Search Results

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

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 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 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 I). Horizontal sections make it straightforward to view the various layers of the skin in sequence, from the outer surface of the stratum comeum, through the granular, spinous and basal layers, 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 [ocal 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 supportin 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.

The provided document is a 510(k) summary for the VivaScope® System, which is a medical device intended to acquire, store, retrieve, display, and transfer in vivo images of tissue for review by physicians.

Based on the document, here's how the requested information can be extracted or inferred:

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

The document does not explicitly state "acceptance criteria" and "reported device performance" in a quantitative manner as one might expect for a typical performance study of a new medical device. Instead, the 510(k) summary focuses on demonstrating substantial equivalence to predicate devices. The "performance" is primarily described in terms of its functional capabilities and similarities to the predicates.

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 does not report any sample size for a test set or provide details on data provenance (country of origin, retrospective/prospective). This 510(k) summary focuses on demonstrating substantial equivalence based on technological characteristics and intended use, rather than a clinical performance study with a test set.

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)

Since no clinical performance study with a test set is described, there is no information regarding experts used to establish ground truth or their qualifications.

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

As no clinical performance study is described, there is no information on an adjudication method for a test set.

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

The document does not mention a multi-reader multi-case (MRMC) comparative effectiveness study. The VivaScope® System is described as not providing automated analysis or diagnosis, indicating that it is not an AI-assisted device in that sense, but rather an imaging tool for physician review. Therefore, there is no information on the effect size of human reader improvement with/without AI assistance.

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

The document explicitly states: "The VivaScope® System does NOT provide automated analysis or diagnosis of the images it produces." This indicates that a standalone algorithm performance study was not conducted because the device is not an AI-based diagnostic tool. Its function is to acquire and display images for human review.

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

Since no clinical performance study or test set with specific ground truth evaluation is described, this information is not available in the document.

8. The sample size for the training set

The document does not mention a training set. This is consistent with the device not being an AI-based diagnostic algorithm requiring training data.

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

Since there is no mention of a training set, this information is not applicable and not provided.

Summary of focus from the document:

This 510(k) submission primarily focuses on demonstrating substantial equivalence of the VivaScope® System by:

• Comparing its intended use to legally marketed predicate devices.
• Detailing its technological characteristics (e.g., imaging capabilities, components, operating principle, image handling) and highlighting similarities and differences with predicates.
• Addressing safety aspects, particularly regarding the laser light source, and ensuring compliance with standards.

The document is a regulatory filing for an imaging device, not an AI/CADe/CADx device, and therefore does not include the typical performance study details (test sets, ground truth, expert readers, AI metrics) often found for such technologies.

Ask a specific question about this device

The SIAscope is a non-invasive skin analysis system, which provides color bitmaps called 'SIAscans' that show the relative location of blood, collagen and pigment.
CAUTION : This device should only be used to scan the patient's skin.

The SIAscope is a quick, non-invasive device for imaging skin conditions. It uses a technique known as 'Spectrophotometric Intracutaneous Analysis' (SIAscopy) to identify and display graphically the separate components of the skin. SIAscopy uses a digital camera and light (both visible and near-infrared) to investigate the skin's interior structure.
The SlAscope operates by illuminating the skin with LEDs and measuring the intensity of remitted light. The intensity of the illumination is similar to the emission from a typical hand held torch or remote control unit.

Here's the analysis of the provided text regarding the SIAscope V device, focusing on acceptance criteria and supporting studies:

The provided text is a 510(k) Summary for the SIAscope V, and it primarily focuses on establishing substantial equivalence to a predicate device (SIAscope II). It does not contain information about specific acceptance criteria, a standalone study proving the device meets acceptance criteria, sample sizes for test or training sets, ground truth establishment methods, or Multi-Reader Multi-Case (MRMC) comparative effectiveness studies.

The document states that "Where alterations have been make this have been design to improve the imaging performance, reliability and safety of the device over and above the predicate device." However, no specific performance metrics or studies are provided to substantiate these improvements, nor are there acceptance criteria defined.

Therefore, many of the requested sections will be marked as "Not Available in Document."

Acceptance Criteria and Study Information for SIAscope V

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)

• Sample Size for Test Set: Not Available in Document
• Data Provenance: Not Available in Document (The document focuses on device design and comparison, not clinical study data).

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)

• Number of Experts: Not Available in Document
• Qualifications of Experts: Not Available in Document

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

• Adjudication Method: Not Available in Document

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

• MRMC Study Done?: No, an MRMC study is not mentioned or described in the document. The SIAscope is described as providing "SIAscans" to show relative location of blood, collagen, and pigment, implying it's an imaging tool for analysis, not an AI-assisted diagnostic tool for human readers in the context usually implied by MRMC studies of AI.
• Effect Size of Improvement: Not Applicable / Not Available in Document.

