Transpara Density is a software application intended for use with data from compatible digital breast tomosynthesis systems. Transpara Density utilises deep learning artificial intelligence algorithms to automatically determine volumetric breast density (VBD), breast volume, and an ACR BI-RADS 5th Edition breast density category to aid health care professionals in the assessment of breast tissue composition. It is not a diagnostic aid.

Device Description

Transpara Density is a software module that uses artificial intelligence techniques to assess breast density in mammography (DM) and breast tomosynthesis (DBT) images and provide support to radiologists in this task. The novel methods of Transpara Density, extend the capabilities of computer aided detection systems for mammography by providing radiologists with decision support via the output of density assessment.

The Transpara Density outputs are:

Density Grade, in accordance with categories defined in the ACR BI-RADS Atlas 5th Edition (A = almost entirely fat; B = scattered fibroglandular densities; C = heterogeneously dense; and D = extremely dense)
Volumetric Breast Density in % .
. Breast volume in cm3

Transpara Density is designed as an optional feature of Transpara. To operate in a clinical environment the software must be embedded in a software application that generates output in standardized formats (e.g. DICOM) and handles communication with external devices (such as PACS systems).

AI/ML Overview

Here's a breakdown of the acceptance criteria and the study proving the device meets them, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria are implicitly derived from the performance goals demonstrated in the clinical studies.

Performance Metric Category	Acceptance Criteria (Implicitly from Study Results)	Reported Device Performance
Accuracy (VBD)	Pearson correlation coefficient with physics model (van Engeland 2006) should be high.	0.935 [95% CI: 0.931 - 0.938]
Accuracy (Breast Volume)	Pearson correlation coefficient with physics model (van Engeland 2006) should be high.	0.997
Accuracy (VBD vs. MRI)	Pearson correlation coefficient with volumetric measurements from breast MRI should be high.	0.908 [95% CI: 0.878 - 0.931]
Reproducibility (CC vs. MLO)	VBD in MLO and CC views of the same breast should be similar.	Pearson correlation: 0.947 [95% CI: 0.945 - 0.948], Mean absolute deviation: 1.22% [95% CI: 1.19% - 1.24%]
Reproducibility (Left vs. Right Breast)	VBD in left and right breasts of the same patient should be similar.	Pearson correlation: 0.953 [95% CI: 0.951 - 0.955], Mean absolute deviation: 1.14% [95% CI: 1.10% - 1.17%]
Reproducibility (FFDM vs. DBT)	VBD between FFDM and DBT acquisitions should be similar.	Pearson correlation: 0.912 [95% CI: 0.904 - 0.920], Mean absolute deviation: 1.68% [95% CI: 1.57% - 1.78%]
Agreement (FFDM vs. DBT - DG)	Agreement in four-category DG values for FFDM and DBT should be high.	Quadratically weighted kappa: 0.810 [95% CI: 0.787 - 0.835]
Agreement with Human Readers (4-category DG)	Overall accuracy of Transpara Density against human readers.	70.8% [95% CI: 67.6% - 73.9%]
Agreement with Human Readers (4-category DG Kappa)	Cohen's quadratically weighted kappa against human readers.	0.74 [95% CI: 0.70 - 0.79]
Agreement with Human Readers (Dense vs. Non-Dense Accuracy)	Overall accuracy of Transpara Density against human readers for dense vs. non-dense.	88.9% [95% CI: 86.6% - 90.9%]
Agreement with Human Readers (Dense vs. Non-Dense Kappa)	Cohen's quadratically weighted kappa against human readers for dense vs. non-dense.	0.78 [95% CI: 0.72 - 0.84]
Dense vs. Non-Dense Sensitivity	Sensitivity for dense vs. non-dense classification.	87.3% [95% CI: 83.6% - 90.3%]
Dense vs. Non-Dense Specificity	Specificity for dense vs. non-dense classification.	90.4% [95% CI: 87.2% - 92.9%]

