ProFound™ AI V2.1 Software is a computer-assisted detection and diagnosis (CAD) software device intended to be used concurrently by interpreting physicians while reading digital breast tomosynthesis (DBT) exams from compatible DBT systems. The system detects soft tissue densities (masses, architectural distortions and asymmetries) and calcifications in the 3D DBT slices. The detections and Certainty of Finding and Case Scores assist interpreting physicians in identifying soft tissue densities and calcifications that may be confirmed or dismissed by the interpreting physician.

Device Description

ProFound AI V2.1 detects malignant soft-tissue densities and calcifications in digital breast tomosynthesis (DBT) images. ProFound AI V2.1 has the same performance with the DBT systems cleared for use with ProFound AI V2; furthermore, it provides support for additional DBT systems. The ProFound AI V.2.1 Software allows a radiologist to quickly identify suspicious soft tissue densities (masses, architectural distortions and asymmetries) and calcifications by marking the detected areas in the tomosynthesis images. When the ProFound AI V2.1 marks are displayed, the marks will appear as overlays on the 3D tomosynthesis images. For 3D tomosynthesis cases and depending on the functionality offered by the viewing/reading application, the ProFound AI V2.1 marks may also serve as a navigation tool for users because each mark can be linked to the tomosynthesis slice where the detection was identified. Each detected region is also assigned a "score" that corresponds to the ProFound AI V2.1 algorithm's confidence that the detected region is malignant (certainty of finding). Each case is also assigned a case score that corresponds to the ProFound AI V2.1 algorithm's confidence that a case is malignant. The certainty of finding scores are represented as an integer in range of 0 to 100 to indicate the CAD confidence that the detected region or case is malignant. The higher the certainty of finding or case score, the more likely the detected region or case is to be malignant.

AI/ML Overview

Here’s a summary of the acceptance criteria and the study details for the ProFound™ AI Software V2.1, based on the provided FDA 510(k) summary.

1. Table of Acceptance Criteria and Reported Device Performance

The document states that "Case-Level Sensitivity, Lesion-Level Sensitivity, FP Rate in Non-Cancer Cases, and Specificity met design specifications" for both Siemens Standard and Empire Reconstruction datasets. However, the specific numerical acceptance criteria are not explicitly provided in the text. The document refers to "design specifications" and "the detailed results are in the User Manual," implying these numerical targets exist but are not included in the 510(k) summary provided.

For the comparison studies, the acceptance criterion was "the difference between the control group [Hologic] and the test group [Siemens Standard/Empire] is within the margin of non-inferiority for Sensitivity and AUC, and FPPI." The reported performance was that "Each of the three measures produced differences that were within the margin of non-inferiority." Again, specific numerical margins for non-inferiority are not detailed.

Acceptance Criteria (Not explicitly stated numerically, but implied)	Reported Device Performance (Met criteria)
Standalone Performance:
Case-Level Sensitivity meets design specifications	Met design specifications (for both Siemens Standard and Empire Reconstruction)
Lesion-Level Sensitivity meets design specifications	Met design specifications (for both Siemens Standard and Empire Reconstruction)
FP Rate in Non-Cancer Cases meets design specifications	Met design specifications (for both Siemens Standard and Empire Reconstruction)
Specificity meets design specifications	Met design specifications (for both Siemens Standard and Empire Reconstruction)
Non-Inferiority Comparison (vs. Hologic):
Difference in Sensitivity (Siemens vs. Hologic) within non-inferiority margin	Within the margin of non-inferiority (for both Siemens Standard and Empire Reconstruction)
Difference in FPPI (Siemens vs. Hologic) within non-inferiority margin	Within the margin of non-inferiority (for both Siemens Standard and Empire Reconstruction)
Difference in AUC (Siemens vs. Hologic) within non-inferiority margin	Within the margin of non-inferiority (for both Siemens Standard and Empire Reconstruction)

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

Siemens Standard Reconstruction Dataset:
- Sample Size: 694 cases (238 cancer, 456 non-cancer)
- Provenance: Not explicitly stated (e.g., country of origin). The study is described as a "screening population dataset," implying it is collected for screening purposes. The terms "stratified bootstrap procedure was used to estimate performance over a screening patient population" suggest it's representative of a screening population. Whether it's retrospective or prospective is not explicitly stated, but "dataset consisted of" typically implies retrospective collection for testing.
Siemens Empire Reconstruction Dataset:
- Sample Size: 322 cases (140 cancer, 182 non-cancer)
- Provenance: Not explicitly stated (e.g., country of origin). Similar to the Standard Reconstruction dataset, it is described as a "screening population dataset," implying it is collected for screening purposes. Whether it's retrospective or prospective is not explicitly stated, but "dataset consisted of" typically implies retrospective collection for testing.
Hologic (Control Group for Comparison): The document references "baseline performance of ProFound AI for DBT V2.0 with Hologic DBT images." While a control group is mentioned, the specific sample size for the Hologic dataset used in the comparison is not provided in this excerpt, only that the performance was used as a reference for non-inferiority.

