DenSeeMammo provides a BI-RADS breast density 5th Edition category to aid radiologists in the assessment of breast density. DenSeeMammo produces adjunctive information. It is not a diagnostic aid since the final assessment of breast density category is made by an MQSA qualified interpreting physician.

DenSeeMammo core software has been built and tested on OS X based computers.

DenSeeMammo graphical use interface software has been built and tested on Windows, OS X and Linux based computers. DenSeeMammo is compatible for images obtained from GE Senographe Essentials and Hologic Selenia Dimension systems.

Device Description

DenSeeMammo is a software application intended for use with Full Field Digital Mammography systems. DenSeeMammo estimates BI-RADS breast density category by analyzing processed digital 2D mammograms using a fully automated comparison procedure. DenSeeMammo provides a BI-RADS breast density 5th Edition category to aid radiologists in the assessment of breast density. DenSeeMammo produces adjunctive information. It is not a diagnostic aid since the final assessment of breast density category is made by an MQSA qualified interpreting physician. DenSeeMammo core software has been built and tested on OS X based computers. DenSeeMammo graphical use interface software has been built and tested on Windows, OS X and Linux based computers. DenSeeMammo v1.2 is compatible for images obtained from GE Senographe Essentials and Hologic Selenia Dimension systems.

The software use processed digital 2D mammograms in a fully automated comparison procedure that produces a BI-RADS breast density category. The software processes and analyses the image according to proprietary algorithms that allow comparison to qualified databases containing images previously visually assessed by radiologists. For each patient it provides measures of BI-RADS breast density category. DenSeeMammo provides results per patient based on the maximum density category of the two breasts.

The software works in a client-server mode and requires that the user computer be on the same local network as the server. Computations are made on the server part of the system that also provide the graphical user interface to display the results. A web browser is required to display the graphical user interface: to select the patients' images and to display the assessment of the breast density according to the BI-RADS standards and the similar images.

The software was developed using the Java-1.8 language as a 3-component web application. The software was developed following an adapted version of the model – view – controller software architectural pattern.

The device does not contact the patient, nor does it control any life-sustaining devices.

AI/ML Overview

The provided text describes the DenSeeMammo software, a device that estimates BI-RADS breast density category from digital 2D mammograms. The document is a 510(k) summary, specifically for DenSeeMammo v1.2, which is an updated version of the previously cleared DenSeeMammo v1.0.

Here's an analysis of the acceptance criteria and the study that proves the device meets them, based on the provided text:

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

The document does not provide a formal table of explicit acceptance criteria with specific numerical targets for performance metrics (e.g., accuracy, sensitivity, specificity). Instead, it broadly states that "All verification and validation testing was successful in that established acceptance criteria was met for all of the tests conducted."

The performance testing section (Section 9) describes various tests performed to demonstrate the device's functionality and consistency. While it indicates that the tests were successful, it does not report specific quantitative performance metrics for DenSeeMammo v1.2 against radiologists' assessments, nor does it define what "established acceptance criteria" were.

Observed Performance (as described, but without numerical values):

Performance Aspect	Description from Document
Reproducibility	DenSeeMammo v1.2 software was run over twice on data sets of images to test reproducibility. DenSeeMammo v1.2 software was run over on a sample of exams, and left and right breast densities were compared to test reproducibility. (Implicit success, but no statistical measure provided).
Accuracy/Agreement	DenSeeMammo v1.2 software results were compared to visual assessment from MQSA-qualified radiologists. (Implicit success, but no statistical measure provided).
Compatibility	DenSeeMammo v1.2 software was run over substantial data sets of two views images (CC + MLO) from GE and Hologic systems, which had been previously assessed by MQSA-qualified radiologists. DenSeeMammo v1.2 software was run over substantial data sets of one view images from GE (CC) and Hologic (CC or MLO) systems, which had been previously assessed by MQSA-qualified radiologists. (Implicit success).
Usability	Beta site testing to assess the ability of physicians to successfully integrate the software into their existing systems as well as assess usability for target users. (Implicit success).

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

Test Set Sample Size: The document repeatedly uses the phrase "substantial data sets" when referring to the images used for testing (e.g., "substantial data sets of two views images," "substantial data sets of one view images"). However, it does not specify the exact number of cases or images in these test sets.
Data Provenance: The document does not explicitly state the country of origin of the data. It mentions compatibility with GE Senographe Essentials and Hologic Selenia Dimension systems, which are widely used globally, but offers no specific geographic information for the data sources. It is also unclear if the data was retrospective or prospective; however, given that it refers to images "previously assessed by MQSA-qualified radiologists," it strongly implies a retrospective collection of existing images.

