(159 days)
Yes.
The device description explicitly states, "BrightHeart View Classifier is a cloud-based software-only device which uses artificial intelligence (AI) to detect standard views during fetal heart scanning in fetal ultrasound images and video clips." It further specifies "using machine learning techniques" and "powered by a neural network."
No.
The device is intended to analyze and classify ultrasound images and video clips to detect standard views, acting as an adjunct to and aiding in the interpretation of fetal ultrasound examinations. It does not directly provide therapy or actively treat a disease or condition.
No
The device is intended to identify standard views in fetal 2D ultrasound images and video clips to assist in the acquisition and interpretation of fetal anatomic ultrasound examinations. It acts as an "adjunct" tool for quality control and workflow improvement, rather than providing a medical diagnosis or aiding in the diagnosis of a disease, condition, or state of health.
Yes
The device is explicitly described as a "cloud-based software-only device" and its intended use is to analyze existing medical images using AI/ML, generating classifications and annotated files. There is no mention of hardware components provided or required by the device itself for its primary function.
No.
The device analyzes medical images (ultrasound images) to detect standard views for fetal heart scanning, rather than analyzing biological specimens (e.g., blood, urine, tissue) for diagnostic information. Therefore, it does not meet the definition of an In Vitro Diagnostic (IVD) device.
Yes
The letter explicitly states: "FDA's substantial equivalence determination also included the review and clearance of your Predetermined Change Control Plan (PCCP)." This language directly indicates that the PCCP has been cleared for this specific device.
Intended Use / Indications for Use
The BrightHeart View Classifier device is intended to analyze fetal 2D ultrasound images and video clips using machine learning techniques to automatically detect standard views during fetal heart scanning.
The BrightHeart View Classifier device is intended to be used as an adjunct to the acquisition and interpretation of fetal anatomic ultrasound examinations at the second or third trimester of pregnancy performed with transabdominal probes.
Product codes
QIH
Device Description
BrightHeart View Classifier is a cloud-based software-only device which uses artificial intelligence (AI) to detect standard views during fetal heart scanning in fetal ultrasound images and video clips.
BrightHeart View Classifier is intended to be used by qualified, trained healthcare professional personnel in a professional prenatal ultrasound (US) imaging environment (this includes sonographers, MFMs, OB/GYN, and Fetal surgeons), to help fetal ultrasound examination acquisition and interpretation of 2D grayscale ultrasound by providing automatic classification of video clips and images into standard views, by automatically extracting example frames of standard views from video clips, and by automatically assessing whether the documentation of each standard view in video clips and images satisfies an acquisition protocol defined by the center. Annotated DICOM files generated by the device cannot be modified by the user.
Mentions image processing
Medical Image Management and Processing System
Mentions AI, DNN, or ML
- The BrightHeart View Classifier device is intended to analyze fetal 2D ultrasound images and video clips using machine learning techniques to automatically detect standard views during fetal heart scanning.
- BrightHeart View Classifier is a cloud-based software-only device which uses artificial intelligence (AI) to detect standard views during fetal heart scanning in fetal ultrasound images and video clips.
- The BrightHeart View Classifier device is powered by a neural network performing standard view classification in fetal ultrasound images.
- Software algorithm: Machine Learning Model
- Model method: Neural networks
- Training of the machine learning model to achieve sufficient view classification performance for additional standard views, which will assist users in the identification of these views during fetal heart ultrasound scanning.
Input Imaging Modality
Fetal Ultrasound, Ultrasound images and video clips
Anatomical Site
fetal heart, fetal anatomic
Indicated Patient Age Range
The device is for fetal examinations at the second or third trimester of pregnancy. No specific patient age range is provided for the pregnant individual.
Intended User / Care Setting
qualified, trained healthcare professional personnel in a professional prenatal ultrasound (US) imaging environment (this includes sonographers, MFMs, OB/GYN, and Fetal surgeons)
Description of the training set, sample size, data source, and annotation protocol
- The ultrasound examinations used for training and validation are entirely distinct from the examinations used in performance testing.
- Re-training of the BrightHeart View Classifier with new data to optimize its performance followed by performance testing and a comparison of the original BrightHeart View Classifier to the modified BrightHeart View Classifier (using performance metrics) and verification and validation.
- Re-training of the BrightHeart View Classifier with data from new ultrasound machine makes to optimize its performance followed by performance testing and a comparison of the original BrightHeart View Classifier to the modified BrightHeart View Classifier (using performance metrics) and verification and validation.
