(25 days)
Not Found
Yes.
The device description explicitly states, "Fetal EchoScan is a machine learning-based computer-assisted diagnosis (CADx) software device" and "uses neural networks to detect suspicious cardiac radiographic findings". It also mentions "Software algorithm: Machine Learning Model" and "The AI system". These statements directly indicate the presence of an AI model.
No.
The device is a computer-assisted diagnosis (CADx) software that aids interpreting physicians in identifying suspicious radiographic findings, not a therapeutic device. It provides information for diagnosis and doesn't directly treat or cure a condition.
Yes
Fetal EchoScan is explicitly described as a "computer-assisted diagnosis (CADx) software device" and is intended to provide information useful in "rendering an accurate diagnosis regarding the potential presence of morphological abnormalities." While it serves as an adjunct and does not replace the physician, its purpose is to aid in the diagnostic process by detecting suspicious findings.
Yes
The device explicitly states in its description that it is a "cloud-based software-only device." Its function is to process ultrasound video clips using neural networks to identify suspicious findings, which is a software-based operation, without any indication of integrated hardware for its primary medical function.
No.
This device is an imaging analysis software, which is not considered an IVD unless it analyzes in vitro samples.
No
The provided input explicitly states "Control Plan Authorized (PCCP): Not Found," which means there is no language indicating the FDA has reviewed and approved or cleared a PCCP for this device.
Intended Use / Indications for Use
Fetal EchoScan is a machine learning-based computer-assisted diagnosis (CADx) software device indicated as an adjunct to fetal heart ultrasound examination in pregnant women aged 18 or older undergoing second-trimester anatomic ultrasound exams.
When utilized by an interpreting physician, Fetal EchoScan provides information regarding the presence of any of the following suspicious radiographic findings:
- Overriding artery
- Septal defect at the cardiac crux
- Abnormal relationship of the outflow tracts
- Enlarged cardiothoracic ratio
- Right ventricular to left ventricular size discrepancy
- Tricuspid valve to mitral valve annular size discrepancy
- Pulmonary valve to aortic valve annular size discrepancy
- Cardiac axis deviation
Fetal EchoScan is to be used with cardiac fetal ultrasound video clips containing interpretable 4-chamber, left ventricular outflow tract, right ventricular outflow tract standard views.
Fetal EchoScan is intended for use as a concurrent reading aid for interpreting physicians (OB-GYN, maternal fetal medicine specialists). It does not replace the role of the physician or of other diagnostic testing in the standard of care. When utilized by an interpreting physician, this device provides information that may be useful in rendering an accurate diagnosis regarding the potential presence of morphological abnormalities that might be suggestive of fetal congenital heart defects that may be useful in determining the need for additional exams.
Fetal EchoScan is not intended for use in multiple pregnancies, cases of heterotaxy, and postnatal ultrasound exams.
Product codes
POK
Device Description
Fetal EchoScan is a cloud-based software-only device which uses neural networks to detect suspicious cardiac radiographic findings for further review by trained and qualified physicians. Fetal EchoScan is intended to be used as an adjunct to the interpretation of the second-trimester fetal anatomic ultrasound exam performed between 18 and 24 weeks of gestation, for pregnant women aged 18 or more.
Mentions image processing
Not Found
Mentions AI, DNN, or ML
Fetal EchoScan is a machine learning-based computer-assisted diagnosis (CADx) software device
Fetal EchoScan is a cloud-based software-only device which uses neural networks
Software algorithm: Machine Learning Model
Input Imaging Modality
Fetal Ultrasound
Anatomical Site
Fetal heart
Indicated Patient Age Range
Pregnant women aged 18 or older
Intended User / Care Setting
Interpreting physicians (OB-GYN, maternal fetal medicine specialists)
Description of the training set, sample size, data source, and annotation protocol
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 standalone testing.
Description of the test set, sample size, data source, and annotation protocol
Standalone testing:
- Dataset of 877 clinically acquired fetal ultrasound exams during the 2nd trimester of pregnancy (18 to 24 weeks of gestational age), from 11 centers.
- Each exam consisted of all images and video clips recorded during the examination.
- Demographic distribution: gender: female, age: 18 years or older, ethnicity/country: U.S.A. and France.
- Reference standard was derived from the dataset through a truthing process in which three pediatric cardiologists assessed the presence or absence of each of the eight findings, and majority voting was used.
- The truthing process was conducted independently of the Fetal EchoScan device.
