(149 days)
Yes
The document explicitly mentions "AI software features" and provides detailed "AI Testing Summary" sections for several features, including descriptions of training and test data, sample sizes, and performance metrics.
No
Explanation: The device is an ultrasound system intended for diagnostic imaging, not for treating any medical condition.
Yes
Explanation: The "Intended Use / Indications for Use" section explicitly states that the device is an "ultrasound system intended for use by qualified and trained healthcare professionals," and lists numerous specific clinical applications such as "Fetal/OB; Abdominal; Pediatric; Small Organ; Cardiac; Musculo-skeletal; Vascular; Transvaginal; Transrectal." These applications are all performed for diagnostic purposes.
No
The device description explicitly states that the systems consist of a "mobile console with keyboard control panel; color LCD/TFT touch panel, color video display and optional image storage and printing devices." It also mentions the use of "linear, curved linear, matrix phased array transducers." These are all hardware components, indicating it is not a software-only device.
Based on the provided information, this device is not an IVD (In Vitro Diagnostic).
Here's why:
- Intended Use: The intended use clearly states that the device is a "general purpose ultrasound system intended for use by qualified and trained healthcare professionals." It lists various clinical applications related to imaging different parts of the body. IVD devices are specifically intended for use in vitro (outside the body) to examine specimens derived from the human body (like blood, urine, tissue) to provide information for diagnosis, monitoring, or screening. This ultrasound system operates in vivo (inside the body) by emitting and receiving sound waves.
- Device Description: The description details a mobile console with imaging capabilities and transducers, consistent with an ultrasound system used for imaging the body.
- Input Imaging Modality: The input modality is Ultrasound, which is an imaging technique, not an in vitro diagnostic method.
- Anatomical Site: The listed anatomical sites are all parts of the human body that are imaged directly.
- AI Features: While the device incorporates AI features, these features are used to assist in image analysis and workflow within the ultrasound imaging process, not for analyzing in vitro specimens.
- Performance Studies and Metrics: The performance studies and metrics described (Success Rate, Accuracy, Dice Coefficient, Acceptance criteria) are related to the performance of the AI algorithms in identifying and analyzing structures within the ultrasound images, not the performance of a test on a biological sample.
In summary, the device is an ultrasound system used for medical imaging, which is a different category of medical device than an In Vitro Diagnostic.
No
The letter does not explicitly state that the FDA has reviewed and approved or cleared a Predetermined Change Control Plan (PCCP) for this specific device.
Intended Use / Indications for Use
The device is a general purpose ultrasound system intended for use by qualified and trained healthcare professionals. Specific clinical applications remain the same as previously cleared: Fetall OB; Abdominal (including GYN, pelvic and infertility monitoring/follicle development); Pediatric; Small Organ (breast, testes, thyroid etc.); Neonatal and Adult Cephalic; Cardiac (adult and pediatric); Musculo-skeletal Conventional and Superficial; Vascular; Transvaginal (including GYN); Transrectal
Modes of operation include: B, M, PW Doppler, CW Doppler, Color Doppler, Color M Doppler, Power Doppler, Harmonic Imaging, Coded Pulse, 3D/4D Imaging mode, Elastography, Shear Wave Elastography and Combined modes: B/M, B/Color, B/PWD, B/Color/PWD, B/Power/ PWD, B/ Elastography. The Voluson™ Expert 18, Voluson™ Expert 20, Voluson™ Expert 22 is intended to be used in a hospital or medical clinic.
Product codes (comma separated list FDA assigned to the subject device)
IYN, IYO, ITX, QIH
Device Description
The systems are full-featured Track 3 ultrasound systems, primarily for general radiology use and specialized for OB/GYN with particular features for real-time 3D/4D acquisition. They consist of a mobile console with keyboard control panel; color LCD/TFT touch panel, color video display and optional image storage and printing devices. They provide high performance ultrasound imaging and analysis and have comprehensive networking and DICOM capability. They utilize a variety of linear, curved linear, matrix phased array transducers including mechanical and electronic scanning transducers, which provide highly accurate real-time three-dimensional imaging supporting all standard acquisition modes.
The following probes are the same as the predicate: RIC5-9-D, IC5-9-D, RIC6-12-D, 9L-D, 11L-D, ML6-15-D, RAB6-D, C1-6-D, C2-9-D, M5Sc-D, RM7C, eM6CG3, RSP6-16-D , RIC10-D, 6S-D and L18-18i-D, RIC12-D. The RAB7-D is a new probe and is substantially equivalent to the
RAB6-D, it is an incremental improvement in technology. Vscan Air SL and Vscan Air CL wireless Probes are also added.
Mentions image processing
Yes, "3D/4D Imaging mode" and "capturing digital images".
Mentions AI, DNN, or ML
Yes, "The proposed Voluson Expert Series 18/20/22 adds additional AI software features SonoLyst 1st Trimester and Sono Pelvic floor 3.0: which includes MHD (valsava manoeuver detection) and Anal sphincter" and "The proposed Voluson Expert Series 18/20/22 updated existing AI software features SonoLyst 2nd Trimester and SonoAVC follicle 2.0".
Input Imaging Modality
Ultrasound
Anatomical Site
Fetal/OB; Abdominal (including GYN, pelvic and infertility monitoring/follicle development); Pediatric; Small Organ (breast, testes, thyroid etc.); Neonatal and Adult Cephalic; Cardiac (adult and pediatric); Musculo-skeletal Conventional and Superficial; Vascular; Transvaginal (including GYN); Transrectal
Indicated Patient Age Range
Not Found
Intended User / Care Setting
Qualified and trained healthcare professionals. Intended to be used in a hospital or medical clinic.
Description of the training set, sample size, data source, and annotation protocol
AI Testing Summary for new Sono Pelvic floor 3.0: which includes MHD (valsava manoeuver detection) and Anal sphincter:
MHD:
Data is provided by external clinical partners who de-identified the data before sharing it with us. Original data is collected in the form of 4D volume Cines in *.vol5 or *.4dv6 data formats. This preserves the flexibility to re-process data to our needs retrospectively during scan conversion7. A standardized data collection protocol was followed for all acquisitions.
Distribution of train data is as follows:
Total Volumes: 983
Distribution by Systems: V730 (116), Voluson E10 (482), Voluson E6 (21), Voluson E8 (90), Voluson P8 (274)
Distribution by Probes: RAB 4-8L (116), RAB2-6-RS (38), RAB6-D (111), RIC5-9A-RS (236), RIC5-9-D (8), RM6C (474)
Distribution by Countries: Australia (116), Austria (8), Belgium (465), Czech Republic (100), Japan (236), Italy (37), South Africa (21)
Truthing process for training datasets: We undertake a two-stage curation process. In the first stage, curators identify the MHD plane in the relevant frame of the cine. In the next stage, the anatomical structures are marked on the MHD plane. The curated datasets are reviewed by expert arbitrators and changes/edits made if necessary to maintain correctness and consistency in curations.
Anal Sphincter:
Data is provided by external clinical partners who de-identified the data before sharing it with us. Original data is collected in the form of 4D or 3D volume acquisitions in *.vol2 or *.4dv3 data formats. This preserves the flexibility to re-process data to our needs retrospectively during scan conversion4. A standardized data collection protocol was followed for all acquisitions.
