(216 days)
MammoScreen® 4 is a concurrent reading and reporting aid for physicians interpreting screening mammograms. It is intended for use with compatible full-field digital mammography and digital breast tomosynthesis systems. The device can also use compatible prior examinations in the analysis.
Output of the device includes graphical marks of findings as soft-tissue lesions or calcifications on mammograms along with their level of suspicion scores. The lesion type is characterized as mass/asymmetry, distortion, or calcifications for each detected finding. The level of suspicion score is expressed at the finding level, for each breast, and overall for the mammogram.
The location of findings, including quadrant, depth, and distance from the nipple, is also provided. This adjunctive information is intended to assist interpreting physicians during reporting.
Patient management decisions should not be made solely based on the analysis by MammoScreen 4.
MammoScreen 4 is a concurrent reading medical software device using artificial intelligence to assist radiologists in the interpretation of mammograms.
MammoScreen 4 processes the mammogram(s) and detects findings suspicious for breast cancer. Each detected finding gets a score called the MammoScreen Score™. The score was designed such that findings with a low score have a very low level of suspicion. As the score increases, so does the level of suspicion. For each mammogram, MammoScreen 4 outputs the detected findings with their associated score, a score per breast, driven by the highest finding score for each breast, and a score per case, driven by the highest finding score overall. The MammoScreen Score goes from one to ten.
MammoScreen 4 is available for 2D (FFDM images) and 3D processing (FFDM & DBT or 2DSM & DBT). Optionally, MammoScreen 4 can use prior examinations in the analysis.
The results indicating potential breast cancer, identified by MammoScreen 4, are accessible via a dedicated user interface and can seamlessly integrate into DICOM viewers (using DICOM-SC and DICOM-SR). Reporting aid outputs can be incorporated into the practice's reporting system to generate a preliminary report.
Note that the MammoScreen 4 outputs should be used as complementary information by radiologists while interpreting mammograms. For all cases, the medical professional interpreting the mammogram remains the sole decision-maker.
The provided text describes the acceptance criteria and a study to prove that MammoScreen® 4 meets these criteria. Here is a breakdown of the requested information:
Acceptance Criteria and Device Performance
1. Table of Acceptance Criteria and Reported Device Performance
Rationale for using "MammoScreen 2" data for comparison: The document states that the standalone testing for MammoScreen 4 compared its performance against "MammoScreen 2 on Dimension". While MammoScreen 3 is the predicate device, the provided performance data in the standalone test section specifically refers to MammoScreen 2. The PCCP section later references performance targets for MammoScreen versions 1, 2, and 3, but the actual "Primary endpoint" results for the current device validation are given in comparison to MammoScreen 2. Therefore, the table below uses the reported performance against MammoScreen 2 as per the "Primary endpoint" section.
| Metric | Acceptance Criteria | Reported Device Performance (MammoScreen 4 vs. MammoScreen 2) |
|---|---|---|
| Primary Objective | Non-inferiority in standalone cancer detection performance compared to the previous version of MammoScreen (specifically MammoScreen 2 on Dimension). | Achieved. |
| AUC at the mammogram level | Positive lower bound of the 95% CI of the difference in endpoints between MammoScreen 4 and MammoScreen 2. | MS4: 0.894 (0.870, 0.919) MS2: 0.867 (0.839, 0.896) Δ: 0.027 (0.002, 0.052), p<0.0001 (Lower bound of difference 0.002 is positive, meeting criteria) |
| AUC at the breast level | Positive lower bound of the 95% CI of the difference in endpoints between MammoScreen 4 and MammoScreen 2. | MS4: 0.919 (0.897, 0.941) MS2: 0.895 (0.871, 0.920) Δ: 0.023 (0.002, 0.045), p<0.0001 (Lower bound of difference 0.002 is positive, meeting criteria) |
| AUC LROC at the finding level | Positive lower bound of the 95% CI of the difference in endpoints between MammoScreen 4 and MammoScreen 2. | MS4: 0.891 (0.862, 0.921) MS2: 0.837 (0.797, 0.877) Δ: 0.055 (0.032, 0.077), p<0.0001 (Lower bound of difference 0.032 is positive, meeting criteria) |
Study Details
2. Sample size used for the test set and the data provenance
- Sample Size: 1,475 patients, leading to 2,950 included studies (each patient underwent a DBT acquisition with two Hologic mammography systems).