- Re-training of the BrightHeart View Classifier with data from new standard views to optimize its performance followed by performance testing and a comparison of the original BrightHeart View Classifier to the modified BrightHeart View Classifier (using performance metrics) and verification and validation.
- Re-training of the BrightHeart View Classifier with data from new gestational ages to optimize its performance followed by performance testing and a comparison of the original BrightHeart View Classifier to the modified BrightHeart View Classifier (using performance metrics) and verification and validation.
Description of the test set, sample size, data source, and annotation protocol
- The device performance for standard view classification was validated with a dataset of 2290 clinically acquired images and frames from video clips from 579 fetal ultrasound examinations, performed with transabdominal probes at 18 weeks of gestation or later, from 8 centers.
- Demographic distribution: gender: female; age: 18 years or older; ethnicity/country: U.S.A. and France.
- The reference standard was derived from the dataset through a truthing process in which a sonographer and an MFM specialist with experience in fetal echocardiography determined the presence or absence of standard views on fetal ultrasound images.
- The truthing process was conducted independently of the BrightHeart View Classifier device.
- The ultrasound examinations used for training and validation are entirely distinct from the examinations used in performance testing.
Summary of Performance Studies
- Study Type: Bench Testing / Software Verification and Validation Testing
- Sample Size: 2290 clinically acquired images and frames from video clips from 579 fetal ultrasound examinations
- Standalone Performance: The performance testing demonstrated that BrightHeart View Classifier identifies standard views with a mean standard view recognition sensitivity of 0.939 (95% CI, 0.917 ; 0.960) and a mean standard view recognition specificity of 0.984 (95% CI, 0.973 ; 0.996).
- Key Results: Stratified analysis by geographical region, by ultrasound machine make, by gestational age, by mother's BMI, and age, and by record type indicated that performance was consistent across subgroups, while analysis by mother's race showed that the specificity 95% CI lower bound was slightly lower for Asian and Black mothers, possibly due to large confidence intervals and small sample size. BrightHeart View Classifier was validated only with General Electric, Philips, Samsung and Siemens ultrasound devices and is intended only to be used with these ultrasound vendors. BrightHeart View Classifier was validated with pregnancies at 18 weeks of gestation or later recorded with transabdominal probes and is intended to be used only for such examinations.
Key Metrics
Mean standard view recognition sensitivity of 0.939 (95% CI, 0.917 ; 0.960)
Mean standard view recognition specificity of 0.984 (95% CI, 0.973 ; 0.996)
Predicate Device(s)
Reference Device(s)
Predetermined Change Control Plan (PCCP) - All Relevant Information
The BrightHeart View Classifier device is powered by a neural network performing standard view classification in fetal ultrasound images.
Modifications to the BrightHeart View Classifier device will be made in accordance with its Predetermined Change Control Plan (PCCP). The PCCP provides a description of the device's planned modifications, as well as procedures to implement, evaluate and deploy the modifications. These procedures ensure the continued safety and effectiveness of the device, mitigating risks associated with modifications to the BrightHeart View Classifier neural network to not adversely impact the device's performance, safety, or effectiveness associated with its indications for use, and an impact assessment of the planned modifications.
A summary of the planned modifications is provided in the table below. In line with the PCCP, all changes to the BrightHeart View Classifier will undergo development, evaluation and validation before release. Information on the deployment and post market surveillance of the algorithm are also provided for the proposed changes. Implemented modifications to the BrightHeart View Classifier will be communicated to users by email with a release note detailing all expected changes in the new release and user manual.
Summary of changes to BrightHeart View Classifier per the PCCP:
-
Modification: Modification of training and/or validation datasets to update model weights and detection thresholds
-
Rationale: Improvements in the view classification performance of the device.
-
Testing Methods: Re-training of the BrightHeart View Classifier with new data to optimize its performance followed by performance testing and a comparison of the original BrightHeart View Classifier to the modified BrightHeart View Classifier (using performance metrics) and verification and validation.
-
Impact Assessment: Improved performance metrics of modified BrightHeart View Classifier. Benefit-Risk Analysis: Benefits: Improved performance; generalization for diverse cases. Risks: Overfitting; unintended bias. Risk Mitigation: Testing data sequestration and testing on new data will ensure proper evaluation and mitigate risks of overfitting.
