Insight BD is a software application for the volumetric density assessment of digital x-ray images of the breast to aid health care professionals in the assessment of breast tissue composition. Insight BD is not a diagnostic aid and should be used only as adjunctive information when the final assessment of breast density category is made visually by medical professionals.

Device Description

The Siemens volumetric breast density analysis application software Insight BD provides volumetric assessment of digital x-ray images of the breast, including both digital mammograms and raw tomosynthesis projection images.

The assessment consists of generating and evaluating density maps where the value at each pixel represents the thickness of fibroglandular tissue above that pixel. From those density maps the software calculates quantitative values, namely

. volume of fibroglandular tissue in the breast in cm³
breast volume in cm³ .
. volumetric breast density in %
. breast density grade

The breast density grade is computed by thresholding of the volumetric breast density and conforms to BI-RADS® 5th Edition breast composition categories. The masking effect of dense fibroglandular tissue is automatically included in the results.

Insight BD is a software option for the Siemens digital mammography systems. Insight BD may be installed either on Siemens released PC hardware or on the Siemens digital mammography systems. Breast Density results are stored in the DICOM header and can be used for further documentation.

AI/ML Overview

Here's an analysis of the acceptance criteria and the study proving the device meets those criteria, based on the provided text for the Siemens Insight BD (K172832) device.

Device Name: Insight BD
K Number: K172832

The provided text focuses on demonstrating substantial equivalence to a predicate device (Volpara Imaging Software, K152028). While it mentions various performance assessments, it does not explicitly state specific quantitative "acceptance criteria" and "reported device performance" in a structured table as requested. Instead, it describes various tests performed to demonstrate consistency, reproducibility, and equivalence to the predicate.

Therefore, the table below will be constructed based on the types of performance assessments described, with the "Acceptance Criteria" inferred from the need to show "similar" or "expected" results, and "Reported Device Performance" reflecting the general statement that the device was found compliant or similar to expectations/predicate.

1. Table of Acceptance Criteria and Reported Device Performance

Acceptance Criteria (Inferred from study description)	Reported Device Performance (Summary from text)
Measurement Accuracy: Insight BD estimates are consistent with known values from breast phantoms.	"Measurement accuracy was assessed by comparing Insight BD estimates with known values from breast phantoms." (Implies satisfactory results)
Reproducibility (Left/Right, CC/MLO): Results for left and right breasts, and CC and MLO views, are similar.	"Reproducibility was assessed by running Insight BD over substantial data sets and the results for left and right breasts and CC and MLO views were compared to confirm that the results were similar for each view and each breast."
Reproducibility (DBT vs. FFDM): Results for the same woman imaged in tomosynthesis (DBT) and mammography (FFDM) modes are similar.	"Reproducibility was assessed by running Insight BD over substantial data sets where the same woman had been imaged on Siemens mammography systems in both tomosynthesis (DBT) and mammography (FFDM) modes, and the results were compared to confirm they were similar."
Reproducibility (Mammography vs. PRIME): Results for the same woman imaged in mammography and PRIME modes are similar.	"Reproducibility was assessed by running Insight BD over substantial datasets where the same women had been imaged on Siemens units running in both mammography and PRIME modes and the results were compared to confirm they were similar."
Consistency (with age): Results show an expected decrease in breast density with age.	"Consistency was assessed by running Insight BD over substantial datasets where the women's age was known and results were compared with the expected and known decrease in breast density with age."
Relationship to Visual Assessment: Insight BD output aligns with BI-RADS® 5th Edition density categories from qualified radiologists.	"Relationship to visual assessment was assessed by running Insight BD over x-ray images for which a BI-RADS® 5th Edition density category was available from MQSA qualified radiologists followed by a comparison of the two sets of data." (Implies a favorable comparison)
Equivalence to Predicate: Insight BD results are similar to the predicate device (Volpara).	"Equivalence was assessed by running both the predicate device Volpara and Insight BD over substantial datasets and the results were compared to confirm they were similar."

