Search Results

CASIA2 is a non-contact, high-resolution tomographic and biomicroscopic device intended for the in vivo imaging and measurement of ocular structures in the anterior segment. CASIA2 measures corneal thickness, anterior chamber depth and lens thickness.

The Tomey Cornea/Anterior Segment OCT CASIA2 (CASIA2) is a non-contact, high resolution tomographic and biomicroscopic device indicated for in vivo imaging of ocular structures in the anterior segment. The Tomey Cornea/Anterior Segment OCT CASIA2 is indicated as an aid in the visualization and measurement of anterior segment findings. CASIA2 measures corneal thickness, anterior chamber depth and lens thickness.

This medical device product has functions subject to FDA premarket review (corneal thickness, curvature, anterior chamber depth and lens thickness) as well as functions that are not subject to FDA premarket review. For this application, for the (510(k) exempt functions that are not subject to FDA premarket review, FDA assessed those functions only to the extent that they either could adversely impact the safety and effectiveness of the overall device.

CASIA2 consists of several components: the main unit, AC input power source, a touch panel LCD monitor, an external hard drive (HDD), a mouse and a keyboard.

Here’s a breakdown of the acceptance criteria and the study proving the device meets them, based on the provided FDA 510(k) clearance letter for the Tomey CASIA2.

Device: Tomey Cornea/Anterior Segment OCT (CASIA2)
Measurements evaluated: Central Corneal Thickness (CCT), Anterior Chamber Depth (ACD), and Lens Thickness (LT).

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state pre-defined quantitative acceptance criteria (e.g., "CCT agreement must be within X µm"). Instead, it focuses on demonstrating agreement and precision compared to a legally marketed reference device (LENSTAR LS900). The "acceptance criteria" can be inferred from the study's objective to show substantial equivalence through these performance metrics. The reported device performance is presented as the actual agreement (mean difference and 95% Limits of Agreement - LOA) and precision (Repeatability and Reproducibility %CV).

Therefore, the table below reflects the demonstrated performance and implicitly what was considered acceptable for substantial equivalence.

Note on "Acceptance Criteria": The document implies that meeting or exceeding the performance of the LS900 in terms of precision, and demonstrating good agreement via Bland-Altman analysis, constituted the acceptance for substantial equivalence.

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

• Sample Size for Test Set: A total of 224 subjects were enrolled and completed the study for precision and agreement testing.
  • 55 subjects in the normal group
  • 60 subjects in the cataract group
  • 109 subjects in the special eyes group (eyes without a natural lens or eyes containing artificial materials)
    N for specific analyses (e.g., Agreement Analysis for LT) varied based on acceptable scans (e.g., N=122 for LT agreement, N=138 for CCT/ACD precision, N=76 for LT precision).
• Data Provenance: The document does not explicitly state the country of origin. It indicates "The subjects of this study had no notable or unexpected/untoward assessments..." which suggests a single clinical site. However, no specific country is mentioned.
• Retrospective or Prospective: The study was a prospective clinical study, as subjects were "enrolled," "randomized," and "assigned" to configurations and sequences, and data was collected during the study.

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

• The document implies that the LENSTAR LS900 device itself served as the reference standard for establishing "ground truth" (or more accurately, the comparator for agreement) for the measured parameters.
• It states that "The clinical site had 3 device operators trained on the devices used in the study."
• Qualifications of Experts: The specific qualifications (e.g., radiologist, ophthalmologist, optometrist expertise, years of experience) of these 3 device operators are not explicitly stated in the provided text.

4. Adjudication Method for the Test Set

• The document states, "Additional scans were taken at the operator's discretion if image quality was unacceptable based on the device DFU and the Tomey CASIA2 Reference Guide and included, missing scans, truncated scans, image defocus, floaters, presence of eye blinks, eye motion, etc. Each device operator had up to 3 attempts to obtain an acceptable scan for each of the required scans."
• This suggests an operational approach to ensure data quality rather than a formal, independent adjudication process (e.g., 2+1/3+1 consensus by experts) for the measurements themselves. The "ground truth" was derived from the in-device measurements of the LS900, not a separate expert review. Therefore, there was no expert consensus-based adjudication method for the measurements.

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

• No, a traditional MRMC comparative effectiveness study was not done.
• The study design was focused on device-to-device agreement and precision (CASIA2 vs. LENSTAR LS900) rather than evaluating how human readers' performance (e.g., diagnostic accuracy) improved with or without AI assistance.
• The CASIA2 is described as a "tomographic and biomicroscopic device intended for the in vivo imaging and measurement of ocular structures," with software providing "quantitative outputs." It does not appear to be an AI-assisted diagnostic aid for image interpretation that would typically require an MRMC study to show human reader benefit.

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

• The study primarily assessed the measurement performance of the CASIA2 device (algorithm/system) in generating quantitative outputs (CCT, ACD, LT) and compared these directly with a reference device. It's implied that these measurements are generated automatically by the device's software.
• The role of the human operators was to acquire an "acceptable scan" based on predefined image quality criteria, not to interpret the images or provide a human "answer" for comparison with an AI-generated reading.
• Therefore, the precision and agreement studies essentially represent the standalone performance of the CASIA2's measurement capabilities compared to the LS900.