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

Number of Experts: The document does not specify the exact number of MQSA-qualified radiologists used to establish the ground truth. It consistently refers to them in the plural ("radiologists").
Qualifications of Experts: The experts are described as "MQSA-qualified radiologists." MQSA (Mammography Quality Standards Act) qualification is a specific requirement in the United States for interpreting mammography. This indicates a high level of expertise in mammography interpretation.

4. Adjudication method for the test set:

The document mentions "comparison to qualified databases containing images previously visually assessed by MQSA-qualified radiologists." It implies that assessments from these radiologists serve as the ground truth. However, it does not describe any specific adjudication method (e.g., 2+1, 3+1 consensus, or independent reads with a tie-breaker) if there were discrepancies among radiologists for the ground truth establishment. It simply states "previously visually assessed," suggesting a single or pre-determined ground truth per image.

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 describe an MRMC comparative effectiveness study designed to assess how human readers improve with AI assistance versus without it. The device is intended to "aid radiologists in the assessment of breast density" and "produces adjunctive information," but the studies described focus on the standalone performance of the algorithm compared to radiologists' assessments, not on the human-AI team performance.

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

Yes, a standalone performance assessment was conducted. The "Performance Testing" section states:

"DenSeeMammo v1.2 software results were compared to visual assessment from MQSA-qualified radiologists."
"DenSeeMammo v1.2 software was run over substantial data sets... which had been previously assessed by MQSA-qualified radiologists."

This indicates that the algorithm's output (BI-RADS breast density category) was compared directly to the expert-determined ground truth, representing a standalone performance evaluation.

7. The type of ground truth used:

The ground truth used for the test set was expert consensus / visual assessment by MQSA-qualified radiologists using ACR BI-RADS V recommendations. This is explicitly stated: "Comparison to qualified databases containing images previously visually assessed by MQSA-qualified radiologists using ACR BI-RADS V recommendations."

8. The sample size for the training set:

The document does not provide any information regarding the sample size for the training set. It implicitly refers to "qualified databases" that the algorithm uses for "comparison," but it does not specify if these databases also served as training data, nor their size.

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

The document does not provide details on how the ground truth for any potential training set was established. It mentions that the software's algorithms "allow comparison to qualified databases containing images previously visually assessed by radiologists." This suggests a similar process to the test set ground truth (visual assessment by radiologists), but specific methodology for a training set is not described.

Summary

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

Image /page/0/Picture/0 description: The image contains the logo of the U.S. Food and Drug Administration (FDA). The logo consists of two parts: the Department of Health & Human Services logo on the left and the FDA logo on the right. The FDA logo features the letters "FDA" in a blue square, followed by the words "U.S. FOOD & DRUG" and "ADMINISTRATION" in blue text.

STATLIFE % Mrs. Valérie Hélin Authorized Correspondent EPIDEMIO3D 50 Milk Street, 16th Floor BOSTON MA 02109

June 26th, 2018

Re: K173574

Trade/Device Name: DenSeeMammo Regulation Number: 21 CFR 892.2050 Regulation Name: Picture Archiving And Communications System Regulatory Class: Class II Product Code: LLZ Dated: May 29, 2018 Received: May 31, 2018

Dear Mrs. Hélin:

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. 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); medical device reporting of medical device-related adverse events) (21 CFR 803); good manufacturing practice requirements as set forth in the quality systems (OS) regulation (21 CFR Part 820);

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

Page 2 - Mrs. Valérie Hélin

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 http://www.fda.gov/MedicalDevices/Safety/ReportaProblem/default.htm.

For comprehensive regulatory information about mediation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/MedicalDevices/DeviceRegulationandGuidance/) and CDRH Learn (http://www.fda.gov/Training/CDRHLearn). 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 (http://www.fda.gov/DICE) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).

Sincerely,

Jeff Balyer

for Robert Ochs, Ph.D. Director Division of Radiological Health Office of In Vitro Diagnostics and Radiological Health Center for Devices and Radiological Health

Enclosure

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

Indications for Use

Form Approved: OMB No. 0910-0120 Expiration Date: January 31, 2017 See PRA Statement below.

510(k) Number K173574

Device Name DenSeeMammo

Indications for Use (Describe)

DenSeeMammo is a software application intended for use with Full Field Digital Mammography systems.

DenSeeMammo estimates Bl-RADS breast density category by analyzing processed digital 2D mammograms using a fully automated comparison procedure.

DenSeeMammo core software has been built and tested on OS X based computers.