- All ultrasound examinations used for training and validation are entirely distinct from the examinations used in standalone testing.
Reader study:
- 200 exams (18 to 24 weeks of gestational age).
- Each exam consisted of all images and video clips recorded during the examination.
- Demographic distribution: gender: female, age: 18 years or older, ethnicity/country: U.S.A. and France.
- Reference standard was derived from the dataset through a truthing process in which three pediatric cardiologists assessed the presence or absence of each of the eight findings, and majority voting was used.
- The truthing process was conducted independently of the Fetal EchoScan device.
- All ultrasound examinations used for training and validation are entirely distinct from the examinations used in standalone testing.
Summary of Performance Studies (study type, sample size, AUC, MRMC, standalone performance, key results)
Software Verification and Validation Testing: 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 (Standalone Testing):
- Study Type: Standalone performance validation.
- Sample Size: 877 clinically acquired fetal ultrasound exams.
- The AI system had a conclusive output regarding the presence of any finding for 98.8% (95% CI, 97.8 ; 99.3) of exams.
- Key Results: Fetal EchoScan detects suspicious findings with high sensitivity and high specificity. Stratified analysis by gestational age, by mother's age, BMI and race, by ultrasound machine make and model and by image quality indicated that performance was consistent across subgroups.
Reader Study (MRMC study):
- Study Type: Fully-crossed, multiple-reader multiple-case (MRMC) study.
- Sample Size: 14 readers reviewed 200 exams.
- AUC:
- ROC AUC for "Any suspicious findings" aided: 0.974 (95% CI 0.957-0.990)
- ROC AUC for "Any suspicious findings" unaided: 0.825 (0.741-0.908)
- Increase in AUC: +14.9% (p=0.002)
- Key Results: Reviews by interpreting physicians were more accurate when aided by the Fetal EchoScan device compared to when unaided. Stratified analysis by gestational age, by mother's age, BMI and race, by ultrasound machine make and model, image quality, reader specialty, reader country of practice and for each suspicious finding indicated that performance was consistent across subgroups.
Key Metrics (Sensitivity, Specificity, PPV, NPV, etc.)
Standalone Testing:
Any suspicious findings:
- Sensitivity (Worst-Case): 0.977 (0.954 ; 0.989)
- Specificity (Best-Case): 0.977 (0.961 ; 0.987)
- Sensitivity (Best-Case): 0.987 (0.967 ; 0.995)
- Specificity (Worst-Case): 0.963 (0.944 ; 0.976)
Reader Study:
Any suspicious findings:
- Mean sensitivity aided: 0.935 (0.892-0.978)
- Mean sensitivity unaided: 0.782 (0.686-0.878)
- Mean specificity aided: 0.970 (0.949-0.991)
- Mean specificity unaided: 0.759 (0.630-0.887)
Specific sensitivity and specificity values for each suspicious radiographic finding are available in the table "Table 1. Sensitivity and Specificity (with 95% CI) of Fetal EchoScan for the detection of any suspicious radiographic finding and of each suspicious radiographic finding."
Specific AUC values for each suspicious radiographic finding for aided and unaided conditions are available in the table "Table 2. Empirical ROC AUC Analysis by Suspicious Radiographic Finding".
Predicate Device(s)
Reference Device(s)
Not Found
Predetermined Change Control Plan (PCCP) - All Relevant Information
Not Found
§ 892.2060 Radiological computer-assisted diagnostic software for lesions suspicious of cancer.
(a)
Identification. A radiological computer-assisted diagnostic software for lesions suspicious of cancer is an image processing prescription device intended to aid in the characterization of lesions as suspicious for cancer identified on acquired medical images such as magnetic resonance, mammography, radiography, or computed tomography. The device characterizes lesions based on features or information extracted from the images and provides information about the lesion(s) to the user. Diagnostic and patient management decisions are made by the clinical user.(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 algorithms including, but not limited to, a detailed description of the algorithm inputs and outputs, each major component or block, and algorithm limitations.
(ii) A detailed description of pre-specified performance testing protocols and dataset(s) used to assess whether the device will improve reader performance as intended.
(iii) Results from performance testing protocols that demonstrate that the device improves reader performance in the intended use population when used in accordance with the instructions for use. The performance assessment must be based on appropriate diagnostic accuracy measures (
e.g., receiver operator characteristic plot, sensitivity, specificity, predictive value, and diagnostic likelihood ratio). The test dataset must contain sufficient numbers of cases from important cohorts (e.g., subsets defined by clinically relevant confounders, effect modifiers, concomitant diseases, 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) Standalone performance testing protocols and results of the device.