Distribution of train data is as follows:
Total Volumes: 828
Distribution by Systems: Voluson E6 (118), V730 (160), Voluson E10 (149), Voluson S10 (120), Voluson SWIFT (28), Voluson E8 (83), Voluson P8 (155), Voluson S8 (8), SWIFT + (7)
Distribution by Probes: RAB 4-8L (160), RAB6 (409) RIC5-9 (132), RM7C (42), em6C (2), RM6C (83)
Distribution by Countries: Belgium (116), Australia (186), Egypt (136), Japan (132), Germany (125), South Africa (124), Italy (9)
Truthing process for training datasets: We undertake a 3D segmentation of the Anal Canal using VOCAL tool in the 4D View5 Software. Curation protocol is as follows: 1. Align the volume to ensure full visualization of the Anal Canal 2. Segment the Anal Canal in 3D using VOCAL tool. Curation is done on only volumes that have proper visualization of the relevant anatomy. Each volume was reviewed by a skilled arbitrator for correctness. If any error was found, the volume was re-worked.
AI Testing Summary for updated feature SonoAVC Follicle 2.0:
Data is provided by external clinical partners who de-identified the data before sharing it with us. Original data is collected in the form of 3D volumes in *.vol¹ or *.4dv² data formats. This preserves the flexibility to re-process data to our needs retrospectively during scan conversion³.
Train Data Distribution:
Total Volumes: 249
Distribution by Systems: Voluson E8 (20), Voluson E10 (131), Voluson P8 (29), Voluson S10 (48), Voluson S8 (21)
Distribution by Probes: RIC5-9A-RS (98), RIC5-9-D (149), RIC6-12-D (2)
Distribution by Countries: India (62), Germany (29), United Kingdom (29), Spain (103)
Truthing process for training dataset: To ensure correct and reliable "truthing" process of the training data we followed a two-step approach. In the 1st step, a detailed curation protocol (developed by clinical experts) was shared with the curators, and they were trained and instructed to follow the same. As an automated quality control step, we confirm the availability of all the required masks/markings in each of the curated views. Missing masks or inconsistent labels are reported back to the curators and the datasets not used for training/development until all masks are available and consistently labelled. In addition, during and after the data curation process, a arbitrator reviews all the datasets and curations from each curator's completed data pool for their clinical accuracy. In case that any inconsistencies are detected, an optimal curation strategy is discussed and communicated back to the entire curation team.
AI Testing Summary for updated feature 2nd Trimester SonoLyst/SonoLystlive:
Systems: GEHC Voluson V730, E6, E8, E10, Siemens S2000 and Hitachi Aloka
Formats: Still images were obtained in DICOM & JPEG format, cine loops in RAW data format.
Countries: UK, Austria, India and USA
Total number of images: 2.2M
Total number of cine loops: 3595
Truthing process for training datasets: To ensure the quality of the curated data for verification, the following strategy is employed: 1. The images were curated (sorted and graded) by a single sonographer. 2. The images were sorted and graded by ScanNav AutoCapture Second Trimester. This process resulted in some images being reclassified during sorting. 3. Where they differed from the ground truth, the sorted images from step 2 were reviewed by a 5-sonographer review panel, in order to determine the sorting accuracy of the system. The sorting process resulted in some images being reclassified based upon the majority view of the panel. 4. Where they differed from the ground truth, the graded images from step 1 were reviewed by a 5-sonographer review panel, in order to determine the grading accuracy of the system.
AI Testing Summary for updated feature 1st Trimester SonoLyst/SonolysLive:
Systems: GE Voluson V730, P8, S6/S8, E6, E8, E10, Expert 22, Philips Epiq 7G
Formats: Still images were obtained in DICOM & JPEG format, cine loops in RAW data format.
Countries: UK, Austria, India and USA
For training 122,711 labelled source images from 35,861 patients
Truthing process for test datasets (Note: This section seems to describe the truthing for the test set, but it is listed under "Truthing process for training datasets" in the provided text for 1st Trimester SonoLyst. Given the context, it's more likely a description of the test set truthing or a general quality control procedure applied.): To ensure the quality of the curated data for verification, the following strategy is employed: 1. The images were curated (sorted and graded) by a single sonographer. 2. The images were sorted and graded by ScanNav AutoCapture First Trimester. This process resulted in some images being reclassified during sorting. 3. Where they differed from the ground truth, the sorted images from step 2 were reviewed by a 5-sonographer review panel, in order to determine the sorting accuracy of the system. The sorting process resulted in some images being reclassified based upon the majority view of the panel. 4. Where they differed from the ground truth, the graded images from step 1 were reviewed by a 5-sonographer review panel, in order to determine the grading accuracy of the system.
Description of the test set, sample size, data source, and annotation protocol
AI Testing Summary for new Sono Pelvic floor 3.0: which includes MHD (valsava manoeuver detection) and Anal sphincter:
MHD:
Distribution of Test data is as follows:
Total Volumes: 93
Distribution by Systems: Voluson Expert 22 (59), Voluson Expert 20 (4), V730 (5), Voluson E10 (12), Voluson E8 (2), Voluson S10 (10), Voluson Signature 20 (1)
Distribution by Probes: RAB6-D (21), RIC5-9-D (14), RM7C (26), RAB 4-8L (5), RIC10-D (21), RM6C (6)
Distribution by Countries: Italy (21), U.S.A (29), Australia (5), Germany (15), Czech Republic (6), France (2), India (15)
Truthing process for Test datasets: For Evaluation pool: The evaluation was based on interpretation of the Al output by reviewing clinicians. The evaluation was conducted by three independent reviewers, with at least two being US Certified sonographers, with extensive clinical experience.
Independence of Test data: Post model development, we acquired consecutive data from previously unseen sites to test the robustness of the algorithm on new data distributions. We also collected consecutive data (separately) from sites that had contributed to the train pool as well.
Anal Sphincter:
Distribution of Test data is as follows:
Total Volumes: 106
Distribution by Systems: Voluson E10 (37), Voluson Expert 22 (57), Voluson Expert 20 (7), Voluson Signature 20 (5)
Distribution by Probes: RAB6-D (12), RAB7-D (2), RIC10-D (9), RIC5-9 (62), RM6C (2), RM7C (19)
Distribution by Countries: Italy (21), U.S.A (18), France (32), Germany (12), India (23)
Truthing process for Test datasets: For Evaluation pool: The evaluation was based on interpretation of the Al output by reviewing clinicians. The evaluation was conducted by three independent reviewers, with at least two being US Certified sonographers, with extensive clinical experience.
Independence of Test data: Post model development, we acquired data from previously unseen (in train pool) systems as well as new/unseen sites to test the robustness of the algorithm on new data distributions.
AI Testing Summary for updated feature SonoAVC Follicle 2.0:
Test Data Distribution:
Total Datasets: 138
Total follicle count across all volumes: 2708
Distribution by Systems: Voluson E22 (63), E10 (32), Voluson E8 (20), Voluson P8 (8), Voluson S10 (12), Voluson S8 (3)
Distribution by Probes: RIC5-9 (84), RIC10 (37), RIC6-12 (17)
Distribution by Countries: Germany (54), India (11), Spain (43), United Kingdom (7); USA (23)
Truthing process for test data: For Evaluation pool: The evaluation was based on interpretation of the AI output by reviewing clinicians. The evaluation was conducted by three independent reviewers, with at least two being US Certified sonographers, with extensive clinical experience.
