Genius AI Detection is a computer-aided detection and diagnosis (CADe/CADx) software device intended to be used with compatible digital breast tomosynthesis (DBT) systems to identify and mark regions of interest including soft tissue densities (masses, architectural distortions and asymmetries) and calcifications in DBT exams from compatible DBT systems and provide confidence scores that offer assessment for Certainty of Findings and a Case Score. The device intends to aid in the interpretation of digital breast tomosynthesis exams in a concurrent fashion, where the interpreting physician confirms or dismisses the findings during the reading of the exam.

Device Description

Genius AI Detection is a software device intended to identify potential abnormalities in breast tomosynthesis images. Genius Al Detection analyzes each standard mammographic view in a digital breast tomosynthesis examination using deep learning networks. For each detected lesion, Genius AI Detection produces CAD results that include the location of the lesion, an outline of the lesion and a confidence score for that lesion. Genius Al Detection also produces a case score for the entire tomosynthesis exam.

Genius Al Detection packages all CAD findings derived from the corresponding analysis of a tomosynthesis exam into a DICOM Mammography CAD SR object and distributes it for display on DICOM compliant review workstations. The interpreting physician will have access to the CAD findings concurrently to the reading of the tomosynthesis exam. In addition, a combination of peripheral information such as number of marks and case scores may be used on the review workstation to enhance the interpreting physician's workflow by offering a better organization of the patient worklist.

The Genius Al Detection 2.0 now added the CC-MLO Correlation feature. The added feature provides the ability to correlate a suspected lesion in one view with a like finding in the other view and additionally provides a workflow and navigation feature for the interpreting physician.

AI/ML Overview

The provided text describes the regulatory clearance of a medical device, "Genius AI Detection 2.0 with CC-MLO Correlation." While it mentions "acceptance criteria" through the lens of safety and effectiveness, it does not explicitly list quantitative acceptance criteria for the device's performance (e.g., a specific sensitivity or specificity threshold). Instead, it describes internal validation and a standalone evaluation study to demonstrate that the device is "safe and effective."

Here's a breakdown of the requested information based on the provided text:

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

As mentioned, explicit quantitative acceptance criteria are not provided in the document. The document states that the "verification testing showed that the software application satisfied the software requirements." For the standalone evaluation of the CC-MLO Correlation feature, the performance was "estimated in both groups by scoring the detection pairs against the truth pairs and by evaluating the expert radiologist's response, respectively." However, specific performance metrics (e.g., accuracy percentages, sensitivity, specificity for the CC-MLO correlation) are not reported in this summary.

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:
- For the standalone evaluation of the CC-MLO Correlation feature, the dataset included:
  - 106 biopsy-proven malignant cases.
  - 561 screening negative cases.
  - Additionally, the detection pairs generated by the CC-MLO correlation feature were reviewed on 658 screening negative and biopsied benign cases. (It's unclear if this "658 cases" is a subset or superset of the "561 screening negative cases" mentioned earlier, or an entirely separate review of negative/benign cases for correlation specifically.)
Data Provenance: The document does not specify the country of origin of the data or whether it was retrospective or 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: An "expert radiologist" is mentioned in the singular ("an expert radiologist" and "the expert radiologist's response"). This suggests that one expert radiologist was primarily responsible for establishing ground truth for the malignant cases and reviewing detection pairs.
Qualifications of Experts: The document specifies "expert radiologist" but does not provide details on their specific qualifications, such as years of experience.

4. Adjudication method (e.g., 2+1, 3+1, none) for the test set

The text describes ground truth for malignant cases being established by "an expert radiologist by generating ground truth marks and truth pairs." For the CC-MLO correlation feature, generated detection pairs were "reviewed by an expert radiologist."
This suggests a single-reader ground truth establishment and review without an explicit multi-reader adjudication method (like 2+1 or 3+1). It seems to be "none" in terms of multi-reader consensus for the test set ground truth.

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 states, "Standalone evaluation testing was also conducted." It focuses on the performance of the algorithm itself and its ability to correlate findings.
There is no mention of an MRMC comparative effectiveness study where human readers' performance with and without AI assistance was evaluated. Therefore, no effect size for human reader improvement is provided. The device "intends to aid in the interpretation... in a concurrent fashion, where the interpreting physician confirms or dismisses the findings," implying human-in-the-loop, but no study of this combined performance is detailed here.