3. Number of Experts Used to Establish Ground Truth and Qualifications

The document does not explicitly state the number of experts used or their qualifications for establishing ground truth for the test sets.

4. Adjudication Method for the Test Set

The document does not explicitly state the adjudication method used for the test sets (e.g., 2+1, 3+1).

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

No, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study (AI vs. without AI assistance) is not described in this document. The studies presented are standalone performance evaluations of the AI system and non-inferiority comparisons of the AI system's performance across different DBT acquisition systems. The "concurrently by interpreting physicians" in the indication for use suggests a human-in-the-loop interaction, but a specific MRMC study to quantify human improvement with AI is not detailed here.

6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study

Yes, standalone (algorithm only without human-in-the-loop performance) studies were done.

The "ProFound AI for DBT V2.1 Siemens Standard Screening Population Dataset" study explicitly states: "Standalone testing was performed on tomosynthesis slices only."
Similarly, the "ProFound AI for DBT V2.1 Siemens Empire Screening Population Dataset" study states: "Standalone testing was performed on tomosynthesis slices only."
The comparison studies ("Standalone Hologic Comparison Test Results") also involve comparing "the standalone performance of ProFound AI for DBT V2.0 with Hologic DBT images to the performance of ProFound AI for DBT V2.1 with Siemens Standard/Empire Reconstruction DBT images."

7. Type of Ground Truth Used

The type of ground truth used is not explicitly stated in this excerpt. However, in the context of screening population datasets for cancer detection, ground truth is typically established by:

Pathology (biopsy results) for positive cases.
Long-term follow-up (e.g., 1-2 years of negative imaging) for negative cases.

8. Sample Size for the Training Set

The document does not specify the sample size used for the training set.

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

The document does not specify how the ground truth for the training set was established. It only mentions that the "ProFound AI 2.1 algorithm uses deep learning technology to process feature computations and uses pattern recognition to identify suspicious breast lesions." This implies a training process based on labeled data, but details about the origin and establishment of those labels are not provided in this excerpt.

Summary

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

October 4, 2019

Image /page/0/Picture/1 description: The image shows the logo of the U.S. Food and Drug Administration (FDA). The logo consists of two parts: the Department of Health and Human Services logo on the left and the FDA logo on the right. The FDA logo is a blue square with the letters "FDA" in white, followed by the words "U.S. FOOD & DRUG" in blue and "ADMINISTRATION" in a smaller font size.

iCAD, Inc. % Ms. Heather Reed Vice President, Quality Assurance and Regulatory Affairs 98 Spit Brook Road, Suite 100 NASHUA NH 03062

Re: K191994

Trade/Device Name: ProFound™ AI Software V2.1 Regulation Number: 21 CFR 892.2090 Regulation Name: Radiological computer assisted detection and diagnosis software Regulatory Class: Class II Product Code: ODO Dated: July 24, 2019 Received: July 26, 2019

Dear Ms. Reed:

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 801); medical device reporting of medical device-related adverse events) (21 CFR 803) for

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

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,

For

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) K191994

Device Name ProFound™ AI Software V2.1

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/1 description: The image is a logo for ICAD. The logo is made up of the letters "iCAD" in a stylized font. The "i" is gold, and the "CAD" is blue. To the right of the letters is a gold figure of a person with their arms raised. The figure is curved and flowing, and it gives the impression of movement and energy.