-
Modification: Modification of data input sources: ultrasound machine make (Canon, Fujifilm, SIUI)
-
Rationale: Improvement in the view classification performance with ultrasound machine makes not previously validated
-
Testing Methods: Re-training of the BrightHeart View Classifier with data from new ultrasound machine makes to optimize its performance followed by performance testing and a comparison of the original BrightHeart View Classifier to the modified BrightHeart View Classifier (using performance metrics) and verification and validation.
-
Impact Assessment: Improved performance metrics of modified BrightHeart View Classifier on new ultrasound make. Benefit-Risk Analysis: Benefits: Improved performance; generalization for diverse cases. Risks: Overfitting; unintended bias. Risk Mitigation: Testing data sequestration and testing on new data will ensure proper evaluation and mitigate risks of overfitting.
-
Modification: Addition of standard views (short-axis view at the level of the ventricles and short-axis view at the level of the atrioventricular valves)
-
Rationale: Training of the machine learning model to achieve sufficient view classification performance for additional standard views, which will assist users in the identification of these views during fetal heart ultrasound scanning.
-
Testing Methods: Re-training of the BrightHeart View Classifier with data from new standard views to optimize its performance followed by performance testing and a comparison of the original BrightHeart View Classifier to the modified BrightHeart View Classifier (using performance metrics) and verification and validation.
-
Impact Assessment: Improved performance metrics of modified BrightHeart View Classifier on additional standard views. Benefit-Risk Analysis: Benefits: Improved performance; generalization for diverse cases. Risks: Overfitting; unintended bias. Risk Mitigation: Testing data sequestration and testing on new data will ensure proper evaluation and mitigate risks of overfitting.
-
Modification: Modification of data input sources: gestational age
-
Rationale: Enables the device to achieve sufficient view classification performance to assist users in the identification of standard views for examinations corresponding to gestational ages not previously validated.
-
Testing Methods: Re-training of the BrightHeart View Classifier with data from new gestational ages to optimize its performance followed by performance testing and a comparison of the original BrightHeart View Classifier to the modified BrightHeart View Classifier (using performance metrics) and verification and validation.
-
Impact Assessment: Improved performance metrics of modified BrightHeart View Classifier on new gestational age. Benefit-Risk Analysis: Benefits: Improved performance; generalization for diverse cases. Risks: Overfitting; unintended bias. Risk Mitigation: Testing data sequestration and testing on new data will ensure proper evaluation and mitigate risks of overfitting.
§ 892.2050 Medical image management and processing system.
(a)
Identification. A medical image management and processing system is a device that provides one or more capabilities relating to the review and digital processing of medical images for the purposes of interpretation by a trained practitioner of disease detection, diagnosis, or patient management. The software components may provide advanced or complex image processing functions for image manipulation, enhancement, or quantification that are intended for use in the interpretation and analysis of medical images. Advanced image manipulation functions may include image segmentation, multimodality image registration, or 3D visualization. Complex quantitative functions may include semi-automated measurements or time-series measurements.(b)
Classification. Class II (special controls; voluntary standards—Digital Imaging and Communications in Medicine (DICOM) Std., Joint Photographic Experts Group (JPEG) Std., Society of Motion Picture and Television Engineers (SMPTE) Test Pattern).
FDA 510(k) Clearance Letter - BrightHeart View Classifier
Page 1
U.S. Food & Drug Administration
10903 New Hampshire Avenue
Silver Spring, MD 20993
www.fda.gov
Doc ID # 04017.07.05
BrightHeart
Christophe Gardella
CTO
7-11 boulevard Haussmann
Paris, 75009
France
Re: K243684
Trade/Device Name: BrightHeart View Classifier
Regulation Number: 21 CFR 892.2050
Regulation Name: Medical Image Management and Processing System
Regulatory Class: Class II
Product Code: QIH
Dated: March 25, 2025
Received: March 25, 2025
Dear Christophe Gardella:
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.
May 7, 2025
Page 2
K243684 - Christophe Gardella Page 2
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 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
Page 3
K243684 - Christophe Gardella Page 3
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.