Independence of Test data: To ensure separation of train and test data, following steps were undertaken: 1. Post acquiring the data at the start of the model development – the entire data pool was split into train / validation and test datasets ensuring that there is uniqueness in the patient representation in each set - i.e. a single patient is present only in one of the three groups. Also, it was attempted that there is a representation of as many geographical sites as possible in both the test and train pool. Beyond these two constraints, the data was split randomly. 2. Post model development, we acquired consecutive data from previously unseen (in train pool) systems as well as new/unseen probe to test the robustness of the algorithm on new data distributions.
AI Testing Summary for updated feature 2nd Trimester SonoLyst/SonoLystlive:
Independence of Test data: All training data is independent from the test data at a patient level.
Truthing process for Test datasets: For Evaluation pool: The evaluation was based on interpretation of the Al output by reviewing clinicians. The evaluation was conducted by three independent reviewers, with at least two being US Certified sonographers, with extensive clinical experience.
AI Testing Summary for updated feature 1st Trimester SonoLyst/SonolysLive:
For testing the following number of images were used: SonoLyst 1st Trim IR: 5271, SonoLyst 1st Trim X: 2400, SonoLyst 1st Trim Live: 6000, SonoBiometry CRL: 110
Independence of Test data: All training data is independent from the test data at a patient level. A statistically significant subset of the test data is independent from the training data at a site level, with no test data collected at the site being used in training.
Summary of Performance Studies (study type, sample size, AUC, MRMC, standalone performance, key results)
AI Testing Summary for new Sono Pelvic floor 3.0: which includes MHD (valsala manoeuver detection) and Anal sphincter:
MHD:
Expected result: On datasets that were marked as Good in Image/Cine Quality assessment, the success rate should be 70% or higher. On datasets that were marked as challenging in image/cine quality measure the success rate of the feature should be 60% or higher.
Verification Results on actual verification data: Good Image Quality: MHD Tracking 89.3%, Minimum MHD Frame Detection 89.3%, Maximum MHD Frame detection 90.66%. Challenging Image Quality: On Challenging quality datasets: 60.9%. This seems to be for MHD Tracking. The values for Minimum MHD Frame Detection and Maximum MHD Frame detection for challenging IQ are not provided in the table, but the general success rate for challenging IQ is 60.9%
Anal Sphincter:
Expected result: On datasets that were marked as Good in Image/Cine Quality assessment, the success rate should be 70% or higher. On datasets that were marked as challenging in image/cine quality measure the success rate of the feature should be 60% or higher.
Verification results on actual verification data is not explicitly provided in numerical form for Anal Sphincter in the table. The table lists "Challenging Image Quality 77.7% for tracking, 83.3% for Minimum MHD, 77.7% For Maximum MHD." under the Anal Sphincter column, which is an error in the provided text as these values refer to MHD. There are no results explicitly for "Anal Sphincter" in the "Summary test Statistics" section.
AI Testing Summary for updated feature SonoAVC Follicle 2.0:
Expected result: The success rate for Al feature should be 70% or higher.
Verification Results on actual verification data is as follows:
Accuracy: On test data acquired together with train cohort: 94.73%
On test data, acquired consecutively post model development: 92.8%
Overall Accuracy: 93.6%
Performance matrix for the various size ranges for follicles (Dice Coefficient):
3-5 mm: 0.937619
5-10 mm: 0.946289
10-15 mm: 0.962315
15 mm: 0.93206
AI Testing Summary for updated feature 2nd Trimester SonoLyst/SonoLystlive:
Expected result is not explicitly stated in numerical form.
Key results: The verification for the SonoLyst 2nd Trim feature is based on computing confusion matrices for the sorting (SonoLyst IR) and grading (SonoLyst X) features. The verification of the SonoLystLive 2nd Trim features is based on the average agreement between a sonographer panel and the output of the algorithm regarding Traffic light quality (green/amber/none). The average success rate of SonoLyst 2nd Trimester IR, X and SonoBiometry AC and overall traffic light accuracy is 80% or higher. (This seems to be a general statement and not specific results for 2nd trimester as it refers to AC not CRL).
AI Testing Summary for updated feature 1st Trimester SonoLyst/SonolysLive:
Key results: The verification for the SonoLyst 1st Trim IR&X feature is based on computing confusion matrices for the sorting (SonoLyst IR) and grading (SonoLyst X) features. The verification of the SonoLystLive 1st Trim Trimester features is based on the average agreement between a sonographer panel and the output of the algorithm regarding Traffic light quality (green/amber/none). The verification of the SonoBiometry CRL feature is based on the acceptability rate for the placement of CRL callipers. The average success rate of SonoLyst 1st Trimester IR, X and SonoBiometry CRL and overall traffic light accuracy is 80% or higher.
Key Metrics (Sensitivity, Specificity, PPV, NPV, etc.)
Sono Pelvic floor 3.0:
MHD Tracking Success Rate: Good Image Quality: 89.3%, Challenging Image Quality: 60.9% (for tracking).
No specific sensitivity, specificity, PPV, NPV are provided.
SonoAVC Follicle 2.0:
Accuracy: 94.73% (test data with train cohort), 92.8% (consecutive test data), 93.6% (Overall Accuracy).
Dice Coefficient for follicle size ranges: 3-5mm: 0.937619, 5-10mm: 0.946289, 10-15mm: 0.962315, >15mm: 0.93206.
SonoLyst 2nd Trimester and 1st Trimester SonoLyst/SonolysLive:
Average success rate: 80% or higher for IR, X, SonoBiometry AC (2nd Trimester) and CRL (1st Trimester) and overall traffic light accuracy.
No specific sensitivity, specificity, PPV, NPV are provided.
Predicate Device(s): If the device was cleared using the 510(k) pathway, identify the Predicate Device(s) K/DEN number used to claim substantial equivalence and list them here in a comma separated list exactly as they appear in the text. List the primary predicate first in the list.
K231965 Voluson Expert 18, Voluson Expert 20, Voluson Expert 22
Reference Device(s): Identify the Reference Device(s) K/DEN number and list them here in a comma separated list exactly as they appear in the text.
K231301 Vscan Air, K211488 Logiq E10, K240111: Venue
Predetermined Change Control Plan (PCCP) - All Relevant Information for the subject device only (e.g. presence / absence, what scope was granted / cleared under the PCCP, any restrictions, etc).
Not Found
§ 892.1550 Ultrasonic pulsed doppler imaging system.
(a)
Identification. An ultrasonic pulsed doppler imaging system is a device that combines the features of continuous wave doppler-effect technology with pulsed-echo effect technology and is intended to determine stationary body tissue characteristics, such as depth or location of tissue interfaces or dynamic tissue characteristics such as velocity of blood or tissue motion. This generic type of device may include signal analysis and display equipment, patient and equipment supports, component parts, and accessories.(b)
Classification. Class II.