510k Summary

K191994

Date Prepared: September 25, 2019

Submitter:

iCAD, Inc. 98 Spit Brook Road Suite 100 Nashua, NH 03062

Contact Person:

Heather Reed Vice President, Quality Assurance and Regulatory Affairs Email: hreed@icadmed.com Phone: (603) 309-1945 Fax: (603) 880-3043

Device Name:

Trade Name:	ProFound™ AI Software V2.1
Common Name:	Medical Imaging Software
Classification:	Radiological Computer Assisted Detection and Diagnosis Software
Product Code:	QDQ
Regulation Number:	21 CFR 892.2090
Review Panel:

Predicate Device:

510k Number:	K182373
Manufacturer:	iCAD, Inc.
Device Name:	ProFound™ AI V2 (PowerLook® Tomo Detection V2 Software)

Device Description

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

offered by the viewing/reading application, the ProFound AI V2.1 marks may also serve as a navigation tool for users because each mark can be linked to the tomosynthesis slice where the detection was identified. Each detected region is also assigned a "score" that corresponds to the ProFound AI V2.1 algorithm's confidence that the detected region is malignant (certainty of finding). Each case is also assigned a case score that corresponds to the ProFound AI V2.1 algorithm's confidence that a case is malignant. The certainty of finding scores are represented as an integer in range of 0 to 100 to indicate the CAD confidence that the detected region or case is malignant. The higher the certainty of finding or case score, the more likely the detected region or case is to be malignant.

Technical Characteristics:

Lesion Detection

ProFound AI 2.1 Software detects soft tissue densities (masses, architectural distortions and asymmetries) and calcifications in the 3D digital breast tomosynthesis or images. The ProFound AI 2.1 algorithm uses deep learning technology to process feature computations and uses pattern recognition to identify suspicious breast lesions appearing as soft tissue densities or clusters of calcifications. Each detected region is identified or represented by marking the contour of the lesion in the 3D tomosynthesis slice or 2D digital mammography image where it was detected.

Certainty of Finding and Case Scores

Certainty of Finding scores are relative scores assigned to each detected region and a Case Score is assigned to each case regardless of the number of detected regions. Certainty of Finding and Case Scores are computed by the ProFound AI 2.1 algorithm and represent the algorithm's confidence that a specific finding or case is malignant. The scores are represented on a 0% to 100% scale. Higher scores represent a higher algorithm confidence that a finding or case is malignant. Lower scores represent a lower algorithm confidence that a finding or case is malignant. The scores are based on a population with 50% prevalence of cancer and should be interpreted as the probability of the finding or case correctly being identified as malignant in a population of 50% cancers and 50% non-cancers. The scores serve as a guide to interpreting physicians to aid in determining if a suspicious finding or case needs further work-up. These scores are not intended to be the clinically used "probability of malignancy". Certainty of Finding and Case Scores are not calibrated to the prevalence in the intended use population or to the prevalence in the pivotal reader study outlined in the Assessment of Clinical Performance Data section, and consequently, the Certainty of Finding and Case Scores are in general higher than the actual probability of malignancy in an intended use population with less than 50% prevalence. These scores

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

represent a relative level of concern or level of suspicion because they do not represent an absolute clinical probability of malignancy.

Supported Digital Breast Tomosynthesis Systems

The following Digital Breast Tomosynthesis systems have been tested and are compatible with the ProFound AI 2.1 software: Supported 3D digital breast tomosynthesis systems:

Hologic Selenia Dimensions ●
GE Senographe SenoClaire
GE Senographe Pristina ●
Siemens Mammomat Inspiration ●
Siemens Mammomat Revelation ●

Intended Use / "Indications for Use"

ProFound™ AI V2.1 is a computer-assisted detection and diagnosis (CAD) software device intended to be used concurrently by radiologists while reading digital breast tomosynthesis (DBT) exams from compatible DBT systems. The system detects soft tissue densities (masses, architectural distortions and asymmetries) and calcifications in the 3D DBT slices. The detections and Certainty of Finding and Case Scores assist interpreting physicians in identifying soft tissue densities and calcifications that may be confirmed or dismissed by the interpreting physician.

