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.

Device Description

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.

AI/ML Overview

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

Category/Test	Implicit Acceptance Criterion	Reported Device Performance
Software Verification Testing	Software functions as intended and meets specifications.	PASS
Usability Engineering Testing	Device is safe and effective for its intended users and use environments.	PASS
Design Validation	Device functions as specified, including integration with the BDEM-01 device.	PASS (Implied by overall conclusion and no issues reported)
Clinical Validation Activities	Device performance is comparable to the predicate device and supports stated Indications for Use without new safety/effectiveness issues.	Supported by multiple retrospective and prospective studies, leading to a conclusion of substantial equivalence.

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.

Summary

{0}------------------------------------------------

Image /page/0/Picture/0 description: The image contains the logo of the U.S. Food and Drug Administration (FDA). On the left is the Department of Health & Human Services logo. To the right of that is the FDA logo, which is a blue square with the letters "FDA" in white. To the right of the FDA logo is the text "U.S. FOOD & DRUG ADMINISTRATION" in blue.

Barco NV Julie Vandecandelaere Regulatory Affairs Officer President Kennedypark 35 Kortrijk. W-VL 8500 Belgium

February 18, 2021

Re: K201408

Trade/Device Name: Demetra Analytics Toolkit Regulation Number: 21 CFR 878.4580 Regulation Name: Surgical Lamp Regulatory Class: Class II Product Code: PSN Dated: January 18, 2021 Received: January 21, 2021

Dear Julie Vandecandelaere:

We have reviewed your Section 510(k) premarket notification of intent to market the device referenced above and have determined the device is substantially equivalent (for the indications for use stated in the enclosure) to legally marketed predicate devices marketed in interstate commerce prior to May 28, 1976, the enactment date of the Medical Device Amendments, or to devices that have been reclassified in accordance with the provisions of the Federal Food, Drug, and Cosmetic Act (Act) that do not require approval of a premarket approval application (PMA). You may, therefore, market the device, subject to the general controls provisions of the Act. Although this letter refers to your product as a device, please be aware that some cleared products may instead be combination products. The 510(k) Premarket Notification Database located at https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/pmn.cfm identifies combination product submissions. The general controls provisions of the Act include requirements for annual registration, listing of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration. Please note: CDRH does not evaluate information related to contract liability warranties. We remind you, however, that device labeling must be truthful and not misleading.

If your device is classified (see above) into either class II (Special Controls) or class III (PMA), it may be subject to additional controls. Existing major regulations affecting your device can be found in the Code of Federal Regulations, Title 21, Parts 800 to 898. In addition, FDA may publish further announcements concerning your device in the Federal Register.

Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act or any Federal statutes and regulations administered by other Federal agencies. You must comply with all the Act's requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part 801 and Part 809); medical device reporting of medical device-related adverse events) (21 CFR

{1}------------------------------------------------

for devices or postmarketing safety reporting (21 CFR 4, Subpart B) for combination products (see https://www.fda.gov/combination-products/guidance-regulatory-information/postmarketing-safety-reportingcombination-products); good manufacturing practice requirements as set forth in the quality systems (QS) regulation (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.

Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR Part 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to https://www.fda.gov/medical-device-safety/medical-device-reportingmdr-how-report-medical-device-problems.

For comprehensive regulatory information about mediation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/medicaldevices/device-advice-comprehensive-regulatory-assistance) and CDRH Learn (https://www.fda.gov/training-and-continuing-education/cdrh-learn). Additionally, you may contact the Division of Industry and Consumer Education (DICE) to ask a question about a specific regulatory topic. See the DICE website (https://www.fda.gov/medical-device-advice-comprehensive-regulatoryassistance/contact-us-division-industry-and-consumer-education-dice) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).

Sincerely.