7. Type of Ground Truth Used

• The "ground truth" (or clinical reference standard) for comparison was the measurements obtained from the legally marketed predicate/reference device, LENSTAR LS900.
• This is a device-based comparative ground truth, not expert consensus, pathology, or outcomes data. The study aimed to show that the CASIA2's measurements were interchangeable or highly agreeable with those from an established, cleared device.

8. Sample Size for the Training Set

• The document describes a clinical study for validation/testing of the updated software. It does not provide any information about a separate training set size for the development of the algorithms generating these quantitative measurements.
• It only mentions: "The device is a software upgraded version of the predicate K213265 that provides quantitative measurements. All quantitative measurements are derived from OCT images acquired with optical coherence tomography." This implies the software update incorporated algorithms to derive these measurements, but details on their development (including training data) are not provided in this 510(k) summary.

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

• As the document does not describe the training set or its development, there is no information provided on how the ground truth for any training set was established.

Ask a specific question about this device

MYAH is intended to be used by an eye care professional:

• to measure the axial length of the eye in a population age 5 and above
• to capture and store digital images of the meibomian glands under near-infrared illumination in adult population.
  MYAH is not intended to be used in patients with cataracts.

Not Found

I am sorry, but the provided text only contains an FDA 510(k) clearance letter for a device called "MYAH," which is an AC-Powered Slitlamp Biomicroscope. The letter states its indications for use (measuring axial length and capturing meibomian gland images) and mentions it's a Class II device.

However, the document does not contain any information regarding acceptance criteria, study details, sample sizes, expert qualifications, ground truth establishment, or any of the other specific questions you've asked about device performance and validation.

Therefore, I cannot provide the requested information based on the text provided.

Ask a specific question about this device

KOWA SL-19 is intended for use in eye examination of the anterior eye segment, from the cornea epithelium to the posterior capsule. It is used to aid in the diagnosis of diseases or trauma which affect the structural properties of the anterior eye segment.

The KOWA SL-19 is a non-invasive ophthalmic device that is able to illumination, magnification and observation of the human eye.

Illumination light that emitted from a white light source is applied to the eyeball, Refractive media, Eye Anatomy, Ocular Adnexa, Iris, etc. are magnified and observed with a binocular microscope. Fluorescence of the cornea, conjunctiva, etc. can be observed by irradiating background illumination light and irradiating blue illumination light with a built-in light source.

The background White LED function is added to the KOWA SL-19.

The blue filter with white LED for the predicated device is removed, and this function is replaced by blue LED for the KOWA SL-19.

Duration of illumination is lengthened from 140 min to 360 min from predicate device to the KOWA SL-19 due to replace the battery type from AAA battery to AA battery.

The provided text describes a 510(k) premarket notification for the Kowa SL-19, a handheld slit-lamp biomicroscope. This document asserts substantial equivalence to a predicate device (Kowa SL-17) rather than providing a detailed study of an AI/ML-driven device's performance against specific acceptance criteria.

Therefore, the information required to answer your questions regarding acceptance criteria, performance studies, sample sizes, expert involvement, ground truth establishment, and MRMC studies for an AI/ML device is not present in the provided text. The document focuses on the safety and efficacy of a traditional medical device through comparison with a predicate device and adherence to established standards for electrical safety, biocompatibility, software validation, and optical radiation safety.

The acceptance criteria mentioned are related to compliance with recognized standards for safety and performance of a slit lamp, not a new AI-driven diagnostic or assistive technology.

Here's a breakdown of why I cannot fulfill your request based on the provided text:

• No AI/ML Device: The Kowa SL-19 is a hardware device (a slit lamp), not an AI/ML algorithm. Its "software" refers to internal operational software, not an AI model that processes images for diagnosis or assistance.
• No "Acceptance Criteria" for AI Performance: The document does not define specific performance metrics (e.g., sensitivity, specificity, accuracy) for an AI model, nor does it present data demonstrating such performance.
• No "Study Proving Device Meets Acceptance Criteria" for AI: The "Performance Testing" section refers to compliance with safety and performance standards (e.g., IEC, ANSI, ISO), not a clinical study evaluating an AI's diagnostic performance.
• No Discussion of Test Sets, Training Sets, Ground Truth, or Experts for AI: These concepts are relevant to the development and validation of AI/ML models, which are not described here.

In summary, the provided document is a regulatory submission for a conventional medical device and does not contain the information necessary to describe an acceptance criteria and study for an AI/ML-driven device.

Ask a specific question about this device

MY AH is intended for measuring the axial length of the eye in a population age 5 and above and is intended for use under the care of an eye care professional. MYAH is not intended to be used in patients with cataracts.

Not Found

The provided FDA documentation for the Myah device (K211868) does not contain information regarding detailed acceptance criteria, device performance studies, sample sizes, ground truth establishment, expert qualifications, or adjudication methods typically associated with AI/ML device evaluations.

The document is a substantial equivalence (SE) determination letter for a traditional device (AC-powered slitlamp biomicroscope) used for measuring axial length, not an AI/ML diagnostic or assistive device. The letter updates an earlier SE determination to correct typographical errors.

Therefore, I cannot provide the requested information based on the given text.

Ask a specific question about this device

The Myopia Master is an interferometer indicated for measuring the axial length of the eye and is intended as an aid to eye care providers.

