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: 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
Modes of operation include: B, M, PW Doppler, CW Doppler, Color M Doppler, Power 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 20, Voluson™ Expert 22 is intended to be used in a hospital or medical clinic.

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.

AI/ML Overview

Here's an analysis of the acceptance criteria and supporting studies for the device, based on the provided text:

Acceptance Criteria and Device Performance

The document describes several AI features: SonoAVC2.0, SonoPelvicFloor2.0, Fibroid Mapping, and SonoLyst/SonoLyst Live.

SonoAVC2.0 is explicitly stated to have migrated from a previously cleared device (K230346, Voluson SWIFT/SWIFT+) as "Auto Caliper," implying its performance has already met acceptance criteria in that context. No new specific acceptance criteria or performance metrics are provided for SonoAVC2.0 in this document.

SonoPelvicFloor2.0

Acceptance Criteria	Reported Device Performance
Success rate should be 70% or higher on datasets marked as "Good" in Image/Cine Quality (IQ) assessment.	96% accuracy on Good IQ datasets.
Success rate should be 60% or higher on datasets marked as "Challenging" in Image/Cine Quality (IQ) assessment.	93% accuracy on Challenging IQ datasets.

Fibroid Mapping

Acceptance Criteria	Reported Device Performance (Primary Verification)	Reported Device Performance (Secondary Evaluation)
Success rate of each AI component (uterus, endometrium, and fibroid segmentation) should be 70% or higher. (Qualitative assessment)	Uterus: 95%	Uterus: 100%
	Endometrium: 89%	Endometrium: 91%
	Fibroids: 88%	Fibroids: 88%

Fibroid Mapping (Quantitative Evaluation - DICE Scores when successful)

Acceptance Criteria	Reported Device Performance
Implicit: High accuracy of algorithms and correlation between DICE scores and qualitative assessment by independent clinical experts. (No specific numerical threshold given as acceptance criterion, but high DICE scores are presented as evidence of high accuracy when successful.)	Uterus: 0.89 ± 0.03
	Endometrium: 0.70 ± 0.18
	Fibroids: 0.70 ± 0.13

SonoLyst/SonoLyst Live (2nd Trimester Features)

Acceptance Criteria	Reported Device Performance
Average success rate of SonoLyst 2nd Trimester IR and X and overall traffic light accuracy is 80% or higher.	Meets criteria (specific percentages not provided, but stated as "met").

Study Details

SonoPelvicFloor2.0

Sample Size and Data Provenance (Test Set):
- Total Volumes: 94
- Distribution by Systems: Voluson Expert 22 (82), Voluson E8 (8), Voluson E6 (4)
- Distribution by Probes: RAB6-D (41), RIC5-9-D (21), RM7C (32)
- Distribution by Countries: Austria (36), U.S.A (47), South Africa (4), Czech Republic (7)
- Data Provenance: Retrospective. 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, preserving flexibility for retrospective re-processing. The data covers multiple geographical sites.
Number and Qualifications of Experts for Ground Truth (Test Set):
- The verification was "performed by clinical experts" and involved an "internal clinical expert" for assessment.
- Specific numbers or qualifications (e.g., years of experience, specialty) of these experts are not explicitly stated in the provided text.
Adjudication Method (Test Set):
- Not explicitly described as a formal adjudication method (e.g., 2+1). The "internal clinical expert" documents the assessment.
Multi Reader Multi Case (MRMC) Comparative Effectiveness Study:
- No MRMC comparative effectiveness study is mentioned for this feature. Performance is reported as standalone accuracy.
Standalone Performance:
- Yes, the reported accuracy (96% on good IQ, 93% on challenging IQ) is for the algorithm's standalone performance.
Type of Ground Truth:
- "Internal clinical expert" assessment based on a specific workflow (observing automated placement of MHD plane and assessing success/failure). This would constitute expert consensus/judgment on the algorithm's output.
Sample Size for Training Set:
- Volumes: 983 distinct volumes
- Patients: 616 individual patients
- Images (generated): 8847 images (3 slices from each volume with three rotation angles per image)
- 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)
How Ground Truth for Training Set was Established:
- Not explicitly detailed for the training set within the provided text. However, it states that "Data used for both training and validation has been collected across multiple geographical sites" and "Data is provided by external clinical partners who de-identified the data." This implies that clinical experts or medical professionals initially generated the data, which was then de-identified. The process of labeling or establishing "ground truth" (e.g., manual annotations of pelvic floor structures) on these 983 volumes for training is not described.

