Search Results

The VIO System is intended to acquire, store, retrieve, display and transfer in vivo images of tissue - including blood vessels, collagen, pigment, stratum corneum, hair shafts or follicles, solar elastosis, atypia, and epidermal disarray - in and through epidermis for review by physicians to assist in forming a clinical judgment. Physicians who interpret VIO System images must have dermatology medical qualifications with skin histology assessment training.

The VIO System (REF V-1000) is a light-based in vivo microscope intended to provide images of skin tissue for review by physicians to assist in forming a clinical judgment. The device does not provide image analysis or diagnostic information. The VIO System uses a handheld reflectance confocal and multiphoton microscope that contacts the skin and optically scans at a depth where most skin conditions originate, without disrupting the tissue. The VIO System delivers low power laser light of a single wavelength (780 nm infrared, Class 1M) into the skin in brief pulses. The resulting signals are acquired while imaging the skin and each signal is assigned to one of four (4) channels: RCM (Reflectance Confocal Microscopy), SHG (Second Harmonic Generation), 2PS (2-Photon Autofluorescence Short), and 2PL (2-Photon Autofluorescence Long). For each image capture, the VIO System combines the four (4) channels to display a single, multi-color image on the VIO System, referred to as "Tetrachrome™." Three (3) view modes are accessible to the user on the VIO System: Standard View, Superficial Zoom, and Deep Zoom. Acquired images are not stored on nor analyzed by the VIO System. The images are saved on a USB flash drive, which is used to transfer images to a commercially available DICOM viewer for interpretation by a physician.

The provided 510(k) summary for the Enspectra VIO System (K232789) outlines the device's acceptance criteria and the clinical study conducted to validate its performance.

Here's a breakdown of the requested information:

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

The summary states: "The effectiveness endpoint for the study was achieved as the results demonstrated overall >90% agreement between each Blinded Reader VIO image assessment and the answer key developed from the Comparative Reader validation assessment." This indicates that the acceptance criterion was >90% agreement.

Note: While the overall effectiveness endpoint states >90% agreement, the "Blood vessel/Dermis" accuracy is 87.2% (77.7% to 93.7%). This specific feature's lower bound of the CI falls below 90%, but the report concludes that the "effectiveness endpoint... was achieved as the results demonstrated overall >90% agreement." This suggests that the overall average agreement across all features met the criteria, even if individual feature performance varied.

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

• Sample Size for Test Set: The study was conducted with N=65 participants. Participants were randomly assigned to either a Training Set or a Testing Set. The exact number of participants solely in the testing set is not explicitly stated as a specific number (e.g., "N=X for test set"). However, it's implied that the "Blinded Readers" were tested on images derived from this N=65 participant pool.
• Data Provenance: The document does not specify the country of origin of the data. The study involved imaging skin lesions on adults (18 years and above) with Fitzpatrick Skin Type I-V, located on the head, neck, limbs, and torso. It is a prospective study as the VIO System was used to image participants during the study.

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

• Number of Experts for Ground Truth: N=3 Comparative Readers were used to develop the answer key (ground truth) for the test set.
• Qualifications of Experts: The Comparative Readers were physicians, and their role involved "validating VIO images against ground truth pathology." The text also states that "Physicians who interpret VIO System images must have dermatology medical qualifications with skin histology assessment training." It's reasonable to infer that the Comparative Readers held these qualifications.

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

The ground truth was established by "N=3 Comparative Readers developed consensus training materials, then developed an answer key by validating VIO images against ground truth pathology." This implies an expert consensus method among the 3 comparative readers to establish the answer key. The specific adjudication rule (e.g., majority vote, or discussion until agreement) is not detailed, but it's clearly a consensus-based approach rather than simple averaging or individual reading.

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 where human readers were compared with and without AI assistance. The study focuses purely on the performance of human readers (Blinded Readers) interpreting VIO images against a ground truth established by other human experts (Comparative Readers). The VIO System itself does not provide image analysis or diagnostic information; it generates images for physician review. Therefore, it's not an AI-assisted interpretation system in the sense of providing a computer-driven initial read or aiding diagnosis.

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

No standalone algorithm performance was done/reported. The device description explicitly states: "The device does not provide image analysis or diagnostic information." The VIO System is an image acquisition device; the interpretation is performed by physicians.

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

The ground truth for the test set was established by expert consensus of 3 Comparative Readers, validated against pathology. Specifically: "...developed an answer key by validating VIO images against ground truth pathology." This indicates that pathology results served as the definitive reference standard, interpreted and applied to the VIO images by the expert readers.

8. The sample size for the training set

The study involved N=65 participants, randomly assigned to either a Training Set or Testing Set. The exact number of participants specifically in the training set is not explicitly stated as a specific number. However, the N=3 Comparative Readers "developed consensus training materials" which implies a portion of the N=65 dataset was used for this training.

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

The ground truth for the training set was established by the N=3 Comparative Readers who "developed consensus training materials, then developed an answer key by validating VIO images against ground truth pathology." This suggests a similar process to the test set ground truth, involving expert consensus and correlation with pathology.

