Search Results

The Confocal Microprobe Imaging System can enter the human body cavity or surgical channel through an endoscope, allowing confocal laser imaging of the microstructure of tissues, including but not limited to the identification of cells, vessels and their organization or architecture.

The working principle of Confocal Microprobe Imaging System is based on probe-based confocal laser endomicroscopy technology (pCLE). The system combines confocal technology and fiber beam imaging technology. The fiber Optic Microprobe can enter the human cavity through the endoscopic working channel and contact the tissue cells through the object lens at the front end of the Fiber Optic Microprobe. The imaging principle of the device is as follows:

The laser scanning beam emitted by the laser in the Laser Scanning System forms a light source through the grating pinhole and is transmitted to the focal plane of the fluorescent labeled tissue cells through the Fiber Optic Microprobe. The fluorescent substance in the measured tissue cell emits fluorescence under the excitation of the laser. The fluorescence signal is collected by Fiber Optic Microprobe front end object lens and transmitted through the fiber beam microprobe to the detecting hole and then is transmitted to the photomultiplier tube (PMT) of the Photoelectric detector and then to the host for signal analysis and processing. Finally, the image is formed on the computer monitoring screen after software processing.

Light emitted at the top and bottom of the focal plane of the tested tissue produces a large diameter spot (much larger than that of the detecting hole) at the detecting hole, thus only a very small part of the light can be received by the detector through the detecting hole. Moreover, the larger the distance from the focal plane of the object lens, the larger the diffuse spot produced by the non-targeted tissue in the detecting hole and the lesser energy passes through the detecting hole (from 10% to 1%, slowly close to 0%), thus the weaker the unwanted signal is generated on the detector, and smaller the impact is caused by non-targeted tissue. Because confocal microscopy only images the focal plane of the target tissue, it effectively avoids the interference of diffracting light and scattered light, so that it has a higher resolution than ordinary microscopy and has been widely used in biology.

It appears that the provided FDA 510(k) Clearance Letter does not contain detailed information about a clinical study involving human readers or a specific "acceptance criteria" table with reported performance metrics for an AI component.

The document discusses the Confocal Microprobe Imaging System, which is a hardware device for imaging tissues. While it mentions "software" and "cybersecurity," these sections focus on general software validation and cybersecurity considerations, not the performance evaluation of an AI algorithm designed to interpret or analyze the images beyond the device's basic function.

The "Performance Testing" section states that "Performance Verification Test has been conducted in accordance with the internal performance requirements stated in the Performance Validation Scheme (HRD0003932 & HRD0004124)" and lists technical performance requirements like "Field of view, Horizontal resolution, Depth of Observation, Frame rate." These relate to the imaging system's hardware performance, not an AI's diagnostic accuracy.

Therefore,Based on the provided FDA 510(k) clearance letter, I cannot fulfill your request for detailed information regarding acceptance criteria for an AI component and the study that proves the device meets those criteria. The letter primarily addresses the clearance of a Confocal Microprobe Imaging System (hardware), focusing on its substantial equivalence to predicate devices based on technological characteristics, biocompatibility, reprocessing, electrical safety, and general software/cybersecurity validation.

There is no mention of an AI-specific component, its performance criteria, or any clinical studies (e.g., MRMC studies) pertaining to AI algorithm performance within this document. The "Performance Testing" section refers to the optical and functional performance of the imaging system itself, not the diagnostic performance of an AI that might interpret the images generated.

If such an AI component exists, its performance evaluation would typically be described in a separate section with specific metrics like sensitivity, specificity, or AUC, and details about the study design (test set, ground truth, expert adjudication, etc.). This information is absent in the provided text.

Ask a specific question about this device

Cellvizio® 100 Series Systems with Confocal Miniprobes™ are confocal laser systems with fiber optic probes that are intended to allow imaging of the internal microstructure of tissues, including, but not limited to, the identification of cells and their organization or architecture.

