Search Results

The CLARUS 700 ophthalmic camera is indicated to capture, display, annotate and store images to aid in the diagnosis and monitoring of diseases and disorders occurring in the retina, ocular surface and visible adnexa. It provides true color and autofluorescence imaging modes for stereo, widefield, ultra-widefield, and montage fields of view.

The CLARUS 700 angiography is indicated as an aid in the visualization of vascular structures of the retina and the choroid.

The CLARUS 700 is an active, software controlled, high resolution ophthalmic imaging device for In-vivo imaging of the human eye. Imaging modes include True color, Fundus Auto-fluorescence with green excitation, Fundus Auto-fluorescence with blue excitation, Fluorescein Angiography, Stereo External eye and Fluorescein Angiography- Indocyanine green angiography (FA-ICGA). All true color images can be separated into red, green and blue channel images to help enhance visual contrast of details in certain layers of the retina.

The CLARUS 700 angiography imaging aids in the visualization of the vascular structures of the retina and the choroid. With a single capture, CLARUS 700 produces a 90º high definition widefield image. Widefield images are automatically merged to achieve a 135º ultra-widefield of view. The CLARUS 700 makes use of a deep learning algorithm for Optic Nerve Head (ONH) detection. The ultra-widefield montage on CLARUS 700 is no longer dependent just on the patient accurately fixating their gaze on the internal fixation. With the ONH detection, the software will find the optic nerve and determine based on the image(s) captured where the patient was gazing at the point of capture. The CLARUS 700 device allows clinicians to easily review and compare high-quality images captured during a single exam while providing annotation and caliper measurement tools that allow in-depth analysis of eye health. CLARUS 700 is designed to optimize each patient's experience by providing a simple head and chin rest that allows the patient to maintain a stable, neutral position while the operator brings the optics to the patient, facilitating a more comfortable imaging experience. The ability to swivel the device between the right and left eye helps technicians capture an image without realigning the patient. Live IR Preview allows the technician to confirm image quality and screen for lid and lash obstructions, prior to imaging, ensuring fewer image recaptures.

The CLARUS 700 device's principle of operation is Slit Scanning Ophthalmic Camera also referred to as Broad Line Fundus Imaging (BLFI). During image capture, a line of illumination passes through the slit and scans across the retina. A 2D monochromatic camera captures the returned light to image the retina. A single sweep of the illumination is used to illuminate the retina for image capture. Repeated sweeps of near infrared light are used for a live retina view for alignment. Red, green and blue LEDs sequentially illuminate to generate true color images. Blue and green LED illumination enables Fundus Autofluorescence (FAF) imaging. Fluorescein Angiography images are captured with green LED illumination at a wavelength that stimulates fluorescence of the injected sodium fluorescein dye. The principle of operation of CLARUS 700 has not changed since the previous clearance, K191194.

The CLARUS 700 system is mainly comprised of an acquisition device, all-in-one PC, keyboard, mouse, instrument lift table and external power supply.

The device hardware is based on the predicate CLARUS 700 (K191194) hardware. The new ICGA imaging mode on the device required the following hardware changes as stated in the summary above:

• Lightbox for Infrared (IR) Laser
• Modified Slit filter – FA/ICG Slit Excitation Filter – new coating, no change to FA
• Modified Turret Filter 1- FA/ICG Dual Band barrier filter – new coating, no change to FA.
• Added Turret Filter 2 – Added second filter. Same coating as Turret Filter 1 to eliminate cornea reflex band in ICG images with a different shape.
• Added Large Alignment Tool (LAT)
• Added ICG Power Meter Tool

The CLARUS software provides the user the capability to align, capture, review and annotate images. The software has two installation configurations: Software installed on the Instrument (Acquisition & Review) as well as Software installed on a separate 'Review Station' (Laptop or Computer) (only Review).

The DEVICE software version 1.2 is based on the predicate CLARUS 700 software version 1.0 (K191194).

Added capability for DEVICE software version 1.2 include:

• Simultaneous capture of Fluorescein Angiography (FA) + Indocyanine Green Angiography (ICGA)
• Angiography Movie: Capture of multiple pictures in sequence, after a single press of a button. Available for FA, ICGA and Simultaneous FA+ICGA.
• Early Treatment Diabetic Retinopathy Study (ETDRS) – Manual placement of ETDRS grids (7 field ETDRS and Macula ETDRS) over the pictures:
  • The ETDRS 7-fields grid in CLARUS is a display of the standard 7-fields in Color Fundus Photography used to determine an ETDRS (Early Treatment Diabetic Retinopathy Study) level for patients with Diabetic Retinopathy. These 7-fields in and around the macular region are displayed in one single widefield image according to definitions followed by the gold-standard 7-field images using narrow-field fundus cameras.
  • The Macular ETDRS grids display assists in the identification of an ETDRS level in nine subfields centered around the fovea.
• ICGA Boost Mode: user-selectable option for ICGA capture that increase used light to obtain better picture at later phase.
• 8 up view: addition of the possibility to view eight pictures side by side (currently it is only possible to see 1, 2, 4, 16)

The CLARUS 700 device meets the requirements of ISO 10940:2009 standard. The device technical specifications are identical to the predicate device.

The provided text is a 510(k) clearance letter and summary for the CLARUS 700 ophthalmic camera, particularly focusing on the new v1.2 software update. While it discusses the device's intended use, technical characteristics, and various tests performed, it does not contain detailed acceptance criteria or the specific results of a comprehensive clinical study in the format of "acceptance criteria vs. reported device performance."

The document mentions "clinical testing aimed at demonstrating the ability of the new model of CLARUS 700 to image a variety of retinal and choroidal conditions using simultaneous FA and simultaneous ICGA and standalone ICGA." It states that "Our analysis of the grading of angiography images showed that the quality of the images captured by the CLARUS 700 simultaneous FA, simultaneous ICGA, and standalone ICGA were clinically acceptable by three independent graders." However, this is a qualitative statement rather than quantitative acceptance criteria with specific performance metrics.