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

• Standalone Study Done?: Not Available in Document. The document mentions "software algorithms" for SIAscopy, but it does not describe a standalone performance study. The device provides "color bitmaps" or a "synthesized image" for analysis, suggesting it's an image acquisition and processing system rather than an algorithm producing a diagnostic output without human interpretation.

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

• Type of Ground Truth: Not Available in Document. As no study is described to validate the device's diagnostic performance, no ground truth is mentioned. The device's output is "relative location of blood, collagen and pigment," which is an imaging characteristic rather than a definitive diagnosis requiring a ground truth like pathology.

8. The sample size for the training set

• Sample Size for Training Set: Not Applicable / Not Available in Document. The document states that the "software algorithms and theory of SIAscopy is the same as found in the predicate device." This suggests the algorithms were developed prior to this submission and are not described as being subject to a new training phase for the SIAscope V.

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

• Ground Truth Establishment for Training Set: Not Applicable / Not Available in Document. As noted above, the algorithms are stated to be the same as the predicate, and no training data or ground truth establishment is described for this submission.

Ask a specific question about this device

MicroDERM® is intended for the acquisition and storage of images of skin surfaces. These images can then be retrieved, printed, reviewed and displayed.

MicroDERM® is a digital dermascope and software system, which captures images of skin surfaces for physician diagnostic review and referral purposes. These images can be sent to other computers using a modem or network card. It consists of the MicroDERM® camera, MicroDERM® software, and a frame grabber card. The MicroDERM® software runs under the Microsoft® Windows 2000 operating system. MicroDERM is not intended as a diagnostic device.

This document is a 510(k) premarket notification for the MicroDERM® device, which is a digital dermascope and software system. The document states that the device is not intended as a diagnostic device, but rather for the acquisition and storage of images of skin surfaces. Therefore, the acceptance criteria and related studies provided are focused on performance standards for medical devices generally, rather than diagnostic accuracy metrics.

Here's a breakdown of the requested information based on the provided text:

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)

This information is not provided in the document. The document primarily focuses on compliance with general medical device standards and does not detail a clinical test set or data provenance for evaluative purposes.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)

This information is not provided in the document. Since the device is not intended for diagnosis, the concept of "ground truth" for patient outcomes or conditions in a clinical study is not applicable in the context of the provided information.

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

This information is not provided in the document.

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

This information is not provided in the document. The MicroDERM is described as an image acquisition and storage device, not an AI-assisted diagnostic tool.

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

A standalone performance evaluation related to diagnostic accuracy or clinical outcomes was not performed, nor is it relevant given the stated indications for use. The "Performance Standards" listed are for medical device quality systems, electrical safety, and image handling, not for AI algorithm performance. The device is explicitly stated as "not intended as a diagnostic device."

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

This information is not provided and is not applicable in the context of the device's stated purpose as an image acquisition and storage system, rather than a diagnostic tool.

8. The sample size for the training set

This information is not provided in the document. Since the device is not an AI-based diagnostic tool, a "training set" in that sense would not be relevant.

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

This information is not provided and is not applicable as there is no indication of an AI-based diagnostic algorithm requiring a training set with established ground truth.

Ask a specific question about this device

SIAscope is a non-invasive skin analysis system, which provides a synthesized 'image' showing the relative location of blood collagen and pigment.

SIAscope is a non-invasive skin analysis system.

I am sorry, but the provided text is a letter from the FDA regarding a 510(k) premarket notification for a device called SIAscope II. The letter primarily addresses the substantial equivalence determination and regulatory compliance. It does not contain any information about acceptance criteria, device performance studies, sample sizes, expert qualifications, or ground truth establishment. Therefore, I cannot fulfill your request based on the given input.

Ask a specific question about this device

SIAscope is a self -contained non-invasive skin analysis system, which provides a synthesized 'image' showing the relative location of blood, collagen and pigment.

SIAscope is a self -contained non-invasive skin analysis system, which provides a synthesized 'image' showing the relative location of blood, collagen and pigment.

I apologize, but the provided text only contains an FDA 510(k) clearance letter for a device called "SIAscope." This letter confirms that the device is substantially equivalent to a legally marketed predicate device and outlines regulatory information.

However, it does not contain any information regarding acceptance criteria, study details, performance metrics, sample sizes, ground truth establishment, or expert qualifications. Therefore, I am unable to provide the detailed answer you requested based solely on the provided input.

To answer your questions, I would need access to the actual 510(k) submission summary or a separate study report for the SIAscope device.

Ask a specific question about this device