Neil R.P. Ogden, M.S. Assistant Director DHT4A: Division of General Surgery Devices OHT4: Office of Surgical and Infection Control Devices Office of Product Evaluation and Quality Center for Devices and Radiological Health

Enclosure

{2}------------------------------------------------

Indications for Use

510(k) Number (if known) K201408

Device Name Demetra Analytics Toolkit

Indications for Use (Describe)

Type of Use (Select one or both, as applicable)

Prescription Use (Part 21 CFR 801 Subpart D)
Over-The-Counter Use (21 CFR 801 Subpart C)

CONTINUE ON A SEPARATE PAGE IF NEEDED.

This section applies only to requirements of the Paperwork Reduction Act of 1995.

DO NOT SEND YOUR COMPLETED FORM TO THE PRA STAFF EMAIL ADDRESS BELOW.

The burden time for this collection of information is estimated to average 79 hours per response, including the time to review instructions, search existing data sources, gather and maintain the data needed and complete and review the collection of information. Send comments regarding this burden estimate or any other aspect of this information collection, including suggestions for reducing this burden, to:

Department of Health and Human Services Food and Drug Administration Office of Chief Information Officer Paperwork Reduction Act (PRA) Staff PRAStaff(@fda.hhs.gov

"An agency may not conduct or sponsor, and a person is not required to respond to, a collection of information unless it displays a currently valid OMB number."

{3}------------------------------------------------

K201408

510(k) Summary
1. Company	Barco N.V.Healthcare Division35 President Kennedypark8500 KortrijkBELGIUM
2. Contactperson	Julie VandecandelaereRegulatory Affairs OfficerTel: +32 (0)56 26 13 19julie.vandecandelaere@barco.com
3. Date ofsubmission	February 17 2021
4. Deviceinformation	Trade name/model: Demetra Analytics ToolkitCommon name: Light Based ImagingClassification name: Surgical LampClassification code: PSNRegulation number: 878.4580Regulatory class: 2
5. Predicatedevice	SIAscope V - Astron Clinica Limited - K062736
6. Devicedescription	The Barco Demetra Analytics Toolkit is a software application used to support analysis ofdermoscopic 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 highlightingsurface contours. The Skin Parameter Maps Tool provides images generated frommultispectral image sets and aids the user in visualizing blood and pigment patterns in theskin. 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.
7. Indicationsfor Use of theDevice	The Barco Demetra Analytics Toolkit is a non-invasive skin analysis system. The BarcoDemetra Skin Parameter Maps Tool provides maps that show the relative location ofblood and pigment. The Barco Demetra Skin Parameter Maps Tool is intended only tocomplement dermoscopy.

Image /page/3/Picture/5 description: The image shows the word "BARCO" in white letters against a red background. The letters are bold and sans-serif. The "O" in "BARCO" is stylized with a circle and a line extending from it.

{4}------------------------------------------------

K201408

8. Comparison	Trade Name/Device Name	Analytics Toolkit	SIAscope V
of technological	Product Code	PSN	PSN
characteristics	Regulatory Class	II	II
	Indications for use	The Barco Demetra AnalyticsToolkit is a non-invasive skinanalysis system. The BarcoDemetra Skin Parameter MapsTool provides maps that show therelative location of blood andpigment. The Barco DemetraSkin Parameter Maps Tool isintended only to complementdermoscopy.	The SIAscope is a non-invasive skin analysissystem, which providescolor bitmaps called'SIAscans' that show therelative location of blood,collagen and pigment
	Functionality	The Skin Parameter Maps aregenerated from multispectralimage sets and aid the user invisualizing blood and pigmentpatterns in the skin. The output ofthe Skin Parameter Maps isshown to the user as grayscaletwo-dimensional maps.	SIAscans show the relativelocation of blood, collagenand pigment
	Operating principle	Measuring intensity of remittedlight based on Beer-Lambertprinciple	Measuring intensity ofremitted light, based onKubelka-Munk skin model
	Analysis of images of	Skin	Skin
	Where used	Professional environment	Professional environment
	Digital or Analog images	Digital	Digital
	Illumination of thecompatible dermatoscope	White light LEDs (for live previewmode and dermoscopic images)	LEDs both visible andnear-infrared
		Multispectral LEDs (fordermoscopic images)• Amber• Deep Red• Green• Cyan• Blue• Royal Blue• Far Red• Red-Orange
	Design	Only software, compatible withBarco's Demetra BDEM-01dermatoscope (K192830)	Hardware dermatoscope +software (Dermetrics)