Ask a specific question about this device

Aveli is indicated for long-term reduction in the appearance of cellulite in the buttocks and thigh areas as supported by clinical data demonstrating treatment benefits through one year of observation. Avéli is also indicated for soft tissue dissection during general and plastic surgical procedures.

Avéli is a sterile, single-use manual instrument that releases fibrous tissue (septa) beneath cellulite for long-term reduction in the appearance of cellulite in the buttocks and thigh areas of adult females. Avéli also dissects soft tissue in general and plastic surgical procedures. The device consists of a Handle and a Distal End. The Handle houses components used to actuate the moving parts at the distal end of the device. The Distal End is advanced into subcutaneous tissue through a small incision to a procedure location. An integrated light source provides illumination and allows the user to track and advance to the procedure location. The Distal End contains a Blade and a Blocker forming a Hook. When the Handle is moved in a retrograde fashion, the Hook captures the nearby septa or other soft tissue resulting in tugging. The user feels the resistance, confirming that septa under a cellulite depression or other treatment area have been identified and then exposes the Blade at the Distal End. The user pushes the skin distally with the free hand while maintaining the device stable or applies additional retrograde motion with the device to release the soft tissue. The user then retracts the Blocker into the device, allowing removal without further tissue engagement. The user can verify all appropriate soft tissue has been released by passing through the area again with the Hook. The step is repeated for each visible cellulite depression or other surgical area.

The provided text describes the Avéli device, which is indicated for long-term reduction in the appearance of cellulite and for soft tissue dissection. The 510(k) submission (K232153) is to expand the indications of use to include soft tissue dissection during general and plastic surgical procedures.

Here's an analysis of the acceptance criteria and study information based on the provided document:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state quantitative acceptance criteria for the expanded indication of "soft tissue dissection during general and plastic surgical procedures" in the same format as a table with reported device performance against specific numerical targets.

Instead, it lists types of verification testing conducted to support the substantial equivalence determination for this expanded indication. The conclusion states that "Performance test data demonstrates sufficient performance for soft tissue dissection." This implies that the device met internal design specifications and performance requirements for the soft tissue dissection function.

Here's a summary of the types of performance testing that serve as the basis for demonstrating compliance for the soft tissue dissection indication:

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

The document does not specify the sample sizes used for the various non-clinical verification tests (e.g., number of devices tested for functional, mechanical, or electrical tests). It only lists the types of tests performed.

The document also does not provide any information about the provenance of data (e.g., country of origin, retrospective or prospective) for these non-clinical tests. These are typically internal lab tests conducted by the manufacturer.

For the initial indication of "long-term reduction in the appearance of cellulite in the buttocks and thigh areas," the text states it is "supported by clinical data demonstrating treatment benefits through one year of observation." However, details on this clinical data (sample size, provenance, study design) are not provided within this document specifically for the cellulite indication. This submission focuses on the expanded indication for soft tissue dissection which is supported by non-clinical testing for substantial equivalence to a predicate device.

3. 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. The tests described are non-clinical verification tests, which typically involve laboratory measurements and assessments against engineering specifications, rather than expert-derived ground truth in the context of diagnostic accuracy.

4. Adjudication Method for the Test Set

This information is not provided. Given that the tests listed are non-clinical engineering and performance tests, an "adjudication method" in the sense of resolving disagreements among expert reviewers of test data is not typically applicable or described in this type of summary.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was Done

No MRMC comparative effectiveness study is mentioned for the expanded indication of soft tissue dissection. The review pathway is based on substantial equivalence to predicate devices through non-clinical testing.

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

The Avéli device is a powered surgical instrument used by a human operator, not an AI algorithm. Therefore, the concept of a "standalone (algorithm only)" performance study is not applicable. The performance is inherently human-in-the-loop.

7. The Type of Ground Truth Used

For the expanded indication of soft tissue dissection, the "ground truth" for the non-clinical tests is represented by the design specifications, performance requirements, and relevant international standards (e.g., IEC 60601-1 for electrical safety, ISO 10993-1 for biocompatibility, ISO 11135-1 for sterilization) that the device was tested against. The tests verify that the device performs as intended and meets these established engineering and regulatory benchmarks.

For the cellulite indication, the ground truth would likely have been based on clinical assessment of appearance reduction (e.g., by investigators or independent evaluators) as stated by "clinical data demonstrating treatment benefits." However, the details of this ground truth establishment are not provided here.

8. The Sample Size for the Training Set

No training set is mentioned in the context of this device. The Avéli is a physical surgical instrument, not a machine learning algorithm that requires a training set.

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

Not applicable, as there is no mention of a training set for this device.

Ask a specific question about this device

The DeepX DermoSight Dermatoscope is a non-invasive skin imaging system, which acquires white light dermatoscopic images and clinical photographs of the skin. These can be stored, retrieved, displayed and reviewed by trained medical practitioners.