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

Accuracy (Physics Model & MRI):
- Physics Model Comparison: 5,468 exams.
- MRI Comparison: 190 exams.
Reproducibility (CC vs. MLO, Left vs. Right Breast, FFDM vs. DBT):
- CC vs. MLO and Left vs. Right Breast: 10,804 exams.
- FFDM vs. DBT: 433 exams (where images of both modalities were available).
Agreement with Human Readers (Main Study): 800 women (400 DM and 400 DBT examinations).
Data Provenance:
- The test data originated from multiple clinical centers in the US, UK, Turkey, and five EU countries (Netherlands, Sweden, Germany, Spain, Belgium, Italy).
- The data collection sites are described as "representative for regular breast cancer screening and diagnostic assessment in hospitals."
- The studies were retrospective, using existing data. The human reader study implies a retrospective collection of images to be reviewed.

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

Number of Experts: Eight (8) MQSA-qualified radiologists.
Qualifications of Experts: "MQSA-qualified radiologists according to the ACR BI-RADS Atlas 5th Edition." (MQSA stands for Mammography Quality Standards Act, indicating they are qualified to interpret mammograms clinically in the US).

4. Adjudication Method for the Test Set

Panel Majority Vote: For each exam, a panel majority vote of the eight radiologists was computed to serve as the reference standard.
Tie Resolution: Ties in the panel majority vote were resolved by taking the majority vote of the three most experienced radiologists in the panel.

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, a multi-reader multi-case (MRMC) comparative effectiveness study was not explicitly described as being done to assess human reader improvement with AI assistance. The study focused on the standalone performance of the Transpara Density device against human reader consensus, not how the AI assists human readers.

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

Yes, extensive standalone performance testing was done. The entire "Summary of non-clinical performance data" section describes the device's performance in terms of accuracy, reproducibility, and agreement with human readers, all reflecting the algorithm's direct output. The conclusion explicitly states: "Standalone performance tests demonstrated that requirements were met."

7. The Type of Ground Truth Used

Expert Consensus (Proxy for Ground Truth): For the agreement with human readers, the ground truth for the ACR BI-RADS 5th Edition breast density category was established by a panel majority vote of eight MQSA-qualified radiologists, with tie-breaking by the three most experienced.
Physics-Based Model / MRI Measurements (Reference for Accuracy): For the volumetric breast density (VBD) and breast volume (BV) accuracy assessments, the ground truth was based on:
- A validated physics-based model described in literature (van Engeland 2006).
- Volumetric measurements from breast MRI studies in the same patients.

8. The Sample Size for the Training Set

The document does not explicitly state the sample size for the training set. It only mentions that the "test data was not used for algorithm training and was not accessible to members of the research and development team."

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

The document does not provide details on how the ground truth for the training set was established. It only indicates that the test data was separate from the training data.

Summary

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

December 11, 2023

Image /page/0/Picture/1 description: The image shows 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 consists of the letters "FDA" in a blue square, followed by the words "U.S. FOOD & DRUG" in blue, with the word "ADMINISTRATION" underneath.

Screenpoint Medical B.V. % Robin Barwegen Head of Regulatory and Quality Affairs Mercator II, 7th floor, Toernooiveld 300 Nijmegen, Gelderland 6525EC NETHERLANDS

Re: K232096

Trade/Device Name: Transpara Density 1.0.0 Regulation Number: 21 CFR 892.2050 Regulation Name: Medical Image Management and Processing System Regulatory Class: Class II Product Code: QIH Dated: July 6, 2023 Received: July 13, 2023

Dear Robin Barwegen:

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 (the 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 available 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.

Additional information about changes that may require a new premarket notification are provided in the FDA guidance documents entitled "Deciding When to Submit a 510(k) for a Change to an Existing Device" (https://www.fda.gov/media/99812/download) and "Deciding When to Submit a 510(k) for a Software Change to an Existing Device" (https://www.fda.gov/media/99785/download).