0
December 20, 2024
Image /page/0/Picture/1 description: The image shows the logo of the U.S. Food and Drug Administration (FDA). The logo consists of two parts: the Department of Health & Human Services seal on the left and the FDA acronym with the full name of the agency on the right. The FDA part of the logo is in blue, with the acronym in a square and the full name written out to the right of the square.
GE Medical Systems Ultrasound and Primary care Diagnostics Bryan Behn Regulatory Affairs Director 9900 Innovation Drive Wauwatosa, Wisconsin 53226
Re: K242168
Voluson Expert 18; Voluson Expert 20; Voluson Expert 22 Trade/Device Name: Regulation Number: 21 CFR 892.1550 Regulation Name: Ultrasonic Pulsed Doppler Imaging System Regulatory Class: Class II Product Code: IYN, IYO, ITX, QIH Dated: November 18, 2024 Received: November 18, 2024
Dear Behn Bryan:
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/cfpm/pm.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.
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
1
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 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-regulatoryinformation/postmarketing-safety-reporting-combination-products); good manufacturing practice requirements as set forth in the quality systems (OS) 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-device-advice-comprehensive-regulatory-assistance/unique-deviceidentification-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-device-safety/medical-device-reporting-mdr-how-report-medicaldevice-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/deviceadvice-comprehensive-regulatory-assistance) and CDRH Learn (https://www.fda.gov/training-and-continuingeducation/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-deviceadvice-comprehensive-regulatory-assistance/contact-us-division-industry-and-consumer-education-dice) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).
Sincerely,
YANNA S. KANG -S
Yanna Kang, Ph.D. Assistant Director Mammography and Ultrasound Team DHT8C: Division of Radiological Imaging and Radiation Therapy Devices OHT8: Office of Radiological Health Office of Product Evaluation and Quality Center for Devices and Radiological Health
2
Indications for Use
Submission Number (if known)
K242168
Device Name
Voluson Expert 18: Voluson Expert 20;
Voluson Expert 20,
Voluson Expert 22
Voluson Expert 22
Indications for Use (Describe)
The device is a general purpose ultrasound system intended for use by qualified and trained healthcare professionals. Specific clinical applications remain the same as previously cleared: Fetall OB; Abdominal (including GYN, pelvic and infertility monitoring/follicle development); Pediatric; Small Organ (breast, testes, thyroid etc.); Neonatal and Adult Cephalic; Cardiac (adult and pediatric); Musculo-skeletal Conventional and Superficial; Vascular; Transvaginal (including GYN); Transrectal
Modes of operation include: B, M, PW Doppler, CW Doppler, Color Doppler, Color M Doppler, Power Doppler, Harmonic Imaging, Coded Pulse, 3D/4D Imaging mode, Elastography, Shear Wave Elastography and Combined modes: B/M, B/Color, B/PWD, B/Color/PWD, B/Power/ PWD, B/ Elastography. The Voluson™ Expert 18, Voluson™ Expert 20, Voluson™ Expert 22 is intended to be used in a hospital or medical clinic.
Type of Use (Select one or both, as applicable)
X Prescription Use (Part 21 CFR 801 Subpart D)
Over-The-Counter Use (21 CFR 801 Subpart C)
CONTINUE ON A SEPARATE PAGE IF NEEDED.
This section applies only to requirements of the Paperwork Reduction Act of 1995.
DO NOT SEND YOUR COMPLETED FORM TO THE PRA STAFF EMAIL ADDRESS BELOW.
The burden time for this collection of information is estimated to average 79 hours per response, including the time to review instructions, search existing data sources, gather and maintain the data needed and complete and review the collection of information. Send comments regarding this burden estimate or any other aspect of this information collection, including suggestions for reducing this burden, to:
Department of Health and Human Services Food and Drug Administration Office of Chief Information Officer Paperwork Reduction Act (PRA) Staff PRAStaff(@fda.hhs.gov
"An agency may not conduct or sponsor, and a person is not required to respond to, a collection of information unless it displays a currently valid OMB number."
3
Image /page/3/Picture/0 description: The image shows the logo for GE HealthCare. The logo consists of a circular emblem on the left and the text "GE HealthCare" on the right. The emblem is purple and features a stylized "GE" monogram inside a circle. The text "GE HealthCare" is also purple.
K242168
510(k) Summary
| In accordance with 21 CFR 807.92 the following summary of information is provided: | |
|---|---|
| Date: | July 24, 2024 |
| Submitter: | GE Healthcare [GE Healthcare Austria GmbH & Co OG] |
| Tiefenbach 15 | |
| Zipf, Austria 4871 | |
| Primary Contact | |
| Person: | Bryan Behn |
| Regulatory Affairs Director | |
| GE Healthcare | |
| 9900 Innovation Drive, | |
| Wauwatosa, WI 53226 | |
| USA | |
| T:(262)247-5502 | |
| F:(414)918-8275 | |
| Secondary Contact | |
| Person: | Thomas Reisenberger |
| Sr. Regulatory Affairs Leader | |
| GE Healthcare Austria GmbH & Co OG | |
| T:(+43)7682-3800-332 | |
| F:(+43)7682 3800-47 | |
| Device: Trade | |
| Name | Voluson Expert Series |
| Models: Voluson Expert 18, Voluson Expert 20, Voluson Expert 22 | |
| Common/Usual | |
| Name: | Ultrasound system |
| Classification | |
| Names: | |
| Product Code: | Class II |
| Ultrasonic Pulsed Doppler Imaging System. 21CFR 892.1550, 90-IYN | |
| Ultrasonic Pulsed Echo Imaging System, 21CFR 892.1560, 90-IYO | |
| Diagnostic Ultrasound Transducer, 21 CFR 892.1570, 90-ITX | |
| Primary Predicate | |
| Device(s): | K231965 Voluson Expert 18, Voluson Expert 20, Voluson Expert 22 |
| Diagnostic Ultrasound System |
4
Image /page/4/Picture/0 description: The image shows the GE HealthCare logo. The logo consists of a circular emblem on the left and the text "GE HealthCare" on the right. The emblem is a stylized version of the letters "GE" inside a circle, and the text is in a simple, sans-serif font.
510(k) Premarket Notification Submission
| Classification | Class II |
|---|---|
| Names: | Ultrasonic Pulsed Doppler Imaging System. 21CFR 892.1550, 90-IYN |
| Ultrasonic Pulsed Echo Imaging System, 21CFR 892.1560, 90-IYO | |
| Diagnostic Ultrasound Transducer, 21 CFR 892.1570, 90-ITX | |
| Product Code: | |
| Reference | K231301 Vscan Air |
| Predicatee | K211488 Logiq E10 |
| Device(s): | K240111: Venue |
Class II
Ultrasonic Pulsed Doppler Imaging System. 21CFR 892.1550, 90-IYN
Ultrasonic Pulsed Echo Imaging System, 21CFR 892.1560, 90-IYODiagnostic Ultrasound Transducer, 21 CFR 892.1570, 90-ITX
Classification Names: Product Code:
Device Description: The systems are full-featured Track 3 ultrasound systems, primarily for general radiology use and specialized for OB/GYN with particular features for real-time 3D/4D acquisition. They consist of a mobile console with keyboard control panel; color LCD/TFT touch panel, color video display and optional image storage and printing devices. They provide high performance ultrasound imaging and analysis and have comprehensive networking and DICOM capability. They utilize a variety of linear, curved linear, matrix phased array transducers including mechanical and electronic scanning transducers, which provide highly accurate real-time three-dimensional imaging supporting all standard acquisition modes.