The DeepX Health DermoSight Dermatoscope is designed to acquire images of the skin and optimize the imaging storage and documentation workflow. The DeepX Health DermoSight Dermatoscope system consists of a hardware device and a software application. The hardware device is a hand-held, dermatoscope (camera) for acquiring and transmitting images of the skin. The hand-held, portable unit includes an LED light-source, a digital camera and a USB cable to transfer images to a standard PC workstation. The device acquires optical dermatoscopic images in a contact mode (acquired with the device in contact with the skin). In addition, the device can also acquire a clinical close-up image, when it is positioned 15cm from the skin.

The stand-alone software application is cloud-based software with a related web application. The cloud software allows for storage and retrieval of the acquired images and patient data for review by medical professionals.

DeepX Health DermoSight Dermatoscope software is a stand-alone application to be accessed via a standard computer connected to the hospital/clinic server or directly to the internet.

The software displays the patient demographic and identification information (e.g., date of image acquisition and anatomic location of photographed site). The images and identification data may be output to the computer used for image acquisition or downloaded to an alternate computer or storage device identified by the user.

The provided text describes the DeepX DermoSight Dermatoscope, a non-invasive skin imaging system, and its FDA 510(k) clearance process. However, the document does not contain specific acceptance criteria or details of a study proving the device meets acceptance criteria in the manner requested (e.g., performance metrics like sensitivity, specificity, or accuracy compared to predefined thresholds).

The document states that "The following documentation was submitted in the 510(k): Hardware Requirements Level of Concern Statement, Software Description, Software Architecture Specification, User Manual and Instructions for Use, Software Design Specification, Risk Analysis, Traceability Matrix, Software Validation Report, Usability Evaluation Report, Software Development and Lifecycle Plan, Unresolved Anomalies, Cybersecurity, Electromagnetic Compatibility and Safety, Biocompatibility Data."

This list indicates that various engineering, regulatory, and safety tests were performed, but it lacks the clinical or performance study details (e.g., accuracy against a gold standard or comparison with human readers) that would provide acceptance criteria and reported device performance metrics specifically for image interpretation or diagnostic accuracy.

Therefore, I cannot populate the table or answer most of the questions directly from the provided text.

Here's a breakdown of what can be extracted or inferred based on the document's content:

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

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

• Not provided. The document lists "Software Validation Report" and "Usability Evaluation Report" as submitted documentation, but it does not detail the methodology, sample size, or data provenance for these tests. There is no mention of a clinical or retrospective/prospective study with a test set of images for performance evaluation.

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 provided. Given that there's no described performance study (e.g., for diagnostic accuracy), there's no mention of experts establishing ground truth for such a test set.

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

• Not provided. (See #3)

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 evidence of an MRMC study. This device is a dermatoscope and an archiving system; it's explicitly stated to be for "acquiring, storing, retrieving, displaying and reviewing" by trained medical practitioners. It does not appear to incorporate AI for image analysis or diagnostic assistance, so an MRMC study comparing human readers with and without AI assistance is not applicable based on the provided information.

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

• No evidence of a standalone algorithm performance study. The device description focuses on image acquisition, storage, and display for review by medical practitioners, implying it is a tool for human review, not a standalone diagnostic AI.

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

• Not explicitly stated for performance metrics. For the various engineering tests (software validation, usability, safety), the ground truth would be adherence to specified requirements, standards, and safety regulations. However, for diagnostic accuracy, no such ground truth establishment is described.

8. The sample size for the training set

• Not applicable / Not provided. Since there's no mention of an AI algorithm requiring a training set for diagnostic purposes, this information is not present. The software is described as for "Image acquisition, Image transfer, Image and patient data storage and retrieval, Image display and comparison."

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

• Not applicable / Not provided. (See #8)

Summary of what the document focuses on regarding performance:

The document emphasizes that DeepX DermoSight Dermatoscope is substantially equivalent to a previously cleared predicate device (Demetra BDEM-01). The "Performance Testing" section lists various engineering and regulatory reports (e.g., Software Validation, Cybersecurity, Biocompatibility), which are typical for demonstrating safety and effectiveness for a 510(k) clearance, especially for a device primarily focused on image acquisition, storage, and display rather than automated diagnosis. The comparison table directly addresses the technical specifications and intended use against the predicate, highlighting similarities rather than presenting novel performance metrics against a clinical gold standard.

Ask a specific question about this device

Transmission of light energy from the light source to an optical instrument.

The light-guide cable is used to transmit light during endoscopic procedures or for other medical illumination application when the properties and operating instructions are complied with.

The light-guide cable is designed for use with halogen, xenon or LED based light which are utilized in medical applications that involve endoscopes, medical instruments or microscopes.

The Olympus Light-Guide Cables that are subject to this submission are intended to transmit light from the light source to an optical instrument. For that purpose the Light-Guide Cable includes a bundle of optical fibers as transmission medium. The light guide adapters are intended for the mechanical connection of the Light-Guide Cables to light sources or to endoscopes.