- Data Provenance: The document explicitly mentions "Data provenance" as a considered subgroup for analysis but does not specify the country of origin. It indicates that the data for standalone performance testing only belonged to the "test group," which means it was "unseen data" from sources entirely left out during training and tuning. The study appears to be retrospective as it uses existing patient data.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
The document states that for the clinical testing (MRMC studies), "MQSA-qualified and ACR-certified readers" were used. However, for the standalone performance testing (which is where the ground truth for the algorithm's performance is established), the document only describes the "Truthing process" and does not specify the number or qualifications of experts involved in establishing the ground truth.
4. Adjudication method (e.g., 2+1, 3+1, none) for the test set
The document describes the "Truthing process" for the standalone performance testing but does not specify an adjudication method involving multiple readers. The ground truth establishment is described as:
- Positive cases: biopsy-proven presence of cancer.
- Benign cases: cases confirmed by biopsy result and cases confirmed by imaging follow-up.
- Negative cases: verified by imaging follow-up.
This indicates a reliance on clinical outcomes/pathology rather than reader consensus for ground truth for the standalone performance data.
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
- Was an MRMC study done? Yes, "Clinical Testing" section explicitly states: "The clinical validation of MammoScreen 4 includes three multi-reader multi-case (MRMC) studies: One for FFDM, One for DBT, One for combined DBT and 2D mammograms (FFDM or 2DSM), and using prior examinations."
- Effect size of improvement: The document states, "The studies demonstrated the superiority of the Area Under the Receiver Operating Characteristic Curve of the radiologist using the MammoScreen algorithm compared to the unaided radiologist." However, specific effect sizes (e.g., AUC difference, confidence intervals) for the human reader performance improvement with AI assistance versus without AI assistance are not provided in the excerpt. Only the result of superiority is mentioned, not the quantitative measure of that superiority.
6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done
- Was a standalone study done? Yes. The section "The standalone performance testing carried out to validate the device is summarized in what follows:" directly addresses this.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
For the standalone performance testing:
- Positive cases: Biopsy-proven presence of cancer.
- Benign cases: Confirmed by biopsy result and cases confirmed by imaging follow-up.
- Negative cases: Verified by imaging follow-up.
This indicates a mix of pathology (biopsy) and outcomes data (imaging follow-up) as the ground truth.
8. The sample size for the training set
The document states: "Sources in the training/tuning group may only be used for model training and tuning. Sources in the test group may only be used for external validation of the model's performances on unseen data (i.e., from sources entirely left out during training and tuning)." However, it does not provide the specific sample size for the training set. It only implies it was "very large databases."
9. How the ground truth for the training set was established
The document states: "These modules are trained with very large databases of biopsy-proven examples of breast cancer and normal tissue." This implies that the ground truth for the training set was primarily established through biopsy results for cancerous cases and likely outcomes/clinical confirmation for normal or benign cases, similar to the test set ground truth. However, detailed methodology on training set ground truth establishment is not provided beyond "biopsy-proven examples."
FDA 510(k) Clearance Letter - MammoScreen® (4)
Page 1
U.S. Food & Drug Administration
10903 New Hampshire Avenue
Silver Spring, MD 20993
www.fda.gov
Doc ID # 04017.07.05
July 3, 2025
Therapixel
℅ Alex Cadotte
VP, Digital Health, AI and Radiology
MCRA, an IQVIA Business
803 7th St NW
Washington, District of Columbia 20001
Re: K243679
Trade/Device Name: MammoScreen® (4)
Regulation Number: 21 CFR 892.2090
Regulation Name: Radiological Computer Assisted Detection And Diagnosis Software
Regulatory Class: Class II
Product Code: QDQ, QIH
Dated: June 3, 2025
Received: June 3, 2025
Dear Alex Cadotte:
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.
FDA's substantial equivalence determination also included the review and clearance of your Predetermined Change Control Plan (PCCP). Under section 515C(b)(1) of the Act, a new premarket notification is not
Page 2
K243679 - Alex Cadotte Page 2
required for a change to a device cleared under section 510(k) of the Act, if such change is consistent with an established PCCP granted pursuant to section 515C(b)(2) of the Act. Under 21 CFR 807.81(a)(3), a new premarket notification is required if there is a major change or modification in the intended use of a device, or if there is a change or modification in a device that could significantly affect the safety or effectiveness of the device, e.g., a significant change or modification in design, material, chemical composition, energy source, or manufacturing process. Accordingly, if deviations from the established PCCP result in a major change or modification in the intended use of the device, or result in a change or modification in the device that could significantly affect the safety or effectiveness of the device, then a new premarket notification would be required consistent with section 515C(b)(1) of the Act and 21 CFR 807.81(a)(3). Failure to submit such a premarket submission would constitute adulteration and misbranding under sections 501(f)(1)(B) and 502(o) of the Act, respectively.
