training set in the typical sense. The software (Sonata System Software v2.1.2) is likely developed through traditional software engineering processes, not by training on a large dataset of patient images or outcomes.

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

    • Not Applicable. As this is not an AI/ML system requiring a training set in the typical sense, there is no discussion of how ground truth for a training set was established. The software's functionality and guidance (the "SMART Guide") are based on established medical principles of ultrasound imaging and radiofrequency ablation, not derived from a trained dataset.
    Ask a Question

    Ask a specific question about this device

    K Number
    K211535
    Manufacturer
    Date Cleared
    2021-06-17

    (30 days)

    Product Code
    Regulation Number
    884.4160
    Reference & Predicate Devices
    Why did this record match?
    Reference Devices :

    K150533

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

    The Sonata® Transcervical Fibroid Ablation System 2.2 is intended for diagnostic intrauterine imaging and transcervical treatment of symptomatic uterine fibroids, including those associated with heavy menstrual bleeding.

    Device Description

    The Sonata System 2.2 provides radiofrequency (RF) ablation of uterine fibroids using a transcervical approach that is uterine sparing without incisions or material uterine distension. The system enables a clinician to deliver radiofrequency energy to fibroid tissue resulting in thermal fixation and coagulative necrosis of the tissue. The system combines two technologies - ultrasound for visualization, and radiofrequency energy for ablative therapy - in a single integrated handpiece. The Sonata System is comprised of medical equipment, software, and various single-use and reusable instruments. A single-use Radiofrequency Ablation (RFA) Handpiece attaches to a reusable Intrauterine Ultrasound (IUUS) Probe to provide sonography-guided RF ablation. Once connected, the combination is referred to as the "Treatment Device". The RFA Handpiece connects to the Sonata RF Generator and contains the Needle Electrodes that deliver radiofrequency energy to the target tissue. The IUUS Probe connects to the SMART Tablet and provides diagnostic ultrasound imaging and guidance. Ultrasound guidance is used to localize the fibroids from within the uterine cavity, guide placement of the RFA Handpiece Needle Electrodes into a target fibroid and ensure safety with respect to the serosa. The Sonata System allows for treatment planning through the use of a graphical interface and automated control of RF energy delivery. Sonata Graphical Guidance Software (GGS) includes the SMART Guide and integrates treatment planning, targeting, and ablation of fibroids. The SMART Guide displays a real-time graphic overlay on the live ultrasound image for targeting and deployment of radiofrequency ablation.

    AI/ML Overview

    The provided document is a 510(k) summary for the Sonata® Transcervical Fibroid Ablation System 2.2. It describes changes made to the device compared to its predicate (Sonata System 2.1) and summarizes the testing conducted to demonstrate substantial equivalence.

    However, the document does not contain the detailed information requested regarding acceptance criteria for a study proving the device meets acceptance criteria. Instead, it outlines the company's internal design control procedures, risk analysis, and verification/validation activities for the modifications to the device. It also references prior clinical data from the predicate device and states that no additional clinical data was needed for the 2.2 version.

    Specifically, the document does not provide:

    1. A table of acceptance criteria and reported device performance from a study proving device meets acceptance criteria. It lists "Performance testing - System level (bench)" and "Performance testing - Ablation" but describes the types of tests, not the specific acceptance criteria or quantitative results.
    2. Sample sizes used for a test set in the context of proving performance against acceptance criteria.
    3. Number of experts, their qualifications, or adjudication methods for establishing ground truth for a test set. This type of information is usually relevant for AI/ML device evaluations, which this device is not.
    4. Details on an MRMC comparative effectiveness study or standalone performance. This device is not an AI/ML device subject to these types of studies.
    5. Type of ground truth (e.g., pathology, outcomes data) for a test set.
    6. Sample size for a training set.
    7. How ground truth for a training set was established.