There are two variants of Light-Guide Cables which differ according to the shaft diameter of the connected endoscope. Cable WA03300A (2.8 mm, 3 m, CF type) can be combined with endoscopes, which have a diameter ≤ 4.1mm. Endoscopes with a diameter > 4.1mm are combined with WA03310A (4.25 mm, 3 m, CF type). Otherwise the Light-Guide Cables are identical.

This document describes the FDA's 510(k) clearance for Olympus Light-Guide Cables. The core of this submission is to demonstrate substantial equivalence to a predicate device, not necessarily to provide full performance study details typical of a de novo device. Therefore, the specific information requested in the prompt, such as detailed acceptance criteria, sample sizes for test/training sets, expert qualifications, and effect sizes for human-in-the-loop studies, is largely not present in this type of regulatory document.

Here's an analysis of the provided text based on your request:

Acceptance Criteria and Reported Device Performance

The document states, "The Light-Guide Cables comply with all applicable requirements/standards as listed in Appendix IIIc of this submission." However, Appendix IIIc is not provided, so the specific acceptance criteria and their corresponding reported device performance values are not detailed in this text.

The document also mentions that "the design of the subject device Light-Guide Cables is identical to that of the predicate devices" with "minor design modifications." It asserts that these differences "do not negatively impact safety or effectiveness" and "do not raise different questions of safety or effectiveness."

Based on the provided text, a table of acceptance criteria and reported device performance cannot be fully constructed. The document primarily relies on the substantial equivalence to a predicate device that has been "used safely and effectively for years," and compliance with general safety standards.

The closest we get to "reported performance" is the mention of electrical safety testing and reprocessing validation.

Study Information (Based on provided text)

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

   • Sample Size: Not explicitly stated as a separate "test set" in the context of a new performance study. The document states that because the devices are substantially equivalent and the predicate has been used for years, "it was not considered necessary to re-test the performance of the Light-Guide Cables concerned." However, "complete evidence of the performance test records is included in this submission" (referenced in Appendix 12a-e, which is not provided).
   • Data Provenance: Not specified. Given the reliance on predicate device history and general standards compliance, no specific new clinical data is presented here.

2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable. No new "ground truth" was established for a new clinical test set as the submission relies on substantial equivalence and existing predicate safety/effectiveness.

3. Adjudication method (e.g. 2+1, 3+1, none) for the test set: Not applicable, as no new clinical test set requiring adjudication for ground truth was conducted.

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: Not applicable. This device is a passive light-guide cable, not an AI-assisted diagnostic or therapeutic device.

5. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not applicable. This is not an algorithm-based device. Physical bench testing was likely done for electrical safety and reprocessing validation, but not a "standalone algorithm" performance.

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

   • For the aspects that were tested (Electrical Safety, Reprocessing), the "ground truth" would be the established international and national standards (e.g., ANSI AAMI ES60601-1, IEC 60601-2-18) against which the device's electrical performance was measured, and validated sterilization protocols for reprocessing.
   • For the overall device, the "ground truth" for safety and effectiveness is largely based on the predicate device's established use history and compliance with general device regulations.

7. The sample size for the training set: Not applicable. This is a physical medical device, not an AI model requiring a training set.

8. How the ground truth for the training set was established: Not applicable.

Ask a specific question about this device

The Barco Digital Dermatoscope is a non-invasive skin imaging system, which acquires multispectral and white light dermoscopic images and clinical photographs of the skin. These can be stored, retrieved, displayed and reviewed by trained medical practitioners.

The Barco Demetra BDEM-01 is designed to capture images of the skin and optimize the imaging and documentation workflow. The “Barco Demetra BDEM-01” consists of a hardware device and a software application. The hardware device is a portable, battery powered medical device for acquiring and visualizing images of the skin. The device acquires multispectral optical dermoscopic images in a contact mode (device in contact with the skin). In addition, the device can also acquire a clinical close-up image, when it is held at up to 10 to 15 cm from the skin, and a clinical overview image when it is held at a distance of approximately 35-55 cm from the skin. The stand-alone software application is cloud software with a related web application. The cloud software can generate reports containing white light dermoscopic images and clinical photographs of the skin to be reviewed by trained medical practitioners.

The provided document describes a 510(k) premarket notification for the Demetra Dermatoscope BDEM-01 (K213957), which is a "Special 510(k)" submission. This typically means the device has minor changes from a previously cleared predicate device (K192829 in this case).

Crucially, the document does NOT contain information about a clinical study or performance testing that would typically establish acceptance criteria for an AI/ML medical device and prove its performance against those criteria.

Instead, this submission focuses on demonstrating substantial equivalence to a predicate device, specifically highlighting:

• Identical Indications for Use: The current device has the same intended use as its predicate.
• Minor modifications: The changes are related to the Multispectral Image Acquisition Workflow, micro-chip, supplier of camera, data acquisition/handling/display, and inclusion of an Analytics Toolkit (which itself was cleared via a separate 510(k), K201408).
• Bench testing: The document states "bench tests mentioned below were performed to validate the device characteristics that differ from the predicate device in the original 510(k) K192829." These tests are listed as "Functionality Tested" with a "PASS" criterion.