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,
Jessica Lamb, PhD
Assistant Director,
Imaging Software Team
DHT8B: Division of Radiological Imaging
Devices and Electronic Products
OHT8: Office of Radiological Health
Office of Product Evaluation and Quality
Center for Devices and Radiological Health
Enclosure
Page 4
FORM FDA 3881 (6/20) Page 1 of 1 PSC Publishing Services (301) 443-6740 EF
DEPARTMENT OF HEALTH AND HUMAN SERVICES
Food and Drug Administration
Indications for Use
Form Approved: OMB No. 0910-0120
Expiration Date: 06/30/2023
See PRA Statement below.
510(k) Number (if known): K243684
Device Name: BrightHeart View Classifier
Indications for Use (Describe)
The BrightHeart View Classifier device is intended to analyze fetal 2D ultrasound images and video clips using machine learning techniques to automatically detect standard views during fetal heart scanning.
The BrightHeart View Classifier device is intended to be used as an adjunct to the acquisition and interpretation of fetal anatomic ultrasound examinations at the second or third trimester of pregnancy performed with transabdominal probes.
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 - K243684 Page 1 of 9
1. SUBMITTER
Applicant: BrightHeart
7-11 boulevard Haussmann
Paris 75009, France
Contact: Christophe Gardella
Chief Technical Officer
Tel. +0033686543950
Email. christophe@brightheart.fr
Submission Correspondent: Christophe Gardella
Date Prepared: May 5, 2025
2. DEVICE
Device Trade Name: BrightHeart View Classifier
Device Common Name: Fetal ultrasound view classifier
Classification Name: 21 CFR §892.2050, Medical image management and processing system
Product Code(s): QIH
Regulatory Class: Class II
3. PREDICATE DEVICE
Predicate Device: Sonix Health [K230209]
Reference Device: HeartAssist feature in the Samsung V8 Diagnostic Ultrasound System, V7 Diagnostic Ultrasound System [K223387]
4. DEVICE DESCRIPTION
BrightHeart View Classifier is a cloud-based software-only device which uses artificial intelligence (AI) to detect standard views during fetal heart scanning in fetal ultrasound images and video clips.
BrightHeart View Classifier is intended to be used by qualified, trained healthcare professional personnel in a professional prenatal ultrasound (US) imaging environment (this includes sonographers, MFMs, OB/GYN, and Fetal surgeons), to help fetal ultrasound examination acquisition and interpretation of 2D grayscale ultrasound by providing automatic classification of video clips and images into standard views, by automatically extracting example frames of standard views from video clips, and by automatically assessing whether the documentation of
Page 6
510(k) Summary - K243684 Page 2 of 9
each standard view in video clips and images satisfies an acquisition protocol defined by the center. Annotated DICOM files generated by the device cannot be modified by the user.
5. INTENDED USE/INDICATIONS FOR USE
The BrightHeart View Classifier device is intended to analyze fetal ultrasound images and video clips using machine learning techniques to automatically detect standard views during fetal heart scanning.
The BrightHeart View Classifier device is intended to be used as an adjunct to the acquisition and interpretation of fetal anatomic ultrasound examinations at the second or third trimester of pregnancy performed with transabdominal probes.
6. SUBSTANTIAL EQUIVALENCE
Technological Comparisons
The table below compares the key technological features of the subject device to the predicate device, Sonix Health.
Technological Comparison:
| Subject Device | Predicate Device | Reference Device | |
|---|---|---|---|
| BrightHeart View Classifier | Sonix Health | HeartAssist feature in the Samsung V8 Diagnostic Ultrasound System, V7 Diagnostic Ultrasound System | |
| 510(k) Number | TBD | K230209 | K223387 |
| Applicant | BrightHeart | Ontact Health | Samsung |
| Classification Regulation | 21 CFR §892.2050 | 21 CFR §892.2050 | 21 CFR §892.2150, 21 CFR §892.1560, 21 CFR §892.1570 |
| Product Code | QIH | QIH, LLZ | IYN, IYO, ITX |
| Device Type | SaMD | SaMD | SaMD |
| Software algorithm | Machine Learning Model | Machine Learning Model | Machine Learning Model |
Page 7
510(k) Summary - K243684 Page 3 of 9
| Subject Device | Predicate Device | Reference Device | |
|---|---|---|---|
| BrightHeart View Classifier | Sonix Health | HeartAssist feature in the Samsung V8 Diagnostic Ultrasound System, V7 Diagnostic Ultrasound System | |
| Imaging Modality | Fetal Ultrasound | Adult Echocardiography | The Samsung V8 and V7 are general purpose, mobile, software controlled, diagnostic ultrasound systems, including fetal ultrasound. |
| Model Inputs | Ultrasound images and video clips | Ultrasound images and video clips | Ultrasound images |
| Model method | Neural networks | Neural networks | Neural networks |
| Model trained to identify | Classification of ultrasound images into standard views of fetal heart. | Classification of ultrasound images into standard views of adult heart, determination cardiac measurements. | Classification of ultrasound images into standard views of fetal heart scanning, and detection of calipers used for measurements |
| Model Output | Identifies standard views of the heart and abdomen in images and video clips. | Identifies standard views of the heart in images and video clips, detection of cardiac measurements. | Identifies standard views of the heart and abdomen in images |
| PCCP | Included | Not included | Not included |
The BrightHeart View Classifier and Sonix Health devices differ in that the BrightHeart View Classifier device uses as input fetal ultrasounds, whereas the Sonix Health device uses as input adult echocardiograms. The PCCP in the subject device includes proposed modifications related to modification of training and/or validation datasets, modification of data input sources regarding ultrasound machine make, addition of standard view, and modification of data input sources regarding gestational age.