(v) Appropriate software documentation (
e.g., device hazard analysis; software requirements specification document; software design specification document; traceability analysis; and description of verification and validation activities including system level test protocol, pass/fail criteria, results, and cybersecurity).(2) Labeling must include:
(i) A detailed description of the patient population for which the device is indicated for use.
(ii) A detailed description of the intended reading protocol.
(iii) A detailed description of the intended user and recommended user training.
(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, including 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) Detailed instructions for use.
(viii) 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 (
e.g., lesion and organ characteristics, disease stages, and imaging equipment).
FDA 510(k) Clearance Letter - Fetal EchoScan v1.1
Page 1
U.S. Food & Drug Administration
10903 New Hampshire Avenue
Silver Spring, MD 20993
www.fda.gov
Doc ID # 04017.04.27
BrightHeart
Christophe Gardella
Cto
7-11 boulevard Haussmann
Paris, 75009
France
Re: K251071
Trade/Device Name: Fetal EchoScan (v1.1)
Regulation Number: 21 CFR 892.2060
Regulation Name: Radiological computer-assisted diagnostic software for lesions suspicious of cancer
Regulatory Class: Class II
Product Code: POK
Dated: April 7, 2025
Received: April 7, 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 (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
May 2, 2025
Page 2
BrightHeart
Christophe Gardella
Cto
7-11 boulevard Haussmann
Paris, 75009
France
May 2, 2025
Re: K251071
Trade/Device Name: Fetal EchoScan (v1.1)
Regulation Number: 21 CFR 892.2060
Regulation Name: Radiological computer-assisted diagnostic software for lesions suspicious of cancer
Regulatory Class: Class II
Product Code: POK
Dated: April 7, 2025
Received: April 7, 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 (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
K251071 - Christophe Gardella Page 2
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 803) for devices or postmarketing safety reporting (21 CFR 4, Subpart B) for combination products (see https://www.fda.gov/combination-products/guidance-regulatory-information/postmarketing-safety-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 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-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
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 3
DEPARTMENT OF HEALTH AND HUMAN SERVICES
Food and Drug Administration
Form Approved: OMB No. 0910-0120
Expiration Date: 07/31/2026
See PRA Statement below.
Indications for Use
Submission Number (if known)
K251071
Device Name
Fetal EchoScan (v1.1)
Indications for Use (Describe)
Fetal EchoScan is a machine learning-based computer-assisted diagnosis (CADx) software device indicated as an adjunct to fetal heart ultrasound examination in pregnant women aged 18 or older undergoing second-trimester anatomic ultrasound exams.
When utilized by an interpreting physician, Fetal EchoScan provides information regarding the presence of any of the following suspicious radiographic findings:
- Overriding artery
- Septal defect at the cardiac crux
- Abnormal relationship of the outflow tracts
- Enlarged cardiothoracic ratio
- Right ventricular to left ventricular size discrepancy
- Tricuspid valve to mitral valve annular size discrepancy
- Pulmonary valve to aortic valve annular size discrepancy
- Cardiac axis deviation
Fetal EchoScan is to be used with cardiac fetal ultrasound video clips containing interpretable 4-chamber, left ventricular outflow tract, right ventricular outflow tract standard views.
Fetal EchoScan is intended for use as a concurrent reading aid for interpreting physicians (OB-GYN, maternal fetal medicine specialists). It does not replace the role of the physician or of other diagnostic testing in the standard of care. When utilized by an interpreting physician, this device provides information that may be useful in rendering an accurate diagnosis regarding the potential presence of morphological abnormalities that might be suggestive of fetal congenital heart defects that may be useful in determining the need for additional exams.
Fetal EchoScan is not intended for use in multiple pregnancies, cases of heterotaxy, and postnatal ultrasound exams.
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.
Page 4
510(k) Summary Page 1 of 8
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: | April 7, 2025 |
2. DEVICE
| Device Trade Name: | Fetal EchoScan v1.1 |
|---|---|
| Device Common Name: | Medical image analyzer |
| Classification Name | Radiological computer-assisted diagnostic software for lesions suspicious for cancer 21 CFR 892.2060 |
| Regulatory Class: | Class II |
| Product Code: | POK |
3. PREDICATE DEVICE
Predicate Device: Fetal EchoScan [K242342], termed "Fetal EchoScan v1.0" in the following.
