K Number
K210752
Date Cleared
2021-04-14

(30 days)

Product Code
Regulation Number
878.4300
Panel
SU
Reference & Predicate Devices
AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

The HydroMARK Breast Biopsy Site Marker is intended to mark tissue during a percutaneous breast biopsy procedure, be visible under ultrasound for at least 6 weeks, and be permanently visible by x-ray and MRI.

Device Description

The HydroMARK Breast Biopsy Site Marker [subject device] is a two-component marker that provides permanent marking of a breast biopsy site; a resorbable hydrogel component and a metallic component, and is not intended to be removed unless the marked tissue is determined to require surgical removal. The marker is supplied pre-loaded in a sterile, disposable applicator that is compatible with specified commercially available biopsy devices.

The HydroMARK Breast Biopsy Site Marker is a resorbable component that is a highly expandable solid cylinder of polymerized and desiccated hydrogel. The hydrogel has features that are unique and highly desirable for breast tissue marking. The hydrogels absorb fluid, they are readily visible by ultrasound imaging. During a breast biopsy procedure, the marker is deployed through a delivery tool into the cored-out space created by a breast biopsy device. Upon expansion, the hydrogel fills the space and conforms to the site of biopsy. Embedded in the hydrogel is a coiled metallic wire made of Titanium or Stainless Steel. The wire is coiled into loops to provide a unique identifier under ultrasound, x-ray, and MRI imaging. The embedded metallic wire coil is visible under ultrasound for up to 6 weeks and is permanently visible under X-ray and MRI.

AI/ML Overview

This document describes a 510(k) premarket notification for the HydroMARK Breast Biopsy Site Marker. The notification is for modifications to the labeling of an already cleared device, not for a new device or significant changes to its fundamental scientific technology, materials, manufacturing, or intended use.

Therefore, the "acceptance criteria" and "study that proves the device meets the acceptance criteria" in this context are focused on demonstrating that the labeling changes do not raise new or different issues of safety and effectiveness compared to the previously cleared devices.

Acceptance Criteria and Reported Device Performance (Table):

Acceptance CriteriaReported Device Performance
Device meets all system labeling requirementsPassed Document Analysis of Labeling Changes
Device is as safe and effective as predicateDemonstrated through verification testing by document analysis of labeling changes and comparison of technological characteristics
Device performs as well as predicateDemonstrated through verification testing by document analysis of labeling changes and comparison of technological characteristics
No new or different issues of safety and effectiveness arise from labeling changesConclusion based on comparison of technological characteristics and verification testing

Detailed Breakdown of the Study and Related Information:

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

    • Sample Size: Not applicable in the traditional sense of a clinical or performance study involving patient data. The "test set" here refers to the revised labeling documents.
    • Data Provenance: The study involved document analysis of labeling changes to the existing HydroMARK Breast Biopsy Site Marker and its predicate/reference devices (K121113, K130537, K161021). No patient-specific data or data from a specific country of origin is mentioned for this particular submission, as it focuses on regulatory labeling compliance.
  2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

    • Not explicitly stated. The "ground truth" for labeling changes would likely be established by the manufacturer's regulatory affairs and quality assurance teams, in consultation with relevant internal subject matter experts (e.g., medical, engineering) to ensure accuracy, clarity, and compliance with regulations. External regulatory consultants might also be involved. Specific numbers or qualifications of individual experts are not provided in this summary.
  3. Adjudication method for the test set:

    • Not applicable as this was a document analysis assessing compliance with regulatory and safety information, not a comparative review of clinical outcomes by multiple experts. The "adjudication" would be internal review and approval processes within the submitting company to ensure the labeling changes are justified and complete.
  4. 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, an MRMC comparative effectiveness study was not done. This submission is for a breast biopsy site marker (a physical device), not an AI-powered diagnostic tool. The concept of "human readers improve with AI" is not relevant to this device.
  5. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:

    • No, a standalone algorithm performance study was not done. This device is a physical implantable marker, not a software algorithm.
  6. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):

    • The "ground truth" for this submission is regulatory compliance and demonstration that the modified labeling does not introduce new safety or effectiveness concerns, based on the established safety and performance of the physical device (which was previously cleared). This is primarily based on:
      • Comparison to the predicate device's cleared labeling and performance.
      • Internal design verification and risk assessment processes (implied by ISO 14971:2007 mention).
      • Applicable regulatory standards and guidelines for medical device labeling.
  7. The sample size for the training set:

    • Not applicable. This is not a machine learning or AI-based device, so there is no "training set" in the context of data used to train an algorithm.
  8. How the ground truth for the training set was established:

    • Not applicable for the same reason as above.

§ 878.4300 Implantable clip.

(a)
Identification. An implantable clip is a clip-like device intended to connect internal tissues to aid healing. It is not absorbable.(b)
Classification. Class II.