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

Prescription Use (Part 21 CFR 801 Subpart D) র

__ 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}------------------------------------------------

510(K) SUMMARY

Prepared June 20, 2018

Submitter Information 1

Company Name:	STATLIFE
Company Address:	39 RUE CAMILLE DESMOULINS94800 VILLEJUIF FRANCE
Company Phone:	+33 660 848 385
Company Facsimile:	+33 185 091 475
Contact Person:	Stéphane Ragusa, CEO
Authorized Correspondent Phone	Valérie Hélin, Director of medical and regulatory affair+33 682 437 010

2 Trade name and Common name

Trade Name:	DenSeeMammo
Software Version:	1.2
Common Name:	Imaging Software

3 Device Classification

Regulatory Class:	II
Review category:	Class II
Classification Panel:	Radiology;
Product Code:	LLZ
Classification:	System, Image Processing, Radiological: 21 CFR § 892.205

Identification of Predicate Device 4

The modified software is substantially equivalent to DenSeeMammo Software version 1.0 cleared pursuant to K152009 cleared December 5吨, 2017

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

5 Predicate Device Description

DenSeeMammo analyzes processed digital 2D mammograms in a fully automated comparison procedure that produces a BI-RADS breast density category.

DenSeeMammo handles processed images extracted from DICOM files as input.

DenSeeMammo core software has been built and tested on OS X based computers.

DenSeeMammo graphical user interface software has been built and tested on Windows, OS X and Linux based computers.

DenSeeMammo software is a component which accepts digital mammography images as an input. The software processes and analyses the image according to proprietary algorithms which allow comparison to qualified databases containing images previously assessed by radiologists. For each patient it provides measures of BI-RADS breast density category. DenSeeMammo provides results per patient based on the maximum density category of the two breasts.

The patient population is symptomatic and asymptomatic women undergoing mammography. The software does perform illustrative image display but only for illustrative purposes and not for interpretation or diagnostic.

б Comparison with Predicate device

DenSeeMammo software version 1.2 works in the same way as DenSeeMammo software 1.0 but is updated to make it compatible with digital mammograms from Hologic mammography systems and can work with a pair of images composed of two views (craniocaudal (CC) and mediolateral oblique (MLO)) or with an image composed of one view (CC for GE images, and CC or MLO for Hologic images).

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

Table 1 Substantial Equivalence comparison table

Characteristics	Predicate DeviceDENSEEMAMMO v1.0 (K152009)	Submission DeviceDENSEEMAMMO v1.2
Classification	LLZ	LLZ
Classification	892.2050	892.2050
Software level of concern	Moderate	Moderate
Device type	Not an interpretive or diagnostic aid	Not a diagnostic aid
Intended Use	DenSeeMammo is a softwareapplication intended for use with digitalmammography systems.DenSeeMammo estimates BI-RADSbreast density value by analyzingprocessed digital 2D mammogramsusing a fully automated comparisonprocedure.DenSeeMammo provides a BI-RADSbreast density 5th Edition category toaid radiologists in the assessment ofbreast density.DenSeeMammo produces adjunctiveinformation. It is not an interpretive ordiagnostic aid when the finalassessment of breast density category ismade by an MQSA-qualified interpretingphysician.DenSeeMammo core software has beenbuilt and tested on OS X basedcomputers. DenSeeMammo graphicaluse interface software has been builtand tested on Windows, OS X and Linuxbased computers.	DenSeeMammo is a software applicationintended for use with Full Field DigitalMammography systems.DenSeeMammo estimates BI-RADSbreast density category by analyzingprocessed digital 2D mammograms usinga fully automated comparison procedure.DenSeeMammo provides a BI-RADSbreast density 5th Edition category to aidradiologists in the assessment of breastdensity.DenSeeMammo produces adjunctiveinformation. It is not a diagnostic aidsince the final assessment of breastdensity category is made by an MQSAqualified interpreting physician.DenSeeMammo core software has beenbuilt and tested on OS X basedcomputers.DenSeeMammo graphical use interfacesoftware has been built and tested onWindows, OS X and Linux basedcomputers.DenSeeMammo v1.2 is compatible forimages obtained from GE SenographeEssentials and Hologic Selenia Dimensionsystems.
Intended users	Radiologists	Radiologists
Patient population	Symptomatic and asymptomatic womenundergoing mammography	Symptomatic and asymptomatic womenundergoing mammography
Image source	Digital mammography images	Digital mammography images
Compatibility	GE Digital Mammography systems	GE and Hologic Digital Mammographysystems
Anatomical area	Breast	Breast
Assessment scope	Provides results per patient based onthe maximum density category of thetwo breasts	Provides results per patient based on themaximum density category of the twobreasts
Assessment type	Comparison to qualified databasescontaining images previously visuallyassessed by MQSA-qualified radiologistsusing ACR BI-RADS V recommendations	Comparison to qualified databasescontaining images previously visuallyassessed by MQSA-qualified radiologistsusing ACR BI-RADS V recommendations
Characteristics	Predicate DeviceDENSEEMAMMO v1.0 (K152009)	Submission DeviceDENSEEMAMMO v1.2
Measures provided	For each breast: BI-RADS V breastdensity categoryFor each patient: BI-RADS V breastdensity category	For each breast: BI-RADS V breastdensity categoryFor each patient: BI-RADS V breastdensity category
Operating environment	Software core: OS X based computersSoftware graphical user interface:Windows, OS X or Linux basedcomputers	Software core: OS X based computersSoftware graphical user interface:Windows, OS X or Linux basedcomputers
Deployment	Stand-alone computer	Stand-alone computer

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

7 Indications for Use

DenSeeMammo is a software application intended for use with Field Digital Mammography systems.