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).
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 (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-reporting-combination-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.
All medical devices, including Class I and unclassified devices and combination product device constituent parts are required to be in compliance with the final Unique Device Identification System rule ("UDI Rule"). The UDI Rule requires, among other things, that a device bear a unique device identifier (UDI) on its label and package (21 CFR 801.20(a)) unless an exception or alternative applies (21 CFR 801.20(b)) and that the dates on the device label be formatted in accordance with 21 CFR 801.18. The UDI Rule (21 CFR 830.300(a) and 830.320(b)) also requires that certain information be submitted to the Global Unique Device Identification Database (GUDID) (21 CFR Part 830 Subpart E). For additional information on these requirements, please see the UDI System webpage at https://www.fda.gov/medical-devices/device-advice-comprehensive-regulatory-assistance/unique-device-identification-system-udi-system.
Page 3
K243679 - Alex Cadotte Page 3
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-devices/medical-device-safety/medical-device-reporting-mdr-how-report-medical-device-problems.
For comprehensive regulatory information about medical devices and radiation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/medical-devices/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-devices/device-advice-comprehensive-regulatory-assistance/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
Page 4
Food and Drug Administration
Indications for Use
Form Approved: OMB No. 0910-0120
Expiration Date: 07/31/2026
See PRA Statement below.
DEPARTMENT OF HEALTH AND HUMAN SERVICES
Submission Number (if known)
K243679
Device Name
MammoScreen® (4)
Indications for Use (Describe)
MammoScreen 4 is a concurrent reading and reporting aid for physicians interpreting screening mammograms. It is intended for use with compatible full-field digital mammography and digital breast tomosynthesis systems. The device can also use compatible prior examinations in the analysis.
Output of the device includes graphical marks of findings as soft-tissue lesions or calcifications on mammograms along with their level of suspicion scores. The lesion type is characterized as mass/asymmetry, distortion, or calcifications for each detected finding. The level of suspicion score is expressed at the finding level, for each breast, and overall for the mammogram.
The location of findings, including quadrant, depth, and distance from the nipple, is also provided. This adjunctive information is intended to assist interpreting physicians during reporting.
Patient management decisions should not be made solely based on the analysis by MammoScreen 4.
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."
Page 5
510(k) Summary
Page 1 of 8
510(k) submission MammoScreen 4
510(k) Summary
This 510(k) summary of safety and effectiveness information is prepared in accordance with the requirements of 21 CFR § 807.92.
Applicant Information:
Therapixel
455 Promenade des Anglais,
06200 Nice
France
Phone: +33 9 72 55 20 39
Company Representative:
Pierre Fillard
Chief Scientific Officer
Email: pfillard@therapixel.com
Phone: +33 683712809
Primary Correspondent:
Alex Cadotte, PhD
VP, Digital Health, AI and Radiology
Email: acadotte@mcra.com
Phone: (347)-302-4549
Date Summary Prepared: November 21, 2024
Device Information:
Trade Name: MammoScreen®
Model: 4
Common Name: Computer-Assisted Detection Device
Device Classification Name: Radiological Computer Assisted Detection/Diagnosis Software For Lesions Suspicious For Cancer
Regulation Number: 892.2090
Regulation Class: Class II
Product Code: QDQ
Associated Product Code: QIH
Submission type: Traditional 510(k)
510(k) number: K243679
Page 6
Page 2 of 8
510(k) submission MammoScreen 4
Predicate Device:
The predicate device is MammoScreen 3, cleared under K240301 (Product code QDQ).
Device Description:
MammoScreen 4 is a concurrent reading medical software device using artificial intelligence to assist radiologists in the interpretation of mammograms.
MammoScreen 4 processes the mammogram(s) and detects findings suspicious for breast cancer. Each detected finding gets a score called the MammoScreen Score™. The score was designed such that findings with a low score have a very low level of suspicion. As the score increases, so does the level of suspicion. For each mammogram, MammoScreen 4 outputs the detected findings with their associated score, a score per breast, driven by the highest finding score for each breast, and a score per case, driven by the highest finding score overall. The MammoScreen Score goes from one to ten.