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

Yes, a standalone evaluation was done. The document explicitly states: "Standalone evaluation testing was also conducted." The performance of the CC-MLO Correlation feature was "estimated... by scoring the detection pairs against the truth pairs."

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)

For the malignant cases (106 cases): Ground truth was established by "an expert radiologist by generating ground truth marks and truth pairs." It also mentions these were "biopsy proven malignant cases," indicating pathology was also part of the ground truth for these malignant cases. The "truth pairs" were essentially expert annotations of pathologically confirmed lesions on both orthogonal views.
For the screening negative cases (561 and 658 cases reviewed): The ground truth was presumably based on their screening negativity, validated by clinical follow-up or expert review. The review of detection pairs was against "the expert radiologist's response," implying expert judgment as ground truth for these negative/benign cases.

8. The sample size for the training set

The sample size for the training set is not provided in this document. The description focuses solely on the "standalone evaluation of the CC-MLO Correlation feature" which used a specific test dataset.

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

As the training set sample size is not provided, how its ground truth was established is also not detailed in this document. It only mentions the use of "deep learning networks" which implies a trained model, but the specifics of its training data and ground truth establishment are absent from this summary.

Summary

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

May 23, 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 is a blue square with the letters "FDA" in white. To the right of the blue square is the text "U.S. FOOD & DRUG ADMINISTRATION" in blue.

Hologic, Inc. % Deborah Thomas Senior Principal Regulatory Affairs 250 Campus Drive MARLBOROUGH MA 01730

Re: K230096

Trade/Device Name: Genius AI Detection 2.0 with CC-MLO Correlation Regulation Number: 21 CFR 892.2090 Regulation Name: Radiological computer assisted detection and diagnosis software Regulatory Class: Class II Product Code: QDQ Dated: April 13, 2023 Received: April 13, 2023

Dear Deborah Thomas:

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); 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,

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) K230096

Device Name

Genius AI Detection 2.0 with CC-MLO Correlation

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

Traditional 510(k) Summary

This 510(k) Summary is submitted in accordance with the requirements of 21 CFR Part 807.92

Date Prepared:	January 12, 2023
Manufacturer:	Hologic, Inc.
	36 Apple Ridge
	Road Danbury, CT
	06810 USA
Establishment Registration #:	1220984
Contact Person:	Deborah Thomas
	Senior Principal Regulatory Affairs
	P: 508.210.6107

Identification of the Device:

Proprietary/Trade Name:	Genius Al Detection 2.0 with CC-MLO Correlation
Classification Name:	Radiological Computer Assisted Detection/Diagnosis Software for Lesions Suspicious for Cancer
Regulatory Number:	21 CFR 892.2090
Product Code:	QDQ
Device Class:	Class II
Review Panel:	Radiology

Identification of the Legally Marketed Predicate and Reference Devices:

Predicate Device	Genius Al Detection 2.0
Trade Name:	Radiological Computer Assisted Detection/Diagnosis
Classification Name:	Software for Lesions Suspicious for Cancer
	21 CFR 892.2090
Regulatory Number:	QDQ
Product Code:	Class II
Device Class:	Radiology
Review Panel:	Hologic, Inc.
Submitter/510(k)	K221449 (cleared October 6, 2022)
Holder: Clearance:

Reference Device	Transpara 1.7.2
Trade Name:	Radiological Computer Assisted Detection/Diagnosis
Classification Name:	Software for Lesions Suspicious For Cancer

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

Regulatory Number: Product Code: Device Class: Review Panel: Submitter/510(k) Holder: Clearance:

21 CFR 892.2090 QDQ Class II Radiology ScreenPoint Medical B.V K221347 (cleared August 3, 2022)

Device Description:

Indications for Use:

Genius Al Detection is a computer-aided detection and diagnosis (CADe/CADx) software device intended to be used with compatible digital breast tomosynthesis (DBT) systems to identify and mark regions of interest including soft tissue densities (masses, architectural distortions and asymmetries) and calcifications in DBT exams from compatible DBT systems and provide confidence scores that offer assessment for Certainty of Findings and a Case Score. The device intends to aid in the interpretation of digital breast tomosynthesis exams in a concurrent fashion, where the interpreting physician confirms or dismisses the findings during the reading of the exam.

Standards:

IEC 62304: 2015 Medical device software Software Life Cycle Processes (#13-79) ●
ISO 14971: 2012 – Medical devices – Application of Risk Management to Medical Devices
DEN180005 Evaluation of automatic class III designation for OsteoDetect Decision ● summary with special controls.