The OCULUS Myopia Master integrates the axial length measurement function of the cleared OCULUS Pentacam AXL (K152311) into the cleared PARK 1 device (K073508), which is an ocular device that includes Scheimpflug imaging, autorefractometry and keratometry functionalities. The Myopia Master combines the following measuring functions in one unit: Axial length, Auto-Refractometer, Keratometer.

Here's a breakdown of the acceptance criteria and the study proving the Myopia Master device meets them, based on the provided FDA 510(k) summary:

It's important to note that the provided document is a 510(k) summary for a combination device (Myopia Master integrates functionalities from two previously cleared predicate devices: PARK 1 and Pentacam AXL). The focus of this 510(k) is on demonstrating substantial equivalence to existing devices, rather than establishing de novo performance for a novel device. Therefore, the depth of clinical study details for acceptance criteria might differ from a full PMA or de novo submission. The document primarily emphasizes that the integrated functionalities maintain the safety and effectiveness of the individual predicate devices.

Acceptance Criteria and Reported Device Performance

The document doesn't explicitly lay out "acceptance criteria" in a typical table format with specific numerical targets for accuracy, precision, sensitivity, or specificity. Instead, the "acceptance" is implied through the demonstration of substantial equivalence to predicate devices. The performance data section refers to compliance with safety and technical standards and software validation, but not specific clinical performance metrics with target values for this combined device's primary function of axial length measurement in a clinical population.

Implied Acceptance Criterion: The primary implied acceptance criterion is that the Myopia Master's performance, particularly for axial length measurement, is comparable in safety and effectiveness to its predicate device, the Pentacam AXL.

Reported Device Performance (as demonstrated by comparison to predicate):

Study Details Proving Device Meets Acceptance Criteria

The document states: "Only eyes without any ocular disease were evaluated during the clinical study performed for FDA clearance of this device, so it is unknown whether accuracy and precision when used in patients with ocular pathology will yield acceptable results." This indicates a clinical study was performed, but the details are very brief.

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

   • Sample Size: Not explicitly stated. The document mentions "clinical study," but does not provide the number of subjects or eyes included in the test set.
   • Data Provenance: Not explicitly stated (e.g., country of origin). It states "clinical study performed for FDA clearance of this device," which usually implies data from a regulated clinical trial, likely involving human subjects. The retrospective/prospective nature is also not specified, though clinical studies for clearance are often prospective.

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

   • This information is not provided in the document. For a device like this, the "ground truth" for axial length measurement is typically established by comparative measurements against a highly accurate, established gold standard biometer, rather than expert consensus on images.

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

   • This information is not provided. Given the nature of a biometry device, adjudication methods as typically used for image-based diagnostic AI (e.g., radiologists reviewing images) are less relevant. The "ground truth" would be the measurement from a reference device.

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 study was not indicated or described. This device is an interferometer for measuring axial length, not an AI-assisted diagnostic imaging tool that would typically involve human readers interpreting images. Its clinical value is in providing an objective measurement.

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

   • Yes, implicitly. The device functions as a measurement tool. The "performance" refers to its ability to accurately and precisely measure axial length. While a human operates the device to capture the measurements, the "algorithm only" performance would be its measurement accuracy and precision compared to a gold standard, which would have been evaluated in bench and clinical testing. The document states: "Bench and Clinical testing demonstrate that the Myopia Master is as safe and effective as its predicate devices."

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

   • Not explicitly stated, but highly likely comparative measurements against a clinical gold standard biometer. For devices that measure parameters like axial length, ground truth is typically a direct measurement from a highly accurate, established clinical reference device (e.g., another clinically validated optical biometer) rather than expert review of images or pathology. The document's statement about only eyes without ocular disease suggests a focus on establishing accuracy in a "healthy" or "normal" population.

7. The sample size for the training set:

   • Not provided. As a non-AI measurement device (combining existing technologies), the concept of a "training set" in the context of deep learning models isn't directly applicable for its primary function. If there were internal software algorithms that involved data-driven optimization (e.g., for image processing to find edges for white-to-white), the data used for development or "training" of these algorithms is not detailed. The software uses algorithms adopted from previously cleared devices.

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

   • Not applicable in the context of a typical AI training set. For established measurement technologies, the "ground truth" is defined by the physical principles of measurement and validated against known standards and other devices. The document highlights that "The algorithms and functions for measuring, keratometry and refraction determination are unchanged from the PARK 1, while the algorithms and functions for measuring the axial length were adopted from the Pentacam AXL software." This implies leveraging the pre-established validity of the predicate devices' internal algorithms.

Ask a specific question about this device

The CellChek 20 rc is a software program intended to analyze ophthalmic images captured by the Konan Specular Microscope XVII for examination of corneal endothelium.

Konan Medical has developed the CellChek 20 rc to provide photographic data taken exclusively by the Konan Specular Microscope XVII, CellChek 20, which was cleared by FDA under 510(k) number K191558 on Mar 26, 2020, to research and learning centers for the advancement of ophthalmic sciences and practice. The CellChek 20 rc was developed based on the software program of CellChek 20.

CellChek 20 rc is a software program to analyze ophthalmic images for examination of corneal endothelium. This has the cell counting analysis program, and allows for analysis of the images of the cell distribution of the eye.

