(138 days)
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. 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 fetal heterotaxy and postnatal ultrasound exams.
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.
Here's a breakdown of the acceptance criteria and study details for the Fetal EchoScan (v1.2) device, based on the provided FDA 510(k) clearance letter:
1. Table of Acceptance Criteria and Reported Device Performance (Standalone Study)
The document primarily provides performance data from a standalone study, which implies these are the acceptance criteria met by the device.
| Acceptance Criteria (Performance Measure) | Reported Device Performance (95% CI) |
|---|---|
| Any suspicious findings detection: | |
| Sensitivity (Worst-Case) | 0.984 (0.963 ; 0.993) |
| Specificity (Best-Case) | 0.970 (0.952 ; 0.981) |
| Sensitivity (Best-Case) | 0.990 (0.972 ; 0.997) |
| Specificity (Worst-Case) | 0.958 (0.938 ; 0.971) |
| Conclusive output rate: | 99.0% (98.1 ; 99.5) |
| Individual Suspicious Findings Detection (Worst-Case Sensitivity / Best-Case Specificity): | |
| Overriding artery - Sensitivity | 0.933 (0.868 ; 0.967) |
| Overriding artery - Specificity | 0.988 (0.975 ; 0.994) |
| Cardiac crux septal defect - Sensitivity | 0.917 (0.838 ; 0.959) |
| Cardiac crux septal defect - Specificity | 0.995 (0.985 ; 0.998) |
| Abnormal OT relationship - Sensitivity | 0.869 (0.781 ; 0.925) |
| Abnormal OT relationship - Specificity | 0.988 (0.975 ; 0.994) |
| Enlarged CTR - Sensitivity | 0.955 (0.876 ; 0.985) |
| Enlarged CTR - Specificity | 0.996 (0.987 ; 0.999) |
| Cardiac axis deviation - Sensitivity | 0.945 (0.851 ; 0.981) |
| Cardiac axis deviation - Specificity | 1.000 (0.993 ; 1.000) |
| PV/AV size discrepancy - Sensitivity | 0.959 (0.921 ; 0.979) |
| PV/AV size discrepancy - Specificity | 0.986 (0.972 ; 0.993) |
| RV/LV size discrepancy - Sensitivity | 0.950 (0.900 ; 0.975) |
| RV/LV size discrepancy - Specificity | 1.000 (0.993 ; 1.000) |
| TV/MV size discrepancy - Sensitivity | 0.950 (0.904 ; 0.974) |
| TV/MV size discrepancy - Specificity | 1.000 (0.993 ; 1.000) |
The document does not explicitly state the pre-defined target values for these metrics, but the presented data demonstrates the device's performance against the ground truth.
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size (Standalone Study Test Set): 877 clinically acquired fetal ultrasound exams.
- Data Provenance: The data was acquired from 11 centers in the U.S.A. and France. The data is retrospective, as it refers to "clinically acquired fetal ultrasound exams."
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of those Experts
- Number of Experts: Three (3)
- Qualifications of Experts: Pediatric cardiologists.
4. Adjudication Method for the Test Set
- Adjudication Method: Majority voting. Three pediatric cardiologists assessed the presence or absence of each of the eight findings, and majority voting was used to establish the reference standard.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
- Was an MRMC study done? Yes, a fully-crossed MRMC study was conducted.
- Effect Size of Human Readers' Improvement with AI vs. without AI assistance:
- ROC AUC for detection of any suspicious radiographic finding:
- AI-aided: 0.974 (95% CI 0.957-0.990)
- Unaided: 0.825 (95% CI 0.741-0.908)
- Increase in AUC: +14.9% (0.149, statistically significant with p=0.002)
- Mean Sensitivity for any claimed suspicious finding:
- AI-aided: 0.935 (0.892-0.978)
- Unaided: 0.782 (0.686-0.878)
- Increase in Sensitivity: +15.3%
- Mean Specificity for any claimed suspicious finding:
- AI-aided: 0.970 (0.949-0.991)
- Unaided: 0.759 (0.630-0.887)
- Increase in Specificity: +21.1%
- ROC AUC for detection of any suspicious radiographic finding:
6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study
- Was a standalone study done? Yes, "Standalone testing" was explicitly performed and described. The results are presented in the "Table 1. Sensitivity and Specificity (with 95% CI) of Fetal EchoScan..." section.
