WRDensity is a software application intended for use with compatible full field digital mammography and digital breast tomosynthesis systems. WRDensity provides an ACR BI-RADS 5th Edition breast density category to aid interpreting physicians in the assessment of breast tissue composition. WRDensity produces adjunctive information. It is not a diagnostic aid.

Device Description

WRDensity is a standalone software application that automatically analyzes "for presentation" data from digital breast x-ray systems with a deep learning algorithm to assess breast tissue composition. WRDensity primarily generates two outputs for an exam, the Breast Density Level (BDL) and the Breast Density Level Probabilities (BDLP).

The Breast Density Level is a categorical breast density assessment in accordance with the American College of Radiology (ACR) Breast Imaging Reporting and Data System (BI-RADS®) Atlas 5th Edition breast density categories "A" through "D". The BDL is the primary output of WRDensity.

The Breast Density Level Probabilities are the probabilities calculated by WRDensity for each of the four density categories. The BDLP is a secondary output that provides more information about the breast density of an exam and the device's confidence level.

WRDensity takes in images via a Digital Imaging and Communications in Medicine (DICOM) transfer from the facility's mammography imaging system, Picture Archive and Communication Server (PACS), or DICOM router. After analysis, WRDensity sends outputs to be stored in the PACS and Radiology Information System (RIS). These outputs can then be reviewed by the radiologist on the mammography workstation as a DICOM Secondary Capture Image, a DICOM Structured Report, and in the RIS. These outputs can be configured to match user preferences.

AI/ML Overview

Here's a breakdown of the acceptance criteria and study details for WRDensity by Whiterabbit.ai, based on the provided text:

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

Metric / Category	Acceptance Criteria (Implied)	Reported Device Performance
Four-Class Task (A,B,C,D)	High agreement with radiologist consensus using quadratically-weighted Cohen's kappa.	Quadratically-weighted Cohen's kappa: 0.90 (95% CI [0.88, 0.92])
BI-RADS A	-	82% agreement with consensus
BI-RADS B	-	90% agreement with consensus
BI-RADS C	-	85% agreement with consensus
BI-RADS D	-	85% agreement with consensus
Binary Task (Dense vs. Non-dense)	High agreement with radiologist consensus using Cohen's kappa.	Cohen's kappa: 0.88 (95% CI [0.85, 0.91])
Non-dense (A+B)	-	93% agreement with consensus
Dense (C+D)	-	95% agreement with consensus
Consistency	High agreement between MLO and CC views of the same breast.	Assessed (Specific value not provided, but stated as evaluated).
Reproducibility	Low root mean square error between initial and second processing runs on predicted probabilities.	Assessed (Specific value not provided, but stated as evaluated).

Note: The document implies "high agreement" as the acceptance criteria for kappa scores and other metrics, as specific numerical thresholds for acceptance criteria are not explicitly stated in this summary portion.

2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
- Test Set Sample Size: 871 exams from unique patients.
- Data Provenance: Not explicitly stated (e.g., country of origin, retrospective/prospective).
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)
- Number of Experts: Five expert radiologists.
- Qualifications of Experts: Not explicitly stated, only referred to as "expert radiologists."
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
- Adjudication Method: "radiologist consensus." This implies a method where multiple radiologists (in this case, five) review cases and come to an agreement on the ground truth. The specific mechanics of how "consensus" was reached (e.g., majority vote, discussion and agreement, or specific rule sets like 3+1) are not detailed.
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 MRMC comparative effectiveness study is described where human readers' performance with and without AI assistance is compared. The study focuses solely on the standalone performance of the AI device against a radiologist consensus as ground truth.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
- Yes, a standalone performance study was done. The performance metrics (quadratically-weighted Cohen's kappa, Cohen's kappa for binary classification, and agreement percentages from confusion matrices) directly compare the WRDensity output against the radiologist consensus, without human readers interacting with the AI output.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
- The ground truth used was expert consensus from five expert radiologists.
8. The sample size for the training set
- The sample size for the training set is not provided in the given text.
9. How the ground truth for the training set was established
- How the ground truth for the training set was established is not provided in the given text.

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, with the letters "FDA" in a blue square, followed by the words "U.S. FOOD & DRUG" in blue, and then the word "ADMINISTRATION" in a smaller font below.