Therefore, I cannot populate a table of acceptance criteria and reported device performance from the provided text. I can, however, extract related information from the "Clinical Data" section:

Acceptance Criteria and Study Details (Based on provided text)

1. Table of Acceptance Criteria and Reported Device Performance:

Explanation: The document states that the "quality of the images... were clinically acceptable by three independent graders." This implies an implicit acceptance criterion that images must be "clinically acceptable." However, no quantitative threshold (e.g., "90% of images must be clinically acceptable") is provided, nor are specific quantitative performance metrics (e.g., actual percentage of acceptable images).

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

• Test Set Sample Size: Not specified in the provided text.
• Data Provenance: Not specified (e.g., country of origin, retrospective/prospective). The text only states "ZEISS conducted clinical testing."

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

• Number of Experts: Three independent graders.
• Qualifications of Experts: Not specified (e.g., "radiologist with 10 years of experience").

4. Adjudication Method for the Test Set:

• Adjudication Method: Not specified beyond "three independent graders." It does not mention if consensus, majority rule (e.g., 2+1), or another method was used for discordant readings.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done and the Effect Size of how much human readers improve with AI vs without AI assistance:

• MRMC Study: No, an MRMC comparative effectiveness study was not described. The study focused on the image quality produced by the device as assessed by human graders, not on the improvement of human readers' performance with AI assistance.
• Effect Size: Not applicable, as no MRMC study comparing human readers with/without AI assistance was conducted or reported. The device's deep learning algorithm for ONH detection is noted, but its specific impact on reader performance or an MRMC study related to it is not detailed.

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

• Standalone Performance: Not explicitly detailed or quantified. The document notes that "The CLARUS 700 makes use of a deep learning algorithm for Optic Nerve Head (ONH) detection." However, no standalone performance metrics (e.g., specificity, sensitivity, accuracy) for this algorithm are provided in the clinical data summary.

7. The Type of Ground Truth Used:

• Type of Ground Truth: Expert grading/consensus from "three independent graders" on "clinical acceptability" of angiography images. It is not stated if this was against a pathology or outcomes data gold standard.

8. The Sample Size for the Training Set:

• Training Set Sample Size: Not specified in the provided text. The document refers to a "deep learning algorithm for Optic Nerve Head (ONH) detection." While this implies a training set was used, its size is not disclosed.

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

• Ground Truth for Training Set: Not specified.

Ask a specific question about this device

The CIRRUS™ HD-OCT is a non-contact, high resolution tomographic and biomicroscopic imaging device. It is indicated for in-vivo viewing, axial cross-sectional, and three-dimensional imaging and measurement of anterior and posterior ocular structures, including cornea, retinal nerve fiber layer, ganglion cell plus inner plexiform layer, macula, and optic nerve head.

The CIRRUS™ HD-OCT Reference Database is a quantitative tool used for the comparison of retinal nerve fiber layer thickness, macular thickness, ganglion cell plus inner plexiform layer thickness, and optic nerve head measurements to a database of healthy subjects.

CIRRUS™ HD-OCT AngioPlex angiography is indicated as an aid in the visualization of vascular structures of the retina and choroid.

The CIRRUS™ HD-OCT is indicated for use as a diagnostic device to aid in the detection and management of ocular diseases including, but not limited to, macular holes, cystoid macular edema, diabetic retinopathy, age-related macular degeneration, and glaucoma.

The subject device is a computerized instrument that acquires and analyses cross-sectional tomograms of anterior ocular structures (including comea, retinal nerve fiber layer, macula, and optic disc). It employs non-invasive, non-contact, low-coherence interferometry to obtain these high-resolution images. CIRRUS 6000 has a 100kHz scan rate for all structural and angiography scans.

The subject device uses the same optical system, and principle of operation as the previously cleared CIRRUS 6000 (K222200) except for the reference database functionality.

The subject device contains a newly acquired reference database which was collected on K222200. This study data compares macular thickness, ganglion cell thickness, optic disc and RNFL measurements to a reference range of healthy eyes as guided by the age of the patient and /or optic disc size. Reference database outputs are available on Macular Cube 200x200, and Optic Disc Cube 200x20 scan patterns. All other technical specifications have remained the same as the predicate K222200.

Here's a breakdown of the acceptance criteria and the study proving the device meets them, based on the provided text:

Acceptance Criteria and Reported Device Performance

The acceptance criteria are implicitly met by the successful development of the CIRRUS™ HD-OCT Reference Database (RDB) and its ability to provide normative data for comparison. The study aims to establish these reference limits.

Study Details

1. Sample Size and Data Provenance:

   • Test Set (for RDB establishment): 870 subjects had one eye included in the analysis from an initial enrollment of 1000 subjects.
     • Data Provenance: Prospective, multi-site study conducted at eight (8) clinical sites across the USA.

2. Number of Experts and Qualifications for Ground Truth:

   • The document does not specify the number or qualifications of experts used to establish the ground truth for the test set regarding the "healthiness" of the subjects. The eligibility and exclusion criteria (e.g., "presence of any clinicant vitreal, retinal optic nerve, or choroidal disease in the study eye, including glaucoma or suspected glaucoma. This was assessed based on clinical examination and fundus photography.") imply that ophthalmologists or optometrists would have made these clinical judgments, but the specific number or their experience level is not detailed.

3. Adjudication Method for the Test Set:

   • The document does not explicitly describe an adjudication method for determining the "healthy" status of the subjects. It states that inclusion/exclusion was "assessed based on clinical examination and fundus photography" by unnamed personnel at the clinical sites. There is no mention of a consensus process, independent review, or other adjudication for the ground truth.

4. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:

   • No MRMC comparative effectiveness study was done to assess how human readers improve with AI vs. without AI assistance. The study focuses solely on establishing the normative reference database for the device's measurements. The RDB itself is a tool to be used by clinicians, but its impact on clinical decision-making or reader performance was not evaluated in this submission.

5. Standalone Performance:

   • This is a standalone performance study in the sense that the device, equipped with the new reference database, generates the normative values and compares patient data to them. It's the performance of the device's RDB calculation and display, not an AI algorithm performing diagnostic tasks without human input.

6. Type of Ground Truth Used:

   • Clinical Ground Truth: The ground truth for defining "healthy subjects" was based on extensive clinical examination, fundus photography, and adherence to strict inclusion/exclusion criteria (e.g., no known ocular disease, specific visual acuity, IOP, refraction limits). This represents a clinically defined healthy population.