The predicate device has not been subject to a design-related recall.
4. DEVICE DESCRIPTION
Fetal EchoScan is a cloud-based software-only device which uses neural networks to detect suspicious cardiac radiographic findings for further review by trained and qualified physicians. Fetal EchoScan is intended to be used as an adjunct to the interpretation of the second-trimester fetal anatomic ultrasound exam performed between 18 and 24 weeks of gestation, for pregnant women aged 18 or more.
Page 5
510(k) Summary Page 2 of 8
5. INTENDED USE/INDICATIONS FOR USE
Fetal EchoScan is a machine learning-based computer-assisted diagnosis (CADx) software device indicated as an adjunct to fetal heart ultrasound examination in pregnant women aged 18 or older undergoing second-trimester anatomic ultrasound exams.
When utilized by an interpreting physician, Fetal EchoScan provides information regarding the presence of any of the following suspicious radiographic findings:
- overriding artery
- septal defect at the cardiac crux
- abnormal relationship of the outflow tracts
- enlarged cardiothoracic ratio
- right ventricular to left ventricular size discrepancy
- tricuspid valve to mitral valve annular size discrepancy
- pulmonary valve to aortic valve annular size discrepancy
- cardiac axis deviation
Fetal EchoScan is to be used with cardiac fetal ultrasound video clips containing interpretable 4-chamber, left ventricular outflow tract, right ventricular outflow tract standard views.
Fetal EchoScan is intended for use as a concurrent reading aid for interpreting physicians (OB-GYN, MFM). It does not replace the role of the physician or of other diagnostic testing in the standard of care. When utilized by an interpreting physician, this device provides information that may be useful in rendering an accurate diagnosis regarding the potential presence of morphological abnormalities that might be suggestive of fetal congenital heart defects that may be useful in determining the need for additional exams.
Fetal EchoScan is not intended for use in multiple pregnancies, cases of heterotaxy and postnatal ultrasound exams.
6. SUBSTANTIAL EQUIVALENCE
Technological Comparisons
The table below compares the key technological features of the subject devices to the predicate device.
Table 1. Device Comparison Table
| | Subject Device
Fetal EchoScan v1.1 | Predicate Device
Fetal EchoScan v1.0 |
|---|---|---|
| 510(k) Number | TBD | K242342 |
| Applicant | BrightHeart | BrightHeart |
| Classification Regulation | 892.2060 | 892.2060 |
Page 6
510(k) Summary Page 3 of 8
| | Subject Device
Fetal EchoScan v1.1 | Predicate Device
Fetal EchoScan v1.0 |
|---|---|---|
| Product Code | POK | POK |
| Device Type | SaMD | SaMD |
| Software algorithm | Machine Learning Model | Machine Learning Model |
| Imaging Modality | Fetal Ultrasound | Fetal Ultrasound |
| Model Inputs | Fetal ultrasound study containing the following views: 4 chamber, left ventricular outflow tract, right ventricular outflow tract | Fetal ultrasound study containing the following views: 4 chamber, left ventricular outflow tract, right ventricular outflow tract |
| Model method | Suspicious radiographic findings categorized into 2 groups:
• "classification" features are based on the identification of morphological features within the video clip.
• "measurement" features are based on the detection and segmentation of key anatomic points | Suspicious radiographic findings categorized into 2 groups:
• "classification" features are based on the identification of morphological features within the video clip.