MammoScreen 4 is available for 2D (FFDM images) and 3D processing (FFDM & DBT or 2DSM & DBT). Optionally, MammoScreen 4 can use prior examinations in the analysis.
The results indicating potential breast cancer, identified by MammoScreen 4, are accessible via a dedicated user interface and can seamlessly integrate into DICOM viewers (using DICOM-SC and DICOM-SR). Reporting aid outputs can be incorporated into the practice's reporting system to generate a preliminary report.
Note that the MammoScreen 4 outputs should be used as complementary information by radiologists while interpreting mammograms. For all cases, the medical professional interpreting the mammogram remains the sole decision-maker.
Indication for Use:
MammoScreen® 4 is a concurrent reading and reporting aid for physicians interpreting mammograms. It is intended for use with compatible full-field digital mammography and digital breast tomosynthesis systems. The device can also use compatible prior examinations in the analysis.
Output of the device includes graphical marks of findings as soft-tissue lesions or calcifications on mammograms along with their level of suspicion scores. The lesion type is characterized as mass/asymmetry, distortion, or calcifications for each detected finding. The level of suspicion score is expressed at the finding level, for each breast, and overall for the mammogram.
The location of findings, including quadrant, depth, and distance from the nipple, is also provided. This adjunctive information is intended to assist interpreting physicians during reporting.
Patient management decisions should not be made solely based on the analysis by MammoScreen 4.
Page 7
Page 3 of 8
510(k) submission MammoScreen 4
Predicate device comparison:
| Predicate device (MammoScreen 3) | Subject device (MammoScreen 4) | |
|---|---|---|
| Manufacturer | Therapixel | Therapixel |
| Regulation number | 892.2090 | 892.2090 |
| Product Code | QDQ | QDQ |
| Intended Use | MammoScreen 3 is a concurrent reading and reporting aid for physicians interpreting screening mammograms. It is intended for use with compatible full-field digital mammography and digital breast tomosynthesis systems. The device can also use compatible prior examinations in the analysis.Output of the device includes graphical marks of findings as soft-tissue lesions or calcifications on mammograms along with their level of suspicion scores. The lesion type is characterized as mass/asymmetry, distortion, or calcifications for each detected finding. The level of suspicion score is expressed at the finding level, for each breast, and overall for the mammogram.The location of findings, including quadrant, depth, and distance from the nipple, is also provided. This adjunctive information is intended to assist interpreting physicians during reporting.Patient management decisions should not be made solely based on the analysis by MammoScreen 3. | MammoScreen® 4 is a concurrent reading and reporting aid for physicians interpreting mammograms. It is intended for use with compatible full-field digital mammography and digital breast tomosynthesis. The device can also use compatible prior examinations in the analysis.Output of the device includes graphical marks of findings as soft-tissue lesions or calcifications on mammograms along with their level of suspicion scores. The lesion type is characterized as mass/asymmetry, distortion, or calcifications for each detected finding. The level of suspicion score is expressed at the finding level, for each breast, and overall for the mammogram.The location of findings, including quadrant, depth, and distance from the nipple, is also provided. This adjunctive information is intended to assist interpreting physicians during reporting.Patient management decisions should not be made solely based on the analysis by MammoScreen 4. |
| Intended user population | Physicians qualified to read mammograms. | Physicians qualified to read mammograms. |
| Intended patient population | Women undergoing mammography. | Women undergoing mammography. |
| Anatomical Location | Breast | Breast |
| Design | Software-only device | Software-only device |
| Type of artificial intelligence | MammoScreen 3 is powered by artificial intelligence/machine learning-based software algorithm | Same. |
| Level of suspicion | MammoScreen 3 outputs a level of suspicion at the finding, breast and case level. | Same. |
Page 8
Page 4 of 8
510(k) submission MammoScreen 4
Predicate device comparison:
| Predicate device (MammoScreen 3) | Subject device (MammoScreen 4) | |
|---|---|---|
| Manufacturer | Therapixel | Therapixel |
| Regulation number | 892.2090 | 892.2090 |
| Product Code | QDQ | QDQ |