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

FDA Guidance Documents:

Guidance for Industry and FDA Staff Guidance for the Content of Premarket ● Submissions for Software Contained in Medical Devices (Issued on May 11, 2005)
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 - Premarket Approval (PMA) and Premarket Notification [510(k)] Submissions (Issued on January 22, 2020)
"Off-the-Shelf Software Use in Medical Devices," issued on September 9, 1999
. "Content of Premarket Submissions for Management of Cybersecurity in Medical Devices" issued on October 2, 2014.

Features andCharacteristics	Subject DeviceHologic, Inc.Genius Al Detection 2.0with CC-MLOCorrelation	PredicateHologic, Inc.Genius AlDetection 2.0	Reference DeviceScreenPointMedicalTranspara 1.7.2	Difference andcomments
510(k) Number	pending	K221449	K221347	N/A
RegulationNumber/Name	21 CFR 892.2090 /Radiological ComputerAssisted Detection andDiagnosis Software	Same	Same	N/A
Product Code	QDQ	Same	Same	N/A
Indicationsfor Use		Same		Similar
	Genius AI Detection isa computer-aideddetection anddiagnosis (CADe/CADx)software deviceintended to be usedwith compatible digitalbreast tomosynthesis(DBT) systems toidentify and markregions of interestincluding soft tissuedensities (masses,architecturaldistortions andasymmetries) andcalcifications in DBTexams fromcompatible DBTsystems and provideconfidence scores thatoffer assessment forCertainty of Findingsand a Case Score.The device intends toaid in theinterpretation ofdigital breasttomosynthesis examsin a concurrentfashion, where theinterpreting physicianconfirms or dismissesthe findings duringthe reading of theexam.		Transparasoftware isintended for useas a concurrentreading aid forphysiciansinterpretingscreening full-field digitalmammographyexams and digitalbreasttomosynthesisexams fromcompatible FFDMand DBT systems,to identifyregionssuspicious forbreast cancer andassess theirlikelihood ofmalignancy.Output of thedevice includeslocations ofcalcificationsgroups and soft-tissue regions,with scoresindicating thelikelihood thatcancer is present,and an examscore indicatingthe likelihoodthat cancer ispresent in theexam. Patientmanagementdecisions shouldnot be madesolely on thebasis of analysisby Transpara.
CompatibleDBTSystems	Hologic SeleniaDimensionsHologic 3DimensionsSupports both modelsin the followingmodes:• standardresolution 1-mmslices• high resolution 1-mm slices (ClarityHD)high resolution 6-mm SmartSlices(3DQuorum)	Same	Giotto FFDMGeneral Electric DBTFujifilm DBT	The predicateand subjectdevice includethe support ofthe followingmodes on theHologic DBTsystems only:• standard res.1-mm slices• high res. 1-mm slices.• high resolution6-mmSmartSlices
Type of CADSoftware	Radiologicalcomputer assisteddetection anddiagnostic software.	Same	Same	N/A
Mode of Action	Image processingdevice utilizingmachine learning toaid in the detection,localization, andcharacterization ofsoft tissue densities(masses, architecturaldistortions, andasymmetries) andcalcifications in the 1-mm 3D DBT slices.Findings are co-registered to 6-mmSmartSlices.	Same	Software that appliesalgorithms forrecognition ofsuspiciouscalcifications and softtissue lesions todetect andcharacterize findingsin radiological breastimages and provideinformation aboutthe presence,location, andcharacteristics of thefindings to the user.	Similar
ClinicalOutput	To inform theprimary diagnosticand patientmanagementdecisions that aremade by the clinicaluser.	Same	Same	N/A
PatientPopulation	Symptomaticandasymptomaticwomenundergoingmammography	Same	The device isintended to be usedin the population ofwomen undergoingscreeningmammography anddigital breasttomosynthesis.	Similar
End Users	MQSA-QualifiedInterpretingPhysicians andRadiologists	Same	Intended users ofTranspara® arephysicians qualifiedto read screeningmammographyexams and digitalbreast tomosynthesisexams.	Similar
Image SourceModalities	Digital breasttomosynthesis slices	Same	Same	N/A
Output Device	Softcopy Workstation	Same	Same	N/A
Deployment	Stand-alone computer	Same	Same	N/A
Method Of Use	Concurrent read	Same	Same	N/A
VisualizationFeatures	Places mark withinsuspicious lesion bydefault (Emphasize™;RightOn™) and reportsconfidence of findingnext to each identifiedlesion in the image. CADdisplay may be toggledon/off. Option toautomatically zoom intoor contour the suspiciousregion of interest(PeerView™).	Same	Computer aideddetection (CAD)marks to highlightlocations where thedevicedetected suspiciouscalcifications or softtissue lesionsDecision support isprovided by regionscores on a scaleranging from 0-100,withhigher scoresindicating a higherlevel of suspicion.	Similar
WorkflowFeatures	Correlates a suspectedlesion in one view with alike finding in the otherview, providing aworkflow and navigationfeature for theinterpreting physician.	No correlation oflesions betweenimage views.	Links betweencorrespondingregions in differentviews of the breast,which maybe utilized toenhance userinterfaces andworkflow.	Similar to thereference device,Genius Al Detection2.0 with CCMLOprovides correlationof the CC and MLOviews when afinding is identified.