The subject BrightHeart View Classifier and the predicate Sonix Health devices are both intended to be used to analyze ultrasound images to determine standard views during heart scanning. Both the subject and the predicate are Software as a Medical device (SaMD) applications that rely on a trained neural network to identify the standard views. The Sonix Health device also includes a measurement functionality which is not included in the BrightHeart
Page 8
510(k) Summary - K243684 Page 4 of 9
device. Both devices are intended to be used as an adjunct to professional decision-making by trained healthcare providers.
Similarities of the device with the predicate are maintained following PCCP modifications, and PCCP modifications do not incur additional differences with the predicate device.
In summary, the subject and predicate devices share the same fundamental technological characteristics, namely the use of software to assist healthcare professionals who are interpreting ultrasound images of the heart to determine standard views. The differences in implementations described above do not raise different questions of safety and effectiveness, so the Sonix Health device can be used as a predicate device for the BrightHeart View Classifier device.
7. PERFORMANCE DATA
Software Verification and Validation Testing
Software verification and validation testing was conducted and documentation was provided as recommended by FDA's Guidance for Industry and FDA Staff, "Guidance for the Content of Premarket Submissions for Software Contained in Medical Devices." and in accordance with IEC 62304:2016, Medical device software - Software life cycle processes.
Cybersecurity documentation was provided as recommended by FDA's Guidance for Industry and FDA Staff, "Content of Premarket Submissions for Management of Cybersecurity in Medical Devices".
Bench Testing
The following bench testing was performed to demonstrate substantial equivalence:
The device performance for standard view classification was validated with a dataset of 2290 clinically acquired images and frames from video clips from 579 fetal ultrasound examinations, performed with transabdominal probes at 18 weeks of gestation or later, from 8 centers.
Demographic distribution:
- gender: female
- age: 18 years or older
- ethnicity/country: U.S.A. and France.
Information about how the reference standard was derived from the dataset:
- The reference standard was derived from the dataset through a truthing process in which a sonographer and an MFM specialist with experience in fetal echocardiography determined the presence or absence of standard views on fetal ultrasound images.
- The truthing process was conducted independently of the BrightHeart View Classifier device.
Description of how the independence of test data from training data was ensured:
- The ultrasound examinations used for training and validation are entirely distinct from the examinations used in performance testing.
Page 9
510(k) Summary - K243684 Page 5 of 9
The performance testing demonstrated that BrightHeart View Classifier identifies standard views with a mean standard view recognition sensitivity of 0.939 (95% CI, 0.917 ; 0.960) and a mean standard view recognition specificity of 0.984 (95% CI, 0.973 ; 0.996).
Stratified analysis by geographical region, by ultrasound machine make, by gestational age, by mother's BMI, and age, and by record type indicated that performance was consistent across subgroups, while analysis by mother's race showed that the specificity 95% CI lower bound was slightly lower for Asian and Black mothers, possibly due to large confidence intervals and small sample size.
BrightHeart View Classifier was validated only with General Electric, Philips, Samsung and Siemens ultrasound devices and is intended only to be used with these ultrasound vendors.
BrightHeart View Classifier was validated with pregnancies at 18 weeks of gestation or later recorded with transabdominal probes and is intended to be used only for such examinations.