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

Your device is also subject to, among other requirements, the Quality System (QS) regulation (21 CFR Part 820), which includes, but is not limited to, 21 CFR 820.30, Design controls; 21 CFR 820.90, Nonconforming product; and 21 CFR 820.100, Corrective and preventive action. Please note that regardless of whether a change requires premarket review, the QS regulation requires device manufacturers to review and approve changes to device design and production (21 CFR 820.30 and 21 CFR 820.70) and document changes and approvals in the device master record (21 CFR 820.181).

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 Part 803) for devices or postmarketing safety reporting (21 CFR Part 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 Part 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR Parts 1000-1050.

Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR 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,

Yanna S. Kang -S

Yanna Kang, Ph.D. Assistant Director Mammography and Ultrasound Team DHT8C: Division of Radiological Imaging and Radiation Therapy Devices OHT8: Office of Radiological Health Office of Product Evaluation and Quality Center for Devices and Radiological Health

Enclosure

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

Indications for Use

510(k) Number (if known) K232096

Device Name Transpara Density 1.0.0

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

K232096

510(k) Summary Transpara Density

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

Submitter 1.

Manufacturer:

ScreenPoint Medical B.V.

Mercator II, 7th floor

Toernooiveld 300

6525 EC Nijmegen

Netherlands

www.screenpoint-medical.com

Contact person:

Robin Barwegen

Office: +31 24 3030045 | +31 24 2020020

Mobile: +31 6 44077104

Mercator II, 7th floor, Toernooiveld 300, 6525 EC Nijmegen, Netherlands

Date:

11 December 2023

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

2. Device

Device trade name	Transpara Density
Device	System, Image Processing, Radiological
Classification regulation	21 CFR 892.2050
Panel	Radiology
Device class	II
Product code	QIH
Submission type	Traditional 510(k)

3. Legally marketed predicate device

Device trade name	Volpara Imaging Software
Legal Manufacturer	Volpara Health Technologies Limited
Device	System, Image Processing, Radiological
Classification regulation	21 CFR 892.2050
Panel	Radiology
Device class	II
Product code	LLZ
Clearance number	K182310

Device description 4.

The Transpara Density outputs are:

Density Grade, in accordance with categories defined in the ACR BI-RADS Atlas 5th Edition (A = almost entirely fat; B = scattered fibroglandular densities; C = heterogeneously dense; and D = extremely dense)
Volumetric Breast Density in % .
. Breast volume in cm3

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

5. Indications for use

Transpara Density is a software application intended for use with data from compatible digital mammography and digital breast tomosynthesis systems. Transpara Density utilizes deep learning artificial intelligence algorithms to automatically determine volumetric breast density (VBD), breast volume, and an ACR BI-RADS 5th Edition breast density category to aid health care professionals in the assessment of breast tissue composition. It is not a diagnostic aid.

Intended user population

Intended users of Transpara Density are healthcare professionals involved in breast imaging.

Intended patient population

The device is intended to be used in the population of women having a digital mammogram or digital breast tomosynthesis exam.

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.

6. Predicate device comparison

It can be concluded that the subject device Transpara Density is substantially equivalent to the commercially available predicate device Volpara Imaging Software (K182310). It has the same intended use, intended users, and numeric output as the predicate device. The substantial equivalence comparison table below provides details.