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

The document consistently uses the phrase "substantial data sets" to describe the sample sizes for reproducibility and equivalence testing, but does not provide specific numbers for the exact sample size of the test sets.

Data Provenance:

Country of Origin: Not explicitly stated, but the manufacturing site is Forchheim, Germany (Siemens Healthcare GmbH). The lack of specific country for the data implies it could be multi-national or from Siemens' internal clinical collaborators.
Retrospective or Prospective: Not explicitly stated. Given the use of "available from MQSA qualified radiologists" and "same woman had been imaged," it strongly suggests a retrospective collection of existing image data.

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

The document mentions "MQSA qualified radiologists" for establishing BI-RADS® 5th Edition density categories based on visual assessment.

Number of Experts: Not specified. The document states "a BI-RADS® 5th Edition density category was available from MQSA qualified radiologists," implying multiple radiologists might have contributed to the "available" categories, but it doesn't specify if this was a consensus reading or individual readings used for comparison.
Qualifications: "MQSA qualified radiologists." This implies they are certified to interpret mammograms in the U.S. and have relevant clinical experience in breast imaging.

4. Adjudication Method for the Test Set

The document does not describe a specific adjudication method (e.g., 2+1, 3+1) for resolving disagreements among experts during the ground truth establishment for the visual assessment comparison. It simply states that BI-RADS categories were "available from MQSA qualified radiologists," which could imply a single read or an already adjudicated consensus (though not explicitly stated).

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

No, a MRMC comparative effectiveness study was not explicitly done/described in the context of comparing human readers with AI assistance versus without AI assistance.

The study focuses on validating the standalone performance of Insight BD and its relationship to visual assessment and equivalence to a predicate. It does not evaluate the impact of the AI on human reader performance.

6. Standalone Performance Study (Algorithm Only)

Yes, standalone performance was done. The entire "Performance Data" Section 9 describes tests where the Insight BD software (algorithm only) was run on datasets to assess:

Measurement accuracy (against phantoms)
Reproducibility across different views and imaging modes
Consistency with known biological trends (age-related density decrease)
Relationship to visual assessment (comparison of algorithm output to radiologist-assigned BI-RADS categories)
Equivalence to the predicate device

These are all evaluations of the algorithm's output directly.

7. Type of Ground Truth Used

Multiple types of "ground truth" or reference standards were used:

Known values from breast phantoms: For measurement accuracy. This is an objective, engineered truth.
Expected and known medical trends (decrease in breast density with age): For consistency analysis. This represents biological/clinical truth.
BI-RADS® 5th Edition density categories available from MQSA qualified radiologists: For comparing the algorithm's output to human visual assessment. This is an expert consensus/visual assessment ground truth, though the consensus process isn't detailed.
Predicate device output: For assessing equivalence. This uses another validated device's output as a reference, implying its output serves as a de facto "truth" for comparative purposes.

8. Sample Size for the Training Set

The document does not specify the sample size used for the training set for the Insight BD algorithm. It only discusses the "Performance Data" for the test (validation) phase.

9. How Ground Truth for the Training Set Was Established

The document does not describe how the ground truth for the training set was established. This information is typically proprietary to the developer and not always fully disclosed in 510(k) summaries, which tend to focus on the validation/testing to demonstrate substantial equivalence.

Summary

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

Image /page/0/Picture/0 description: The image contains the logos of the U.S. Department of Health & Human Services and the U.S. Food & Drug Administration (FDA). The Department of Health & Human Services logo is on the left, featuring a stylized eagle. To the right of that is the FDA logo, which includes the letters "FDA" in a blue square, followed by the words "U.S. FOOD & DRUG" in blue, with "ADMINISTRATION" underneath.

Siemens Medical Solutions, Inc Denise Adams Regulatory Affairs Specialist 40 Liberty Boulevard 65-1A MALVERN, PA 19355

February 6, 2018

Re: K172832

Trade/Device Name: Insight BD Regulation Number: 21 CFR 892.2050 Regulation Name: Picture Archiving And Communications System Regulatory Class: Class II Product Code: LLZ Dated: February 1, 2018 Received: September 19, 2017

Dear Denise Adams:

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); and if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.