The software program is installed on a general-use computer to analyze corneal endothelial images photographed exclusively by the Konan Specular Microscope XVII, CellChek 20. The analysis function is to calculate mainly the cell density, the coefficient of variation of cell area, and the percent hexagonality. In the manual methods, cornea endothelial cells and cell boundaries are actually identified by users. In the automatic methods, this software detects cells and cell boundaries, however, users can modify the detection results. During operating, the users interact with the software by visually placing dots in the center of each of cells and/or by tracing cell boundaries displayed on a computer screen, or use the automatic algorithm.

The provided document primarily focuses on the FDA 510(k) clearance process for the Konan Medical CellChek 20 rc software, establishing its substantial equivalence to a predicate device. It does not contain detailed information about specific acceptance criteria or an explicit study proving performance against those criteria.

However, it does mention that "CellChek 20 rc was developed according to the harmonized standard for software, IEC 62304, and FDA requirements for software and cybersecurity for the 510(k) clearance." It also states that "The following testing was performed on the CellChek 20 rc which was the same software function standard as those for CellChek 20: CellChek 20 rc device was subjected to software testing in accordance with IEC62304."

Based on the information available, here's what can be extracted and what is NOT available:

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

No explicit table of acceptance criteria with corresponding performance metrics is provided in the document. The document focuses on demonstrating substantial equivalence to a predicate device and adherence to general software safety standards.

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

This information is not provided in the document.

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. The document mentions that users can identify cells and boundaries manually or modify automatic detections, implying human interaction with the software's analysis. However, it doesn't specify how ground truth for testing was established.

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

There is no mention of an MRMC comparative effectiveness study in the document. The software allows for both manual and automatic methods for cell analysis, with user modification, but no study is described to quantify human performance improvement with AI assistance.

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

The document mentions both "manual methods" where "cornea endothelial cells and cell boundaries are actually identified by users" and "automatic methods" where "this software detects cells and cell boundaries, however, users can modify the detection results." This implies the algorithm can operate somewhat standalone, but the user is always in a position to review and adjust. However, no formal standalone performance study results, such as sensitivity, specificity, or accuracy, are presented for the algorithm itself.

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

This information is not provided in the document.

8. The sample size for the training set

This information is not provided in the document. The document states that "CellChek 20 rc was developed based on the software program of CellChek 20," suggesting that any machine learning components (if present and requiring training data) would have been integrated or refined from the existing CellChek 20 platform.

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

This information is not provided in the document.

Summary of available information regarding acceptance criteria and study:

The document primarily focuses on regulatory clearance through the 510(k) pathway, emphasizing "substantial equivalence" to a predicate device and adherence to general software development and safety standards (IEC 62304). It does not detail specific performance studies with quantitative acceptance criteria, ground truth establishment, or human reader performance metrics that are typical for demonstrating the effectiveness of an AI-driven medical device. The "study" mentioned is general "software testing in accordance with IEC62304," which is a standard for medical device software life cycle processes, focusing on safety and quality, rather than clinical performance metrics.

Ask a specific question about this device

The Pentacam AXL Wave is intended to image the anterior segment of the eye which includes the cornea, pupil, anterior chamber and lens. It is indicated for the evaluation of

• corneal shape,
• condition of the lens (opaque crystalline lens),
• the anterior chamber angle,
• anterior chamber depth,
• the volume of the anterior chamber,
• anterior or posterior cortical opacity,
• the location of cataracts using cross slit imaging with densitometry,
• corneal thickness,
• axial length,
• white-to-white distance.
• optical aberrations of the eye,
• and retroillumination imaging.

The Pentacam AXL Wave also performs calculations to assist physicians in determining the power of the intraocular lens for implantation.

The Pentacam AXL Wave is intended to image the anterior segment of the eye to measure eye components, such as corneal thickness, anterior chamber depth, corneal cylinder, corneal cylinder axis and white-to-white-distance. The axial length of the eye can be measured by a built-in interferometer. An also integrated aberrometer can determine the optical aberrations of the eye. By using retroillumination imaging, the back-lit eye can be observed.

The measured parameters can be used by physicians to calculate the power of the intraocular lens (IOL) implanted during a cataract surgery.

While rotating around the eye, the Pentacam AXL Wave captures Scheimpflug images of the anterior eye segment through varying axes. The Scheimpflug images created during an examination are transmitted to a connected PC.

Scheimpflug images can be captured within maximum of two seconds. Up to 138,000 genuine height values are measured and analyzed from the Scheimpflug images.

The Scheimpflug images are the basis for the height data which are used to calculate a mathematical 3D model of the anterior eye segment.

The mathematical 3D model, corrected for eye movements, provides the basis for all subsequent analysis.

The axial length of the eye is measured by interferometry measurements are done by a common Hartmann-Shack-Aberrometer. The retroillumination works similar to the illumination method of slit-lamps.

The medical device described, the OCULUS Pentacam AXL Wave, is a combination device that integrates functionalities from two predicate devices: the Pentacam AXL (K152311) and the LUNEAU SAS, VX120 (K143086). The submission focuses on demonstrating substantial equivalence to these predicates, rather than proving performance against specific quantitative acceptance criteria for de novo claims.