	Transpara Density	Predicate Device VolparaImaging SoftwareK182310	Comments
Intended Use	Transpara Density is a software application intended for use with data from compatible	VolparaDensity is a software application intended for use with the raw data from digital	Similar from the user perspective. Main outputs for the user are volumetric density and
	digital mammographyand digital breasttomosynthesis systems.Transpara Density utilizesdeep learning artificialintelligence algorithms toautomatically determinevolumetric breast density(VBD), breast volume,and an ACR BI-RADS 5thEdition breast densitycategory to aid healthcare professionals in theassessment of breasttissue composition. It isnot a diagnostic aid.	breast x-ray systems,including tomosynthesis.VolparaDensity calculatesand quantifiesa density map and fromthat determinesvolumetric breast densityas a ratio offibroglandular tissue andtotal breast volumeestimates. Volparaprovides these numericalvalues along with a BI-RADS breast density 4thor 5th Edition category toaid health careprofessionals in theassessment of breasttissue composition.VolparaDensity is not aninterpretive or diagnosticaid and should be usedonly as adjunctiveinformation when thefinal assessment of breastdensity category is madeby an MQSA-qualifiedinterpretingphysician.	the BI-RADS 5th Editiondensity category. Theseoutputs are the same.
Intended Users	Health Care Professionals	Health Care Professionals	Same
Image Source	Digital mammogramsfrom mammography ortomosynthesis systems(any paddle type)	Digital mammogramsfrom mammography ortomosynthesis systems,including those obtainedusing with curvedpaddles.	Same. The subject deviceis insensitive for paddleshapes because it usesimages processed by themanufacturer which arenot affected by paddleshape.
Input image type	FOR PRESENTATION(processed) images formammography andSynthetic 2D images forDBT	FOR PROCESSING (raw)images formammography and thecentral raw projectionimage for DBT	The core algorithm fordensity computation ofthe subject device has adifferent design whichdoes not require rawdata.
Anatomical area	Breast	Breast	Same
Assessment Scope		Volumetric
Image Storage and ReportGeneration		YesOutput to the console.
Numeric Output	Volume of BreastVolumetric Breast Density	Volume of BreastVolumetric Breast Density	Similar, the clinicallyrelevant outputs inpractice are the same.
	BIRADS 5th Edition BreastDensity Category	BIRADS 4th or 5th EditionBreast Density Category
		Volume of Fibroglandulartissue
		Average thickness ofdense tissue
		Maximum thickness ofdense tissue (andlocation)
		Maximum volume ofdense tissue above any1cm2 square region
Image Output	None	Density map in DICOMSCI format, forvisualization as userspecifies.	Density maps are notrequired in clinicalpractice
Classification	21 CFR 892.2050	21 CFR 892.2050	Same
Software Level ofConcern	Moderate	Moderate	Same

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

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

Summary of non-clinical performance data 7.

In the design and development of Transpara Density, ScreenPoint applied the following voluntary FDA recognized standards and guidelines:

Standard ID	Standard Title	FDA Recognition #
IEC 62366-1 Edition1.1 2020-06	Medical devices - Part 1: Application of usabilityengineering to medical devices	5-129
ISO 14155 Thirdedition 2020-07	Clinical investigation of medical devices forhuman subjects - Good clinical practice	2-282
ISO 14971 ThirdEdition 2019-12	Medical devices - Application of riskmanagement to medical devices	5-125
IEC 62304 Edition1.1 2015-06CONSOLIDATEDVERSION	Medical Device Software - Software Life CycleProcesses	13-79
IEC 82304-1: 2016	Health software - Part 1: General requirementsfor product safety	13-97

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

ISO 15223-1 FourthEdition 2021-07	Medical devices - Symbols to be used withmedical device labels labelling and informationto be supplied - Part 1: General requirements	5-134
ISO 20417 Firstedition 2021-04Corrected version2021-12	Medical devices – Information to be supplied bythe manufacturer	5-135

The following quidance documents were used to support this submission:

Guidance for Industry and FDA Staff Guidance for the Content of Premarket ● Submissions for Software Contained in Medical Devices (Issued on May 11, 2005)
Guidance for Industry and Food and Drug Administration Staff Computer-● Assisted Detection Devices Applied to Radiology Images and Radiology Device Data - Premarket Notification [510(k)] Submissions (Issued on July 3, 2012)
Guidance for Industry and FDA Staff - Clinical Performance Assessment: Considerations for Computer-Assisted Detection Devices Applied to Radiology Images and Radiology Device Data in Premarket notification [510(k)] Submissions (Issued on July 3, 2012)
. Guidance for Industry and Food and Drug Administration Staff - The 510(k) Program: Evaluating Substantial Equivalence in Premarket Notifications [510(k)] (Issued on July 28, 2014)
Guidance for Industry and Food and Drug Administration Staff Unique Device ● Identification: Direct Marking of Devices (Issued on November 17, 2017)
. Guidance for Industry and Food and Drug Administration Staff - Technical Performance Assessment of Quantitative Imaging in Radiological Device Premarket Submissions (Issued on June 16, 2022)

Transpara Density is a software-only device. The level of concern for the device is determined as Moderate Level of Concern.

Non-clinical performance tests

Verification testing was conducted, which consisted of software unit testing, software integration testing and software system testing. The verification tests showed that the software application satisfied the software requirements.

{9}------------------------------------------------

Transpara Density was evaluated by tests covering accuracy, reproducibility, consistency, and agreement with visual assessment by healthcare professionals involved in breast imaging.

Test data

The test data used for the evaluation of the automated density algorithm included exams from 10,804 women with ages ranging from 40-92. The dataset includes FFDM (10,804 exams) and DBT (833 exams) from multiple vendors including GE (26%), Siemens (16%), Hologic (37%) and Fujifilm (21%). All exams contained at least the four standard views (left and right MLO/CC). The test data was not used for algorithm training and was not accessible to members of the research and development team.

Data originated from multiple clinical centers located in the US, the UK, Turkey, and five countries in the EU (the Netherlands, Sweden, Germany, Spain, Belgium, Italy), Data collection sites are representative for reqular breast cancer screening and diagnostic assessment in hospitals.

Characteristics of the test set, i.e. Density Grade distribution, were evaluated and compared to those reported in literature, confirming that the test set is representative of the target population in the intended use.

Accuracy

Volumetric breast density (VBD) and breast volume (BV) should be in agreement with measurements obtained using a validated physics based model described in the literature (van Engeland 2006). https://doi.org/10.1109/TMI.2005.862741). Performance was tested with a dataset of 5,468 exams. The Pearson correlation between VBD computed with Transpara Density and the physics model was 0.935 [95% Cl: 0.931 - 0.938]. For breast volume the Pearson correlation coefficient was 0.997.

VBD obtained with Transpara Density was also compared to volumetric measurements based on breast MRI studies in the same patients, for exams acquired within a short time frame. Using a dataset of 190 exams, the Pearson correlation coefficient was 0.908 [95% Cl: 0.878 - 0.931].

Results show that Transpara Density provides accurate estimates of VBD compared to breast MRI and a physics based model.

Reproducibility

VBD computed in MLO and CC views of the same breast should be similar. In a comparison performed using 10,804 exams. Transpara Density has a Pearson correlation coefficient of 0.947 [95% Cl: 0.945 - 0.948] and a mean absolute deviation of 1.22% [95%

{10}------------------------------------------------

CI: 1.19% - 1.24%] between CC and MLO views. Minor deviations may be explained by differences in breast positioning.

Using the same dataset, a comparison was also made of VBD computed in the right and left breast of the same patient. The Pearson correlation coefficient was 0.953 [95% Cl: 0.951 - 0.955] with a mean absolute deviation of 1.14% [95% CI: 1.10% - 1.17%] between the left and right breast.

To compare VBD and DG for DM and DBT acquisitions a dataset of 433 exams was used in which images of both modalities were available. The Pearson correlation coefficient in this comparison was 0.912 [95% Cl: 0.904 - 0.920], with a mean absolute deviation of 1.68% [95% C1: 1.57% - 1.78%] between VBD values on FFDM and DBT acquisitions. There was a high agreement in the four category DG values for DM and DBT with a quadratically weighted kappa of 0.810 [95% Cl: 0.787 - 0.835].