BAR

{5}------------------------------------------------

9.Performancetesting	The following performance data were provided in support of the substantial equivalencedetermination.
	Test performed	Result
	Software VerificationTesting	PASS
	Usability EngineeringTesting	PASS
	Design Validation, whichincludes integration testingwith BDEM-01 device
	The Demetra Analytics Toolkit software has a moderate level of concern.
	Several clinical validation activities have been performed to support safety andeffectiveness of the device. This included:
	- A retrospective clinical study "Clinical validation of Demetra Skin Parameter Maps".This retrospective reader study was performed by four board certifieddermatologists from different sites in the USA. The selected dataset contains a mixof 28 cases, representing various dermatology conditions for which a dermatologistcan use a dermatoscope during evaluation, with a focus on skin lesions suspiciousfor skin cancer. For each of the cases, all readers provided a subjective rating ofthe skin parameter maps corresponding to these cases. Statistical analysis wasperformed on the collected ratings. In addition qualitative feedback from the readerswas also collected.
	- A retrospective study "SIAScans vs. Barco Analytics Toolkit" performed by a boardcertified dermatologist from OHSU Dermatology Clinic, Portland. This studycompared performance of the Barco skin parameter maps with performance of thepredicate device (Siascope) for a representative set of specific types of cases.Contribution of 'other' signals to the maps (for both Siascope and Barco) was alsoincluded in the performance comparison.
	- A prospective clinical study performed by a board certified dermatologist fromWashington DC; and a dermato pathologist from Maryland. The study "Correlationof structures visualized in the Skin Parameter Maps with pathology findings" directlycompared skin parameter maps with pathology H&E images for collected 15 cases.Subjective rating as well as qualitative case analysis was performed. Statisticalanalysis was performed on the collected ratings.
	- A clinical study performed by a dermatologist from University Hospital Leuven inBelgium. This study "Validation of skin structures imaged in the Skin ParameterMaps" included 15 cases for which a dermatologist would typically use the skinparameter maps. Subjective rating as well as qualitative case analysis wasperformed. Statistical analysis was performed on the collected ratings.
	- A clinical study performed at Charité Universitätsmedizin Berlin, Germany; and at adermatology practice in Oregon, USA. Four observers participated in thisretrospective reader study. 28 representative cases were collected from an existingdatabase. Purpose of this study was to validate the skin parameter maps, and morespecifically also to validate the device when used with and without liquid interface.All observers provided subjective ratings for every case. Statistical analysis wasperformed on the collected ratings.
10.Conclusion	Demetra Analytics Toolkit was found to be as safe, as effective, and performs as well as the legally marketed predicate device, due to the following reasons:a) Device and predicate device have a similar intended useb) The technological characteristics differences from the predicate device do not affect safety or effectivenessc) Bench testing showed that the device has similar characteristics compared to the predicate device and did not reveal new issues of safety and performance.

P 3 / 4

BAI

{6}------------------------------------------------

K201408

Image /page/6/Picture/5 description: The image shows the word "BARCO" in white letters against a red background. The letters are bold and sans-serif. The "O" in "BARCO" is stylized with a circle and two horizontal lines extending from either side.

Regulation Number and Section

§ 878.4580 Surgical lamp.

(a)
Identification. A surgical lamp (including a fixture) is a device intended to be used to provide visible illumination of the surgical field or the patient.(b)
Classification. Class II (special controls). The device, when it is an operating room lamp, a surgical instrument light, a surgical floor standing light, an endoscopic surgical light, a surgical light connector, a ceiling mounted surgical light, a surgical light carrier, surgical light accessories, a surgical lamp, a remote illuminator, or an incandescent surgical lamp, is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 878.9.