The following probes are the same as the predicate: RIC5-9-D, IC5-9-D, RIC6-12-D, 9L-D, 11L-D, ML6-15-D, RAB6-D, C1-6-D, C2-9-D, M5Sc-D, RM7C, eM6CG3, RSP6-16-D , RIC10-D, 6S-D and L18-18i-D, RIC12-D. The RAB7-D is a new probe and is substantially equivalent to the
RAB6-D, it is an incremental improvement in technology. Vscan Air SL and Vscan Air CL wireless Probes are also added.
- The device is a general purpose ultrasound system intended for use by Intended Use: qualified and trained healthcare professionals. Specific clinical applications remain the same as previously cleared:
Abdominal (including GYN, pelvic and infertility Fetal/OB; monitoring/follicle development); Pediatric; Small Organ (breast, testes, thyroid etc.); Neonatal and Adult Cephalic; Cardiac (adult and pediatric); Musculo-skeletal Conventional and Superficial; Vascular; Transvaginal (including GYN); Transrectal
Modes of operation include: B, M, PW Doppler, CW Doppler, Color
5
Image /page/5/Picture/0 description: The image shows the GE HealthCare logo. The logo consists of a circular emblem on the left and the text "GE HealthCare" on the right. The emblem is a purple circle with a stylized "GE" inside. The text "GE HealthCare" is also in purple.
510(k) Premarket Notification Submission
Doppler, Color M Doppler, Power Doppler, Harmonic Imaging, Coded Pulse, 3D/4D Imaging mode, Elastography, Shear Wave Elastography and Combined modes: B/M, B/Color, B/PWD, B/Color/PWD, B/Power/ PWD, B/Elastography. The Voluson™ Expert 18, Voluson™ Expert 20, Voluson™ Expert 22 is intended to be used in a hospital or medical clinic.
The Voluson Expert Series (Voluson Expert 18/20/22) employs the Technology: same fundamental scientific technology as its predicate devices.
Determination of Comparison to Predicates
Substantial The proposed Voluson Expert 18/20/22 is substantially equivalent to Equivalence: the predicate device with regards to intended use, imaging capabilities, technological characteristics and safety and effectiveness.
Model Names and Model differences:
Voluson Expert 18. Voluson Expert 20 and Voluson Expert 22 are same in hardware . Voluson Expert 18 is lower version and not all probes or functions are available. Voluson Expert 20 is mid version and product with complete configuration with all the probes and functions of software with exception of 4D electronically probe eM6C G3, 4d realtime Probes: RIC6-12-D, and RM7C. The high-end model Voluson Expert 22 supports all probes including electronical 4D probe eM6C G3.
- . The systems are all intended for diagnostic ultrasound imaging and fluid flow analysis.
- . The proposed Voluson Expert 18/20/22 and predicate Voluson Expert 18/20/22 systems have the same clinical intended use.
- The proposed Voluson Expert 18/20/22 and predicate Voluson Expert 18/20/22 systems have the same imaging modes.
- � The proposed Voluson Expert 18/20/22 and predicate Voluson Expert 18/20/22 system transducers are equivalent. New RAB7-D and VscanAir SL and VscanAir CL wireless probes were added.
- There is no change to the system indications for use. ●
- The systems are manufactured with materials which have ● been evaluated and found to be safe for the intended use of the device.
- . The systems have acoustic power levels which are below the applicable FDA limits.
6
Image /page/6/Picture/0 description: The image shows the GE HealthCare logo. The logo consists of a circular emblem on the left and the text "GE HealthCare" on the right. The emblem is a purple circle with a stylized "GE" inside, and the text is also in purple.
- The proposed Voluson Expert Series 18/20/22 and predicate . Expert 18/20/22 system have similar capability in terms of performing measurements, capturing digital images, reviewing and reporting studies.
- The proposed Voluson Expert Series 18/20/22 and predicate systems have been designed in compliance with approved electrical and physical safety standards.
- There proposed Voluson Expert Series 18/20/22 and predicate ● Expert 18/20/22 system Software Features are equivalent (except below Changes). Some minor improvements to the existing Software features have been implemented into the proposed system.
- The proposed Voluson Expert Series 18/20/22 adds additional AI software features SonoLyst 1st Trimester and Sono Pelvic floor 3.0: which includes MHD (valsava manoeuver detection) and Anal sphincter
- . The proposed Voluson Expert Series 18/20/22 updated existing AI software features SonoLyst 2nd Trimester and SonoAVC follicle 2.0
- The proposed Voluson Expert Series 18/20/22 adds additional software features
- O-RADS=(Ovarian-Adnexal Reporting & Data System) o
- OTI live, Automation of bulk speed of sound о implemented (similar method as existing ADAPT with eM6C)
- The following software feature has been migrated from Venue ● (K240111): Vscan Air Probe Support
- . The proposed Voluson Expert Series 18/20/22 adds one new Probe: RAB7-D which is similar to predicate probe RAB6-D (K231965) and support of wireless Probes Vscan Air CL and Vscan Air SL Probes (K240111):
7
Image /page/7/Picture/0 description: The image shows the GE HealthCare logo. The logo consists of a circular emblem on the left and the text "GE HealthCare" on the right. The emblem is purple and features a stylized "GE" in a circular design. The text "GE HealthCare" is also purple and is written in a clean, sans-serif font.