    What the document does provide, relative to your questions:

    • Acceptance Criteria & Performance (General):

      • The document states that "The test methods and acceptance criteria used established methods consisting of FDA recognized standards and/or the same methods and criteria as were used in the predicate device submission; thus, meeting the FDA's requirement for a Special 510(k). In all cases, the verification and validation testing met the acceptance criteria."
      • It lists general safety and performance standards met (e.g., Electrical Safety & EMC: ANSI/AAMI ES60601-1, IEC 60601-1-2, etc.).
      • Acoustic Output: Specific values are given for B Mode: ISPTA ≤ 720 mW/cm² (Value: 162 mW/cm²) and MI ≤ 1.9 (Value: 1.7). These are presented as performance measurements.
    • Study Proving Device Meets Acceptance Criteria:

      • The document focuses on demonstrating that the changes to the Sonata System 2.2 do not raise new questions of safety and effectiveness, relying heavily on the predicate device's existing data.
      • It mentions "verification and validation testing met the acceptance criteria" for the changes, but doesn't provide a specific study report for this, instead summarizing design control activities in Table 5. These are generally internal engineering tests.
      • For clinical data: "No additional clinical study data was needed to validate the Sonata System 2.2." It explicitly states that "Sonata System 2.2 continues to rely on the clinical trial study as Sonata System 2.1."
    • Clinical Trial for Predicate Device (G140114, NCT02228174):

      • Sample Size: n = 147 subjects.
      • Data Provenance: 22 centers with treated patients. (Country of origin not specified, but typically US-based for FDA filings). The trial design was a "Single-arm cohort study with each subject serving as her own control."
      • Ground Truth: For the clinical trial, the "ground truth" would be related to clinical outcomes (safety and effectiveness, e.g., reduction in heavy menstrual bleeding, fibroid volume reduction, adverse events) as assessed by clinicians or objective measurements, not image-based expert consensus. The document does not detail how these clinical outcomes were specifically established, but this is typical for clinical trials where physician assessment and quantitative measurements are used.
      • Retrospective/Prospective: Clinical trials are typically prospective.
    • AI/ML Specific Questions (not applicable to this device, as it's not an AI/ML diagnostic tool):

      • Number of experts, qualifications, and adjudication methods for ground truth (Q3, Q4) are not relevant as this is not an AI/ML device.
      • MRMC comparative effectiveness study (Q5) is not relevant.
      • Standalone performance (Q6) is not relevant in the context of AI/ML algorithms. The device's performance is as an integrated system, not a standalone algorithm.
      • Training set information (Q8, Q9) is not relevant as there's no mention of a machine learning algorithm being trained.

    Summary Table based on provided text (limited details):

    Acceptance Criteria CategoryAcceptance Criteria (from text, often general statements or standards)Reported Device Performance (from text, values if available)Notes
    General ComplianceMet FDA recognized standards and/or methods from predicate submission"In all cases, the verification and validation testing met the acceptance criteria."Refers to internal testing of modifications.
    Electrical Safety & EMCANSI/AAMI ES60601-1:2005/(R)2012, IEC 60601-1-2 Ed 4: 2014-02, etc.Implied compliance by citing standards.
    BiocompatibilityISO 10993-1, -5, -10, -11"Is biocompatible with intended use in compliance with..."
    Usability & Human FactorsIEC 60601-1-6 Ed 3.1 2013-10, ANSI AAMI IEC 62366-1:2015"Sonata System 2.2 continues to rely on HFE validation of Sonata System 2.1."Prior HFE validation was "successfully completed."
    Ablation Performance"System performs as intended and per specifications.""Ablation capability was confirmed and the radiofrequency ablation provides a reproducible, discretely demarcated zone of tissue necrosis."Concluded from early clinical and bench ablation testing (predicate).
    Acoustic Output (B Mode)ISPTA ≤ 720 mW/cm² ; MI ≤ 1.9ISPTA: 162 mW/cm² ; MI: 1.7Meets limits.
    Safety Features (Software)Enhanced safety by enabling automatic RF termination for hazardous situationsRF delivery "terminated without physician intervention."Modification is an "enhancement" to risk mitigation.
    Reusable Cable Durability(Implied) Validation of thorough cleaning/sterilization; cable life testing.Cable Life testing including shipping stress & multiple cycles of simulated use, cleaning, disinfection & sterilization; System Integration Testing completed.These are verification activities for the changes.
    Sterilization Options(Implied) Addition of validated instructions for STERIS V-PRO sterilizers.Sterilization Validation; Residuals Testing; Impact on IUUS Probe Use Life completed.These are verification activities for the changes.