October 30, 2020

Whiterabbit.ai Inc. % Mr. Jason Su CTO and Co-founder 3930 Freedom Cir., Ste 101 SANTA CLARA CA 95054

Re: K202013

Trade/Device Name: WRDensity by Whiterabbit.ai Regulation Number: 21 CFR 892.2050 Regulation Name: Picture archiving and communications system Regulatory Class: Class II Product Code: QIH Dated: September 29, 2020 Received: September 30, 2020

Dear Mr. Su:

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

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

801 and Part 809); medical device reporting of medical device-related adverse events) (21 CFR 803) 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,

Thalia T. Mills, Ph.D. Director Division of Radiological Health OHT7: Office of In Vitro Diagnostics and Radiological Health Office of Product Evaluation and Quality Center for Devices and Radiological Health

Enclosure

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

Indications for Use

510(k) Number (if known)

Device Name

WRDensity by Whiterabbit.ai

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

Section 5. 510(k) Summary

5.1 General Information

510(k) Sponsor	Whiterabbit AI Inc.
Address	3930 Freedom Cir., Ste 101Santa Clara, CA 95054
Correspondence Person	Jason Su
Contact Information	914-275-1097jason@whiterabbit.ai
Date Prepared	October 29, 2020

5.2 Subject Device

Proprietary Name	WRDensity by Whiterabbit.ai
Common Name	WRDensity
Classification Name	Automated Radiological Image Processing Software
Regulation Number	21 CFR 892.2050
Product Code	QIH
Regulatory Class	II

5.3 Predicate Device

Proprietary Name	Densitas densityai
Premarket Notification	K192973
Classification Name	System, Image Processing, Radiological
Regulation Number	21 CFR 892.2050
Product Code	LLZ
Regulatory Class	II

5.4 Device Description

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

5.5 Indications for Use

WRDensity is a software application intended for use with compatible full-field digital mammography and digital breast tomosynthesis systems. WRDensity provides an ACR BI-RADS 5th Edition breast density category to aid interpreting physicians in the assessment of breast tissue composition. WRDensity produces adjunctive information. It is not a diagnostic aid.

5.6 Comparison of Technological Characteristics with the Predicate Device

	Subject DeviceWRDensity	Predicate Devicedensityai (K192973)
ClassificationName	Automated Radiological ImageProcessing Software	System, Image Processing,Radiological
Product Code	QIH	LLZ
RegulationNumber	892.2050	892.2050
RegulationDescription	Picture archiving andcommunication system	Picture archiving andcommunication system
	Subject DeviceWRDensity	Predicate Devicedensityai (K192973)
Indications forUse	WRDensity is a softwareapplication intended for use withcompatible full field digitalmammography and digital breasttomosynthesis systems.WRDensity provides an ACRBI-RADS Atlas 5th Edition breastdensity category to aidinterpreting physicians in theassessment of breast tissuecomposition. WRDensityproduces adjunctive information.It is not a diagnostic aid.	Densitas densityai™ is a softwareapplication intended for use withcompatible full field digitalmammography and digital breasttomosynthesis systems. Densitasdensityai™ provides an ACRBI-RADS Atlas 5th Edition breastdensity category to aid interpretingphysicians in the assessment ofbreast tissue composition. Densitasdensityai™ produces adjunctiveinformation. It is not a diagnosticaid.
PatientPopulation	Symptomatic andasymptomatic womenundergoingmammography	Symptomatic andasymptomatic womenundergoingmammography
End Users	Interpreting Physicians	Interpreting Physicians
Image SourceModalities	FFDMHologic Selenia DimensionsHologic Lorad SeleniaSynthetic 2DHologic C-View	FFDMHologic Selenia DimensionsHologic Lorad SeleniaGE Senographe EssentialGE Senographe PristinaSiemens MAMMOMATInspirationSiemens MAMMOMAT NovationDRSiemens MAMMOMAT FusionSiemens MAMMOMATInspiration PrimeSiemens MAMMOMATRevelation
		Synthetic 2DHologic C-View
Input: ImageData Format	DICOM digital mammographyimages - For Presentation; RCC,LCC, RMLO, LMLO	DICOM digital mammographyimages - For Presentation; RCC,LCC, RMLO, LMLO