Therefore, I cannot extract the requested information regarding acceptance criteria, study details, sample sizes, expert involvement, ground truth, or MRMC studies, as the provided text pertains to a special 510(k) for a hardware and fixed software device based on substantial equivalence and bench testing, not an AI/ML algorithm requiring a comprehensive performance study as typically seen for novel AI claims.

If this were an AI/ML device with performance claims, such information would be mandatory. Since it is not present, it implies that the device (or at least this specific submission) is not an AI/ML algorithm making clinical claims that require such validation. The "Analytics Toolkit" mentioned is noted as "display of skin parameters map only, cleared via K201408," suggesting its AI component (if any) was addressed in a prior submission or is limited to visualization rather than diagnostic or prognostic output.

Ask a specific question about this device

The Barco Demetra Analytics Toolkit is a non-invasive skin analysis system. The Barco Demetra Skin Parameter Maps Tool provides maps that show the relative location of blood and pigment. The Barco Demetra Skin Parameter Maps Tool is intended only to complement dermoscopy.

The Barco Demetra Analytics Toolkit is a software application used to support analysis of dermoscopic images captured with the Barco Demetra BDEM-01 dermatoscope (K192829). The system is intended for use by medical practitioners. Scatter Contrast Maps provide additional information to dermoscopy by highlighting surface contours. The Skin Parameter Maps Tool provides images generated from multispectral image sets and aids the user in visualizing blood and pigment patterns in the skin. The output of the Skin Parameter Maps is shown to the user as grayscale two-dimensional maps. The maps are intended only to complement dermoscopy.

The provided text describes several clinical validation activities for the Demetra Analytics Toolkit, but it does not explicitly state specific acceptance criteria in a quantitative manner (e.g., minimum sensitivity, specificity, or agreement score). Instead, it describes general performance testing and multiple clinical studies aiming to support the device's safety and effectiveness and its substantial equivalence to a predicate device.

Given this limitation, I will infer the "acceptance criteria" from the descriptions of the studies and their reported "PASS" results for software verification, usability engineering, and design validation. The implicit acceptance criteria appear to be that the device "performs as well as the legally marketed predicate device" and that the evaluations did not "reveal new issues of safety and performance."

Here's an attempt to structure the information based on your request, acknowledging the gaps in explicit quantitative acceptance criteria:

Acceptance Criteria and Device Performance

The provided document does not explicitly define quantitative acceptance criteria for the Demetra Analytics Toolkit's clinical performance (e.g., specific accuracy, sensitivity, or agreement thresholds). Instead, the studies aim to demonstrate that the device is "as safe, as effective, and performs as well as the legally marketed predicate device." The "Result" column in the table below reflects the general "PASS" status for foundational tests and the overall conclusion of substantial equivalence.

Table of Acceptance Criteria (Implicit) and Reported Device Performance

Study That Proves the Device Meets the Acceptance Criteria:

The document describes five distinct clinical validation activities. It's important to note that these studies collectively support the device's substantial equivalence to the predicate device, rather than each proving specific quantitative "acceptance criteria" for clinical performance.

2. Sample Sizes and Data Provenance:

• "Clinical validation of Demetra Skin Parameter Maps" (Retrospective Reader Study):
  • Test Set Sample Size: 28 cases
  • Data Provenance: Retrospective, mixed dermatology conditions, focus on skin lesions suspicious for skin cancer, no country explicitly stated but experts were from USA.
• "SIAScans vs. Barco Analytics Toolkit" (Retrospective Study):
  • Test Set Sample Size: "representative set of specific types of cases" (exact number not specified)
  • Data Provenance: Retrospective, from OHSU Dermatology Clinic, Portland (USA).
• "Correlation of structures visualized in the Skin Parameter Maps with pathology findings" (Prospective Clinical Study):
  • Test Set Sample Size: 15 cases
  • Data Provenance: Prospective, from Washington DC (USA) and Maryland (USA).
• "Validation of skin structures imaged in the Skin Parameter Maps" (Clinical Study):
  • Test Set Sample Size: 15 cases
  • Data Provenance: From University Hospital Leuven in Belgium.
• Clinical Study at Charité Universitätsmedizin Berlin & Oregon, USA (Retrospective Reader Study):
  • Test Set Sample Size: 28 representative cases
  • Data Provenance: Retrospective, from existing database, conducted in Germany and Oregon, USA.

3. Number of Experts and Qualifications:

• "Clinical validation of Demetra Skin Parameter Maps":
  • Number of Experts: 4
  • Qualifications: Board certified dermatologists from different sites in the USA.
• "SIAScans vs. Barco Analytics Toolkit":
  • Number of Experts: 1
  • Qualifications: Board certified dermatologist from OHSU Dermatology Clinic, Portland.
• "Correlation of structures visualized in the Skin Parameter Maps with pathology findings":
  • Number of Experts: 2
  • Qualifications: Board certified dermatologist from Washington DC; and a dermatopathologist from Maryland.
• "Validation of skin structures imaged in the Skin Parameter Maps":
  • Number of Experts: 1
  • Qualifications: Dermatologist from University Hospital Leuven.
• Clinical Study at Charité Universitätsmedizin Berlin & Oregon, USA:
  • Number of Experts: 4 observers (qualifications not explicitly stated beyond "observers," but context implies medical professionals, likely dermatologists).