The AQ-Flex™ 19 Confocal Miniprobe™ is intended to allow imaging of anatomical tracts, i.e., gastrointestinal and respiratory tracts, accessed by an endoscope, or endoscopic accessories (e.g. aspiration needles used during procedures including EUS-FNA, EBUS-TBNA and TBNA needles).

AQ-Flex™ 19 Confocal Miniprobes™ is used with Cellvizio® 100 Series system to provide imaging of anatomical tracts, i.e., gastrointestinal and respiratory tracts, accessed by an endoscope, or endoscopic accessories. It is designed to be used during transbronchial needle aspiration (TBNA), endoscopic ultrasound transbronchial needle aspiration (EBUS-TBNA) and endoscopic ultrasound-guided fine-needle aspiration (EUS-FNA) procedures.

There are no changes in design, materials, or function between the subject AQ-Flex™ 19 device and the cleared AQ-Flex™ 19 Confocal Miniprobe™ (K123676, K150831, and K172844), except for the length of the AQ-Flex 19 which has been reduced from 4 to 3 meters (AQ-Flex™ 19 Confocal Miniprobe™ has previously been cleared with a length of 4 meters).

A locking accessory already available in the package of the predicate device is used as an aid to secure placement inside the needle used during EUS-FNA procedures and can also be used during TBNA, and EBUS-TBNA procedures.

Here's an analysis of the provided text regarding the acceptance criteria and study for the Cellvizio® 100 Series Confocal laser imaging systems and their Confocal Miniprobe™ AQ-Flex™ 19:

1. Table of Acceptance Criteria and Reported Device Performance

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

The document primarily focuses on bench testing and compatibility assessments, not clinical performance studies with human data in the test set.

• Mechanical tests for sharp edges: 25 samples ("Pass (25/25)")
• Mechanical strength test (insertion/extraction and bending): 25 samples ("Pass (25/25)")
• Protrusion test: 5 samples ("Pass (5/5)")

The provenance of this data is not explicitly stated as country of origin, retrospective, or prospective. Given that these are primarily compatibility and mechanical tests, they are likely prospective bench tests conducted by the manufacturer.

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

The document does not mention human experts being used to establish ground truth for the "test set" in the context of clinical performance. The "ground truth" for the mechanical and compatibility tests would primarily be adherence to engineering specifications and international standards (like ISO 8600-1), which are verified by testers, not expert clinicians establishing a diagnostic truth.

4. Adjudication Method for the Test Set

Not applicable as the reported tests are primarily objective mechanical and compatibility tests against predefined criteria and standards, not subjective assessments requiring adjudication.

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

There is no mention of an MRMC comparative effectiveness study in this document. The device is a confocal laser imaging system for visualizing tissue microstructure, and the submission is for an expanded indication of use for an existing component (AQ-Flex™ 19 Confocal Miniprobe™) in specific endoscopic procedures. There is no AI component or human-in-the-loop performance evaluation described.

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

Not applicable. This device is an imaging tool that provides visual information to a human operator, not an AI algorithm performing a diagnostic task independently.

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

The "ground truth" for the tests reported is primarily:

• Adherence to engineering specifications and standards (e.g., ISO 8600-1 for smooth distal surface, absence of spikes/edges).
• Verification of mechanical integrity and functionality after stress tests.
• Compliance with safety standards (e.g., laser safety).
• Internal validation of performance characteristics (e.g., image quality, resistance to reprocessing).

There is no mention of clinical ground truth such as pathology or outcomes data in this submission for the expanded indication.

8. The Sample Size for the Training Set

Not applicable. This document describes the testing and validation for a hardware device and its accessories, not the development or training of an algorithm or AI system.

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

Not applicable, as there is no training set for an algorithm described in this document.

Ask a specific question about this device

The Cellvizio® 100 Series systems with Confocal Miniprobes™are confocal laser systems with fiber optic probes that are intended to allow imaging of the internal microstructure of tissues including, but not limited to, the identification of cells and vessels and their organization or architecture.