GE HealthCare 510(k) Premarket Notification Submission
AI Testing Summary for new Sono Pelvic floor 3.0: which includes MHD (valsava manoeuver detection) and Anal sphincter:
| MHD | Anal Sphincter | ||
|---|---|---|---|
| Expected result. | Expected result. | ||
| On datasets that were | |||
| marked as Good in | |||
| Image/Cine Quality | |||
| assessment, the success | |||
| rate should be 70% or | |||
| higher. On datasets that | |||
| were marked as | |||
| challenging in image/cine | |||
| quality measure the | |||
| success rate of the feature | |||
| should be 60% or higher. | On datasets that were | ||
| marked as Good in | |||
| Image/Cine Quality | |||
| assessment, the success rate | |||
| should be 70% or higher. On | |||
| datasets that were marked as | |||
| challenging in image/cine | |||
| quality measure the success | |||
| rate of the feature should be | |||
| 60% or higher. | |||
| Rationale for clinical | |||
| adequacy. | Rationale for clinical | ||
| adequacy. | |||
| Summary | |||
| test | |||
| Statistics | Requirements for success | ||
| rates of this workflow tool | |||
| were discussed with | |||
| internal and external | |||
| clinical experts. User | |||
| scanning experience and | |||
| expected image quality in | |||
| clinical practice was | |||
| considered and reflected in | |||
| the verification data pool. | |||
| Based on the expert | |||
| opinion the above success | |||
| rates were considered | |||
| appropriate. | |||
| Verification Results on | |||
| actual verification data is | |||
| as follows | Requirements for success | ||
| rates of this workflow tool | |||
| were discussed with internal | |||
| and external clinical experts. | |||
| User scanning experience | |||
| and expected image quality | |||
| in clinical practice was | |||
| considered and reflected in | |||
| the verification data pool. | |||
| Based on the expert opinion | |||
| the above success rates were | |||
| considered appropriate. | |||
| Verification results on actual | |||
| verification data is as follows | |||
| MHD Tracking | |||
| Minimum MHD | |||
| Frame Detection | |||
| Maximum MHD | |||
| Frame detection | Good Image | ||
| Quality | |||
| 89.3% | |||
| 89.3% | |||
| 90.66% | Challenging | ||
| Image Quality | |||
| 77.7% | |||
| 83.3% | |||
| 77.7% | |||
| On Good IQ datasets: 81.9% | |||
| On Challenging quality | |||
| datasets: 60.9% | |||
| The primary confounders | |||
| present in the data pool | |||
| are as follows: | Confounder: | ||
| Confound | |||
| ers | 1. Phase of examination: | ||
| Rest, Contraction and | |||
| Valsalva | 1. Multiple probes (both | ||
| Transabdominal and | |||
| transvaginal) are represented | |||
| in the verification pool as | |||
| detailed above. | |||
| 2. Multiple probes (both | |||
| Transabdominal and | |||
| transvaginal) are | |||
| represented in the | |||
| verification pool as detailed | |||
| above. | 2. The data is acquired across | ||
| diverse regions and sites | |||
| 3. The data is acquired | |||
| across diverse regions and | |||
| sites | 3. There is also image quality | ||
| variation in the data sets - | |||
| marked as challenging or | |||
| good IQ by clinical experts. | |||
| 4. There is also image | |||
| quality variation in the data | |||
| sets – marked as | |||
| challenging or good IQ by | |||
| clinical experts. |
8
Image /page/8/Picture/0 description: The image shows the logo for General Electric (GE). The logo is a purple circle with the letters "GE" in a stylized, cursive font in the center. The circle has white accents around the edges, giving it a slightly three-dimensional appearance.
GE HealthCare
9
Image /page/9/Picture/0 description: The image shows the GE HealthCare logo. The logo consists of a circular emblem on the left and the text "GE HealthCare" on the right. The emblem is purple and features a stylized design. The text is also purple and is written in a sans-serif font.
GE HealthCare 510(k) Premarket Notification Submission
| | Data is provided by
external clinical partners
who de-identified the data
before sharing it with us.
Original data is collected in
the form of 4D volume
Cines in *.vol5 or *.4dv6
data formats. This
preserves the flexibility to
re-process data to our
needs retrospectively
during scan conversion7. A
standardized data
collection protocol was
followed for all
acquisitions. | Data is provided by external
clinical partners who de-
identified the data before
sharing it with us. Original
data is collected in the form
of 4D or 3D volume
acquisitions in *.vol2 or
*.4dv3 data formats. This
preserves the flexibility to re-
process data to our needs
retrospectively during scan
conversion4. A standardized
data collection protocol was
followed for all acquisitions. |
|----------------------------------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| | Distribution of train data is
as follows | Distribution of train data is
as follows |
| | Total Volumes: 983 | Total Volumes: 828 |
| Data
Collection | Distribution by Systems: | Distribution by Systems: |
| | V730 (116), Voluson E10
(482), Voluson E6 (21),
Voluson E8 (90), Voluson
P8 (274) | Voluson E6 (118), V730 (160),
Voluson E10 (149), Voluson
S10 (120), Voluson SWIFT
(28), Voluson E8 (83),
Voluson P8 (155), Voluson S8
(8), SWIFT + (7) |
| | Distribution by Probes: RAB
4-8L (116), RAB2-6-RS (38),
RAB6-D (111), RIC5-9A-RS
(236), RIC5-9-D (8), RM6C
(474) | Distribution by Probes: RAB
4-8L (160), RAB6 (409) RIC5-9
(132), RM7C (42), em6C (2),
RM6C (83) |
| | Distribution by Countries:
Australia (116), Austria (8),
Belgium (465), Czech
Republic (100), Japan (236),
Italy (37), South Africa (21)
Distribution of Test data is
as follows | Distribution by Countries:
Belgium (116), Australia
(186), Egypt (136), Japan
(132), Germany (125), South
Africa (124), Italy (9)
Distribution of Test data is as
follows |
| | Total Volumes: 93 | Total Volumes: 106 |
| | Distribution by Systems:
Voluson Expert 22 (59),
Voluson Expert 20 (4), V730
(5), Voluson E10 (12),
Voluson E8 (2), Voluson
S10 (10), Voluson Signature
20 (1) | Distribution by Systems:
Voluson E10 (37), Voluson
Expert 22 (57), Voluson
Expert 20 (7), Voluson
Signature 20 (5) |
| | Distribution by Probes:
RAB6-D (21), RIC5-9-D (14),
RM7C (26), RAB 4-8L (5),
RIC10-D (21), RM6C (6) | Distribution by Probes: RAB6-
D (12), RAB7-D (2), RIC10-D
(9), RIC5-9 (62), RM6C (2),
RM7C (19) |
| | Distribution by Countries:
Italy (21), U.S.A (29),
Australia (5), Germany (15),
Czech Republic (6), France
(2), India (15) | Distribution by Countries:
Italy (21), U.S.A (18), France
(32), Germany (12), India
(23) |
| Truthing
process
for
training
datasets | We undertake a two-stage
curation process. In the
first stage, curators identify
the MHD plane in the
relevant frame of the cine.
In the next stage, the
anatomical structures are
marked on the MHD plane.
The curated datasets are
reviewed by expert
arbitrators and
changes/edits made if
necessary to maintain
correctness and
consistency in curations, | We undertake a 3D
segmentation of the Anal
Canal using VOCAL tool in the
4D View5 Software. Curation
protocol is as follows:
- Align the volume to ensure
full visualization of the Anal
Canal - Segment the Anal Canal in
3D using VOCAL tool.
Curation is done on only
volumes that have proper
visualization of the relevant
anatomy
Each volume was reviewed
by a skilled arbitrator for
correctness. If any error was
found, the volume was re-
worked |
| Truthing
process
for Test
datasets | For Evaluation pool:
The evaluation was based
on interpretation of the Al
output by reviewing
clinicians. The evaluation
was conducted by three | For Evaluation pool:
The evaluation was based on
interpretation of the Al
output by reviewing
clinicians. The evaluation was
conducted by three |
| | independent reviewers,
with at least two being US
Certified sonographers,
with extensive clinical
experience. | independent reviewers, with
at least two being US
Certified sonographers, with
extensive clinical experience. |
| | To ensure separation of
train and test data,
following steps were
undertaken: | To ensure separation of train
and test data, following steps
were undertaken: |
| Independ
ence of
Test data | Post model development,
we acquired consecutive
data from previously
unseen sites to test the
robustness of the algorithm
on new data distributions.