4. Adjudication Method for the Test Set:

The document mentions "statistical analysis was performed on the collected ratings" for several studies, but it does not specify an adjudication method (e.g., 2+1, 3+1) for cases where expert opinions might differ in reader studies. For the studies comparing maps to pathology or physical structures, it implies direct comparison or subjective rating/qualitative analysis rather than expert consensus on a ground truth prior to analysis.

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

• Was an MRMC study done? Yes, several of the described studies, particularly the "retrospective reader study" involving multiple board-certified dermatologists, appear to be MRMC in nature, as they involve multiple readers evaluating multiple cases. However, the studies are framed as "validation activities" and comparisons for substantial equivalence, rather than a direct MRMC comparative effectiveness study aiming to quantify human reader improvement with AI vs. without AI assistance.
• Effect Size of Human Readers Improving with AI vs. Without AI Assistance: The document does not report any effect size for how much human readers improve with AI assistance vs. without AI assistance. The described studies focus on validating the skin parameter maps themselves and comparing them to existing methods/predicate devices. The device is intended "only to complement dermoscopy," suggesting its role as an adjunct.

6. Standalone (Algorithm Only) Performance:

The document does not describe a standalone (algorithm only without human-in-the-loop performance) study for the Demetra Analytics Toolkit. The device provides "maps that show the relative location of blood and pigment" which are "intended only to complement dermoscopy." Its function is described as aiding the user in visualizing patterns, indicating it's an assistive tool for a human reader rather than a diagnostic algorithm operating in isolation.

7. Type of Ground Truth Used:

The ground truth for the test sets varied across the studies:

• Expert Consensus/Subjective Rating: For several reader studies ("Clinical validation of Demetra Skin Parameter Maps," "Validation of skin structures imaged in the Skin Parameter Maps," Clinical Study at Charité/Oregon), the "ground truth" for evaluation appears to be the subjective ratings and qualitative feedback directly from the participating dermatologists/observers on the utility and consistency of the maps.
• Pathology Findings: For the "Correlation of structures visualized in the Skin Parameter Maps with pathology findings" study, the ground truth was pathology H&E images.
• Predicate Device Performance: For "SIAScans vs. Barco Analytics Toolkit," the performance of the predicate device (Siascope) served as a comparative reference.
• Physical Structures/Clinical Use: For "Validation of skin structures imaged in the Skin Parameter Maps," the ground truth was the expected clinical utility and visualization of skin structures by a dermatologist. For "Clinical validation of Demetra Skin Parameter Maps," the cases represented "various dermatology conditions for which a dermatologist can use a dermatoscope."

8. Sample Size for the Training Set:

The document does not provide any information regarding the sample size used for the training set of the Demetra Analytics Toolkit's algorithms.

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

The document does not provide any information on how the ground truth for the training set was established. Given the focus on clinical validation for substantial equivalence and the absence of standalone AI performance claims, details about the model's training might not have been explicitly required or provided in this summary.

Ask a specific question about this device

The TruView Light Cable is intended to provide surgical site illumination from a fiber optic light source.

The TruView Light Cable is a fiber optic surgical light designed to be compatible with a variety of fiber optic light sources.

The provided text describes the submission of a 510(k) premarket notification for a medical device called the "TruView Light Cable" and its variants. This document does not describe a study involving an AI/Machine Learning device or a diagnostic algorithm. Instead, it focuses on the substantial equivalence of a physical medical device (a fiber optic light cable) to existing predicate devices.

Therefore, many of the requested criteria related to AI/ML model performance, such as sample sizes for training/test sets, expert adjudication, MRMC studies, standalone algorithm performance, and ground truth establishment for AI models, are not applicable to this document.

However, the document does contain information about performance testing for the physical device. Here's a breakdown of the relevant information provided:

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

The document states that the TruView Light Cable was subjected to three performance tests and "met the acceptance criteria for the testing performed." While specific numerical acceptance criteria and performance values are not explicitly detailed in a table, the document lists the types of tests and their purpose:

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

• Sample Size: Not specified. The document simply states "three (3) performance tests." It does not indicate the number of units tested for each performance test.
• Data Provenance: Not specified regarding "country of origin of the data" or "retrospective/prospective." This testing would typically be prospective, in-house laboratory testing of the manufactured devices.

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 Applicable. This is a physical device performance test, not a diagnostic algorithm requiring expert interpretation of medical images or data. Ground truth would be defined by engineering specifications and objective measurements (e.g., temperature, fit, light intensity).

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

• Not Applicable. See point 3.

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:

• Not Applicable. This is not an AI-assisted diagnostic device.

