LogoFDA 510(k) Search
K Number
K222075
Device Name
CellFX System
Manufacturer
Pulse Biosciences, Inc.
Date Cleared
2022-09-02

(50 days)

Product Code
GEI
Regulation Number
878.4400
Type
Traditional
Panel
SU
Reference & Predicate Devices
K211444
AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

The CellFX® System is intended for dermatological procedures requiring ablation and resurfacing of the skin.

Device Description

The Pulse Biosciences® CellFX® System is a proprietary platform technology. The CellFX System consists of the CellFX Console, CellFX Handpiece, CellFX Treatment Tips, and CellFX Software. The CellFX System delivers nanosecond duration electrical pulses that disrupt the function of cells leading to cell death, while sparing non-cellular tissue. The CellFX System delivers a series of timed, nanosecond electrical pulses (referred to as a "Cycle") to ablate and resurface tissue areas in dermatologic conditions.

The CellFX Console is capable of delivering short electric pulses at amplitudes up to 15 kV and pulse widths up to 700 ns. The electrical energy pulses are applied directly to targeted tissue using sterile Treatment Tips with stainless steel microneedles. The treatment parameters are selected by the user through a user interface on the Touchscreen Display of the CellFX Console.

AI/ML Overview

The provided document is a 510(k) summary for the CellFX System, which is an electrosurgical device for dermatological procedures. It outlines the substantial equivalence determination to a previously cleared predicate device (K211444). The document does not describe an AI/ML-driven device or an acceptance criteria table with reported device performance, sample sizes for test/training sets, expert adjudication methods, MRMC studies, or specific ground truth establishment for AI models.

Therefore, I cannot fulfill the request as the provided text lacks the necessary information about an AI/ML device and its performance evaluation. The document focuses on the CellFX System's electrical safety, biocompatibility, bench testing, software validation, and an animal study to demonstrate its safety and performance for ablation and resurfacing.

The term "acceptance criteria" is used in a general sense for biocompatibility tests and performance of the device in the animal study, but not in the context of an AI/ML model's diagnostic or predictive performance against a ground truth.

Here's what I can extract given the limitations of the provided text, related to the general performance data presented:

General Performance Data from the Document (Not AI/ML Specific):

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

    • Biocompatibility Testing:
      • Acceptance Criteria: All biocompatibility tests (Pyrogenicity, Systemic Toxicity, Sensitization, Irritation, Cytotoxicity, Hemolysis) met their respective acceptance criteria per FDA Guidance.
      • Reported Performance: "All biocompatibility tests met their respective acceptance criteria."
    • Electrical Safety and Electromagnetic Compatibility (EMC):
      • Acceptance Criteria: Compliance with IEC 60601-1, IEC 60601-1-2, IEC 60601-2-2, IEC 60601-1-6, IEC 62366, and IEC 62304.
      • Reported Performance: "All electrical safety and EMC tests passed."
    • Bench Testing:
      • Acceptance Criteria: Device performs as intended and meets product specifications.
      • Reported Performance: "The performance testing for the CellFX System (Console, Handpiece and Tip) verified that the CellFX System performed as intended and met product specifications."
    • Software Verification and Validation Testing:
      • Acceptance Criteria: Supports safety and effectiveness; cybersecurity controls mitigate risk.
      • Reported Performance: "Completed software testing supports the safety and effectiveness of the device." "Cybersecurity controls have been implemented..."
    • Animal Study (Safety and Performance):
      • Acceptance Criteria (Safety): No acute procedural-related adverse events or complications. Full and acceptable healing of treated sites, no effect on draining lymph nodes or non-target organs.
      • Reported Performance (Safety): "All CellFX treatments were successfully completed with no acute procedural-related adverse events or procedural complications..." "Pathology results support the safety of the CellFX System as there was full and acceptable healing of treated sites, no effect on draining lymph nodes or nontarget organs."
      • Acceptance Criteria (Performance): All test articles meet the acceptance criteria; treatment zones successfully achieve degeneration and necrosis of active treatment sites while epidermis remains intact in majority of sites.
      • Reported Performance (Performance): "All test articles met the acceptance criteria for device performance. The treatment zones met the acceptance criteria and successfully achieved degeneration and necrosis of active treatment sites while the epidermis remained intact in the majority of the treatment sites. The device performed as intended."

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

    • Animal Study: 10 Yucatan mini-pigs.
    • Provenance: Animal study (swine skin). The document does not specify a country of origin, nor whether it's retrospective or prospective, but animal studies for regulatory submission are typically prospective.

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

    • Not applicable/Not mentioned for any of the tests described. The "ground truth" for the animal study appears to be a pathological assessment of tissue changes and healing, implicitly performed by qualified veterinary pathologists, though details are not provided.

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

    • Not applicable/Not mentioned.

  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 MRMC study was mentioned. This device is not an AI-assisted diagnostic tool.

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

    • Not applicable. This is not an AI/ML device. The "performance" assessment focuses on the physical and biological effects of the electrosurgical device.

  7. The type of ground truth used:

    • For the animal study: Pathological assessment of tissue degeneration, necrosis, healing, and lack of adverse effects on lymph nodes/organs.

  8. The sample size for the training set:

    • Not applicable. This is not an AI/ML device.

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

    • Not applicable. This is not an AI/ML device.

§ 878.4400 Electrosurgical cutting and coagulation device and accessories.

(a)
Identification. An electrosurgical cutting and coagulation device and accessories is a device intended to remove tissue and control bleeding by use of high-frequency electrical current.(b)
Classification. Class II.