Here's an analysis of the provided text in the requested format:

1. Table of Acceptance Criteria and Reported Device Performance

The FDA submission for the Pentacam AXL Wave does not explicitly state quantitative acceptance criteria in terms of sensitivity, specificity, accuracy, or other performance metrics, nor does it provide a direct table of reported device performance against such criteria. Instead, it relies on demonstrating substantial equivalence to predicate devices. The "performance" assessment is based on the device conforming to established standards and showing that its combined functionalities are as safe and effective as the individual functionalities of the predicate devices.

However, the document lists various technical specifications and qualitative aspects that can be inferred as "performance characteristics" that are deemed acceptable because they are equivalent to or do not significantly deviate from the predicates.

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

The document does not specify a sample size for a "test set" or provide details on data provenance (country of origin, retrospective/prospective). The submission relies on "bench and clinical testing" to demonstrate safety and effectiveness and substantial equivalence to predicates, rather than presenting a de novo clinical study with a defined test set for performance metrics.

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

This information is not provided in the document. The submission focuses on technical equivalence and compliance with established standards, not on a clinical validation study requiring expert-established ground truth.

4. Adjudication Method

This information is not provided in the document. As no specific clinical study with expert ground truth establishment is detailed, an adjudication method is not described.

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

A MRMC comparative effectiveness study was not described or presented in the provided text. The document does not discuss human reader improvement with or without AI assistance. This device is an imaging and measurement device, not an AI-powered diagnostic algorithm with a human-in-the-loop component in the context of this submission.

6. Standalone Performance Study (Algorithm Only)

While the device itself is a standalone system, the provided text does not describe or present a separate "standalone" performance study akin to an algorithm-only evaluation for a machine learning model. Instead, it refers to "bench and clinical testing" which demonstrated the overall device's safety and effectiveness and its substantial equivalence to the predicate devices. The "algorithm" here refers to the underlying physics-based calculations (Scheimpflug analysis, interferometry, Hartmann-Shack principle) rather than a machine learning algorithm requiring separate standalone performance assessment.

7. Type of Ground Truth Used

Given the nature of the device (measuring physical characteristics of the eye) and the submission's focus on substantial equivalence to existing devices, the "ground truth" for the device's measurements would inherently be based on:

• Physical principles/measurements: The accuracy of Scheimpflug imaging for corneal shape, interferometry for axial length, and Hartmann-Shack for aberrations are based on established optical and physical principles.
• Comparison to predicate devices: The "ground truth" for proving equivalence is implicitly the performance and measurements obtained from the legally marketed predicate devices (Pentacam AXL and VX120), which themselves would have been validated against established clinical standards or other "gold standard" instruments.
• The document states "bench and clinical testing demonstrate that the Pentacam AXL Wave is as safe and effective as its predicate devices," suggesting that a comparison of measurements against the predicate devices was likely a core part of the "ground truth" for validation.

8. Sample Size for the Training Set

The document does not mention a training set sample size. This indicates that the device's underlying computational methods for image processing and measurement are likely based on established deterministic algorithms (e.g., optical physics, mathematical modeling of 3D structures) rather than iterative machine learning models requiring large training datasets.

9. How Ground Truth for the Training Set Was Established

Since there is no mention of a "training set" in the context of a machine learning model, the concept of establishing ground truth for a training set does not apply in this document. The device uses established optical and measurement principles, where the accuracy of its internal calculations and measurements would be validated through engineering verification and clinical validation against known physical standards or established clinical measurement methods, as reflected in the "bench and clinical testing" reference.

Ask a specific question about this device

The Konan Specular Microscope XVII, CellChek 20, is a non-contact ophthalmic microscope, optical pachymeter, and camera intended for examination of the corneal endothelium and for measurement of the thickness of the cornea.

The Konan Specular Microscope XVII, CellChek 20, is a non-contact ophthalmic microscope, optical pachymeter, and camera intended for examination of corneal endothelium and for measurement of the thickness of the cornea. Cell counting and analysis program are included, and allow for analysis of the images of the cell distribution of the eye.

When photographing the corneal endothelium, the device performs the alignment and automatically focuses by capturing the reflected light from patient's eye with the camera. The device permits visual inspection and photography of the corneal endothelium and measurement of the corneal thickness without any object contacting the eye. It features focusing by means of infrared techniques, as well as computer-assisted cell counting and cell analysis capabilities. The computer functions are also used to aid in setting up the various features of the machine and to aid in photography. Photographic images are temporarily stored in the system's memory and can be preserved by using a printer.

The parts of the device that come into contact with a patient are the forehead rest and the chin rest. Their material is acrylonitrile butadiene styrene (ABS), the same material used in reference device and one with proven biocompatibility.

The function of the software installed in the device is to calculate mainly the cell density, the coefficient of variation of cell area and the percent hexagonality. In the manual methods, Actual identification if the cells and cell boundaries is done by the (physician) user. In the automatic method, the software detects the cells and cell boundaries, however, the user is given the opportunity to make corrections. In use, the user interacts with the software by visually placing dots in the center of cells as or by tracing cell boundaries as they appear or on a screen or uses the automatic algorithm.