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

• Not Applicable. This is not an algorithm.

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

• For a physical device like a light cable, the "ground truth" would be established by engineering specifications, regulatory standards, and objective measurements.
  • For the Fit Test: Successful mechanical coupling and operation.
  • For the Collateral Heating Test: Temperature measurements staying below defined safety thresholds for burns.
  • For the Intensity Test: Light intensity measurements meeting efficacy requirements while staying below defined thresholds to prevent patient injury.

8. The sample size for the training set:

• Not Applicable. This is not an AI/ML model that requires a training set.

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

• Not Applicable. See point 8.

Ask a specific question about this device

The Barco Digital Dermatoscope is a non-invasive skin imaging system, which acquires multispectral and white light dermoscopic images and clinical photographs of the skin. These can be stored, retrieved, displayed and reviewed by trained medical practitioners.

The Barco Demetra BDEM-01 is designed to capture images of the skin and optimize the imaging and documentation workflow. The “Barco Demetra BDEM-01” consists of a hardware device and a software application. The hardware device is a portable, battery powered medical device for acquiring and visualizing images of the skin. The device acquires multispectral optical dermoscopic images in a contact mode (device in contact with the skin). In addition, the device can also acquire a clinical close-up image, when it is held at up to 10 to 15 cm from the skin, and a clinical overview image when it is held at a distance of approximately 35-55 cm from the skin. The stand-alone software application is cloud software with a related web application. The cloud software can also generate one or more reports and feedback to the device.

The provided text is a Premarket Notification (510(k)) summary for the Demetra BDEM-01 device, a non-invasive skin imaging system. It focuses on demonstrating substantial equivalence to a predicate device (Microderm - K040171) rather than presenting a performance study against specific acceptance criteria for an AI/algorithm-driven device.

Therefore, this document does not contain the information required to describe acceptance criteria and a study that proves a device meets them in the context of an AI-driven medical device, as it describes a non-algorithm-driven imaging system.

Here's why and what information is missing:

• No AI/Algorithm: The device description clearly states "The Barco Demetra BDEM-01 is designed to capture images of the skin and optimize the imaging and documentation workflow. The 'Barco Demetra BDEM-01' consists of a hardware device and a software application." There is no mention of any artificial intelligence, machine learning, or algorithm that processes these images beyond storage, retrieval, display, and review by trained medical practitioners. The "multispectral images" are acquired, but there's no indication of AI interpretation of these multispectral data for diagnosis or risk assessment.
• No Diagnostic Aid Claim (for AI): The Indications for Use state "These can be stored, retrieved, displayed and reviewed by trained medical practitioners." This implies a tool for human review, not an autonomous diagnostic or assistive AI.
• Performance Testing Focus: The "Performance testing" section (9) focuses on bench tests validating differences from the predicate device related to hardware modifications (Multispectral LEDs illumination, hand-held design, biocompatibility) and basic image acquisition review, not on the performance of a diagnostic algorithm. The criteria listed are simply "PASS," indicating compliance with safety and engineering standards.

To answer your request, if this were an AI-driven device, the following information would typically be found in a 510(k) summary or an associated clinical study report for an AI/ML product:

1. A table of acceptance criteria and the reported device performance: This would list metrics like sensitivity, specificity, AUC, F1-score, accuracy, etc., along with the target values and the achieved values from the study.
2. Sample sizes used for the test set and the data provenance: Details on the number of cases/images used for testing, where the data came from (e.g., specific hospitals, geographical regions), and whether it was retrospectively collected or prospectively gathered.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Information on the number of clinicians (e.g., dermatologists, radiologists) who provided the reference standard for the test data, and their relevant experience and certifications.
4. Adjudication method for the test set: How disagreements among the experts establishing ground truth were resolved (e.g., majority vote, third expert review, consensus meeting).
5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done: For AI-assisted reading, this study would compare human performance with and without AI assistance, quantifying the improvement (effect size) in diagnostic accuracy, efficiency, or other relevant metrics.
6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done: Often, an initial study evaluates the AI's performance independently against the ground truth.
7. The type of ground truth used: Whether ground truth was established by expert consensus, biopsy/pathology results, long-term patient outcomes, or a combination.
8. The sample size for the training set: The number of cases/images used to train the AI model.
9. How the ground truth for the training set was established: Similar to the test set, but for the data used during model development.

Because the provided document pertains to a primary imaging device, and not an AI/ML diagnostic aid, it lacks the specific study design elements and performance metrics that would be associated with an AI product's acceptance criteria.

Ask a specific question about this device

The VivaScope® System is intended to acquire, store, retrieve, display and transfer in vivo images of tissue, including blood, collagen and pigment, in exposed unstained epithelium and the supporting stroma for review by physicians to assist in forming a clinical judgment.