• "measurement" features are based on the detection and segmentation of key anatomic points |
| Model trained to identify | Identifiable suspicious radiographic findings of the fetal heart
• overriding artery
• septal defect at the cardiac crux
• abnormal relationship of the outflow tracts
• enlarged cardiothoracic ratio
• right ventricular to left ventricular size discrepancy
• tricuspid valve to mitral valve annular size discrepancy
• pulmonary valve to aortic valve annular size discrepancy
• cardiac axis deviation | Identifiable suspicious radiographic findings of the fetal heart
• overriding artery
• septal defect at the cardiac crux
• abnormal relationship of the outflow tracts
• enlarged cardiothoracic ratio
• right ventricular to left ventricular size discrepancy
• tricuspid valve to mitral valve annular size discrepancy
• pulmonary valve to aortic valve annular size discrepancy
• cardiac axis deviation |
| Model Output | For each frame the software evaluates whether the findings are: present, absent, or inconclusive. A "record summary table" displays a summary of results for each video clip. An "exam summary table" displays a summary of the results for the overall study. | For each frame the software evaluates whether the findings are: present, absent, or inconclusive. A "record summary table" displays a summary of results for each video clip. An "exam summary table" displays a summary of the results for the overall study. |
Page 7
510(k) Summary Page 4 of 8
| | Subject Device
Fetal EchoScan v1.1 | Predicate Device
Fetal EchoScan v1.0 |
|---|---|---|
| Output Display | • Annotated DICOMs within the user PACS viewer
• Device web interface | • Annotated DICOMs within the user PACS viewer |
Discussion of Similarities and Differences
The Fetal EchoScan v1.1 subject device and Fetal EchoScan v1.0 predicate device differ in that the outputs of the predicate device are annotated DICOM files displayed in a DICOM viewer, while the outputs of the subject device are annotated DICOM files displayed in a DICOM viewer and may optionally be displayed on a web interface. The Fetal EchoScan v1.1 web interface uses a similar output presentation compared to the device annotated DICOMs.
The subject and predicate devices share the same fundamental technological characteristics, namely the use of software to assist physicians who are interpreting ultrasound images in making a diagnosis of the fetal heart and share the exact same algorithm to identify suspicious radiographic findings in the fetal heart.
In summary, the differences in implementations described above do not raise different questions of safety and effectiveness, so the Fetal EchoScan v1.0 device can be used as a predicate device for the Fetal EchoScan v1.1 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 algorithm for the detection of suspicious findings is exactly the same between the subject and predicate devices, therefore bench testing for the subject device remains valid for the predicate device. We remind here the corresponding Bench testing results:
Standalone testing
The device performance for identification of suspicious radiographic findings was validated with a dataset of 877 clinically acquired fetal ultrasound exams during the 2nd trimester of pregnancy (18 to 24 weeks of gestational age), from 11 centers. Each exam consisted of all images and
Page 8
510(k) Summary Page 5 of 8
video clips recorded during the examination.
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 three pediatric cardiologists assessed the presence or absence of each of the eight findings, and majority voting was used.
- The truthing process was conducted independently of the Fetal EchoScan 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 standalone testing.
The subject device was evaluated based on 2 different scenarios:
- One where all inconclusive device outputs are counted as negative. This corresponds to a "worst-case scenario" for sensitivity (all Inconclusive exams which are Positive for the ground truth are counted as False Negative), and a "best-case scenario" for specificity (all Inconclusive exams which are Negative for the ground truth are counted as True Negative).
- One where all inconclusive device outputs are counted as positive. This corresponds to a "worst-case scenario" for specificity (all Inconclusive exams which are Negative for the ground truth are counted as False Positive), and a "best-case scenario" for sensitivity (all Inconclusive exams which are Positive for the ground truth are counted as True Positive).
The AI system had a conclusive output regarding the presence of any finding for 98.8% (95% CI, 97.8 ; 99.3) of exams. The standalone testing demonstrated that Fetal EchoScan detects suspicious findings with high sensitivity and high specificity, as shown in Table 1.
Table 1. Sensitivity and Specificity (with 95% CI) of Fetal EchoScan for the detection of any suspicious radiographic finding and of each suspicious radiographic finding.
Note: Specificity for each suspicious radiographic finding is computed on exams negative to all findings according to the ground truth (i.e., excluding exams negative to the analyzed finding but possibly positive to other findings).