7. Type of Ground Truth Used
- Type of Ground Truth: Expert consensus (majority voting by three pediatric cardiologists).
8. Sample Size for the Training Set
- The document states, "The ultrasound examinations used for training and validation are entirely distinct from the examinations used in standalone testing," but it does not explicitly provide the sample size for the training set.
9. How the Ground Truth for the Training Set Was Established
- The document states, "The ultrasound examinations used for training and validation are entirely distinct from the examinations used in standalone testing."
- Similar to the test set, it is highly probable that the ground truth for the training set was established through a robust expert review process, likely involving pediatric cardiologists. However, the specific details of the training set's ground truth establishment are not provided in this document. It only confirms that the truthing process for the test set was "conducted independently of the Fetal EchoScan device."
FDA 510(k) Clearance Letter - Fetal EchoScan (v1.2)
Page 1
U.S. Food & Drug Administration
10903 New Hampshire Avenue
Silver Spring, MD 20993
www.fda.gov
Doc ID # 04017.08.02
BrightHeart
Christophe Gardella
CTO
7-11 Boulevard Haussmann
Paris, 75009
France
Re: K252294
Trade/Device Name: Fetal EchoScan (v1.2)
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: November 13, 2025
Received: November 13, 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.
December 8, 2025
Page 2
K252294 - Christophe Gardella
Page 2
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.
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
Page 3
K252294 - Christophe Gardella
Page 3
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, Ph.D.
Assistant Director
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
DEPARTMENT OF HEALTH AND HUMAN SERVICES
Food and Drug Administration
Indications for Use
Form Approved: OMB No. 0910-0120
Expiration Date: 07/31/2026
See PRA Statement below.
Submission Number (if known): K252294
Device Name: Fetal EchoScan (v1.2)
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. 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 fetal 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 5
510(k) Summary - K252294
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: December 8, 2025
2. DEVICE
Device Trade Name: Fetal EchoScan (v1.2)
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 (v1.1) [K251071].
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.
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.
Page 6
510(k) Summary - K252294
Page 2 of 8
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. 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 | Predicate Device | |
|---|---|---|
| Fetal EchoScan v1.2 | Fetal EchoScan v1.1 | |
| 510(k) Number | K252294 | K242342 |
| Applicant | BrightHeart | BrightHeart |
| Classification Regulation | 892.2060 | 892.2060 |
| Product Code | POK | POK |
| Device Type | SaMD | SaMD |
| Software algorithm | Machine Learning Model | Machine Learning Model |
| Imaging Modality | Fetal Ultrasound | Fetal Ultrasound |
Page 7
510(k) Summary - K252294
Page 3 of 8
| Subject Device | Predicate Device | |
|---|---|---|
| Fetal EchoScan v1.2 | Fetal EchoScan v1.1 | |
| Model Inputs | Fetal ultrasound studies containing the following views in recordings: 4 chamber, left ventricular outflow tract, right ventricular outflow tract | Fetal ultrasound recordings 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 | Video clips featuring the fetal heart.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.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. |
| Output Display | • Annotated DICOMs within the user PACS viewer• third-party user interface | • Annotated DICOMs within the user PACS viewer• Device web interface |
Page 8
510(k) Summary - K252294
Page 4 of 8
Discussion of Similarities and Differences
The Fetal EchoScan v1.2 subject device and Fetal EchoScan v1.1 predicate device differ in that the outputs of the predicate device are annotated DICOM files displayed in a DICOM viewer and may optionally be displayed on the device web interface, while the outputs of the subject device are annotated DICOM files displayed in a DICOM viewer and may optionally be displayed on a validated 3rd party user interface. The Fetal EchoScan outputs displayed on a user interface use 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 v1.1 device can be used as a predicate device for the Fetal EchoScan v1.2 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 and testing was conducted 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
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 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 9
510(k) Summary - K252294
Page 5 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.