The VivaScope® System is a reflectance confocal microscope, full color macroscopic imager, and software that captures images of in vivo tissue specimens from the exposed surface of the tissue, through the unstained epithelium and into the superficial supporting stroma. It provides non-invasive in vivo images of the epithelium and supporting stroma. The VivaScope® System does NOT provide automated analysis or diagnosis of the images it produces. It is capable of imaging cells in the epidermis of skin and the fibrous tissue (primarily collagen and fibrin) in the dermis. In addition, it is possible to visualize circulation of blood cells (including both erythrocytes and leukocytes) in capillaries and other small vessels.

The VivaScope® System produces horizontal sections of the skin using safe. low power infrared laser light at nominal wavelength of 830 nm (CDRH laser Class 1). Horizontal sections make it straightforward to view the various lavers of the skin in sequence, from the outer surface of the stratum corneum, through the granular, spinous and basal lavers, to the level of the superficial reticular dermis.

The VivaScope® System produces high resolution images of the skin using confocal laser scanning microscopy. The key feature of confocal microscopy is the ability to produce in-focus images of thick specimens called "optical sectioning". The system is able to accomplish this by having the point source laser light, the illuminated spot in the sample, and the pinhole all lie in optically conjugate focal planes. The size of the pinhole (located in front of the photodiode) is matched to the size of the illuminated spot to reject out of focus light allowing for imaging of thin optical sections.

The VivaScope® System can image, display, store, retrieve, import and export in vivo confocal and macroscopic color images using the VivaScan® operating software and supporting PC hardware. Images are saved and stored using standard lossless image compression algorithms. Images are communicated to other devices using DICOM standard functionality that is incorporated into the VivaScan® operating software.

The VivaScope® System is comprised of four (4) major functional components: an imager, a display, a PC and a cart. A VivaScope® System will have either a VivaScope® arm mounted imaging head or a VivaScope® handheld imaging head, or both, and optionally, a VivaCam® full color macroscopic imaging head.

This document describes a 510(k) submission for the VivaScope® System, an in vivo confocal reflectance microscope.

Acceptance Criteria and Device Performance

The provided document does not contain a table of acceptance criteria nor reported device performance data in the manner typically expected for demonstrating clinical efficacy or diagnostic accuracy. Instead, the submission focuses on demonstrating substantial equivalence to a predicate device based on technological characteristics and safety testing.

The "Performance Data" section states: "Validation data to confirm the visualization of blood collagen and pigment in the images produced by the VivaScope were submitted for the predicate. No similar data were generated for the modified device because the fundamental scientific technology did not change." This indicates that the performance criteria for visualization were met by the predicate, and since the core technology is unchanged, these criteria are considered met by the modified device.

The performance data presented are primarily regarding safety and compliance with engineering standards:

Study Information

The document does not describe a clinical study with a test set, ground truth, or statistical analysis of diagnostic performance for the modified VivaScope® System. The regulatory approach taken here is substantial equivalence to a predicate device, arguing that the changes are minor and do not affect the fundamental scientific technology or intended use.

Therefore, the following information points cannot be provided from the given text:

2. Sample size used for the test set and the data provenance: Not applicable, no new clinical test set described for diagnostic performance.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable, no new clinical test set described.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set: Not applicable, no new clinical test set described.
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: Not applicable. The device does NOT provide automated analysis or diagnosis.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not applicable. The device does NOT provide automated analysis or diagnosis.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc): For the predicate device, visualization data were submitted. The type of ground truth for that visualization is not specified in this document.
8. The sample size for the training set: Not applicable. The device does not involve AI or machine learning that would require a training set.
9. How the ground truth for the training set was established: Not applicable. The device does not involve AI or machine learning.

Ask a specific question about this device

The Isolux Ilc OptiLux LED Illuminator is indicated for use in transmitting light for illumination purposes from an LED source via a fiber optic cable and attached to either an endoscope, surgical head light or other tools that contain in providing illumination to body cavities during examinations or surgical procedures.

Not Found

The provided documents are a 510(k) clearance letter and an Indications for Use statement for the "OptiLux LED Illuminator." These documents, from the FDA, confirm the device's regulatory clearance and its intended use but do not contain any information regarding acceptance criteria, device performance studies, or data about the device's accuracy or efficacy.

Therefore, I cannot fulfill your request for information on the following:

1. A table of acceptance criteria and the reported device performance: This information is not present in the provided text.
2. Sample size used for the test set and the data provenance: Not available.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not available.
4. Adjudication method for the test set: Not available.
5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, and the effect size: Not available.
6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done: The OptiLux LED Illuminator is a physical device for illumination, not an algorithm. Therefore, this type of study is not applicable, and no information about it would be found here.
7. The type of ground truth used: Not applicable and not available.
8. The sample size for the training set: Not applicable and not available.
9. How the ground truth for the training set was established: Not applicable and not available.

The documents primarily focus on:

• The FDA's determination of substantial equivalence to a predicate device.
• The regulatory classification of the device (Class II).
• The indications for use: "transmitting light for illumination purposes from an LED source via a fiber optic cable and attached to either an endoscope, surgical head light or other tools that contain in providing illumination to body cavities during examinations or surgical procedures."

Ask a specific question about this device