    Study Proving Device Meets Acceptance Criteria (Clinical Trial of Predicate):

    • Sample size: n = 147 subjects.
    • Data Provenance: 22 centers. (Retrospective/Prospective: Typically Prospective for clinical trials). Country not explicitly stated, but for FDA submissions, often includes US sites.
    • Number of experts used to establish ground truth & qualifications: Not applicable for a device that is not an AI/ML diagnostic. The clinical trial would establish efficacy and safety through patient outcomes and physician assessments.
    • Adjudication method for the test set: Not applicable for device performance against a test set in the AI/ML sense. Data in the clinical trial would be collected and analyzed using standard clinical trial methodologies.
    • MRMC comparative effectiveness study: No.
    • Standalone performance: Not applicable in the AI/ML context. This is an integrated surgical system.
    • Type of ground truth used: Clinical outcomes data (e.g., reduction in heavy menstrual bleeding, fibroid volume, adverse events) from a single-arm cohort study where each subject served as her own control.
    • Sample size for training set: Not applicable (not an AI/ML device).
    • How ground truth for training set was established: Not applicable.
    Ask a Question

    Ask a specific question about this device

    K Number
    K193516
    Manufacturer
    Date Cleared
    2020-05-04

    (137 days)

    Product Code
    Regulation Number
    884.4160
    Reference & Predicate Devices
    Why did this record match?
    Reference Devices :

    K150533

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

    The Sonata® Sonography-Guided Transcervical Fibroid Ablation System 2.1 is intended for diagnostic intrauterine imaging and transcervical treatment of symptomatic uterine fibroids, including those associated with heavy menstrual bleeding.

    Device Description

    The Sonata® System 2.1 provides radiofrequency (RF) ablation of uterine fibroids using a transcervical approach that is uterine sparing, without incisions or material uterine distension. The system enables a clinician to deliver radiofrequency energy to fibroid tissue resulting in thermal fixation and coagulative necrosis of the tissue. The system combines two technologies - ultrasound for visualization, and radiofrequency energy for ablative therapy - in a single integrated handpiece. The Sonata® System 2.1is comprised of medical equipment, software, and various single-use and reusable instruments.

    AI/ML Overview

    Here's a breakdown of the acceptance criteria and the study information for the Gynesonics Sonata® Sonography-Guided Transcervical Fibroid Ablation System 2.1, based on the provided FDA 510(k) summary:

    The document (K193516) is a 510(k) premarket notification for the Sonata® Sonography-Guided Transcervical Fibroid Ablation System 2.1. It asserts substantial equivalence to a predicate device (Sonata® System, K173703) rather than presenting a novel device requiring a full clinical trial for de novo acceptance criteria. Therefore, the "acceptance criteria" here largely refer to the successful demonstration of the modified device's performance against its specifications and existing standards, and its equivalence to the predicate device's established safety and effectiveness.

    1. Table of Acceptance Criteria and Reported Device Performance

    Since this is a 510(k) submission asserting substantial equivalence and not a clinical trial establishing new efficacy, the "acceptance criteria" are generally met by demonstrating that the updated device performs equivalently or better than the predicate device and meets relevant performance standards.