The provided text describes the 510(k) summary for the Konan Specular Microscope XVII, CellChek 20. The bulk of the performance study provided is focused on demonstrating agreement, accuracy and precision with a reference device (NONCON ROBO PACHY F&A) and comparing various analysis methods within the subject device itself. It does not present acceptance criteria in a quantitative format nor directly compare the device performance against specific, pre-defined thresholds for acceptance. Instead, it focuses on comparative equivalence.

However, based on the provided clinical study data and the overall goal of demonstrating "substantial equivalence," we can infer the implicit "acceptance criteria" through the statistical results presented, particularly the correlations and comparisons against the reference device and internal method consistency. The study design is primarily a comparative study rather than a standalone AI performance evaluation or a multi-reader, multi-case study with human readers.

Here's an attempt to structure the information based on the request, interpreting the "acceptance criteria" from the study's conclusions on "strong positive correlation" and "superiority/equivalence in precision."

Implicit Acceptance Criteria and Reported Device Performance

The acceptance criteria are implicitly based on demonstrating "strong positive correlation" and "superiority to or equivalence with" the predicate/reference device and consistency across different analysis methods within the subject device for key metrics.

Table of Implicit Acceptance Criteria and Reported Device Performance

• CD: R² = 0.9193 (Strong Positive Correlation)
• CV: R² = 0.5677 (Strong Positive Correlation, although the R² value quantitatively is moderate)
• HEX: R² = 0.2460 (Strong Positive Correlation, although the R² quantitatively is weak)

Peripheral Area:

• CD: R² = 0.9209 (Strong Positive Correlation)
• CV: R² = 0.4974 (Strong Positive Correlation, although the R² quantitatively is moderate)
• HEX: R² = 0.1439 (Weak Positive Correlation, as stated in Table 14 conclusion) |
  | Agreement Across Internal Methods | Strong positive correlation (high R²) and acceptable limits of agreement between different analysis methods (e.g., Trace, Auto Trace) and the Center Method within the subject device. | Center Area - Center Method vs. Others:
• Trace: CD, CV, HEX all showed "Strong Positive Correlation" (R² range 0.8097 to 0.9973)
• Auto Trace: CD, CV showed "Strong Positive Correlation" (R²=0.8479, 0.5682), HEX showed "Positive Correlation" (R²=0.4050)
• Auto Center: CD, CV, HEX all showed "Strong Positive Correlation" (R² range 0.6055 to 0.8504)
• Flex Center: CD, CV, HEX all showed "Strong Positive Correlation" (R² range 0.7587 to 0.9971)
• Auto Flex Center: CD, CV showed "Strong Positive Correlation" (R²=0.8480, 0.6499), HEX showed "Positive Correlation" (R²=0.4564). This aligns with the "Strong/Positive Correlation" statements in Table 15. |
  | Precision (Repeatability & Reproducibility) vs. Reference Device | Repeatability and Reproducibility of the subject device should be superior or equivalent to the predicate/reference device. | Center Area (Center Method vs F&A): CD, CV, HEX for CellChek 20 (Subject Device) were "superior to" F&A (Reference Device) based on lower Repeatability SD, Reproducibility SD, and narrower limits. This general superiority was maintained across other CellChek 20 analysis methods (Auto Trace, Auto Center, Auto Flex Center are "very superior," and Trace/Flex Center are "partially superior or equivalent"). |

Detailed Study Information:

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

   • Sample Size: 80 subjects (patients).
   • Data Provenance: The study was a "prospective clinical study" conducted at an "ophthalmic clinic" that agreed to cooperate. The country of origin is not explicitly stated in the provided text, but Konan Medical, Inc. is based in Japan. Without that specific detail in the document, it's assumed to be from a clinical setting, but the geographical location of that clinic isn't mentioned beyond "ophthalmic clinic."

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

   • The study states: "Three analysts analyzed the examinees' images with each of the 6 methods, Center Method, Auto Center Method, Trace Method, Auto Trace Method, Flex Center Method, Auto Flex Center Method, of CellChek 20, and Center Method of F&A."
   • The qualifications of these "analysts" are not specified. It is implied they are trained individuals capable of performing these analyses, but their explicit qualifications (e.g., "radiologist with 10 years of experience" or similar) are not provided. The document mentions that in manual methods, "Actual identification if the cells and cell boundaries is done by the (physician) user," implying physicians are involved in the process, but it doesn't state if the "three analysts" were physicians.

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

   • The document does not describe any adjudication method for establishing a single "ground truth" or reference standard. The "three analysts" each performed their analysis, and the study then compares the subject device's methods (analyzed by these three) with the reference device's method (also analyzed by these three). It appears to be a direct comparison of device outputs without an independent, adjudicated ground truth.

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, a multi-reader, multi-case (MRMC) comparative effectiveness study involving human readers improving with AI assistance vs. without AI assistance was not performed. The study evaluates the device's measurements (Corneal Endothelial Cell Density, Coefficient of Variation, and Hexagonality) against a reference device and compares different analysis methods within the device. There is no mention of human-in-the-loop performance improvement.

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

   • Yes, in a sense. The study assesses the performance of the device's various analysis methods (Trace, Auto Trace, Center, Auto Center, Flex Center, Auto Flex Center) in terms of agreement, accuracy, and precision compared to a reference device. While analysts operate the device and its software, the measurements themselves are output by the device's algorithms. The "Auto Trace," "Auto Center," and "Auto Flex Center" methods specifically involve automated detection, and their performance is evaluated. Thus, the performance of the built-in algorithms for measurement is evaluated.