7. Sample Size for the Training Set:

   • The term "training set" is not explicitly used in the context of a machine learning model, as the primary objective was to establish a statistical reference database. The entire dataset of 870 subjects (with qualified scans) was used to develop the reference database. So, the sample size for developing the reference database was 870 subjects.

8. How Ground Truth for the Training Set Was Established:

   • The "ground truth" for the subjects included in the reference database was established by defining them as "healthy subjects" through rigorous inclusion and exclusion criteria applied at 8 clinical sites across the USA. These criteria included:
     • Age 18 years and older
     • Best corrected visual acuity (BCVA) of 20/40 or better in either eye
     • IOP

Ask a specific question about this device

VISULAS yag is intended for use in photodisrupting ocular tissue in the treatment of diseases of the eye, including Posterior capsulotomy, Iridotomy and Posterior Membranectomy.

This device is for Prescription Use (Rx) only.

VISULAS yag uses a Q-switched, flashlamp-pumped solid-state laser for photodisruption treatments of diseases of the eye, including posterior capsulotomy, iridotomy and membranectomy. Laser radiation is generated by means of a neodymium-doped yttrium aluminum garnet (Nd:YAG) gain medium inside the laser source. The emitted laser radiation with a near-infrared wavelength of = 1064 nm has a pulse duration of

I am sorry, but the provided text is a 510(k) summary for a medical device (VISULAS yag), which focuses on demonstrating substantial equivalence to a predicate device rather than presenting a study design with acceptance criteria and device performance results as requested.

The document does not contain:

• A table of acceptance criteria and reported device performance for a specific study.
• Information on sample size, data provenance, number of experts, adjudication methods, MRMC studies, standalone performance, or ground truth for a clinical study.
• Details regarding training set size or how ground truth was established for a training set.

Instead, the document primarily compares the subject device's indications for use and technical characteristics to two predicate devices (Ellex YAG Laser K212630 and VISULAS YAG III K042139) to establish substantial equivalence. It mentions "Non-Clinical Performance Testing" and "functional and system level testing showed that the system met the defined specifications," and "Software verification and validation testing were conducted... All testing passed," but these are general statements and do not provide the detailed study information you've asked for.

Therefore, I cannot fulfill your request based on the provided text.

Ask a specific question about this device

· INFRARED 800 with FLOW 800 Option is a surgical microscope accessory intended to be used with a compatible surgical microscope in viewing and visual assessment of intraoperative blood flow in cerebral vascular area including, but not limited to, assessing cerebral aneurysm and vessel branch occlusion, as well as patency of very small perforating vessels. It also aids in the real-time visualization of blood flow and visual assessment of vessel types before and after Arteriovenous Malformation (AVM) surgery. Likewise, INFRARED 800 with FLOW 800 Option used during fluorescence guided surgery aids in the visual assessment of intra-operative blood flow as well as vessel patency in bypass surgical procedures in neurosurgery, plastics and reconstructive procedures and coronary artery bypass graft surgery.

· YELLOW 560 is a surgical microscope accessory intended to be used with a compatible surgical microscope in viewing and visual assessment of intraoperative blood flow in cerebral vascular area including, but not limited to, assessing cerebral aneurysm and vessel branch occlusion, as well as patency of very small perforating vessels. It also aids in the real-time visualization of blood flow and visual assessment of vessel types before and after Arteriovenous Malformation (AVM) surgery.

Fluorescence accessories (YELLOW 560 and INFRARED 800 with FLOW 800 option) are an accessory to surgical microscope and are intended for viewing and visual assessment of intra-operative blood flow as well as aids in the real-time visualization of blood flow and visual assessment of vessel types before and after Arteriovenous Malformation (AVM) surgery. The functionality of these filters is derived from their ability to hight fluorescence emitted from tissue that has been treated with a fluorescence agent by applying appropriate wavelengths of light and utilizing selected filters. This helps a surgeon to visualize different structural body elements (such as vessels, tissue, blood flow, occlusions, aneurysms, etc.) during various intraoperative procedures. The fluorescence accessory can be activated by the user via the Graphical User Interface (GUI), foot control panel or the handgrips, for example.

For these accessories to be used with a qualified surgical microscope, the critical components of the surgical microscope need to fulfill the clinically relevant parameters for the Indications for Use of YELLOW 560 and INFRARED 800 with FLOW 800 Option.

The fluorescence accessories are embedded into the surgical microscope. The emission filter wheels are present within the head of the microscope. For filter installation into the surgical microscope, two emissions filters (one for each eyepiece) are placed into each of these filter wheel is present in front of the light source, which is installed along with the excitation filter

The provided text is a 510(k) summary for the Carl Zeiss Meditec Inc. "Fluorescence Accessories (YELLOW 560 and INFRARED 800 with FLOW 800 Option)". This document focuses on demonstrating substantial equivalence to predicate devices rather than providing detailed acceptance criteria and a study proving the device meets those criteria.

The 510(k) summary primarily addresses:

• Indications for Use: The device is a surgical microscope accessory for viewing and visual assessment of intraoperative blood flow in the cerebral vascular area (e.g., assessing cerebral aneurysm, vessel branch occlusion, patency of small perforating vessels, and vessel types before/after Arteriovenous Malformation (AVM) surgery). It also aids in real-time visualization of blood flow and vessel patency in bypass surgical procedures in neurosurgery, plastics, reconstructive procedures, and coronary artery bypass graft surgery.
• Technological Characteristics: Comparison to predicate devices (YELLOW 560 (K162991) and INFRARED 800 with FLOW 800 Option (K100468)) is presented, showing substantial equivalence in application, patient population, device description, fluorescent agents used, visualization of real-time images, display, physical method, fluorescence excitation/detection, white light application, camera adaption, zoom, autofocus, autogain, control system, storage, and upgrade options. Minor differences are noted and deemed not to affect substantial equivalence.
• Non-Clinical Testing: A list of performance testing parameters for the system is provided, confirming that the "functional and system level testing showed that the system met the defined specifications."

Therefore, based on the provided text, a detailed table of acceptance criteria and a study proving the device meets those criteria (with specific performance metrics) cannot be fully constructed as requested. The document attests that the device met internal specifications through software verification and non-clinical system testing, but does not provide the specific numerical acceptance criteria or the study results themselves.