| Intended Use | MammoScreen 3 is a concurrent reading and reporting aid for physicians interpreting screening mammograms. It is intended for use with compatible full-field digital mammography and digital breast tomosynthesis systems. The device can also use compatible prior examinations in the analysis.Output of the device includes graphical marks of findings as soft-tissue lesions or calcifications on mammograms along with their level of suspicion scores. The lesion type is characterized as mass/asymmetry, distortion, or calcifications for each detected finding. The level of suspicion score is expressed at the finding level, for each breast, and overall for the mammogram.The location of findings, including quadrant, depth, and distance from the nipple, is also provided. This adjunctive information is intended to assist interpreting physicians during reporting.Patient management decisions should not be made solely based on the analysis by MammoScreen 3. | MammoScreen® 4 is a concurrent reading and reporting aid for physicians interpreting mammograms. It is intended for use with compatible full-field digital mammography and digital breast tomosynthesis. The device can also use compatible prior examinations in the analysis.Output of the device includes graphical marks of findings as soft-tissue lesions or calcifications on mammograms along with their level of suspicion scores. The lesion type is characterized as mass/asymmetry, distortion, or calcifications for each detected finding. The level of suspicion score is expressed at the finding level, for each breast, and overall for the mammogram.The location of findings, including quadrant, depth, and distance from the nipple, is also provided. This adjunctive information is intended to assist interpreting physicians during reporting.Patient management decisions should not be made solely based on the analysis by MammoScreen 4. |
| Intended user population | Physicians qualified to read mammograms. | Physicians qualified to read mammograms. |
| Intended patient population | Women undergoing mammography. | Women undergoing mammography. |
| Anatomical Location | Breast | Breast |
| Design | Software-only device | Software-only device |
| Type of artificial intelligence | MammoScreen 3 is powered by artificial intelligence/machine learning-based software algorithm | Same. |
| Level of suspicion | MammoScreen 3 outputs a level of suspicion at the finding, breast and case level. | Same. |
| Lesion type | For each detected finding MammoScreen 3 classifies them as mass/asymmetry, distortion or calcifications. | Same. |
| Localization | For each finding MammoScreen 3 provides a quadrant, a depth and a distance to the nipple. | Same. |
| Inputs | FFDM or 2DSM & DBT or FFDM & DBT, with an optional prior (FFDM or 2DSM & DBT) expect for the former. | Same. |
| Support of Hologic Envision system | Not included. | Included. |
| Inclusion of PCCP | Not Included. | Included.The PCCP in the subject device includes proposed modifications related to extending supported image acquisition systems. |
The indication for the use of MammoScreen 4 is similar to that of the predicate device. Both devices are intended for concurrent use by physicians interpreting breast images to help them with localizing and characterizing findings. The devices are not intended as a replacement for the review of a physician or their clinical judgment.
The predicate device and the subject device are two software versions of MammoScreen. They both rely on the same fundamental scientific technology.
The design changes of this new version of MammoScreen have been assessed at the software design level and do not raise different questions of safety and effectiveness than the previous version. For both devices, a choice of medical image processing and machine learning techniques are implemented. The system includes 'deep learning' modules for the detection of suspicious calcifications and soft tissue lesions. These modules are trained with very large databases of biopsy-proven examples of breast cancer and normal tissue.
The overall design of MammoScreen 4 is the same than the design of the predicate device. Both versions detect and characterize findings in radiological breast images and provide information about the presence, location, and characteristics of the findings to the user in a similar manner. While MammoScreen 4 has been evaluated on mammograms produced by a wider range of systems to accept those, these modifications do not raise different questions about the safety and effectiveness of the device as compared to the predicate device. The devices have the same intended use. The modifications do not raise different questions about the safety and effectiveness of the device as compared to the predicate device. The safety and effectiveness of the device have been evaluated with a similar methodology as for the predicate device.
Non clinical Testing
MammoScreen is a software-only device.
Tests have been performed in compliance with the following recognized consensus standards:
Page 9
Page 5 of 8
510(k) submission MammoScreen 4
- IEC 62304:2006/A1:2016 - Medical device software - Software life-cycle processes
- IEC 62366-1:2015+AMD1:2020 - Medical devices - Application of usability engineering to medical devices.
MammoScreen 4 has successfully completed integration and verification testing and beta validation. In addition, potential hazards have been evaluated and mitigated, and have acceptable levels.