    Aspect of Performance / Acceptance CriteriaReported Device Performance (Sonata® System 2.1)Original (Predicate) Performance (Sonata® System K173703)
    Ablation Dimensions (via SMART Guide)Consistent with established Ablation Zone (AZ) and Thermal Safety Border (TSB) in ex vivo non-perfused bovine tissue model.Developed from ex vivo bench ablation data and in vivo peri- and pre-hysterectomy studies.
    Acoustic Output (ISPTA)72.5 mW/cm² (under regulatory limit of 720 mW/cm²)162 mW/cm² (under regulatory limit of 720 mW/cm²)
    Acoustic Output (MI)1.2 (under regulatory limit of 1.9)1.7 (under regulatory limit of 1.9)
    Ultrasound Clinical Measurement AccuracyMeets stated product specification for ultrasound clinical measurement accuracy.(Not explicitly detailed for predicate in this context, but implied to be met)
    Electrical Safety & EMCComplies with updated international standards (e.g., IEC 60601-1 Ed 4)Complied with earlier versions of international standards (e.g., IEC 60601-1 Ed 3)
    BiocompatibilityEstablished for all changed patient-contacting devices; complies with updated ISO 10993 standards.Complied with earlier versions of ISO 10993 standards.
    Human Factors (Treatment Tasks)Summative HF testing validated safety and effectiveness of user interface, labeling, and training for intended users/use contexts.(Not explicitly detailed for predicate in this context, but implied to be met with earlier design)
    Human Factors (Reprocessing Tasks)HF summative testing for reprocessing validated for predicate device, deemed applicable to subject device (due to minor changes).Validated that the system's reprocessing aspects were safe and effective.
    Sterilization EfficacyValidated for components provided sterile (RFA Handpiece, Cable, sterile IUUS Probes).Validated for predicate components.
    Shelf LifeRFA Handpiece: 1 year; RFA Cable: 1 year; Dispersive Electrode: 3 years; Sterile IUUS Probe: 1 year.(Not explicitly detailed for predicate in this context, but established)

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

    The document primarily relies on bench testing for the modified components and leverages clinical data from the predicate device.

    • Bench Testing: Sample sizes are not explicitly stated for most individual bench tests (e.g., "ex vivo testing," "type testing"). However, for the Human Factors (HF) Evaluation for Treatment, 15 gynecologists participated.
    • Data Provenance:
      • Bench testing: Primarily ex vivo (bovine tissue models) and in vitro (phantoms, component testing) conducted by the manufacturer, Gynesonics, Inc.
      • Human Factors Evaluation: Conducted with representative users (gynecologists).
      • Clinical Data (Leveraged): The document explicitly states "No additional clinical study data was needed to validate the Sonata® System 2.1." It leverages clinical data from the predicate device, K173703, which was based on an IDE study (G140114, NCT02228174) with n = 147 subjects across 22 centers. This predicate clinical data would be considered prospective from the original study. The country of origin for the predicate clinical study is not specified in the provided text.

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

    • Bench Testing: "Ground truth" for bench tests is generally based on metrology, physical measurements, and adherence to engineering specifications and international standards. This does not involve human experts establishing ground truth in the diagnostic sense.
    • Human Factors Evaluation: 15 gynecologists participated in the HF study. Their qualifications are described as "representative of typical users involved with performing RFA for fibroids and impacted by device changes." Specific years of experience or board certifications are not provided in this summary.
    • Clinical Data (Leveraged from Predicate): For the predicate clinical study (n=147), ground truth would have been established through standard clinical diagnostic methods for uterine fibroids (imaging, pathology, physician assessment of symptoms and outcomes). The number and qualifications of experts involved in establishing this clinical ground truth are not detailed in this 510(k) summary, as it's leveraging previously cleared data.

    4. Adjudication Method for the Test Set

    • Bench Testing: Adjudication is typically against pre-defined specifications and standards; it does not involve expert consensus in the way a diagnostic study would.
    • Human Factors Evaluation: The HF study assesses the device's usability and user-related risks. The "ground truth" here is whether the device can be used safely and effectively by typical users without critical errors. This is usually determined by observing user performance against a task list and assessing identified use errors by a Human Factors team. An explicit "adjudication method" like 2+1 or 3+1 is not applicable for this type of study.

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

    • No, an MRMC comparative effectiveness study was not done.
    • The Sonata® System 2.1 is an interventional medical device for fibroid ablation, not an AI-assisted diagnostic imaging device. Therefore, the concept of "human readers improve with AI vs. without AI assistance" is not applicable in this context. The integrated ultrasound is for real-time visualization and guidance during the procedure, not primarily for diagnostic interpretation by multiple readers.