Here's a breakdown of what can be extracted and what is missing:

1. Table of Acceptance Criteria and Reported Device Performance

Cannot be fully provided as specific numerical acceptance criteria and reported device performance are not detailed in the provided document. The document states that "functional and system level testing showed that the system met the defined specifications" and lists the parameters tested. However, the values for these specifications and the results of the testing are not included.

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

• Sample Size: Not specified. The document mentions "non-clinical system testing" and "software verification testing" but does not provide details on the number of samples, test cases, or images used.
• Data Provenance: Not specified. This appears to be internal company testing (bench testing) rather than a study involving patient data.

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

• Not applicable/Not specified. This was a non-clinical bench and software performance testing; it does not involve expert ground truth for clinical assessment.

4. Adjudication method for the test set

• Not applicable/Not specified. As noted above, this was non-clinical bench and software performance testing.

5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance

• No MRMC study was mentioned. The device is an accessory to a surgical microscope providing visualization, not an AI diagnostic tool that assists human readers in interpreting images.

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

• Not applicable. The device provides "real-time visualization" and "visual assessment," which implies human interpretation of the images/data it presents. It's an accessory, not a standalone automated diagnostic algorithm. The testing described is for the functional and system performance of the accessory.

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

• Not applicable for the non-clinical and software testing described. The "ground truth" for the performance testing would be the predefined specifications that the system components were designed to meet.

8. The sample size for the training set

• Not applicable. The description does not suggest this device uses machine learning or AI that would require a "training set" in the conventional sense for image analysis. It's a fluorescence visualization system.

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

• Not applicable, as there is no mention of a training set.

Ask a specific question about this device

CIRRUS™ HD-OCT is a non-contact, high resolution tomographic and biomicroscopic imaging device intended for in vivo viewing, axial cross-sectional, and three-dimensional imaging of anterior ocular structures. The device is indicated for visualizing and measuring and posterior ocular structures, including corneal epithelium, retinal nerve fiber layer, ganglion cell plus inner plexiform layer, macula, and optic nerve head.

CIRRUS' AngioPlex OCT Angiography is indicated as an aid in the visualization of vascular structures of the retina and choroid.

CIRRUS HD-OCT is indicated as a diagnostic device to aid in the detection and management of ocular diseases including, but not limited to, macular holes, cystoid macular edema, diabetic retinopathy, age-related macular degeneration, and glaucoma.

This device is Prescription Use (Rx) only.

The CIRRUS™ HD-OCT Model 6000 is indicated for in-vivo viewing, axial cross-sectional, and threedimensional imaging and measurement of anterior and posterior ocular structures. The clinical purpose of this device has not been modified as compared to the predicate.

CIRRUS 6000 uses the same optical system, architecture, and principle of operation as the previously cleared CIRRUS 5000 (K181534). CIRRUS 6000 has a 100 kHz scan rate for all structural and angiography scans. The primary impact of the higher acquisition speed is its impact on signal-to-noise ratio. The signal-to-noise ratio m the subject device is calibrated to match the specifications of the CIRRUS 6000 uses the same segmentation algorithms as the predicate device and therefore the segmentation results will be equivalent.

In addition to the acquisition speed change, CIRRUS 6000 also has a wider field of view (FOV) and has increased the number of fixation points to 21.

Here's an analysis of the acceptance criteria and the studies that prove the device meets them, based on the provided text.

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria are implicitly defined by the reported precision summaries (Repeatability %CV and Reproducibility %CV and Limits) for various measurements on the CIRRUS HD-OCT 6000 (C6000) and the qualitative image quality results. The studies aim to demonstrate that the C6000 performs comparably to the predicate device, the CIRRUS HD-OCT 5000 (C5000), and that its image quality is clinically acceptable.

Since explicit numerical acceptance criteria (e.g., "Repeatability %CV must be

Ask a specific question about this device

The CLARUS 700 ophthalmic camera is indicated to capture, display, annotate and store images to aid in the diagnosis and monitoring of diseases and disorders occurring in the retina, ocular surface and visible adnexa. It provides true color and autofluorescence imaging modes for stereo, widefield, ultra-widefield, and montage fields of view. The CLARUS 700 angiography is indicated as an aid in the visualization of vascular structures of the retina and the choroid.

The CLARUS™ model 700 is a new addition to the CLARUS product family consisting of existing model 500 (K181444). The CLARUS 700 is an active, software controlled, highresolution ophthalmic imaging device for In-vivo imaging of the human eye. Imaging modes include True color, Fundus Auto-fluorescence with green excitation. Fundus Auto-fluorescence with blue excitation. Fluorescein Angiography, Stereo and External eve. All true color images can be separated into red, green and blue channel images to help enhance visual contrast of details in certain layers of the retina. The CLARUS 700 angiography imaging aids in the visualization of the vascular structures of the retina and the choroid. With a single capture, CLARUS 700 produces a 90° high definition widefield image. Widefield images are automatically merged to achieve a 135° ultra-widefield of view. The CLARUS 700 makes use of a deep learning algorithm for Optic Nerve Head (ONH) detection. The ultra-widefield montage on CLARUS 700 is no longer dependent just on the patient accurately fixating their gaze on the internal fixation. With the ONH detection, the software will find the optic nerve and determine based on the image(s) captured where the patient was gazing at the point of capture. The CLARUS 700 device allows clinicians to easily review and compare high-quality images captured during a single exam while providing annotation and caliper measurement tools that allow in-depth analysis of eye health. CLARUS 700 is designed to optimize each patient's experience by providing a simple head and chin rest that allows the patient to maintain a stable, neutral position while the operator brings the optics to the patient. facilitating a more comfortable imaging experience. The ability to swivel the device between the right and left eye helps technicians capture an image without realigning the patient. Live IR Preview allows the technician to confirm image quality and screen for lid and lash obstructions, prior to imaging, ensuring fewer image recaptures.

The CLARUS 700 device's principle of operation is Slit Scanning Ophthalmic Camera also referred to as Broad Line Fundus Imaging (BLFI), same as the predicate CLARUS 500 (K181444). During image capture, a line of illumination passes through the slit and scans across the retina. A 2D monochromatic camera captures the returned light to image the retina. A single sweep of the illumination is used to illuminate the retina for image capture. Repeated sweeps of near infrared light are used for a live retina view for alignment. Red, green and blue LEDs sequentially illuminate to generate true color images. Blue and green LED illumination enables Fundus Autofluorescence (FAF) imaging. Fluorescein Angiography images are captured with green LED illumination at a wavelength that stimulates fluorescence of the injected sodium fluorescein dye.