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

   • The "ground truth" or reference standard for comparison was the output from a legally marketed predicate/reference device, the NONCON ROBO PACHY F&A (K062763), specifically using its Center Method, which was also analyzed by the "three analysts." It is an instrument-based reference standard rather than an independent clinical ground truth like pathology or long-term patient outcomes.

7. The sample size for the training set:

   • The document describes a clinical performance study for the Konan Specular Microscope XVII, CellChek 20 (test set of 80 subjects). It does not provide any information regarding the training set size or methodology for the software algorithms embedded in the device. The algorithms were likely developed and validated internally by the manufacturer prior to this submission study.

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

   • As no information about the training set is provided, how its ground truth was established is also not described in this document.

Ask a specific question about this device

MiiS Horus Eye Anterior Camera is a digital hand-held slit lamp system indicated for non- invasive illumination, magnification, visualization and to record digital photographs and video of anterior segment (including cornea, anterior chamber, and lens) of the human eye and surrounding area.

MiiS Horus Eye Anterior Camera is a digital hand-held slit lamp system indicated for non-invasive illumination, magnification, visualize and to record digital photographs and video of anterior segment (including cornea, anterior chamber, and lens) of the human eye and surrounding area. It is a Li-ion battery-powered optical device. It brings more complete medical records about the static photos as well as the dynamic videos. MiiS Horus Eye Anterior Camera has an LED light source with visible white light. The device is designed with high-resolution lens and 5M pixels CMOS Sensor, faithful rendering color of the anterior segment (including cornea, anterior chamber, and lens) of the human eye and surrounding area. The device can store pictures or videos in memory card, or via the USB, Wi-Fi and Bluetooth transfer pictures or videos to a computer. In addition to rendering images in the 3.5-inch full color TFT-LCD, through the HDMI output, you can connect the device to the big screen (TV, LCD screen) showing the pictures or videos.

MiiS Horus Eye Anterior Camera includes two models. The first model consists of control unit DSC 300 and lens unit DEA 200. The second model consists of control unit DSC 300P and lens unit DEA 200P. Either auto or manual focus can be used in first model while only manual focus is used in the second model.

The control unit DSC 300 includes a cover glass while DSC 300P does not. The contact rim in lens unit DEA 200 is different from that in DEA 200P.

This document does not include information about AI/ML features, acceptance criteria, or ground truth establishment. The device described, MiiS Horus Eye Anterior Camera, is a digital hand-held slit lamp system. It is a traditional medical device for visualization and recording of the anterior segment of the eye, not an AI/ML-powered diagnostic tool.

Therefore, I cannot provide details on acceptance criteria for AI/ML performance, study designs involving AI assistance, or related ground truth methodologies, as these are not relevant to the information provided in the input text.

The closest relevant sections in the provided text are regarding nonclinical tests and optical radiation safety assessment. These sections outline tests performed to ensure the device's safety and functionality in a traditional sense, not related to AI/ML performance metrics.

Specifically, the document states:

• Nonclinical Tests: "The following tests have been performed in support of the substantial equivalence determination: IEC 62304 for Software verification and validation testing. - IEC/EN 60601-1:2005/2006+A1:2012/2013 for electrical safety. - IEC/EN 60601-1-2:2014/2015 for electromagnetic compatibility. - Bluetooth testing for compatibility and functionality. - HDMI compliance test was conducted in compliance with HDMI 1.4b sink and source devices. - ISO 14971:2007 and EN ISO 14971:2012 for risk management. - -ISO 15004-2:2007 for light hazards. ISO10993-5:2009 and ISO10993-10:2010 standards for biocompatibility. The patient contacting parts are the holder of chin rest CR100 and the forehead stopper."
• Clinical Tests: "No clinical studies were performed."
• Optical Radiation Safety Assessment: "The MiiS Horus Eye Anterior Camera was tested according to 15004-2:2007 to determine acceptable light safety limits for both the illumination and background lights. The test results demonstrate the MiiS Horus Eye Anterior Camera is in compliance with the of Group 2 instrument requirements provided by the standard."

These tests confirm the device's compliance with safety and performance standards for a medical imaging device, but not for an AI/ML algorithm's diagnostic accuracy or performance.

Ask a specific question about this device

The OPHTHALMIC YAG LASER SYSTEM YC-200 consists of a slit lamp and the YAG Laser and is indicated for the performance of posterior capsulotomy, pupillary membranectomy, iridotomy (hole in the iris) and selective laser trabeculoplasty.

The OPHTHALMIC YAG LASER SYSTEM YC-200 is an ophthalmic pulsed laser system using a 1,064 nm Q-switched pulsed Nd: YAG laser as the treatment beam source. The system consists of the types, differing only in the available types of laser emission. The two types are collectively referred to as "YC-200" throughout this 510(k). The operation mode available differs depending on the type.

As shown in the above table, the YC-200 S Plus provides the operator with two treatment modes, YAG mode and SLT mode, whereas the YC-200 type provides the operator with a single treatment mode, YAG mode. Hereafter, these two types are collectively referred to as "YC-200".