The standalone performance testing carried out to validate the device is summarized in what follows:
| Statistics tests for primary objective | Non-inferiority in standalone cancer detection performance compared to the previous version of MammoScreen |
|---|---|
| Primary endpoint | • AUC at the mammogram level MS4: 0.894 (0.870, 0.919), MS2: 0.867 (0.839, 0.896), Δ: 0.027 (0.002, 0.052), p<0.0001• AUC at the breast level: MS4: 0.919 (0.897, 0.941), MS2: 0.895 (0.871, 0.920), Δ: 0.023 (0.002, 0.045), p<0.0001• AUC LROC at the finding level: MS4: 0.891 (0.862, 0.921), MS2: 0.837 (0.797, 0.877), Δ: 0.055 (0.032, 0.077), p<0.0001 |
| Acceptance criteria | Positive lower bound of the 95% CI of the difference in endpoints between the version under evaluation (MammoScreen 4 on Envision) and the reference version (MammoScreen 2 on Dimension) |
| Number of included patients | 1,475 |
| Number of included studies | 2,950 (each patient underwent a DBT acquisition with two Hologic mammography systems) |
| Age distribution | Age <= 50: 44650 < Age <= 65: 64265 > Age: 372 |
| Race and Ethnicity distribution | Asian: 16White: 1180Black: 94Other (including American Indian, Alaska Native, Native Hawaiian or Other Pacific Islander): 14Hispanic: 88Not Hispanic: 1136 |
| Considered subgroups | Density, Lesion type (mass/asymmetries, calcifications, distortion), Age, Lesion size, Lesion severity, Race, Ethnicity, Data provenance, Reference standard for negative cases. |
| Truthing process | Positive cases: biopsy-proven presence of cancer.Benign cases: cases confirmed by biopsy result and cases confirmed by imaging follow-up.Negative cases: verified by imaging follow-up. |
| Independence of test data from training data | Data sources are separated into the training/tuning group and the test group. Sources in the training/tuning group may only be used for model training and tuning. Sources in the test group may only be used for external validation of the model's performances on |
Page 10
Page 6 of 8
510(k) submission MammoScreen 4
unseen data (i.e., from sources entirely left out during training and tuning).
Data used for the standalone performance testing only belongs to the test group.
Clinical Testing
The clinical validation of MammoScreen 4 includes three multi-reader multi-case (MRMC) studies:
- One for FFDM
- One for DBT
- One for combined DBT and 2D mammograms (FFDM or 2DSM), and using prior examinations.
The objective of these MRMC studies was to determine whether the radiologist's performance when using MammoScreen is superior to unaided radiologist performance for interpretation of mammograms.
The three studies used a multi-reader multi-case cross-over design with an enriched sample set with MQSA-qualified and ACR-certified readers to compare the performance of unaided radiologists to that of radiologists using MammoScreen.
The studies demonstrated the superiority of the Area Under the Receiver Operating Characteristic Curve of the radiologist using the MammoScreen algorithm compared to the unaided radiologist.
Predetermined Change Control Plan (PCCP)
MammoScreen is powered by machine-learning neural architecture. Therapixel will make future algorithm improvements under a PCCP. The plan describes future modifications and assesses their impact, and a modification protocol details how data management, re-training, performance evaluation and update procedures will be handled.
The table below lists and describes the anticipated modifications:
| Modification #1 summary | Support of GE mammograms (no re-training required) |
|---|---|
| Modification #2 summary | Support of a new mammography manufacturer other than Hologic and GE (re-training required) – this modification may also include the support of GE mammograms in case Modification #1 does not conclude to the non-inferiority on GE mammograms compared to Hologic |
| Statistics tests for primary objective | Non-inferiority of device standalone performance on mammograms of the manufacturer under evaluation compared to Hologic mammograms |
| Primary endpoints | AUC at the mammogram, breast and finding level (AUC LROC) |
Page 11
Page 7 of 8
510(k) submission MammoScreen 4
| Acceptance criteria | • Modification #1: See Table 1.• Modification #2: See Table 1 (unpaired comparisons) and Table 2 (paired comparisons). |
|---|---|
| Validation activities | Upon demonstration of the non-inferiority through the standalone performance testing, changes will be documented in a minor release amending:- The Algorithm test protocol and results documents- The User Guide- The device label |
| Communication plan | Upcoming updates are communicated to users through advisory notices sent by email at least 2 weeks before deployment. Users may choose to opt-out the update during the 2-week notice period. |
Table 1: Primary endpoints and acceptance criteria for unpaired comparisons.