The CLARUS 700 system is mainly comprised of an acquisition device, all-in-one PC, keyboard, mouse, instrument lift table and external power supply.

The CLARUS 700 hardware is based off the predicate CLARUS 500 (K181444) hardware. New FA imaging mode on the CLARUS 700 require the below hardware changes:

• Added filters to support FA imaging mode .
• Updated slim turret and motor with new positions for reliability, angiography filters and ● FPGA code
• Updated calibration tool for new turret positions and differentiation
• Change to lightbox board for reliability and support higher duty cycle in support of FA imaging
• Updated Onyx All-in-one Computer for 32GB RAM and 2TB HDD storage space
• Updated belt driven slit for reliability and to support FA imaging mode ●
• . Updated camera to support FA imaging mode

The CLARUS software provides the user the capability to align, capture, review and annotate images. The software has two installation configurations: Software installed on the Instrument (Acquisition & Review) as well as Software installed on a separate 'Review Station' (Laptop or Computer) (only Review).

The CLARUS software version 1.1 is based off the predicate CLARUS software version 1.0 (K181444). Added image capture modality includes Fluorescein Angiography. Other changes implemented in the software version 1.1 include:

• Automated Optic Nerve Head (ONH) detection for montaging ●
• Smart (Region of Interest) Focus ●
• Auto brightness for FA image series
• Calibration software update for DEVICE hardware changes ●
• . FORUM/ Other EMR connectivity updates for new FA imaging mode

The CLARUS 700 device meets the requirements of ISO 10940:2009 standard. The device technical specifications are identical to the predicate device. The performance specifications relevant to the user are summarized in the Table 1 below.

Here's a breakdown of the acceptance criteria and the study that proves the device meets them, based on the provided FDA 510(k) summary for the CLARUS 700:

1. Table of Acceptance Criteria and Reported Device Performance:

Note: The document only provides the reported device performance as "passing rates" for the Fluorescein Angiography (FA) imaging mode, without explicitly stating numerical acceptance criteria for each point. The acceptance criteria are implied to be high percentages, demonstrating good clinical utility and image interpretability.

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

• Sample Size: 20 eyes from 13 subjects (11 male, 2 female)
• Data Provenance: The document does not explicitly state the country of origin or whether the study was retrospective or prospective. However, based on the nature of a "clinical study to support indications for use," it is highly probable that it was a prospective study designed for regulatory submission. The location of the manufacturer (Dublin, California, USA) suggests the study might have been conducted in the US, but this is not explicitly stated for the clinical data itself.

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

The document does not explicitly state the number of experts used or their specific qualifications for establishing the ground truth of the test set images. It mentions "clinically useful image" and "ability to interpret image," implying expert evaluation, but the specifics are not provided in this summary.

4. Adjudication Method for the Test Set:

The document does not mention any specific adjudication method (e.g., 2+1, 3+1). Expert consensus or independent review by a single expert is implied by the evaluation of "clinical utility" and "interpretability," but the process is not detailed.

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

• Was an MRMC study done? No, a traditional MRMC comparative effectiveness study involving human readers with and without AI assistance was not explicitly conducted or reported for the performance of AI on human readers.
• Effect Size: Therefore, no effect size for human reader improvement with AI assistance is reported.

Note on AI: The device does make use of a deep learning algorithm for Optic Nerve Head (ONH) detection to improve montage creation, but the clinical study described focuses on the overall performance of the Fluorescein Angiography imaging mode, not specifically on the impact of ONH detection AI on reader performance.

6. Standalone (Algorithm Only) Performance:

The document does not present separate standalone (algorithm-only) performance metrics for the deep learning algorithm (ONH detection). The clinical study evaluates the device's ability to capture useful images, which would indirectly incorporate the functionality of the device's software, but it's not a standalone performance evaluation of the AI component in isolation.

7. Type of Ground Truth Used:

The ground truth used for evaluating the clinical utility of the Fluorescein Angiography images appears to be expert clinical judgment/interpretation of the images. The criteria like "Area and lesion of interest is visible on the angiogram" and "Clinically useful image" strongly suggest evaluation by a medical professional or panel thereof. The study's objective was to demonstrate the device's ability to capture images useful for "diagnosis and monitoring of diseases and disorders," further supporting expert clinical judgment as the ground truth.

8. Sample Size for the Training Set:

The sample size for the training set of the deep learning algorithm (ONH detection) is not specified in the provided document.

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

The document briefly mentions "deep learning algorithm for Optic Nerve Head (ONH) detection" but does not detail how the ground truth for training this algorithm was established. It can be inferred that it would involve expertly annotated images for ONH location, but the specifics are not provided.

Ask a specific question about this device

CIRRUS™ HD-OCT is a non-contact, high resolution tomographic and biomicroscopic imaging device intended for invivo viewing, axial cross-sectional, and three-dimensional imaging of anterior ocular structures. The device is indicated for visualizing and measuring and posterior ocular structures, including corneal epithelium, retinal nerve fiber layer, ganglion cell plus inner plexiform layer, macula, and optic nerve head. The CIRRUS normative databases are quantitative tools indicated for the comparison of retinal nerve fiber layer thickness, macular thickness, ganglion cell plus inner plexiform layer thickness, and optic nerve head measurements to a database of normal subjects.

CIRRUS' AngioPlex OCT Angiography is indicated as an aid in the visualization of vascular structures of the retina and choroid. (Model 5000 only.)

CIRRUS HD-OCT is indicated as a diagnostic device to aid in the detection and management of ocular diseases including, but not limited to, macular holes, cystoid macular edema, diabetic retinopathy, age-related macular degeneration, and glaucoma.

The CIRRUSTM HD-OCT is a computerized instrument that acquires and analyses crosssectional tomograms of anterior and posterior ocular structures (including cornea, retinal nerve fiber layer, macula, and optic disc). It employs non-invasive, non-contact, low-coherence interferometry to obtain these high-resolution images. Using this non-invasive optical technique, CIRRUS HD-OCT produces high-resolution cross-sectional tomograms of the eye without contacting the eye. It also produces images of the retina and layers of the retina from an en face perspective (i.e., as if looking directly in the eye).