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

    • The Sonata® System 2.1 is an interventional device with integrated imaging and ablation capabilities, inherently designed for human-in-the-loop operation. It's not a standalone diagnostic algorithm. The "SMART Guide" is a graphical overlay that assists the clinician, not an autonomous algorithm. Therefore, a standalone performance study without human-in-the-loop is not relevant or applicable for this device.

    7. The Type of Ground Truth Used

    • Benchmark Ground Truth: For the "SMART Guide" development and confirmation, ex vivo ablation dimensions in bovine tissue models served as a physical, measured "ground truth" to ensure the graphical representation (Ablation Zone, Thermal Safety Border) accurately reflects the physical effect of ablation.
    • Conformance Ground Truth: For most other bench tests (electrical safety, biocompatibility, sterilization, mechanical testing), the "ground truth" is conformance to established international standards (e.g., ISO, IEC) and internal product specifications.
    • Usability Ground Truth: For Human Factors studies, the ground truth is the demonstration that the device design, labeling, and training allow intended users to perform critical tasks safely and effectively, avoiding critical use errors.
    • Clinical Ground Truth (Leveraged): For the predicate device's clinical trial (K173703), the ground truth for fibroid treatment effectiveness would have been based on clinical outcomes data (e.g., reduction in heavy menstrual bleeding, fibroid volume reduction, patient symptom scores) and potentially pathology for confirmed fibroid presence.

    8. The Sample Size for the Training Set

    • Training Set for SMART Guide (Algorithm/Graphical Overlay):

      • Ex vivo testing with non-perfused bovine tissue models was used for preliminary development of the Ablation Zone (AZ) and Thermal Safety Border (TSB) dimensions. This would represent the "training" data for these graphical representations.
      • In vivo peri- and pre-hysterectomy studies data were also used to "set final SMART Guide dimensions." The exact sample size for these in vivo studies specifically for SMART Guide development is not given, but they refer to the predicate's clinical experience. (Note: These would be considered part of the training/development of the SMART Guide, not necessarily the training of a machine learning algorithm).
    • No explicit "training set" in the machine learning sense is described for an AI algorithm for diagnostic purposes, as this is primarily a procedural device with graphical guidance, not an AI diagnostic tool.

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

    • For the SMART Guide:
      • Ex vivo tissue models: Physical measurements of ablation zones created in bovine tissue.
      • In vivo peri- and pre-hysterectomy studies: Clinical observation and potentially pathological examination of ablated tissue in human subjects. This would have been established through a combination of imaging (ultrasound, MRI), physician assessment, and potentially macroscopic/microscopic examination of excised tissue if a hysterectomy followed ablation. The specific methodology for establishing this "ground truth" for SMART Guide dimensions is not fully detailed in this 510(k) summary for the updated device, as it leverages prior work.
    Ask a Question

    Ask a specific question about this device

    K Number
    DEN190040
    Device Name
    Caption Guidance
    Manufacturer
    Date Cleared
    2020-02-07

    (164 days)

    Product Code
    Regulation Number
    892.2100
    Type
    Direct
    Reference & Predicate Devices
    Why did this record match?
    Reference Devices :

    K150533, K173780

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

    The Caption Guidance software is intended to assist medical professionals in the acquisition of cardiac ultrasound images. Caption Guidance software is an accessory to compatible general purpose diagnostic ultrasound systems.

    Caption Guidance software is indicated for use in two-dimensional transthoracic echocardiography (2D-TTE) for adult patients, specifically in the acquisition of the following standard views: Parasternal Long-Axis (PLAX), Parasternal Short-Axis at the Aortic Valve (PSAX-AV), Parasternal Short-Axis at the Mitral Valve (PSAX-MV), Parasternal Short-Axis at the Papillary Muscle (PSAX-PM), Apical 4-Chamber (AP4), Apical 5-Chamber (AP5), Apical 2-Chamber (AP2), Apical 3-Chamber (AP3), Subcostal 4-Chamber (SubC4), and Subcostal Inferior Vena Cava (SC-IVC).

