Search Results

The Eyer 2 is accompanied by accessories: frontal module for the ocular surface (1pc), dock station (charging station) (1pc), eye cap (1pc), lens protector (1 pc), storage case (1 pc), cleaning cloth (1 pc), allen wrench (1 pc), quick start guide (1 pc), welcome card (1 pc), shipping box (1 pc), power supply (1 pc), slit-lamp adapter (1 pc), silica gel bags (2 pcs).

Eyer 2 is designed for use in a medical environment by healthcare professionals. Captured images and videos are used for documentation and consultation. The images and videos are securely stored in an internal smartphone application database.

For the retinal function, the Eyer 2 is designed for non-mydriatic fundus imaging. In non-mydriatic imaging, no mydriasis is needed because infrared light is used for targeting the fundus and white light is flashed when an image is taken. The pupil does not respond to the infrared light so examination is convenient for the patient. With small pupils, it is recommended to use mydriatic drops. Eyer 2 has fixation targets for the patient to fixate on during imaging. The middle fixation target provides a macula-center image. It is possible to fix the optical disc in the center by selecting the appropriate point.

For the ocular surface and surrounding areas function, Eyer 2 has an ocular surface module with white, blue, and infrared light sources for imaging the eye surface and surrounding areas; in this configuration, the device does not make contact with the patient.

The transfer of images to a PC is carried out via DICOM, DICOMWEB, FTPS, or local folder connections, with the client responsible for the connection and subsequent storage.

The Eyer 2 energy comes from the smartphone that has a rechargeable Li-Ion battery and is charged when the device is docked on the charge station, which is connected to the mains by a power supply cable.

N/A

Ask a specific question about this device

The Unity DX instrument is a non-contact ophthalmic imaging and analysis device. It is indicated for visualization of anterior and posterior ocular structures and measurement of anterior segment and biometric parameters including:

• Axial Length
• Anterior Chamber Depth
• Central Corneal Thickness
• Lens Thickness

The Reference Image functionality is intended for use as an ocular image capture tool.

The UNITY DX instrument is a non-contact ophthalmic imaging and analysis device. It is indicated for visualization of anterior and posterior ocular structures and measurement of anterior segment and biometric parameters including axial length, anterior chamber depth, corneal thickness, lens thickness, and reference image. The UNITY DX device has four (4) measurement modalities: HP-OCT, wavefront measurement, reference image, and reflective topography.

N/A

Ask a specific question about this device

The OA-2000 is a non-invasive, non-contact biometer intended for obtaining ocular measurements to assist in the determination of the appropriate power of an intraocular lens for implantation. The OA-2000 measures: Axial length, corneal thickness, anterior chamber depth and lens thickness.

The Tomey OA-2000 ophthalmic optical coherence biometer is an ophthalmology device used to measure the length of living tissue utilizing light interference technology and to measure the corneal shape on captured images. This device is designed to measure axial length, anterior chamber depth, corneal thickness, crystalline lens thickness, and corneal shape.

The instrument contains an internal database and has various IOL power formulae applicable to ordinary cataract surgery and/or cataract surgery of eyes with corrected corneal refractive power and provides data necessary to assist the physician in determining IOL power.

The OA-2000 biometer is equipped with a 10.4-inch large touch-screen monitor for ease of use and includes Auto Alignment and Auto Shot functions. Manual measurement is also available in the event that automatic measurement is difficult.

Fourier-domain optical biometry is a high-resolution, non-invasive optical measurement technique based on the principle of low-coherence interference. It is used to determine the distance or depth of reflective structures. Fourier-domain optical biometry is based on the principle of low-coherence interferometry. A low-coherence light source is split into two beams: one directed toward a reference mirror, and the other toward the patient's eye. Light reflected from both the reference and sample arms is combined to produce an interference pattern, but only if the optical path lengths of the two arms are closely matched. This interference signal indicates the location of reflective structures in the sample and is used to reconstruct depth-resolved images or measurements.

N/A

Ask a specific question about this device

TRK-3 OMNIA is a combination of the non-contact tonometer and pachymeter. The device is indicated for automatic measurement of intraocular pressure without contacting the eye (with less than 3 diopters of corneal astigmatism); and measurement of central corneal thickness.

TRK-3 OMNIA is a multiple function device, a combination of the auto refractometer, keratometer, non-contact tonometer, and pachymeter. The device is capable of automatic measurement of the refractive errors of the eye; measurement of the corneal curvature of the eye; measurement of intraocular pressure without contacting the eye (with less than 3 diopters of corneal astigmatism); and measurement of central corneal thickness. The device also calculates corneal diameter and pupil distance.

N/A

Ask a specific question about this device

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