The CIRRUS HD-OCT is offered in two models, Model 5000 and 500. In the CIRRUS HD-OCT Model 5000, the fundus camera is a line scanning ophthalmoscope. The CIRRUS HD-OCT Model 500 is similar to the Model 5000 except that it provides the fundus image using the OCT scanner only.

The acquired imaging data can be analyzed to provide thickness and area measurements of regions of interest to the clinician. The system uses acquired data to determine the fovea location or the optic disc location. Measurements can then be oriented using the fovea and/or optic disc locations. The patient's results can be compared to subjects without disease for measurements of RNFL thickness, neuroretinal rim area, average and vertical cup-to-disc area ratio, cup volume, macular thickness and ganglion cell plus inner plexiform layer thickness.

In addition to macular and optic disc cube scans, the CIRRUS HD-OCT 5000 also offers scans for OCT angiography imaging, a non-invasive approach with depth sectioning capability to visualize microvascular structures of the eye.

Anterior segment scans enable analysis of the anterior segment including Anterior Chamber Depth, Angle-to-Angle and automated measurement of the thickness of the cornea with the Pachymetry scan.

The provided text describes the 510(k) summary for the Carl Zeiss Meditec, Inc. CIRRUS HD-OCT with Software Version 10. The main study detailed is for corneal epithelial thickness measurements.

Here's a breakdown of the acceptance criteria and study information:

1. Acceptance Criteria and Reported Device Performance

The acceptance criteria are implied by the statistical analyses performed, primarily focusing on repeatability, reproducibility, and agreement with manual measurements. The performance is reported in terms of these statistical metrics rather than predefined thresholds for acceptance.

Corneal Epithelial Thickness Measurements (Pachymetry Scans)

Note: The table provides data for the "Central" sector as an example. The document provides detailed results for 25 different sectors.

2. Sample Size and Data Provenance

• Test Set Sample Size:
  • Normal Corneas (Group 1): 11 adult participants (one eligible eye per participant).
  • Keratoconus/Post-LASIK (Group 2): 12 participants (one eligible eye per participant).
• Data Provenance: The document does not explicitly state the country of origin. It is a prospective clinical study specifically conducted to determine repeatability, reproducibility, and agreement.

3. Number of Experts and Qualifications for Ground Truth

• Number of Experts: Three masked graders.
• Qualifications of Experts: Not explicitly stated beyond "masked graders."

4. Adjudication Method for the Test Set

The document states: "To generate manually marked corneal epithelial thickness measurements, three masked graders reviewed images and manually performed measurements in the 25 sectors." It does not specify an adjudication method like 2+1 or 3+1; it simply mentions that three graders performed the measurements. The comparison is made between the automated measurement and these manual measurements.

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

There is no mention of a multi-reader multi-case (MRMC) comparative effectiveness study comparing human readers with and without AI assistance. The study focuses on the agreement between the device's automated measurements and manual measurements.

6. Standalone (Algorithm Only) Performance

Yes, a standalone performance assessment was done. The study specifically evaluated the "automated corneal epithelial thickness measurements" generated by the device's software. The comparison to manual measurements serves as a validation of this standalone algorithm's performance against human expert measurements.

7. Type of Ground Truth Used

The ground truth for the corneal epithelial thickness measurements was established by expert manual measurements performed by three masked graders. This serves as a reference standard to which the automated measurements were compared.

8. Sample Size for the Training Set

The document does not provide information about the sample size used for the training set of the algorithm. This study focuses on the clinical evaluation of the device in its final form.

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

The document does not provide information on how the ground truth for the training set (if any) was established. The clinical evaluation described pertains to the performance validation of the already developed algorithm.

Ask a specific question about this device

The CLARUS 500 ophthalmic camera is indicated to capture, display, annotate and store images to aid in the diagnosis and monitoring of diseases and disorders occurring in the retina, ocular surface and visible adnexa. It provides true color and autofluorescence imaging modes for stereo, widefield, ultra-widefield, and montage fields of view.

The CLARUS™ 500 is an active, software controlled, high-resolution ophthalmic imaging device for In-vivo imaging of the human eye. Imaging modes include True color, Fundus Autofluorescence with green excitation, Fundus Auto-fluorescence with blue excitation, Stereo and External eye. All true color images can be separated into red, green and blue channel images to help enhance visual contrast of details in certain layers of the retina. With a single capture, CLARUS 500 produces a 90° high definition widefield image. Widefield images are automatically merged to achieve a 135° ultra-widefield view. The technology allows clinicians to easily review and compare high-quality images captured during a single exam while providing annotation and caliper measurement tools that allow analysis of eye health. CLARUS 500 is designed to optimize each patient's experience by providing a simple head and chin rest that allows the patient to maintain a stable, neutral position while the operator brings the optics to the patient, facilitating a more comfortable imaging experience. The ability to swivel the device between the right and left eye helps technicians capture an image without realigning the patient. Live Infrared Preview allows the technician to confirm image quality and screen for lid and lash obstructions, prior to imaging, ensuring fewer image recaptures.

The CLARUS 500 device's principle of operation is based on Slit Scanning Ophthalmoscope also referred to as Broad Line Fundus Imaging (BLFI). During image capture, a broad line of illumination is scanned across the retina. A monochromatic camera captures the returned light to image the retina. A single sweep of the illumination is used to illuminate the retina for image capture. Repeated sweeps of near infrared light are used for a live retina view for alignment. Red, green and blue LEDs sequentially illuminate to generate true color images. Blue and green LED illumination enables Fundus Autofluorescence (FAF) imaging.

The CLARUS 500 system is mainly comprised of an acquisition device, all-in-one PC, keyboard, mouse, instrument lift table and external power supply.

The CLARUS software provides the user the capability to align, capture, review and annotate images. The software has two installation configurations: Software installed on the Instrument (Acquisition & Review) as well as Software installed on a separate 'Review Station' (Laptop or Computer) (only Review).

The CLARUS 500 technical features relevant to the user are: Field of View (FoV), Image Resolution, Pixel Pitch and Focusing Range. The device meets the requirements of ISO 10940:2009 standard. The performance specifications are summarized in the Table 1 below.