Summary of Substantial Equivalence:

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

Hologic, Inc. 510(k) Pre-Market Notification Genius AI Detection 2.0 CC-MLO Correlation

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

Hologic, Inc. 510(k) Pre-Market Notification Genius AI Detection 2.0 CC-MLO Correlation

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

Hologic, Inc. 510(k) Pre-Market Notification Genius AI Detection 2.0 CC-MLO Correlation

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

Hologic, Inc. 510(k) Pre-Market Notification Genius Al Detection 2.0 CC-MLO Correlation

Comparison with Predicate Device:

The Summary of Substantial Equivalence Table above details the similarities and differences between the Genius Al Detection 2.0 with CC-MLO Correlation device with the predicate Genius Al Detection 2.0, K221449 and reference device Transpara 1.7.2, K221347. Genius Al Detection 2.0 with CC-MLO Correlation is the follow-up release to the predicate, Genius Al Detection 2.0, with the ability to correlate a suspected lesion in one view with a like finding in the other view, providing a workflow and navigation feature for the interpreting physician. Both the proposed and predicate devices use the same technology per 21 CFR 892.2090. Both the predicate device and reference device aid in the detection, localization, and characterization of disease specific findings on acquired medical images. The outputs of the devices serve to augment the interpretation of digital breast tomosynthesis exams as a concurrent reading tool. The output is used to inform and assist the interpreting physician, supplementing their clinical expertise and judgment.

Genius Al Detection 2.0 with CC-MLO Correlation is compatible with the same imaging systems as the predicate device and includes a CC-MLO correlation feature similar to the reference device.

Standalone Performance Testing:

Genius AI Detection 2.0 with CC-MLO Correlation is a software-only device. The level of concern for the device is determined as Moderate Level of Concern.

Verification testing consisted of software validation testing, software integration testing and software system testing. The verification testing showed that the software application satisfied the software requirements.

Standalone evaluation testing was also conducted. The dataset used for this standalone evaluation of the CC-MLO Correlation feature is the same dataset used for the standalone evaluation of the detection performance of Genius Al Detection 2.0 (clearance K221449). This evaluation included 106 biopsy proven malignant cases and 561 screening negative cases.

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

The 106 biopsied malignant cases included lesions that were marked by an expert radiologist by generating ground truth marks and truth pairs on both orthogonal views (CC and MLO). Each case in this set contained 4 standard mammographic views.

There were 239 individual truth marks in the 106 malignant cases that were analyzed for this evaluation. 226 of those truth marks came from 113 truth pairs which included the lesions that were linked by the radiologist after identifying them on both views.

In addition, the detection pairs generated by the CC-MLO correlation feature on 658 screening negative and biopsied benign cases were reviewed by an expert radiologist.

The performance of the CC-MLO Correlation feature is evaluated by looking at different subgroups including biopsied malignant cases and negative cases. The accuracy of the CC-MLO Correlation feature was estimated in both groups by scoring the detection pairs against the truth pairs and by evaluating the expert radiologist's response, respectively.

Based on results of the verification and evaluation tests, it is concluded that the Genius AI Detection 2.0 with CC-MLO correlation device is safe and effective in detecting soft tissue lesions and calcification lesions and correlating the CC-MLO findings in tomosynthesis exams acquired with Hologic's 3D Mammography systems.