    Device Description

    The Caption Guidance software is a radiological acquisition and/or optimization guidance system that provides real-time guidance to the users during acquisition of echocardiography to assist them in obtaining anatomically correct images that represent standard 2D echocardiographic diagnostic views and orientations. Caption Guidance is a software-only device that uses artificial intelligence to emulate the expertise of sonographers.

    Caption Guidance is comprised of several different features that, combined, provide expert guidance to the user. These include:

      1. Quality Meter: The real-time feedback from the Quality Meter advises the user on the expected diagnostic quality of the resulting clip, such that the user can make decisions to further optimize the quality, for example by following the prescriptive guidance feature below.
      1. Prescriptive Guidance: The prescriptive guidance feature in Caption Guidance provides direction to the user to emulate how a sonographer would manipulate the transducer to acquire the optimal view.
      1. Auto-Capture: The Caption Guidance Auto-Capture feature triggers an automatic capture of a clip when the quality is predicted to be diagnostic, emulating the way in which a sonographer knows when an image is of sufficient quality to be diagnostic and records it.
      1. Save Best Clip: This feature continually assesses clip quality while the user is scanning and, in the event that the user is not able to obtain a clip sufficient for Auto-Capture, the software allows the user to retrospectively record the highest quality clip obtained so far, mimicking the choice a sonographer might make when recording an exam.

    The Caption Guidance software was trained using echocardiographic clips from studies performed by trained sonographers. The ideal probe pose for each cardiac view was used to determine the Prescriptive Guidance for maneuvering the probe to the ideal pose.

    The Caption Guidance software is labeled for use with the Terason uSmart 3200t Plus, an FDA 510(k) cleared (K150533) ultrasound system. Caption Guidance is installed on the third-party ultrasound system. The user has access to both the Terason user interface (UI) and the Caption Guidance UI and will be able to switch between the two.

    AI/ML Overview

    Here's a breakdown of the acceptance criteria and the study that proves the device meets them, based on the provided text:

    Acceptance Criteria and Device Performance

    The primary acceptance criteria for the Caption Guidance device focused on the ability of medical professionals without specialized echocardiography training (represented by Registered Nurses, RNs) to acquire echocardiographic exams of sufficient image quality for clinical assessment.

    Table of Acceptance Criteria and Reported Device Performance (Pivotal Study - RN Users):

    #Clinical Parameter AssessedAcceptance Criteria (Implicit: High % sufficient quality)Reported Device Performance (MRMC 95% CI)
    1Qualitative Visual Assessment of Left Ventricular Size(High percentage)98.8% (96.7%, 100%)
    2Qualitative Visual Assessment of Global Left Ventricular Function(High percentage)98.8% (96.7%, 100%)
    3Qualitative Visual Assessment of Right Ventricular Size(High percentage)92.5% (88.1%, 96.9%)
    4Qualitative Visual Assessment of Non-Trivial Pericardial Effusion(High percentage)98.8% (96.7%, 100%)

    The text explicitly states: "The four primary endpoints were satisfied and demonstrated the clinical utility of Caption Guidance for users without specialized echocardiography training." This indicates that the reported percentages met their predetermined success criteria.


    Study Details: Pivotal (Nurse) Study

    2. Sample Size and Data Provenance:
    * Test Set Sample Size: 8 Registered Nurses (RNs) each completed scans of 30 patients, resulting in a total of 240 patient studies (8 RNs * 30 patients).
    * Data Provenance: The study was a prospective clinical study conducted with US-based participants (implied by the FDA De Novo classification and the mention of Northwestern Memorial Hospital for the Human Factors study, which typically suggests local clinical trials).

    3. Number of Experts and their Qualifications for Ground Truth:
    * Number of Experts: Five (5) expert cardiologists.
    * Qualifications: "Expert cardiologists" are described as providing independent assessments. While specific years of experience aren't stated, the term "expert" implies significant experience and board certification, aligning with qualifications needed for interpreting echocardiograms.