The provided document describes the Carl Zeiss Meditec CLARUS 500 ophthalmic camera. However, it does not explicitly state acceptance criteria or a detailed study proving the device meets specific performance criteria in the format requested. The document focuses on demonstrating substantial equivalence to predicate devices for FDA clearance.

Despite this, I can extract information related to performance and testing:

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

The document doesn't provide a formal "acceptance criteria" table like one might find in a clinical trial protocol for an AI device. Instead, it lists technical specifications and states that the device meets an ISO standard and passed various verification and validation tests.

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

The document mentions "A clinical study was conducted" for both general imaging modes and FAF imaging modes.

• Sample Size: Not specified.
• Data Provenance: Not specified (country/region, retrospective/prospective). It simply states "A clinical study was conducted."

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):

Not specified. The document only mentions that the study "concluded that similar amount of clinical features can be resolved." There is no detail on how this "ground truth" or comparison was established by experts.

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

Not specified.

5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:

No, this is not an AI device, and therefore no MRMC comparative effectiveness study involving AI assistance for human readers was done or described. The clinical study mentioned compares the device's imaging modes to a reference device. The focus is on the performance of the imaging capture, not an AI interpretation aid.

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

The CLARUS 500 is an imaging device, not an AI algorithm for interpretation. Its performance is inherent in the quality of the image capture. The "standalone" performance would be the image quality itself, which is verified through technical specifications and ISO compliance. The clinical study compares the "performance of the CLARUS 500 imaging modes" (standalone imaging output) to a reference device.

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

For the clinical study on imaging modes, the "ground truth" seems to be the ability to resolve "clinical features" when compared to images from a reference device. This implies a qualitative assessment, likely by clinicians, but the specific method or standard for "ground truth" (e.g., expert consensus on feature visibility, comparison to an actual disease state) is not detailed.

8. The sample size for the training set:

Not applicable, as this is an imaging device, not a machine learning algorithm that requires a training set in the typical sense. The software verification would involve testing against requirements, not "training data."

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

Not applicable, as it's not a machine learning algorithm with a training set.

Ask a specific question about this device

The Retina Workplace is a FORUM application intended for processing and displaying fundus image and optical coherence tomography data. It is also intended for generating reports that contain results from optical coherence tomography and fundus photography.

The Retina Workplace uses CIRRUS algorithms and normative databases as a quantitative tool for the comparison of macular thickness data to a database of normal subjects. It supports the processing and displaying of CIRRUS OCT-Angiography data, which is indicated as an aid in the visualization of vascular structures of the retina and choroid.

The Retina Workplace is intended to aid trained healthcare professionals in the detection, monitoring and management of ocular diseases including, but not limited to, macular edema, diabetic retinopathy and age-related macular degeneration.

The Retina Workplace is designed in conjunction with the FORUM PACS system, which support clinically focused client workplaces to aid the optometric and ophthalmology clinicians with the processing, display, review, management, and storage of digital data contained in patient records. The Retina Workplace is software application of FORUM Archive and Viewer PACs workplace. FORUM is a software system designed for storage, processing, and review of images, videos, and reports originating from computerized diagnostic instruments or electronic documentation systems over a network. The Retina Workplace is connected to the FORUM server via an internal interface. The Retina Workplace retrieves CIRRUS OCT exam data and fundus images from the FORUM server. The Retina Workplace is intended to support the physician with a clinically focused workplace for the retina by using the imported OCT exam data from CIRRUS HD-OCT and CIRRUS Photo to report and display the results.

The Retina Workplace (version 2.5) is the latest generation device in the Retina Workplace series. The version of the 2.5 that is the subject of this submission is a modified version of the Retina Workplace (version 2.0) cleared under K170638.

Like its predecessors, Retina Workplace version 2.5 is designed to process and display CIRRUS OCT exams by using the algorithms and databases that are currently in use on the FDA cleared CIRRUS HD-OCT version 8 (K150977) and CIRRUS Photo (K133217). The CIRRUS HD-OCT OCT-Angiography was also cleared in K150977.

The provided text describes the Retina Workplace device and its substantial equivalence to predicate devices, but it does not contain the specific details required to answer all parts of your request regarding acceptance criteria and a study proving the device meets those criteria.

The document is a 510(k) summary for a medical device cleared by the FDA, which generally focuses on demonstrating substantial equivalence to existing devices rather than presenting the full details of a clinical performance study with specific acceptance criteria, sample sizes, and expert adjudication as you've requested.

Here's what can be extracted and what is missing:

What is present/can be inferred:

• Device Performance: The document generally states that "All criteria for the verification and validation testing were met; the results demonstrate that the Retina Workplace meets all performance specifications and requirements." and "Retina Workplace v2.5 performs as well as the predicate devices." However, it does not specify what those performance specifications and requirements (acceptance criteria) were.
• Study type: "Software testing was conducted to establish the ability of the subject Retina Workplace (version 2.5 - K182318) to meet design and customer requirements. Verification and validation activities for the Retina Workplace were conducted... The system verification test report provides the test cases, expected results for each test case and the actual results obtained. Validation testing was conducted to ensure that the device meets the customer's requirements with respect to performance." This indicates that verification and validation (V&V) testing was performed, typical for software devices, rather than a prospective clinical trial. It sounds more like functional and performance testing against internal specifications.
• Human-in-the-loop/Standalone: The device is intended "to aid trained healthcare professionals," suggesting a human-in-the-loop context. No information on standalone algorithm performance is provided.
• Ground Truth: The document states "The Retina Workplace uses CIRRUS algorithms and normative databases as a quantitative tool for the comparison of macular thickness data to a database of normal subjects." This implies that existing, cleared algorithms and normative databases from the predicate devices (CIRRUS HD-OCT) are leveraged as the "ground truth" or reference for quantitative measurements.
• Training Set (Inferred): Since the device uses "CIRRUS algorithms and reference databases" that are already "currently in use on the FDA cleared CIRRUS HD-OCT version 8 (K150977) and CIRRUS Photo (K133217)", it suggests that the training of these core algorithms would have occurred as part of the predicate device development. No specific "training set" for the Retina Workplace v2.5 itself (as a new algorithm being trained) is mentioned, as its primary function is processing and displaying data using existing cleared algorithms.