Assessment of Benefit-Risk, Safety and Effectiveness, and Substantial Equivalence:

Risk management is ensured through risk analysis which is used to identify and mitigate potential hazards. Any potential hazards are controlled via software development, verification, and validation testing. In addition, device labeling contains instructions for use and any necessary cautions and warnings to provide for safe and effective use of this device. Hologic finds that the proposed device has a positive balance in terms of probable benefits vs probable risks and thus may be considered safe and effective based on verification and validation testing.

Conclusion:

Based on the required information submitted in this premarket notification, the proposed Genius Al Detection 2.0 with CC-MLO Correlation device has been found to be substantially equivalent to the predicate Genius Al Detection 2.0, K221449. The devices have similar indications for use and aid in the detection, localization, and characterization of disease specific findings on acquired medical images. There are no issues of safety and effectiveness of the proposed Genius Al Detection 2.0 with CC-MLO Correlation device.

Regulation Number and Section

§ 892.2090 Radiological computer-assisted detection and diagnosis software.

(a)
Identification. A radiological computer-assisted detection and diagnostic software is an image processing device intended to aid in the detection, localization, and characterization of fracture, lesions, or other disease-specific findings on acquired medical images (e.g., radiography, magnetic resonance, computed tomography). The device detects, identifies, and characterizes findings based on features or information extracted from images, and provides information about the presence, location, and characteristics of the findings to the user. The analysis is intended to inform the primary diagnostic and patient management decisions that are made by the clinical user. The device is not intended as a replacement for a complete clinician's review or their clinical judgment that takes into account other relevant information from the image or patient history.(b)
Classification. Class II (special controls). The special controls for this device are:(1) Design verification and validation must include:
(i) A detailed description of the image analysis algorithm, including a description of the algorithm inputs and outputs, each major component or block, how the algorithm and output affects or relates to clinical practice or patient care, and any algorithm limitations.
(ii) A detailed description of pre-specified performance testing protocols and dataset(s) used to assess whether the device will provide improved assisted-read detection and diagnostic performance as intended in the indicated user population(s), and to characterize the standalone device performance for labeling. Performance testing includes standalone test(s), side-by-side comparison(s), and/or a reader study, as applicable.
(iii) Results from standalone performance testing used to characterize the independent performance of the device separate from aided user performance. The performance assessment must be based on appropriate diagnostic accuracy measures (
e.g., receiver operator characteristic plot, sensitivity, specificity, positive and negative predictive values, and diagnostic likelihood ratio). Devices with localization output must include localization accuracy testing as a component of standalone testing. The test dataset must be representative of the typical patient population with enrichment made only to ensure that the test dataset contains a sufficient number of cases from important cohorts (e.g., subsets defined by clinically relevant confounders, effect modifiers, concomitant disease, and subsets defined by image acquisition characteristics) such that the performance estimates and confidence intervals of the device for these individual subsets can be characterized for the intended use population and imaging equipment.(iv) Results from performance testing that demonstrate that the device provides improved assisted-read detection and/or diagnostic performance as intended in the indicated user population(s) when used in accordance with the instructions for use. The reader population must be comprised of the intended user population in terms of clinical training, certification, and years of experience. The performance assessment must be based on appropriate diagnostic accuracy measures (
e.g., receiver operator characteristic plot, sensitivity, specificity, positive and negative predictive values, and diagnostic likelihood ratio). Test datasets must meet the requirements described in paragraph (b)(1)(iii) of this section.(v) Appropriate software documentation, including device hazard analysis, software requirements specification document, software design specification document, traceability analysis, system level test protocol, pass/fail criteria, testing results, and cybersecurity measures.
(2) Labeling must include the following:
(i) A detailed description of the patient population for which the device is indicated for use.
(ii) A detailed description of the device instructions for use, including the intended reading protocol and how the user should interpret the device output.
(iii) A detailed description of the intended user, and any user training materials or programs that address appropriate reading protocols for the device, to ensure that the end user is fully aware of how to interpret and apply the device output.
(iv) A detailed description of the device inputs and outputs.
(v) A detailed description of compatible imaging hardware and imaging protocols.
(vi) Warnings, precautions, and limitations must include situations in which the device may fail or may not operate at its expected performance level (
e.g., poor image quality or for certain subpopulations), as applicable.(vii) A detailed summary of the performance testing, including test methods, dataset characteristics, results, and a summary of sub-analyses on case distributions stratified by relevant confounders, such as anatomical characteristics, patient demographics and medical history, user experience, and imaging equipment.