8. PREDETERMINED CHANGE CONTROL PLAN
The BrightHeart View Classifier device is powered by a neural network performing standard view classification in fetal ultrasound images.
Modifications to the BrightHeart View Classifier device will be made in accordance with its Predetermined Change Control Plan (PCCP). The PCCP provides a description of the device's planned modifications, as well as procedures to implement, evaluate and deploy the modifications. These procedures ensure the continued safety and effectiveness of the device, mitigating risks associated with modifications to the BrightHeart View Classifier neural network to not adversely impact the device's performance, safety, or effectiveness associated with its indications for use, and an impact assessment of the planned modifications.
A summary of the planned modifications is provided in the table below. In line with the PCCP, all changes to the BrightHeart View Classifier will undergo development, evaluation and validation before release. Information on the deployment and post market surveillance of the algorithm are also provided for the proposed changes. Implemented modifications to the BrightHeart View Classifier will be communicated to users by email with a release note detailing all expected changes in the new release and user manual.
Summary of changes to BrightHeart View Classifier per the PCCP:
| Modification | Rationale | Testing Methods | Impact Assessment |
Page 10
510(k) Summary - K243684 Page 6 of 9
| Modification of training and/or validation datasets to update model weights and detection thresholds | Improvements in the view classification performance of the device. | Re-training of the BrightHeart View Classifier with new data to optimize its performance followed by performance testing and a comparison of the original BrightHeart View Classifier to the modified BrightHeart View Classifier (using performance metrics) and verification and validation. | Improved performance metrics of modified BrightHeart View Classifier |
| | | | Benefit-Risk Analysis: Benefits: Improved performance; generalization for diverse cases. Risks: Overfitting; unintended bias. Risk Mitigation: Testing data sequestration and testing on new data will ensure proper evaluation and mitigate risks of overfitting. |
Page 11
510(k) Summary - K243684 Page 7 of 9
| Modification of data input sources: ultrasound machine make (Canon, Fujifilm, SIUI) | Improvement in the view classification performance with ultrasound machine makes not previously validated | Re-training of the BrightHeart View Classifier with data from new ultrasound machine makes to optimize its performance followed by performance testing and a comparison of the original BrightHeart View Classifier to the modified BrightHeart View Classifier (using performance metrics) and verification and validation. | Improved performance metrics of modified BrightHeart View Classifier on new ultrasound make |
| | | | Benefit-Risk Analysis: Benefits: Improved performance; generalization for diverse cases. Risks: Overfitting; unintended bias. Risk Mitigation: Testing data sequestration and testing on new data will ensure proper evaluation and mitigate risks of overfitting. |
Page 12
510(k) Summary - K243684 Page 8 of 9
| Addition of standard views (short-axis view at the level of the ventricles and short-axis view at the level of the atrioventricular valves) | Training of the machine learning model to achieve sufficient view classification performance for additional standard views, which will assist users in the identification of these views during fetal heart ultrasound scanning. | Re-training of the BrightHeart View Classifier with data from new standard views to optimize its performance followed by performance testing and a comparison of the original BrightHeart View Classifier to the modified BrightHeart View Classifier (using performance metrics) and verification and validation. | Improved performance metrics of modified BrightHeart View Classifier on additional standard views |
| | | | Benefit-Risk Analysis: Benefits: Improved performance; generalization for diverse cases. Risks: Overfitting; unintended bias. Risk Mitigation: Testing data sequestration and testing on new data will ensure proper evaluation and mitigate risks of overfitting. |
Page 13
510(k) Summary - K243684 Page 9 of 9
| Modification of data input sources: gestational age | Enables the device to achieve sufficient view classification performance to assist users in the identification of standard views for examinations corresponding to gestational ages not previously validated. | Re-training of the BrightHeart View Classifier with data from new gestational ages to optimize its performance followed by performance testing and a comparison of the original BrightHeart View Classifier to the modified BrightHeart View Classifier (using performance metrics) and verification and validation. | Improved performance metrics of modified BrightHeart View Classifier on new gestational age |
| | | | Benefit-Risk Analysis: Benefits: Improved performance; generalization for diverse cases. Risks: Overfitting; unintended bias. Risk Mitigation: Testing data sequestration and testing on new data will ensure proper evaluation and mitigate risks of overfitting. |
9. CONCLUSION
The results of the testing described above demonstrate that the BrightHeart View Classifier is as safe and effective as the predicate device and supports a determination of substantial equivalence.