What is missing from the provided text:

1. A table of acceptance criteria and the reported device performance: The specific criteria (e.g., sensitivity, specificity, accuracy targets, imaging quality metrics) are not listed. Only a general statement that "all criteria... were met" is provided.
2. Sample size used for the test set and the data provenance: No details on the number of cases or patients used in the verification and validation (V&V) testing, nor the origin (country, retrospective/prospective) of the data.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: As this appears to be software/functional V&V rather than a clinical reader study, expert ground truth establishment for a test set in the way you describe is not explicitly mentioned. If the V&V largely relies on output comparison to predicate devices or established algorithms, then the "ground truth" might be the output of those validated predicate systems.
4. Adjudication method: Not mentioned.
5. Multi-Reader Multi-Case (MRMC) comparative effectiveness study: Not mentioned. The focus is on the device using existing, cleared algorithms, not on how human readers perform with or without its assistance.
6. Standalone performance: While the device leverages algorithms, no specific standalone performance metrics (e.g., diagnostic accuracy of an automated detection) for the Retina Workplace itself are presented, implying it's an "aid" rather than a fully autonomous diagnostic tool.
7. The sample size for the training set: Not applicable and not mentioned, as the device leverages existing, cleared algorithms.
8. How the ground truth for the training set was established: Not applicable and not mentioned, as the device leverages existing, cleared algorithms.

Conclusion based on the provided text:

The document describes the Retina Workplace (version 2.5) as a software application that integrates and processes data using algorithms and databases already cleared and present in predicate devices (CIRRUS HD-OCT and CIRRUS Photo). The "study" proving it meets acceptance criteria appears to be a software verification and validation (V&V) process, ensuring that the new version correctly implements and displays the functionalities of the existing, cleared algorithms and processes data as intended. It does not appear to involve a new clinical performance study with human readers, novel algorithm training, or the establishment of new, independent ground truth for a diagnostic AI. The acceptance criteria were internal performance specifications for the software, which were reportedly met.

To get the detailed information you're asking for, one would need to refer to the full 510(k) submission (if publicly available beyond this summary) or documentation from the predicate devices (K150977 for CIRRUS HD-OCT version 8 and K133217 for CIRRUS Photo).

Ask a specific question about this device

The VisuMax Femtosecond Laser is cleared for the following indications for use:

· In the creation of a corneal flap in patients undergoing LASIK surgery or other treatment requiring initial lamellar resection of the cornea;

· In patients undergoing surgery or other treatment requiring initial lamellar resection of the cornea;

· In the creation of a lamellar cut/resection of the cornea for lamellar keratoplasty;

· In the creation of a cut/incision for penetrating keratoplasty and corneal harvesting;

· In patients undergoing surgery or other treatment requiring initial lamellar resection of the cornea to create tunnels for placement of corneal ring segments.

The VisuMax Femtosecond Laser is an ophthalmic surgical femtosecond laser intended for use in patients requiring corneal incisions. The cutting action of the VisuMax laser is achieved through precise individual micro-photodisruptions of tissue, created by tightly focused ultrashort pulses which are delivered through a disposable applanation lens while fixating the eye under very low vacuum.

The provided text describes the 510(k) premarket notification for the Carl Zeiss Meditec VisuMax Femtosecond Laser (K173371). The focus of this submission is on software modifications to enable an additional indication for use: "creation of tunnels for placement of corneal ring segments."

The submission concludes that the device is substantially equivalent to predicate devices, but it does not contain specific acceptance criteria, comprehensive study designs, or detailed results typically found in a clinical study report. Instead, it provides a summary of the performance testing.

Here's an attempt to extract the requested information based only on the provided text, with acknowledgments for missing data:

1. Table of Acceptance Criteria and Reported Device Performance

Note: The document states that "Test acceptance criteria...were met" but does not explicitly define the quantitative metrics or thresholds for these criteria. The acceptance criteria above are inferred from the description of the tests.

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

• Sample Size for Test Set: The document mentions "a series of corneal models" and "all corneas tested in this manner," but does not specify the exact number (sample size) of ex vivo corneas or corneal models used for performance testing.
• Data Provenance: The testing involved "ex vivo corneas" and "corneal model material." The country of origin is not specified, and the data is retrospective in the sense that it's laboratory/bench testing and not a prospective clinical trial on human subjects for this specific claim.

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

• The document mentions "ex vivo corneas" and "corneal model material" for performance testing. The evaluation of cut quality mentions "judged to be of good cut quality," implying subjective assessment.
• However, the number of experts and their qualifications (e.g., radiologists with X years of experience) used to establish ground truth or evaluate these ex vivo tests are not specified in the provided text.

4. Adjudication Method for the Test Set

• The document implies subjective judgment for cut quality ("judged to be of good cut quality").
• However, a formal adjudication method (e.g., 2+1, 3+1) is not described for any aspect of the performance testing in the provided text. The non-contact optical techniques used for dimensional measurements suggest objective assessment rather than adjudication by human experts.

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

• A Multi-Reader Multi-Case (MRMC) comparative effectiveness study to assess improvement in human readers with/without AI assistance was not done/described in this submission. This device is a surgical laser, not an AI diagnostic tool that assists human readers.

6. Standalone Performance Study (Algorithm Only)

• A standalone performance study focused on the algorithm's performance without human-in-the-loop was not explicitly described in the conventional sense of AI diagnostic devices. The performance data presented focuses on the physical output of the laser system (tunnel cuts) after software modifications. The software itself was verified and validated against functional requirements.

7. Type of Ground Truth Used

• For the physical performance tests related to tunnel cuts, the "ground truth" was established based on physical measurements using non-contact optical techniques in ex vivo corneas and corneal model materials. Cut quality was assessed subjectively against "performance test acceptance criteria."
• For the software, the "ground truth" was its adherence to specified performance, accuracy, functionality, and safety requirements during verification and validation (V&V) testing.

8. Sample Size for the Training Set

• The document describes software modifications to an existing device and performance testing, not the development or training of a machine learning model.
• Therefore, a "training set" for an AI algorithm is not applicable/not mentioned in this submission.

9. How Ground Truth for the Training Set Was Established

• As a "training set" for an AI algorithm is not applicable, the method for establishing its ground truth is not mentioned. The software verification and validation process involved testing the modified software against predefined functional specifications and safety requirements.

Ask a specific question about this device