	UNMODIFIED DeviceProFound™ AI V2(PowerLook® Tomo DetectionV2 Software)	MODIFIED DeviceProFound™ AI V2.1
Manufacturer	iCAD, Inc.	iCAD, Inc.
Classification Name	Radiological Computer AssistedDetection and DiagnosisSoftware	Radiological Computer AssistedDetection and DiagnosisSoftware
	UNMODIFIED DeviceProFound™ AI V2(PowerLook® Tomo DetectionV2 Software)	MODIFIED DeviceProFound™ AI V2.1
Regulation Number	21 CFR 892.2090	21 CFR 892.2090
Product Code	QDQ	QDQ
510(k) #	K182373	Pending
Intended Use /Indication for Use	ProFound™ AI V2(PowerLook® Tomo DetectionV2) is a computer-assisteddetection and diagnosis (CAD)software device intended to beused concurrently by interpretingphysicians while reading digitalbreast tomosynthesis (DBT)exams from compatible DBTsystems. The system detects softtissue densities (masses,architectural distortions andasymmetries) and calcificationsin the 3D DBT slices. Thedetections and Certainty ofFinding and Case Scores assistinterpreting physicians inidentifying soft tissue densitiesand calcifications that may beconfirmed or dismissed by theinterpreting Physician.	ProFound™ AI V2.1 is acomputer-assisted detection anddiagnosis (CAD) software deviceintended to be used concurrentlyby interpreting physicians whilereading digital breasttomosynthesis (DBT) examsfrom compatible DBT systems.The system detects soft tissuedensities (masses, architecturaldistortions and asymmetries) andcalcifications in the 3D DBTslices. The detections andCertainty of Finding and CaseScores assist interpretingphysicians in identifying softtissue densities and calcificationsthat may be confirmed ordismissed by the interpretingPhysician.
End User	Radiologists	Radiologists
Patient Population	Symptomatic and asymptomaticwomenundergoing mammography.	Symptomatic and asymptomaticwomenundergoing mammography.
	UNMODIFIED DeviceProFound™ AI V2(PowerLook® Tomo DetectionV2 Software)	MODIFIED DeviceProFound™ AI V2.1
Mode of Action	Image processing deviceintended to aid in the detection,localization, and characterizationof soft tissue densities (masses,architectural distortionsand asymmetries) andcalcifications in the 3D DBTslices.	Image processing deviceintended to aid in the detection,localization, and characterizationof soft tissue densities (masses,architectural distortionsand asymmetries) andcalcifications in the 3D DBTslices.
Image SourceModalities	Digital breast tomosynthesisslices	Digital breast tomosynthesisslices
Output Device	Softcopy Workstation	Softcopy Workstation
Deployment	Standalone computer	Standalone computer
Supported DigitalBreast TomosynthesisSystems	ProFound AI V2 Software:• Hologic Selenia Dimensions• Ge Senographe SenoClaire• GE Senographe Pristina	Profound AI V2 Software:• Hologic Selenia Dimensions• Ge Senographe SenoClaire• GE Senographe PristinaProFound AI V2.1 Software:• Siemens MammomatInspiration• Siemens MammomatRevelation

Comparison with Predicate Device

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

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

Summary of Indications for Use:

The "Indications for Use" remain unchanged from the Predicate UNMODIFIED Device ProFound™ AI V2 (PowerLook® Tomo Detection V2 Software).

Summary of Technological Characteristic

The technological characteristics of Modified Device, ProFound AI V2.1 remain unchanged from Unmodified Device ProFound™ AI V2 (PowerLook® Tomo Detection V2 Software) as the predicate. Per 21 CFR 892.2090, both devices are radiological computer assisted detection and diagnostic software intended to aid in the detection, localization, and characterization of disease specific findings on acquired medical images. The outputs of both

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

devices serve as a secondary or concurrent read and not a primary read. The output is used to inform the clinical user (who themselves make the primary diagnostic and patient management decisions) and will not replace the clinical expertise and judgment of the clinical user.

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 this device. Risk management is ensured via a 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, general controls of the FD&C Act, and special controls established for Radiological Computer Assisted Detection and Diagnosis Software are in place to further mitigate any safety and or effectiveness risks.

Assessment of Non-Clinical Performance Data

ProFound AI V2.1 has been verified and validated according to iCAD's design control processes. All supporting documentation has been included in this 510(k) Premarket Notification. Verification activity included unit, integration, and regression testing was performed. Validation testing included System testing was performed according to Standalone Hologic Comparison Protocol 0074-5007A, which is the same protocol used to support the 510(k) clearance of the original ProFound AI V2 device. Lastly, ProFound AI V2.1 is deployed on a DICOM platform that has been successfully tested for clinical network integration.

Standalone Performance:

ProFound AI for DBT V2.1 Siemens Standard Screening Population Dataset The ProFound AI for DBT V2.1 Siemens Standard Screening Population Standalone Study was executed to determine the performance of ProFound AI for DBT V2.1 with Siemens Standard Reconstruction DBT images for comparison with the baseline performance of ProFound AI for DBT V2.0 with Hologic DBT images. Standalone testing was performed on tomosynthesis slices only. Sensitivity was measured on Cancer cases with at least 2 views per breast. Specificity and FP rates were measured on bilateral 2-view Non-Cancer cases (2 standard views for the left breast and 2 standard views for the right breast). Sensitivity, Specificity, and false positive rate per tomosynthesis image volume were measured at the operating point. The standalone data set consisted of 694 Siemens Standard Reconstruction cases (238 cancer, 456 non-cancer) and were used to run the tests. A stratified bootstrap procedure was used to estimate performance over a screening patient population. The bootstrap procedure limits the number of cases in a particular category when computing performance measures. The purpose of the standalone study was to assess the standalone

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

performance of ProFound AI for DBT V2.1 with Siemens Standard Reconstruction DBT on a screening population.