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

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 the CDRH's Office of Surveillance and Biometrics/Division of Postmarket Surveillance.

For comprehensive regulatory information about medical devices and radiation-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,

Mechat D. O'Hara For

Robert A. 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

510(k) Number (if known) K172832

Device Name Insight BD

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}------------------------------------------------

Image /page/3/Picture/0 description: The image shows the logo for Siemens Healthineers. The word "SIEMENS" is written in teal, and the word "Healthineers" is written in orange below it. To the right of the words is an orange graphic of several dots arranged in a circular pattern.

510(k) Summary: Insight BD

Company Siemens Medical Solutions USA, Inc. 40 Liberty Boulevard, 65-1A Malvern, PA 19355

Date Prepared December 15, 2017

This summary of 510(k) safety and effectiveness information is submitted in accordance with the requirements of SMDA 1990 and 21 CFR §807.92.

1. General Information

Importer/Distributor Siemens Medical Solutions USA, Inc. 40 Liberty Boulevard, 65-1A Malvern, PA 19355 Establishment Registration Number: 2240869

Location of Manufacturing Site

Siemens Healthcare GmbH Siemensstr. 1 91031 Forchheim, Germany Establishment Registration Number: 3004977335

2. Contact Person

Denise Adams, RAC Requlatory Affairs Specialist Siemens Medical Solutions USA, Inc. 40 Liberty Boulevard, 65-1A Malvern, PA 19355 adams.denise@siemens-healthineers.com

Alternate Contact Person

Patricia D. Jones, RAC Regulatory Affairs Specialist Siemens Medical Solutions USA, Inc. 40 Liberty Boulevard, 65-1A Malvern, PA 19355 patricia.d.jones@siemens-healthineers.com

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

1. Device Name and Classification

Trade Name	Insight BD
Classification Name	System, Image Processing, Radiological
Classification Panel	Radiology
Classification Regulation	21 CFR §892.2050
Device Class	Class 2
Product Code	LLZ

4. Legally Marketed Predicate Device

Trade Name	Volpara Imaging Software
510(k) #	K152028
Clearance Date	10/26/2015
Classification Name	System, Image Processing, Radiological
Classification Panel	Radiology
Classification Regulation	21 CFR §892.2050
Device Class	Class 2
Product Code	LLZ
Recall Information	This device has not been subject to a designrelated recall

5. Device Description

. volume of fibroglandular tissue in the breast in cm³
breast volume in cm³ .
. volumetric breast density in %
. breast density grade

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

6. Indications for Use

7. Substantial Equivalence

The Siemens Insight BD volumetric breast density application software is substantially equivalent to the commercially available Volpara Imaging Software (K152028).

The Insight BD has the same intended use, fundamental scientific technologies and performance characteristics as the predicate device Volpara Imaging Software and the performance of the Insight BD application software has been verified with similar tests as the predicate. The substantial equivalence comparison table below compares the main performance data of the subject device Siemens Insight BD to the cleared predicate Volpara Imaging Software (K152028).

Features /Technology	Subject DeviceInsight BD	Predicate DeviceVolpara Imaging SoftwareK152028	Remarks
Indications for Use	Insight BD is a softwareapplication for the volumetricdensity assessment of digitalx-ray images of the breast toaid health care professionalsin the assessment of breasttissue composition. InsightBD is not a diagnostic aid andshould be used only asadjunctive information whenthe final assessment ofbreast density category ismade visually by medicalprofessionals.	Volpara is a softwareapplication intended for usewith the raw data from digitalbreast x-ray systems,including tomosynthesis.Volpara calculates a densitymap and from thatdetermines volumetric breastdensity as a ratio offibroglandular tissue and totalbreast volume estimates.Volpara provides thesenumerical values along with aBI-RADS breast density 4thor 5th Edition category to aidhealth care professionals inthe assessment of breasttissue composition. Volparaproduces adjunctive	Same meaning,only wording isdifferent