We also collected
consecutive data
(separately) from sites that
had contributed to the
train pool as well. | Post model development, we
acquired data from
previously unseen (in train
pool) systems as well as
new/unseen sites to test the
robustness of the algorithm
on new data distributions. |
10
Image /page/10/Picture/0 description: The image shows the logo for GE HealthCare. The logo consists of a circular emblem on the left and the text "GE HealthCare" on the right. The emblem is a stylized version of the letters "GE" enclosed in a circle. The text "GE HealthCare" is written in a simple, sans-serif font and is colored purple.
11
Image /page/11/Picture/0 description: The image shows the logo for General Electric (GE). The logo is a purple circle with the letters "GE" in a stylized script in the center. The letters are white. There are three white teardrop shapes around the edge of the circle, evenly spaced.
GE HealthCare
510(k) Premarket Notification Submission
AI Testing Summary for updated feature SonoAVC Follicle 2.0:
| SonoAVC Follicle 2.0 | |
|---|---|
| Expected result | |
| The success rate for Al feature should be 70% or | |
| higher. | |
| Summary test | |
| Statistics | Rational for Clinical Adequacy |
| Requirements for success rates of this workflow toolexperts. User scanning experience and expected image | |
| quality in clinical practice was considered and reflected | |
| in the verification data pool. Based on the expert | |
| opinion the above success rates were considered | |
| appropriate. | |
| Verification Results on actual verification data is as | |
| follows: | |
| Accuracy: | |
| On test data acquired together with train cohort: | |
| 94.73% | |
| On test data, acquired consecutively post model | |
| development: 92.8% | |
| Overall Accuracy: 93.6% |
12
Image /page/12/Picture/0 description: The image shows the GE HealthCare logo. The logo consists of a circular emblem on the left and the text "GE HealthCare" on the right. The emblem is purple and features a stylized "GE" design. The text "GE HealthCare" is also purple and is written in a clean, sans-serif font.
| Confounders | For various confounders the individual accuracy numbers are as follows:
Probe wise distribution:
RIC5-9 – 94.6%
RIC10 – 93,6%
RIC6-12 – 90.6%
Geographical distribution:
Germany - 92.2%
India – 95.1%
Spain - 94.7%
U.K. - 95.5% | | | | | | | | | | |
|-------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|--|--|--|--|--|--|--|--|--|--|
| | The test cohort consists of multiple sets - Set 1 is acquired together with the train data set and remaining sets (2-5) are acquired post model development.
For set 1 – the size distribution of follicles (measured as the largest 3D diameter) is detailed below:
3-5 mm: 31%
5-10 mm: 40%
10-15 mm: 21%
15 mm: 8%
The above is in line with the clinical prevalence of the follicle sizes.
The above, together with data from diverse probes and different sites ensure sufficient diversity is captured in terms of acquisition settings, image quality as well as patient demographics.
The performance matrix for the various size ranges for follicles is as follows. Size Range (mm) Dice Coefficient 3-5 0.937619 5-10 0.946289 10-15 0.962315 >15 0.93206 | | | | | | | | | | |
13
Image /page/13/Picture/0 description: The image shows the logo for GE HealthCare. The logo consists of a circular emblem on the left and the text "GE HealthCare" on the right. The emblem is a stylized version of the letters "GE" inside a circle with decorative flourishes. The text "GE HealthCare" is written in a simple, sans-serif font.
| Data Collection | Data is provided by external clinical partners who de-identified the data before sharing it with us. Original data is collected in the form of 3D volumes in *.vol¹ or *.4dv² data formats. This preserves the flexibility to re-process data to our needs retrospectively during scan conversion³.
Train Data Distribution:
Total Volumes: 249 Distribution by Systems: Voluson E8 (20), Voluson E10 (131), Voluson P8 (29), Voluson S10 (48), Voluson S8 (21) Distribution by Probes: RIC5-9A-RS (98), RIC5-9-D (149), RIC6-12-D (2) Distribution by Countries: India (62), Germany (29), United Kingdom (29), Spain (103) Test Data Distribution
Total Datasets: 138
Total follicle count across all volumes: 2708 Distribution by Systems: Voluson E22 (63), E10 (32), Voluson E8 (20), Voluson P8 (8), Voluson S10 (12), Voluson S8 (3) Distribution by Probes: RIC5-9 (84), RIC10 (37), RIC6-12 (17) Distribution by Countries: Germany (54), India (11), Spain (43), United Kingdom (7); USA (23) |
|------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Truthing process
for training dataset | To ensure correct and reliable "truthing" process of the training data we followed a two-step approach.
In the 1st step, a detailed curation protocol (developed by clinical experts) was shared with the curators, and they were trained and instructed to follow the same.
As an automated quality control step, we confirm the availability of all the required masks/markings in each of the curated views. Missing masks or inconsistent labels are reported back to the curators and the datasets not used for training/development until all masks are available and consistently labelled.
In addition, during and after the data curation process, a arbitrator reviews all the datasets and curations from each curator's completed data pool for their clinical accuracy. In case that any inconsistencies are detected, an optimal curation strategy is discussed and communicated back to the entire curation team. |
| Truthing process
fortest data | For Evaluation pool:
The evaluation was based on interpretation of the AI
output by reviewing clinicians. The evaluation was
conducted by three independent reviewers, with at
least two being US Certified sonographers, with
extensive clinical experience. |
| Independence of
Test data | To ensure separation of train and test data, following
steps were undertaken:
-
Post acquiring the data at the start of the
model development – the entire data pool
was split into train / validation and test
datasets ensuring that there is uniqueness in
the patient representation in each set - i.e. a
single patient is present only in one of the
three groups. Also, it was attempted that
there is a representation of as many
geographical sites as possible in both the test
and train pool. Beyond these two constraints,
the data was split randomly. -
Post model development, we acquired
consecutive data from previously unseen (in
train pool) systems as well as new/unseen
probe to test the robustness of the algorithm
on new data distributions. |
14
Image /page/14/Picture/0 description: The image shows the logo for GE HealthCare. The logo consists of the GE monogram in a circle on the left, followed by the words "GE HealthCare" in a sans-serif font. The color of the logo is a shade of purple.
510(k) Premarket Notification Submission
AI Testing Summary for updated feature 2nd Trimester SonoLyst/SonoLystlive
SonoLyst/SonoLystlive
1230
15
Image /page/15/Picture/0 description: The image shows the logo for GE HealthCare. The logo consists of a circular emblem with the letters 'GE' intertwined in a stylized font. To the right of the emblem, the words 'GE HealthCare' are written in a simple, sans-serif font. The color of the logo is a shade of purple.
| Confounders | In order to demonstrate the generalization
performance of the algorithm, the quantitative
evaluation is performed for two subgroups: a data set
containing of a variety of ultrasound systems and data
formats against a data set containing the target
platform. For both subgroups the acceptance criteria
are met. |
|----------------------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Data Collection | Systems: GEHC Voluson V730, E6, E8, E10,
Siemens S2000 and Hitachi Aloka
Formats: Still images were obtained in DICOM
& JPEG format, cine loops in RAW data
format.
Countries: UK, Austria, India and USA
Total number of images: 2.2M
Total number of cine loops: 3595 |
| | To ensure the quality of the curated data for
verification, the following strategy is employed:
employed
- The images were curated (sorted and graded)
by a single sonographer - The images were sorted and graded by |
| | ScanNav AutoCapture Second Trimester.