The CranioFlex™ (-,-C) Confocal Miniprobes™ are indicated to provide visualization within central nervous system during cranial diagnostic and therapeutic procedures such as tumor biopsy and resection.

The Cellvizio® 100 Series systems with Confocal Miniprobes™ are confocal laser systems with fiber optic probes that are intended to allow imaging of the internal microstructure of tissues. Confocal Miniprobes™ are intended to be used by qualified physicians to provide visualization of body cavities, organs, and canals during endoscopic and laparoscopic surgical procedures, including robot-assisted procedures and during neurosurgical procedures.

CranioFlex™ (-,-C) Confocal Miniprobes™ are used with Cellvizio® 100 Series systems to provide imaging of the brain through contact of their distal tip with the tissue. They are designed to be used and manually handled during neurosurgical procedures.

This document is a 510(k) Premarket Notification for the Cellvizio 100 Series Systems with Confocal Miniprobes, specifically the CranioFlex™ (-,-C) Confocal Miniprobes, for use in neurosurgical procedures.

Important Note: The provided document is a 510(k) summary, which focuses on demonstrating substantial equivalence to a predicate device. It does not present a study with specific acceptance criteria or performance metrics for an AI/algorithm-based device. The device described (Cellvizio with CranioFlex™ Miniprobes) appears to be an optical imaging system that provides direct visualization, not an AI or algorithm that interprets images or assists human readers. Therefore, many of the requested elements for AI acceptance criteria and studies (like MRMC studies, standalone algorithm performance, training set details, ground truth establishment for AI) are not applicable to this type of medical device submission.

The document primarily focuses on comparing the subject device's technological characteristics and intended use to a predicate neuro-endoscope and previously cleared reference devices from the same manufacturer.

Based on the provided text, here's an attempt to address the requested information, highlighting where the information is not applicable (N/A) due to the nature of the device:

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

The document does not explicitly state quantitative acceptance criteria or performance metrics in the format typically seen for AI/algorithm-based devices (e.g., sensitivity, specificity, accuracy thresholds). The "acceptance" for this 510(k) relies on demonstrating substantial equivalence to a predicate device. This is achieved through qualitative comparisons of design, materials, indications for use, and technological characteristics, along with verification that risks are acceptable and don't raise new questions of safety or effectiveness.

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

The document does not describe a "test set" in the context of an algorithm evaluation with a specific number of cases or data provenance. The assessment for this 510(k) is based on technical comparison and risk analysis, not a prospective clinical study with a defined test set.

• Sample Size for Test Set: N/A (Not an algorithm evaluation study requiring a test set of cases).
• Data Provenance: N/A (The submission primarily relies on design specifications, materials, and comparison to predicate/reference devices, along with in-house testing for sterilization and biocompatibility). There is a mention of a "clinical feasibility study published in a peer reviewed journal" being used to confirm risk assessment, but no details on size, type, or provenance of that dataset are provided.

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

N/A. As this is not an AI/algorithm-based device being validated against a ground truth dataset, this information is not relevant or provided.

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

N/A. Not applicable to this type of device submission.

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

N/A. This is not an AI-assisted diagnostic device; it's an imaging tool that provides direct visualization. Therefore, an MRMC study assessing AI assistance is not applicable.

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

N/A. This is a direct visualization device, not a standalone AI algorithm.

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

N/A. The "ground truth" for this submission is implicitly the safety and effectiveness of the legally marketed predicate device (KARL STORZ Flexible Video-Neuro-Endoscope System) and the established safety and performance of the manufacturer's own reference devices (GastroFlex™ Confocal Miniprobes). The CranioFlex™ Miniprobe is asserted to be fundamentally the same device as the GastroFlex™ but with an expanded indication for use into neurosurgery, hence the comparison to a neuro-endoscope predicate.

8. The sample size for the training set

N/A. This is not an AI/machine learning device.

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

N/A. This is not an AI/machine learning device.

Ask a specific question about this device