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

Features /Technology	Subject DeviceInsight BD	Predicate DeviceVolpara Imaging SoftwareK152028	Remarks
		information. It is not aninterpretive or diagnostic aid.
Intended Users	Health Care Professionals	Health Care Professionals	Same
Image Source	Digital mammograms from• mammography or• tomosynthesis systems	Digital mammograms from• mammography or• tomosynthesis systems	Same
Anatomical Area	Breast	Breast	Same
Assessment Scope	Volumetric	Volumetric	Same
OperatingEnvironment	Windows	Windows	Same
Image Storage andReport Generation	YesOutput to the console	YesOutput to the console	Same
Numeric Output	• Volume of Fibroglandulartissue• Volume of Breast• Volumetric Breast Density• Siemens Breast DensityGrade corresponding toBI-RADS® 5th EditionBreast Density Category	• Volume of Fibroglandulartissue• Volume of Breast• Volumetric Breast Density• Volpara Density Gradecorresponding to BI-RADS®4th and 5th Edition BreastDensity Category	Siemensvolumetric breastdensityinformationcorresponds to BI-RADS® 5th Editionbreast densitycategory only
Storage of BreastDensity Informationin Image	Yes	No	Siemensvolumetric breastdensityinformation isstored in theDICOM header
Classification	21 CFR 892.2050; LLZ	21 CFR 892.2050; LLZ	Same
Software Level ofConcern	Moderate	Moderate	Same

8. Summary of Technological Characteristics of Subject Device as Compared with the Predicate Device

The Insight BD software is based on similar technology and algorithms to calculate the volumetric density as the predicate Volpara Imaging Software.

9. Performance Data

The Siemens Insight BD has been verified and validated according to the company's design control process. A risk analysis compliant with ISO 14971 has been provided and incorporated into the development effort. Software testing included both unit level and integrated system level testing.

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

The device was tested and determined to be compliant to the following standards:

ISO 14971	Medical devices – Application of risk management to medical devices
ISO 62304	Medical device software – Software life cycle processes
NEMA PS 3.1-3.20	Digital Imaging and Communications in Medicine (DICOM) Set

Density parameters were evaluated using various image data sets and results were compared against predicate performance, when appropriate.

. Measurement accuracy was assessed by comparing Insight BD estimates with known values from breast phantoms.
. Reproducibility was assessed by running Insight BD over substantial data sets and the results for left and right breasts and CC and MLO views were compared to confirm that the results were similar for each view and each breast.
. Reproducibility was assessed by running Insight BD over substantial data sets where the same woman had been imaged on Siemens mammography systems in both tomosynthesis (DBT) and mammography (FFDM) modes, and the results were compared to confirm they were similar.
. Reproducibility was assessed by running Insight BD over substantial datasets where the same women had been imaged on Siemens units running in both mammography and PRIME modes and the results were compared to confirm they were similar.
. Consistency was assessed by running Insight BD over substantial datasets where the women's age was known and results were compared with the expected and known decrease in breast density with age.
. Relationship to visual assessment was assessed by running Insight BD over x-ray images for which a BI-RADS® 5th Edition density category was available from MQSA qualified radiologists followed by a comparison of the two sets of data.
. Equivalence was assessed by running both the predicate device Volpara and Insight BD over substantial datasets and the results were compared to confirm they were similar.

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

10. General Safety and Effectiveness Concerns

The device labeling contains instructions for use and any necessary cautions and warnings to provide for safe and effective use of the device.

Risk management is ensured via a risk analysis, which is used to identify potential hazards and mitigations. These potential hazards are controlled by software means, user instructions, verification and validation testing to ensure that the product meets its intended uses.

11.Conclusion as to Substantial Equivalence

The Siemens volumetric breast density analysis application software Insight BD has the same intended use, fundamental scientific technology and performance characteristics as the predicate device. The 510(k) premarket notification for Insight BD 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).