This process resulted in some images being
reclassified during sorting. |
| Truthing process
for training
datasets | 3. Where they differed from the ground truth,
the sorted images from step 2 were reviewed
by a 5-sonographer review panel, in order to
determine the sorting accuracy of the system.
The sorting process resulted in some images
being reclassified based upon the majority
view of the panel. |
| | 4. Where they differed from the ground truth,
the graded images from step 1 were reviewed
by a 5-sonographer review panel, in order to
determine the grading accuracy of the system. |
16
Image /page/16/Picture/0 description: The image shows the logo for GE HealthCare. The logo consists of the GE monogram inside of a circle on the left, and the words "GE HealthCare" on the right. The logo is purple.
510(k) Premarket Notification Submission
| Truthing process
for Test datasets | For Evaluation pool:
The evaluation was based on interpretation of the Al
output by reviewing clinicians. The evaluation was
conducted by three independent reviewers, with at
least two being US Certified sonographers, with
extensive clinical experience. |
|---------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Independence of
Test data | All training data is independent from the test data at a
patient level. |
AI Testing Summary for updated feature 1st Trimester SonoLyst/Sonolystlive
| 1st Trimester SonoLyst/SonolysLive | |
|---|---|
| Summary test | |
| Statistics | Data used for both training and validation has |
| • been collected across multiple geographical | |
| sites using different systems to represent the | |
| variations in target population. | |
| The verification for the SonoLyst 1st Trim IR&X | |
| • feature is based on computing confusion | |
| matrices for the sorting (SonoLyst IR) and | |
| grading (SonoLyst X) features | |
| The verification of the SonoLystLive 1st Trim | |
| • Trimester features is based on the average | |
| agreement between a sonographer panel and | |
| the output of the algorithm regarding Traffic | |
| light quality (green/amber/none) | |
| The verification of the SonoBiometry CRL | |
| • feature is based on the acceptability rate for | |
| the placement of CRL callipers | |
| The average success rate of SonoLyst 1st | |
| • Trimester IR, X and SonoBiometry CRL and | |
| overall traffic light accuracy is 80% or higher | |
| Confounders | For SonoLyst 1st Trimester the following confounder is |
| used: the algorithmic performance is tested on two | |
| sub data sets: 1) data acquired with transabdominal | |
| probes 2) data acquired with transvaginal probes. By | |
| choosing transabdominal vs transvaginal probes as | |
| confounder for the data analysis, the robustness of the | |
| algorithm against the influence of the abdominal wall, | |
| the transducer geometry and frequency is evaluated. | |
| For both subgroups the acceptance criteria are met. | |
| This demonstrates the generalization performance of | |
| the algorithm. | |
| Data Collection | - Systems: GE Voluson V730, P8, S6/S8, E6, E8, |
| E10, Expert 22, Philips Epiq 7G |
- Formats: Still images were obtained in DICOM
& JPEG format, cine loops in RAW data
format. - Countries: UK, Austria, India and USA
- For training 122,711 labelled source images
from 35,861 patients - For testing the following number of images
were used:
SonoLyst 1st Trim IR: 5271
SonoLyst 1st Trim X: 2400
SonoLyst 1st Trim Live: 6000
SonoBiometry CRL: 110 |
| Truthing process
for test datasets | To ensure the quality of the curated data for
verification, the following strategy is employed:
employed
-
The images were curated (sorted and graded)
by a single sonographer -
The images were sorted and graded by
ScanNav AutoCapture First Trimester.
This process resulted in some images
being reclassified during sorting. -
Where they differed from the ground truth,
the sorted images from step 2 were
reviewed by a 5-sonographer review
panel, in order to determine the sorting
accuracy of the system.
The sorting process resulted in some images
being reclassified based upon the majority
view of the panel.
- Where they differed from the ground truth,
the graded images from step 1 were
reviewed by a 5-sonographer review
panel, in order to determine the grading
accuracy of the system. |
| Independence of
Test data | All training data is independent from the test data at a
patient level.
A statistically significant subset of the test data is
independent from the training data at a site level, with
no test data collected at the site being used in training. |
17
Image /page/17/Picture/0 description: The image shows the GE HealthCare logo. The logo consists of a circular emblem on the left and the text "GE HealthCare" on the right. The emblem is purple and features a stylized "GE" in a circular design, while the text is also purple and uses a clean, sans-serif font.
18
Image /page/18/Picture/0 description: The image shows the GE HealthCare logo. The logo consists of a circular emblem on the left and the text "GE HealthCare" on the right. The emblem is purple and features a stylized "GE" in a circular design, while the text is also purple and written in a clean, sans-serif font.
Summary of Non-Clinical Tests:
The device has been evaluated for acoustic output, biocompatibility, cleaning and disinfection effectiveness as well as thermal, electrical, electromagnetic, and mechanical safety, and has been found to conform to applicable medical device safety standards. The Voluson Expert Series 18/20/22 and its applications comply with voluntary standards:
- . IEC 60601-1 Edition 3.2 2020-08 CONSOLIDATED VERSION Medical electrical equipment - Part 1: General requirements for basic safety and essential performance
- IEC60601-1-2 Medical Electrical Equipment – Part 1-2: General Requirements for Safety - Collateral Standard: Electromagnetic Compatibility Requirements and Tests, Edition 4.1 CONSOLIDATED VERSION 2020
- IEC60601-2-37, Medical Electrical Equipment Part 2-37: . Particular Requirements for the Safety of Ultrasonic Medical Diagnostic and Monitoring Equipment, 2015
- . ISO10993-1, Biological evaluation of medical devices - Part 1: Evaluation and testing within a risk management process, 2018
- ISO14971, Application of risk management to medical devices: . Third Edition 2019
- NEMA PS 3.1 3.20 (2023e), Digital Imaging and . Communications in Medicine (DICOM) Set. (Radiology)
- AAMI TIR69:2017/(R2020), Risk management of radiofrequency wireless coexistence for medical devices and systems
- . IEC62359 Edition 2.1 2017-09 Consolidated Version; Ultrasonics - Field characterization - Test methods for the determination of thermal and mechanical indices related to medical diagnostic ultrasonic fields
The following quality assurance measures are applied to the development of the system:
- Risk Analysis .
- Requirements Reviews ●
- Design Reviews ●
- Testing on unit level (Module verification)
- Integration testing (System verification)
- Performance testing (Verification) ●
- Safety testing (Verification) ●
- Final Acceptance Testing (Validation) ●
19
Image /page/19/Picture/0 description: The image shows the GE HealthCare logo. The logo consists of a circular emblem on the left and the text "GE HealthCare" on the right. The emblem is a stylized, circular design, and the text is in a sans-serif font and is purple.
510(k) Premarket Notification Submission
Transducer materials and other patient contact materials are biocompatible.
Summary of Clinical Tests:
The subject of this premarket submission, Voluson Expert Series 18/20/22 did not require clinical studies to support substantial equivalence.
- Conclusion: GE Healthcare considers the Voluson Expert Series 18/20/22 to be as safe, as effective, and performance is substantially equivalent to the primary predicate device.