Page 9
510(k) Summary Page 6 of 8
| Inconclusive Exams Counted as Negative | Inconclusive Exams Counted as Positive | |||
|---|---|---|---|---|
| Sensitivity (Worst-Case) | Specificity (Best-Case) | Sensitivity (Best-Case) | Specificity (Worst-Case) | |
| Any suspicious findings | 0.977 (0.954 ; 0.989) | 0.977 (0.961 ; 0.987) | 0.987 (0.967 ; 0.995) | 0.963 (0.944 ; 0.976) |
| Overriding artery | 0.894 (0.820 ; 0.940) | 0.989 (0.977 ; 0.995) | 0.942 (0.880 ; 0.973) | 0.979 (0.963 ; 0.988) |
| Cardiac crux septal defect | 0.905 (0.823 ; 0.951) | 0.995 (0.985 ; 0.998) | 0.917 (0.838 ; 0.959) | 0.989 (0.977 ; 0.995) |
| Abn. OT relationship | 0.869 (0.781 ; 0.925) | 0.991 (0.979 ; 0.996) | 0.952 (0.884 ; 0.981) | 0.989 (0.977 ; 0.995) |
| Enlarged CTR | 0.955 (0.876 ; 0.985) | 1.000 (0.993 ; 1.000) | 0.955 (0.876 ; 0.985) | 1.000 (0.993 ; 1.000) |
| Cardiac axis deviation | 0.945 (0.851 ; 0.981) | 1.000 (0.993 ; 1.000) | 0.945 (0.851 ; 0.981) | 1.000 (0.993 ; 1.000) |
| PV/AV size discrepancy | 0.954 (0.914 ; 0.975) | 0.989 (0.977 ; 0.995) | 0.954 (0.914 ; 0.975) | 0.989 (0.977 ; 0.995) |
| RV/LV size discrepancy | 0.950 (0.900 ; 0.975) | 1.000 (0.993 ; 1.000) | 0.950 (0.900 ; 0.975) | 1.000 (0.993 ; 1.000) |
| TV/MV size discrepancy | 0.943 (0.896 ; 0.970) | 1.000 (0.993 ; 1.000) | 0.943 (0.896 ; 0.970) | 1.000 (0.993 ; 1.000) |
Stratified analysis by gestational age, by mother's age, BMI and race, by ultrasound machine make and model and by image quality indicated that performance was consistent across subgroups.
Reader study
Additionally, clinical performance of Fetal EchoScan was evaluated in a fully-crossed, multiple-reader multiple-case (MRMC) study, in which 14 readers reviewed 200 exams (18 to 24 weeks of gestational age). Readings were done in a randomized order, aided by Fetal EchoScan and unaided, with a 30 days washout period between both readings. Each exam consisted of all images and video clips recorded during the examination.
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:
Page 10
510(k) Summary Page 7 of 8
- The reference standard was derived from the dataset through a truthing process in which three pediatric cardiologists assessed the presence or absence of each of the eight findings, and majority voting was used.
- The truthing process was conducted independently of the Fetal EchoScan 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 standalone testing.
Table 2 and Figure 1 present reader performance when unaided and when aided by the device for identification of any suspicious radiographic finding and for each suspicious radiographic finding. The study results indicate that reviews by interpreting physicians were more accurate when aided by the Fetal EchoScan device compared to when unaided:
- The ROC AUC for detection of any suspicious radiographic finding was significantly higher in the aided compared to the unaided reading condition (see Figure 1): 0.974 (95% CI 0.957-0.990) vs 0.825 (0.741-0.908), p=0.002 (using the Dorfman-Berbaum-Metz and Obuchowski-Rockette method): +14.9% increase in AUC.
- The mean sensitivity for identification of any claimed suspicious finding was 0.935 (0.892-0.978) in the aided reading condition vs 0.782 (0.686-0.878) in the unaided reading condition: +15.3% increase in sensitivity.
- The mean specificity for identification of any claimed suspicious finding was 0.970 (0.949-0.991) in the aided reading condition vs 0.759 (0.630-0.887) in the unaided reading condition: +21.1% increase in specificity.
Table 2. Empirical ROC AUC Analysis by Suspicious Radiographic Finding
Note: Per-finding AUC is based on specificity computed excluding exams negative to the analyzed finding but possibly positive to other findings.
| Aided | Unaided | Aided minus Unaided | ||
|---|---|---|---|---|
| Model Estimate AUC (95% CI) | Model Estimate AUC (95% CI) | Model Estimate Difference (95% CI) | DBM-OR p-value | |
| Any suspicious findings | 0.974 (0.957 ; 0.990) | 0.825 (0.741 ; 0.908) | 0.149 (0.066 ; 0.232) | 0.002 |
| Overriding artery | 0.953 (0.916 ; 0.990) | 0.803 (0.719 ; 0.888) | 0.150 (0.063 ; 0.237) | 0.002 |
| Cardiac crux septal defect | 0.971 (0.943 ; 0.999) | 0.857 (0.782 ; 0.933) | 0.114 (0.042 ; 0.186) | 0.004 |
| Abn. OT relationship | 0.972 (0.953 ; 0.992) | 0.832 (0.738 ; 0.927) | 0.140 (0.048 ; 0.232) | 0.005 |
| Enlarged CTR | 0.960 (0.930 ; 0.989) | 0.746 (0.666 ; 0.826) | 0.214 (0.131 ; 0.297) |