DenSeeMammo estimates BI-RADS breast density category by analyzing processed digital 2D mammograms using a fully automated comparison procedure.

DenSeeMammo provides a BI-RADS breast density 5th Edition category to aid radiologists in the assessment of breast density.

DenSeeMammo produces adjunctive information. It is not a diagnostic aid since the final assessment of breast density category is made by an MQSA qualified interpreting physician.

DenSeeMammo core software has been built and tested on OS X based computers.

DenSeeMammo graphical use interface software has been built and tested on Windows, OS X and Linux based computers.

DenSeeMammo v1.2 is compatible for images obtained from GE Senographe Essentials and Hologic Selenia Dimension systems.

Technological Characteristics 8

DenSeeMammo is a software that aims at assessing the breast density of a woman. The software use processed digital 2D mammograms in a fully automated comparison procedure that produces a BI-RADS breast density category. The software processes and analyses the image according to proprietary algorithms that allow comparison to qualified databases containing images previously visually assessed by radiologists. For each patient it provides measures of BI-RADS breast density category. DenSeeMammo provides results per patient based on the maximum density category of the two breasts.

The software works in a client-server mode and requires that the user computer be on the same local network as the server. Computations are made on the server part of the system that also

{7}------------------------------------------------

provide the graphical user interface to display the results. A web browser is required to display the graphical user interface: to select the patients' images and to display the assessment of the breast density according to the BI-RADS standards and the similar images.

The software was developed using the Java-1.8 language as a 3-component web application (See 11.1 Components). The software was developed following an adapted version of the model – view – controller software architectural pattern.

The device does not contact the patient, nor does it control any life-sustaining devices.

ਰੇ Performance Testing

The DenSeeMammo software has been verified and validated according to the company's design control process and particularly according the IEC 62304 standard. A risk analysis compliant with ISO 14971 has been provided. Software testing included both unit level and integrated system level testing.

In addition to the verification and validation testing conducted for the specific modification to the software detailed in this 510(k), complete verification and validation data testing conducted for the predicate was repeated in order to ensure integration and backwards compatibility.

Verification bench testing included:

DenSeeMammo v1.2 software was run over twice on data sets of images to test reproducibility.
DenSeeMammo v1.2 software was run over on a sample of exams and left and right breast densities were compared to test reproducibility.
DenSeeMammo v1.2 software results were compared to visual assessment from MQSA-qualified radiologists.
DenSeeMammo v1.2 software was run over substantial data sets of two views images (CC + MLO) from GE and Hologic systems, which had been previously assessed by MQSA-qualified radiologists.
DenSeeMammo v1.2 software was run over substantial data sets of one view images from GE (CC) and Hologic (CC or MLO) systems, which had been previously assessed by MQSA-qualified radiologists. Visual assessments were performed from two views CC + MLO images.

{8}------------------------------------------------

Clinical validation testing included:

Beta site testing to assess the ability of physicians to successfully integrate the software into their existing systems as well as assess usability for target users.

All verification and validation testing was successful in that established acceptance criteria was met for all of the tests conducted.

10 General Safety and Effectiveness Concerns

The device contains instructions for use and any necessary cautions and warnings to provide for safe and effective use of this device. Risk management is ensured via a risk analysis, which is used to identify potential hazards. These potential hazards are controlled via software development, verification and validation testing.

Conclusions Drawn from Studies 11

The 510(k) Premarket Notification for DenSeeMammo v1.2 contains adequate information and data to demonstrate substantial equivalence to the predicate device.

Regulation Number and Section

§ 892.2050 Medical image management and processing system.

(a)
Identification. A medical image management and processing system is a device that provides one or more capabilities relating to the review and digital processing of medical images for the purposes of interpretation by a trained practitioner of disease detection, diagnosis, or patient management. The software components may provide advanced or complex image processing functions for image manipulation, enhancement, or quantification that are intended for use in the interpretation and analysis of medical images. Advanced image manipulation functions may include image segmentation, multimodality image registration, or 3D visualization. Complex quantitative functions may include semi-automated measurements or time-series measurements.(b)
Classification. Class II (special controls; voluntary standards—Digital Imaging and Communications in Medicine (DICOM) Std., Joint Photographic Experts Group (JPEG) Std., Society of Motion Picture and Television Engineers (SMPTE) Test Pattern).