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 99.0% (95% CI, 98.1 ; 99.5) 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).
| 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 | 0.984 (0.963 ; 0.993) | 0.970 (0.952 ; 0.981) | 0.990 (0.972 ; 0.997) | 0.958 (0.938 ; 0.971) |
| Overriding artery | 0.933 (0.868 ; 0.967) | 0.988 (0.975 ; 0.994) | 0.942 (0.880 ; 0.973) | 0.979 (0.963 ; 0.988) |
| Cardiac crux septal defect | 0.917 (0.838 ; 0.959) | 0.995 (0.985 ; 0.998) | 0.917 (0.838 ; 0.959) | 0.995 (0.985 ; 0.998) |
| Abn. OT relationship | 0.869 (0.781 ; 0.925) | 0.988 (0.975 ; 0.994) | 0.952 (0.884 ; 0.981) | 0.982 (0.968 ; 0.990) |
| Enlarged CTR | 0.955 (0.876 ; 0.985) | 0.996 (0.987 ; 0.999) | 0.955 (0.876 ; 0.985) | 0.996 (0.987 ; 0.999) |
| Cardiac axis deviation | 0.945 (0.851 ; 0.981) | 1.000 (0.993 ; 1.000) | 0.964 (0.877 ; 0.990) | 1.000 (0.993 ; 1.000) |
| PV/AV size discrepancy | 0.959 (0.921 ; 0.979) | 0.986 (0.972 ; 0.993) | 0.959 (0.921 ; 0.979) | 0.986 (0.972 ; 0.993) |
| 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) |
Page 10
510(k) Summary - K252294
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) | |
| TV/MV size discrepancy | 0.950 (0.904 ; 0.974) | 1.000 (0.993 ; 1.000) | 0.950 (0.904 ; 0.974) | 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
The predicate and subject devices share similar device output displays and similar algorithms, resulting in minor variations of device performance, as presented above. Therefore, bench testing for the predicate device remains valid for the subject device. We remind here the corresponding Reader study results:
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:
- 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%
Page 11
510(k) Summary - K252294
Page 7 of 8
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) | <0.001 |
| Cardiac axis deviation | 0.967 (0.932 ; 1.000) | 0.786 (0.704 ; 0.867) | 0.181 (0.106 ; 0.256) | <0.001 |
| PV/AV size discrepancy | 0.979 (0.962 ; 0.997) | 0.839 (0.756 ; 0.921) | 0.140 (0.060 ; 0.221) | 0.002 |
| RV/LV size discrepancy | 0.991 (0.983 ; 0.999) | 0.868 (0.801 ; 0.936) | 0.123 (0.055 ; 0.190) | 0.001 |
| TV/MV size discrepancy | 0.964 (0.938 ; 0.990) | 0.850 (0.779 ; 0.921) | 0.114 (0.048 ; 0.179) | 0.002 |
Page 12
510(k) Summary - K252294
Page 8 of 8
Figure 1. ROC AUC analysis for detection of any suspicious radiographic finding by OB-GYNs and MFMs in aided and unaided conditions.
[THIS IS FIGURE: A ROC curve graph showing sensitivity (y-axis, 0-1) vs 1-Specificity (x-axis, 0-1). Two curves are shown: AI-aided (AUC: 97.4%) and Unaided (AUC: 82.5%). The AI-aided curve shows superior performance with higher sensitivity and specificity.]
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.
Fetal EchoScan was validated only with Fujifilm, GE, Philips, Samsung and Toshiba ultrasound devices and is intended only to be used with these ultrasound vendors.
8. CONCLUSION
The results of the testing described above demonstrate that the Fetal EchoScan v1.2 is as safe and effective as the predicate device and supports a determination of substantial equivalence.
N/A