In YAG mode, treatment using the YAG treatment beam whose wavelength is 1,064 nm is available. This mode is used mainly for posterior capsulotomy and iridotomy. The 360-degree rotating two-aiming-beam system that separates the YAG aiming beam into two beams is used. The focus position is determined according to the alignment of the beams. In YAG mode, single irradiation mode and burst mode are available. In single mode, one shot of the treatment beam is emitted each time the trigger switch is pressed, whereas in burst mode, two or three shots of the treatment beam are emitted each time the trigger switch is pressed. In YAG mode, the focus shift function to shift the focal points of the YAG treatment beam on the basis of the YAG aiming beam is available. This function allows the operator to shift the focal point of the YAG beam to the posterior chamber side compared to the aiming beam in order to prevent pitting of the intraocular lens.

In SLT mode, treatment using the YAG treatment beam whose wavelength is 532 nm is available. This mode is used for selective laser trabeculoplasty. In this mode, a parfocal optical system is used. In the parfocal optical system, the image of an object surface is formed on the target surface. The SLT aiming beam is emitted from the fiber tip (the object surface) so that it appears as a sharply-edged spot on the target surface. The focus position is determined according to the projection status of the beams. In SLT mode, SLT-NAVI that assists the operator in surgery by specifying the laser emission positions and sequence before the treatment is available. The progress status of laser treatment is intuitively displayed in real time in the SLT-NAVI area of the main screen based on the premise that the treatment is proceeding as scheduled.

The system is mainly comprised of the YC-200 main body that incorporates a laser source, and a slit lamp that is similar to the previously cleared SL-2000 (K163564), head rest, the control box that controls laser emission, and a connector box.

To use the YC-200, the operator should first adjust the focus of the eyepieces to the opera-tor's refractive error and adjusts the eyepieces to the operator's pupillary distance. The operator instructs the patient to place his or her chinrest, to rest his or her forehead on the forehead rest, and to hold the grips. The operator aligns the level of the patient's eye with the eye level marker, fasten the patient's head with the head belt, and instructs the patient to look at the fixation lamp to stabilize his or her visual axis. The operator looks through the microscope to observe the treatment site. The operator sets laser emission conditions such as laser power output through the control box of the YC-200, turns on the aiming beam, and set the YC-200 to the READY mode. Alignment is achieved when the operator adjusts the joystick and contact lens to align the aiming beam focus with the target position. Finally, the operator presses the hand switch or depresses optional foot switch to emit the treatment beam in the READY mode while observing the operative field with the slit lamp.

This document is a 510(k) Premarket Notification from the FDA regarding the Nidek Ophthalmic Yag Laser System YC-200. This type of document is a regulatory approval, not a clinical study report or a technical performance testing report for an AI/ML device.

Therefore, the document does not contain the information required to answer the prompt regarding "acceptance criteria" and "study that proves the device meets the acceptance criteria" in the context of an AI/ML device's performance.

The provided text describes the regulatory clearance process for a traditional medical device (a laser system), focusing on its substantial equivalence to previously cleared predicate devices based on indications for use, technological characteristics, and various bench tests related to laser safety, electrical safety, and usability. It does not involve AI/ML performance metrics, ground truth establishment, expert adjudication, or MRMC studies.

To directly answer your request based on the provided document, the following points would be "Not Applicable" or "Not Provided":

1. A table of acceptance criteria and the reported device performance: Not applicable for AI/ML performance metrics. The document reviews safety and performance of a laser device against standards (e.g., ISO, IEC).
2. Sample sized used for the test set and the data provenance: Not applicable. The testing described (bench testing) is for device safety and functional performance, not AI model validation on a clinical dataset.
3. Number of experts used to establish the ground truth... and qualifications: Not applicable. Ground truth for AI models is not relevant here.
4. Adjudication method for the test set: Not applicable.
5. If a multi reader multi case (MRMC) comparative effectiveness study was done: Not applicable. This is not an AI-assisted device.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not applicable.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.): Not applicable.
8. The sample size for the training set: Not applicable. This device is not an AI/ML model.
9. How the ground truth for the training set was established: Not applicable.

Summary of what the document does provide:

• Device Name: OPHTHALMIC YAG LASER SYSTEM YC-200
• Indications for Use: Performance of posterior capsulotomy, pupillary membranectomy, iridotomy (hole in the iris), and selective laser trabeculoplasty.
• Regulatory Class: Class II (Product Code: HQF, HJO)
• Predicate Device: Quantel Medical OPTIMIS FUSION YAG, and OPTIMIS FUSION YAG/SLT (K140336)
• Reference Devices: Lightmed Corporation LightLas SeLecTor Deux (K090774), NIDEK Slit Lamp SL-2000 (K163564)
• Testing Conducted (Bench Testing): ISO15004-1 (Ophthalmic), Z80.36 and ISO15004-2 (Light Hazard), ISO 10939 (Slit Lamp), IEC 60601-2-22 and IEC 60825-1 (Laser Product Safety), IEC 62366-1 (Usability), ANSI AAMI ES60601-1 (Electrical Safety), IEC60601-1-2 (Electromagnetic Compatibility). These tests are typically defined by engineering and performance standards, not clinical performance metrics for AI.

Therefore, for the specific request about AI acceptance criteria and study details, this document is not relevant.

Ask a specific question about this device