| Primary endpoints | Acceptance criteria proposed for PCCP | |||||
|---|---|---|---|---|---|---|
| AUC ROC (exam level) | AUC ROC (breast level) | AUC LROC (finding level) | Exam level | Breast level | Finding level | |
| MammoScreen (K192854) on Hologic FFDM only | 0.89 (0.87, 0.91) | 0.91 (0.89, 0.92) | 0.88 (0.86, 0.90) | LB 95% CI diff ≥ -0.02 | LB 95% CI diff ≥ -0.02 | LB 95% CI diff ≥ -0.02 |
| MammoScreen 2 (K211541) on Hologic DBT + FFDM | 0.89 (0.87, 0.91) | 0.92 (0.90, 0.93) | 0.88 (0.86, 0.90) | LB 95% CI diff ≥ -0.02 | LB 95% CI diff ≥ -0.02 | LB 95% CI diff ≥ -0.02 |
| MammoScreen 2 (K211541) on Hologic DBT + 2DSM | 0.89 (0.87, 0.91) | 0.92 (0.90, 0.93) | 0.88 (0.86, 0.90) | LB 95% CI diff ≥ -0.02 | LB 95% CI diff ≥ -0.02 | LB 95% CI diff ≥ -0.02 |
| MammoScreen 3 (K240301) on Hologic DBT + FFDM with FFDM priors | 0.93 (0.91, 0.94) | 0.95 (0.93, 0.97) | 0.93 (0.91, 0.95) | LB 95% CI diff ≥ -0.02 | LB 95% CI diff ≥ -0.02 | LB 95% CI diff ≥ -0.02 |
| MammoScreen 3 (K240301) on Hologic DBT + 2DSM with DBT + 2DSM priors | 0.89 (0.84, 0.93) | 0.92 (0.88, 0.96) | 0.87 (0.83, 0.94) | LB 95% CI diff ≥ -0.05 | LB 95% CI diff ≥ -0.04 | LB 95% CI diff ≥ -0.04 |
Table 2: Primary endpoints and acceptance criteria for paired comparisons.
| Primary endpoints | Acceptance criteria proposed for PCCP | |||||
|---|---|---|---|---|---|---|
| AUC ROC (exam level) | AUC ROC (breast level) | AUC LROC (finding level) | Exam level | Breast level | Finding level |
Page 12
Page 8 of 8
510(k) submission MammoScreen 4
| MammoScreen (K192854) on Hologic FFDM only | 0.89 (0.87, 0.91) | 0.91 (0.89, 0.92) | 0.88 (0.86, 0.90) | LB 95%CI ≥0.84 | LB 95%CI ≥0.86 | LB 95%CI ≥0.83 |
|---|---|---|---|---|---|---|
| MammoScreen 2 (K211541) on Hologic DBT + FFDM | 0.89 (0.87, 0.91) | 0.92 (0.90, 0.93) | 0.88 (0.86, 0.90) | LB 95%CI ≥0.84 | LB 95%CI ≥0.87 | LB 95%CI ≥0.83 |
| MammoScreen 2 (K211541) on Hologic DBT + 2DSM | 0.89 (0.87, 0.91) | 0.92 (0.90, 0.93) | 0.88 (0.86, 0.90) | LB 95%CI ≥0.84 | LB 95%CI ≥0.87 | LB 95%CI ≥0.83 |
| MammoScreen 3 (K240301) on Hologic DBT + FFDM with FFDM priors | 0.93 (0.91, 0.94) | 0.95 (0.93, 0.97) | 0.93 (0.91, 0.95) | LB 95%CI ≥0.88 | LB 95%CI ≥0.9 | LB 95%CI ≥0.88 |
| MammoScreen 3 (K240301) on Hologic DBT + 2DSM with DBT + 2DSM priors | 0.89 (0.84, 0.93) | 0.92 (0.88, 0.96) | 0.87 (0.83, 0.94) | LB 95%CI ≥0.84 | LB 95%CI ≥0.87 | LB 95%CI ≥0.83 |
Conclusions
Standalone performance tests on FFDM and DBT demonstrate that MammoScreen 4 achieves non-inferior performance compared to the predicate device.
MRMC studies and standalone tests demonstrated that the device is safe and effective.
Therapixel has applied a risk management process following FDA-recognized standards to identify, evaluate, and mitigate all known hazards related to MammoScreen 4. These hazards may occur when the accuracy of diagnosis is potentially affected, causing either false positives or false negatives. 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 these 510(k) supports the safe and effective use of MammoScreen 4 for its indications for use and substantial equivalence to the predicate device.
§ 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.