Output Data	BIRADS 5th Ed.For each patient:Whiterabbit.ai WRDensity BreastDensity Level, and Breast DensityLevel Probability	BIRADS 5th Ed.For each patient:Densitas densityai™ breast densitygrade

MeasurementScale	4-category breast density scalefrom 5th Ed. ACR BI-RADSAtlas 2013	4-category breast density scalefrom 5th Ed. ACR BI-RADS Atlas2013
Output Device	Mammography Workstation,PACS, RIS	Mammography Workstation,PACS, RIS
OutputFormat	DICOM StructuredReport and SecondaryCaptureText labels presented in aradiologist's PACSand RIS patient worklist.	DICOM StructuredReport and SecondaryCapture


Deployment	Virtual Machine Software	Standalone computer
AssessmentScope	Results per exam	Results per exam
AssessmentType	Image feature-based with deeplearning	Image feature-based
AnatomicalLocation	Breast	Breast

Table 5.1 Predicate Device Table

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

Table 5.2 Indications and Technological Characteristics Comparison

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

5.7 Performance Data

Safety and performance of WRDensity have been evaluated and verified in accordance with software specifications and applicable performance standards through software verification and validation testing. Additionally, software validation activities were performed in

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

accordance with IEC 62304:2006/AC:2015 - Medical device software - Software life cycle processes, in addition to the FDA guidance document, "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices."

The validation testing evaluated the performance of WRDensity along a number of dimensions, including:

· Performance was assessed by comparing the Breast Density Level output to the radiologist consensus using accuracy, quadratically-weighted Cohen's kappa, and confusion matrices. Performance on the four-class task and binary task, i.e. dense (BI-RADS C+D) vs. non-dense (BI-RADS A+B) were both assessed.
Consistency was assessed by evaluating the agreement, in terms of percentage of . cases, between the BDL for the mediolateral oblique (MLO) and craniocaudal (CC) views of the same breast.
Reproducibility was assessed using the maximum root mean square error across all . images between the predicted probabilities produced from an initial processing run and those produced in a second processing run on the same testing data.

The output of WRDensity was compared against a consensus of five expert radiologists who independently assessed breast density on a test dataset that represented all compatible modalities and patient populations. The test dataset comprised 871 exams from unique patients. On the four-class task, WRDensity achieved a quadratically-weighted Cohen's kappa of 0.90, 95% confidence interval [0.88, 0.92]. A confusion matrix demonstrating the level of agreement between the BDL and the radiologist consensus for each BI-RADS breast density category can be found in Figure 1.

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

Image /page/8/Figure/0 description: The image is a confusion matrix showing the relationship between WRDensity and Consensus. The matrix is a 4x4 grid, with each cell showing the percentage and number of observations. The diagonal elements show the percentage of agreement between WRDensity and Consensus, with values of 82%, 90%, 85%, and 85%. The off-diagonal elements show the percentage of disagreement between WRDensity and Consensus.

Figure 1: Confusion matrix comparing the performance of WRDensity against the radiologist consensus assessment of breast density for the four-class BI-RADS breast density task. The number of exams within each bin is shown in parentheses.

On the binary task, WRDensity achieved a Cohen's kappa of 0.88, 95% confidence interval [0.85, 0.91]. The confusion matrix is presented in Figure 2.

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

Image /page/9/Figure/0 description: The image is a confusion matrix comparing WRDensity and Consensus. The matrix shows the percentage and number of cases for each combination of non-dense and dense classifications. For non-dense classifications, 93% (406) are correctly classified, while 7% (29) are misclassified as dense. For dense classifications, 95% (414) are correctly classified, while 5% (22) are misclassified as non-dense.

Figure 2: Confusion matrix comparing the performance of WRDensity against the radiologist consensus assessment of breast density for the binary breast density task, dense (BI-RADS C+D) vs. non-dense (BI-RADS A+B). The number of exams within each bin is shown in parentheses.

5.8 Conclusion

Based on the information submitted in this premarket notification, and based on the indications for use, technological characteristics, and performance testing, WRDensity raises no new questions of safety or effectiveness and is substantially equivalent to the predicate device in terms of safety, efficacy, and performance.

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).