    4. Adjudication Method for the Test Set:
    * The panel of five (5) expert cardiologist readers independently provided assessments. The text does not describe an explicit adjudication method like "2+1" or "3+1" to resolve disagreements. Instead, it seems the data presented (e.g., percentages of sufficient quality) are based on a consensus or aggregated proportion from these independent assessments (likely using an MRMC statistical approach, as indicated by "MRMC CI"). "In addition, each of the cardiologist readers were asked to provide a repeat assessment on a certain percentage of the exams or clips they reviewed in order to assess intra-grader variability." This suggests independent review was a cornerstone, with variability being a key consideration rather than forced consensus.

    5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:
    * Yes, a MRMC study was done, but not to directly compare human readers with AI vs. without AI assistance regarding effectiveness gains.
    * The pivotal study used an MRMC design to evaluate the performance of RNs using Caption Guidance against a control arm where trained sonographers acquired images unassisted. The MRMC primary endpoints focused on the proportion of sufficient quality scans achieved by RNs with Caption Guidance.
    * Effect Size of Human Readers Improve with AI vs. without AI Assistance: This specific metric (improvement of human readers who already know how to scan when assisted by AI) was not explicitly reported as a primary endpoint or effect size in the pivotal study results section.
    * However, a descriptive "Specialist (Sonographer) Study" was conducted with 3 expert cardiologists. This study indicated that "sonographers obtained diagnostic quality images in a high proportion of clips from both study and control exams, demonstrating comparable image quality in clips acquired using Caption Guidance compared to unassisted acquisition." This implies that for already trained sonographers, the AI did not significantly improve their image quality but maintained comparability. The key benefit demonstrated by the pivotal study was enabling untrained users to achieve high-quality images.
    * The pivotal study showed that RNs using Caption Guidance could achieve clinical assessments with high success rates, implicitly demonstrating a significant improvement for these untrained users compared to their performance without the device (which would presumably be very low or non-existent for standard views).

    6. Standalone (Algorithm Only) Performance:
    * Yes, standalone algorithm performance testing was done. The section "Algorithm Performance Testing" details this:
    * "The Caption Guidance algorithm was tested for the performance of the supported features: Quality Meter, Auto-Capture, and Save Best Clip."
    * Metrics included "Frame-level prediction of the current pose of the probe, as compared to the ideal pose," "Relative image quality prediction," and "Auto-Capture of clinically-acceptable images and clips."
    * It also tested "Frame-level PG prediction of the probe maneuver needed to acquire an image/frame" and "Clip-level PG prediction."
    * The text notes these results "provide evidence in support of the functionality of Caption Guidance fundamental algorithms" and "demonstrated a low-level verification of the algorithms."

    7. Type of Ground Truth Used:
    * For the pivotal study, the ground truth was primarily expert consensus (or independent assessment for subsequent aggregation/MRMC analysis) by expert cardiologists using the American College of Emergency Physicians (ACEP) scale for echocardiography quality for individual clips, and global assessment of "sufficient information to assess ten clinical parameters" for patient studies.
    * Additionally, quantitative expert measurements by sonographers ("PLAX Sonographer Measurements") served as ground truth for assessing measurability and variability of linear measurements.
    * For the initial algorithm training, "The ideal probe pose for each cardiac view was used to determine the Prescriptive Guidance," implying a form of expert-defined ideal states/positions as ground truth.

    8. Sample Size for the Training Set:
    * The document states: "The Caption Guidance software was trained using echocardiographic clips from studies performed by trained sonographers." A specific sample size for the training set is not provided in the given text.

    9. How the Ground Truth for the Training Set Was Established:
    * "The Caption Guidance software was trained using echocardiographic clips from studies performed by trained sonographers."
    * "The ideal probe pose for each cardiac view was used to determine the Prescriptive Guidance for maneuvering the probe to the ideal pose."
    * This implies the ground truth for training data likely involved:
    * Labeled echocardiographic clips: Experts (sonographers) provided the "correct" (diagnostic quality, specific view) clips.
    * Expert definition of "ideal probe pose": This would serve as the target for the prescriptive guidance and quality meter. This likely involved expert sonographers demonstrating and labeling ideal probe positions and maneuvers for each cardiac view.

    Ask a Question

    Ask a specific question about this device

    Page 1 of 1