Agreement with human readers

A study was performed with 400 digital mammography and 400 digital breast tomosynthesis examinations from 800 women with a median age of 56, originating from multiple clinical centers and representative for screening and diagnostic assessment procedures. Breast tissue composition in these examinations was independently assessed by eight MQSA-qualified radiologists according to the ACR BI-RADS Atlas 5th Edition. A panel majority vote was computed for each exam to serve as a reference standard in a comparison with the automated breast density grades determined by Transpara Density. Ties in the panel majority-vote were resolved by taking the majority vote of the three most experienced radiologists in the panel. Five exams were excluded from analysis because of non-compliant DICOM headers which caused a failure of the density measurement.

Agreement was assessed by computing accuracy using 4x4 and 2x2 (for non-dense (a+b) and dense (c+d) confusion matrices (figure 1 and figure 2). Also, Cohen's quadratically weighted kappa was calculated to measure the inter-rater agreement for categorical items. Overall the accuracy was 70.8% [95% Cl: 67.6% - 73.9%] [Cohen's weighted kappa = 0.74 [95% Cl: 0.70 - 0.79] for the four breast density categories (a-b-c-d), and 88.9% [95% C1: 86.6% - 90.9%] [Cohen's weighted kappa = 0.78 [95% C1: 0.72 - 0.84]] for the dense vs non-dense assessment.

For dense vs. non-dense classification, Transpara Density has a sensitivity of 87.3% [95% CI: 83.6% - 90.3%], and a specificity of 90.4% [95% CI: 87.2% - 92.9%].

{11}------------------------------------------------

Image /page/11/Figure/0 description: This image is a table showing the PMV (Predicted Mean Vote) of radiologists according to the BIRADS-V (Breast Imaging Reporting and Data System) classification. The rows represent the Transpara Density, labeled a through d, and the columns represent the radiologists' PMV, also labeled a through d. For example, the cell at row 'a' and column 'b' has a value of 75, while the cell at row 'c' and column 'c' has a value of 239.

Agreement 70.8% (67.6% - 73.9% ), K = 0.743 (0.698 - 0.785)

Fig. 1 Confusion matrix between Transpara Density and PMV for the four breast density categories (a-b-c-d).

Image /page/11/Figure/3 description: This image is a confusion matrix that shows the performance of radiologists' PMV according to BIRADS-V. The matrix compares non-dense and dense categories for both Transpara Density and Radiologists' PMV. The matrix shows that there were 376 true positives for non-dense, 331 true positives for dense, 48 false positives, and 40 false negatives.

Agreement 88.9% (86.6% - 90.9% ), K = 0.778 (0.717 - 0.839)

Fig. 2 Confusion matrix between Transpara Density and PMV for the two breast density categories (non-dense (a+b) vs dense (c+d)).

{12}------------------------------------------------

Compatibility

Compatibility with multiple vendors was demonstrated for the Breast Density score: GE, Siemens, Hologic and Fujifilm. For VBD and BV compatibility with GE, Siemens and Hologic was demonstrated.

Conclusions 8.

The data presented in this 510(k) includes all required information to support the review by FDA. Performance tests have shown that Transpara Density delivers results that are in high agreement with the visual assessment done by radiologists and that standalone performance requirements were met. Agreement was found between the majority vote of a panel of eight MQSA-qualified radiologists and Transpara Density in classifying dense from non-dense breasts. Standalone performance tests demonstrated that requirements were met.

ScreenPoint has applied a risk management process in accordance with FDA recognized standards to identify, evaluate, and mitigate all known hazards related to Transpara Density. All identified risks are effectively mitigated and it can be concluded that the residual risk is outweighed by the benefits.

Considering all data in this submission, the data provided in this 510(k) application supports the safe and effective use of Transpara Density for its indications for use and 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).