Results from the standalone study showed that Case-Level Sensitivity, Lesion-Level Sensitivity, FP Rate in Non-Cancer Cases, and Specificity met design specifications. The detailed results are in the User Manual.

ProFound AI for DBT V2.1 Siemens Empire Screening Population Dataset The ProFound AI for DBT V2.1 Siemens Empire Screening Population Standalone Study was executed to determine the performance of ProFound AI for DBT V2.1 with Siemens Empire Reconstruction DBT images for comparison with the baseline performance of ProFound AI for DBT V2.0 with Hologic DBT images. Standalone testing was performed on tomosynthesis slices only. Sensitivity was measured on Cancer cases with at least 2 views per breast. Specificity and FP rates were measured on bilateral 2-view Non-Cancer cases (2 standard views for the left breast and 2 standard views for the right breast). Sensitivity, Specificity, and false positive rate per tomosynthesis image volume were measured at the operating point. The standalone data set consisted of a total of 322 Siemens Empire Reconstruction cases (140 cancer, 182 non-cancer) and were used to run the tests. A stratified bootstrap procedure was used to estimate performance over a screening patient population. The bootstrap procedure limits the number of cases in a particular category when computing performance measures. The purpose of the standalone study was to assess the standalone performance of ProFound AI for DBT V2.1 with Siemens Empire Reconstruction DBT on a screening population.

Standalone Hologic Comparison Test Results:

ProFound AI for DBT V2.1 with Siemens Standard Reconstruction DBT A comparison was made of the standalone performance of ProFound AI for DBT V2.0 with Hologic DBT images to the performance of ProFound AI for DBT V2.1 with Siemens Standard Reconstruction DBT images. For this comparison, the performance on Hologic is considered the control group and performance on Siemens Standard is the test group. The test is to determine if the difference between the control group and the test group is within the margin of non-inferiority for Sensitivity and AUC, and FPPI.

Standalone testing was performed for the control group and the test group individually. Kev performance measures were then compared by subtracting the test group performance from

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

the control group performance. This was done in a way to produce not just an estimate of the mean difference but also a distribution of the expected differences. In order to show statistical significance, the two-sided 95% confidence interval boundaries must be within the margin of non-inferiority.

Three measures were used to compare the performance of ProFound AI for DBT V2.1 with Siemens Standard Reconstruction DBT images to ProFound AI for DBT V2.0 with Hologic DBT. Each of the three measures produced differences that were within the margin of noninferiority. Therefore, in the areas of Sensitivity, FPPI, and AUC, ProFound AI for DBT V2.1 with Siemens Standard Reconstruction DBT system is not inferior to ProFound AI for DBT V2.0 with Hologic DBT system.

ProFound AI for DBT V2.1 with Siemens Empire Reconstruction DBT

A comparison was made of the standalone performance of ProFound AI for DBT V2.0 with Hologic DBT images to the performance of ProFound AI for DBT V2.1 with Siemens Empire Reconstruction DBT images. For this comparison, the performance on Hologic is considered the control group and performance on Siemens Empire is the test is to determine if the difference between the control group and the test group is within the margin of non-inferiority for Sensitivity and AUC, and FPPI.

Standalone testing was performed for the control group and the test group individually. Key performance measures were then compared by subtracting the test group performance from the control group performance. This was done in a way to produce not just an estimate of the mean difference but also a distribution of the expected differences. In order to show statistical significance, the two-sided 95% confidence interval boundaries must be within the margin of non-inferiority.

Three measures were used to compare the performance of ProFound AI for DBT V2.1 with Siemens Empire Reconstruction DBT images to ProFound AI for DBT V2.0 with Hologic DBT. Each of the three measures produced differences that were within the margin of noninferiority. Therefore, in the areas of Sensitivity, FPPI, and AUC, ProFound AI for DBT V2.1 with Siemens Empire Reconstruction DBT system is not inferior to ProFound AI for DBT V2.0 with Hologic DBT system.

Conclusion:

Based upon the information presented in this submission, it is concluded that ProFound AI V2.1 is substantially equivalent to the named predicate 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.