Fibroid Mapping

Sample Size and Data Provenance (Test Set/Verification):
- Primary Verification:
  - Total Volumes: 78
  - Systems: Voluson Expert Series
  - Probes: RIC5-9-D, RIC6-12-D
  - Countries: Egypt, Greece, Korea, Philippines, Romania, USA.
- Secondary Evaluation (Qualitative and Quantitative):
  - Total Volumes: 74
  - Systems: Voluson Expert Series
  - Probes: RIC5-9-D, RIC10-D
  - Countries: Austria, Egypt, Germany, Greece, Korea, Philippines, Romania, USA.
- Data Provenance: Retrospective. Data "provided by external clinical partners who de-identified the data before sharing it with us." Original data is collected in 3D/4D volumes.
Number and Qualifications of Experts for Ground Truth (Test Set):
- Verification "performed by clinical experts."
- "Independent clinical experts" for qualitative assessment and correlation with DICE scores.
- "Internal and external clinical experts" were consulted for defining requirements for success rates.
- Specific numbers or qualifications (e.g., years of experience, specialty) of these experts are not explicitly stated in the provided text.
Adjudication Method (Test Set):
- Not explicitly described as a formal adjudication method. Clinical experts perform the qualitative assessment and judge if segmentation is "satisfying." If not, they may return to an earlier step or activate manual segmentation.
Multi Reader Multi Case (MRMC) Comparative Effectiveness Study:
- No MRMC comparative effectiveness study is mentioned for this feature. Performance is reported as a standalone success rate and DICE scores.
Standalone Performance:
- Yes, the reported success rates and DICE scores are for the algorithm's standalone performance in segmentation.
Type of Ground Truth:
- Qualitative: "Clinical expert" assessment of whether the segmentation is "satisfying."
- Quantitative: DICE scores calculated against what is presumably expert-annotated ground truth segmentations, which are then correlated with the qualitative expert assessment. The explicit method for defining this precise quantitative ground truth (e.g., expert manual segmentation per pixel) is not detailed for the test set.
Sample Size for Training Set:
- Unique Volumes: 779
- Augmented Volumes: 7790
How Ground Truth for Training Set was Established:
- "We collected training data of the following types from hospital centers as well as private practices. We provided a dedicated data collection protocol explaining the required data needs to each provider." This implies a structured collection, but the actual process of defining the ground truth for segmentation (e.g., manual outlining of fibroids, uterus, endometrium by experts on each training image) is not explicitly described.

SonoLyst/SonoLyst Live (2nd Trimester Features) Improvement

Sample Size and Data Provenance (Test Set):
- Quantitative Evaluation for SonoLyst 2nd Trimester IR: 42102 images
- Quantitative Evaluation for SonoLyst 2nd Trimester X: 10424 images
- Quantitative Evaluation for SonoLystLive 2nd Trimester: 5666 images
- Data Provenance: Retrospective. Data collected from routine clinical practice in hospitals and private practice during mid-trimester examinations. Countries include UK, Austria, India, and USA.
Number and Qualifications of Experts for Ground Truth (Test Set):
- Sonographer Panel: 5 sonographers were used to review sorted and graded images for accuracy.
- Initial Curation: A "single sonographer" initially curated (sorted and graded) the images.
- Specific qualifications (e.g., years of experience) for these sonographers are not explicitly stated.
Adjudication Method (Test Set):
- Majority View: For images where the initial sonographer's sorting differed from the algorithm's initial classification, a 5-sonographer review panel determined the sorting accuracy, resulting in reclassification based on the "majority view of the panel."
- For graded images, the 5-sonographer panel reviewed where they differed from the initial ground truth to determine grading accuracy. This is a form of 5-reader consensus/adjudication.
Multi Reader Multi Case (MRMC) Comparative Effectiveness Study:
- The verification of SonoLystLive 2nd Trimester features is based on "the average agreement between a sonographer panel and the output of the algorithm regarding Traffic light quality." While this involves multiple readers assessing the algorithm's output, it's described more as a validation of the algorithm's performance against human judgment rather than a comparative effectiveness study showing human reader improvement with AI assistance. No effect size of human improvement with AI vs. without is provided.
Standalone Performance:
- Yes, the reported average success rate of 80% or higher for SonoLyst 2nd Trimester IR and X and overall traffic light accuracy is a standalone measure of the algorithm's performance in sorting and grading.
Type of Ground Truth:
- Expert Consensus: A "sonographer review panel" (5 sonographers) provided the ground truth for both sorting and grading accuracy, based on a majority view where discrepancies arose with an initial sonographer's assessment.
Sample Size for Training Set:
- Total Images: 2.2 million
- Total Cine Loops: 2570
- Data collected across multiple geographical sites using different systems (GE Voluson V730, E6, E8, E10, Siemens Acuson S2000 and Hitachi Aloka).
How Ground Truth for Training Set was Established:
- Not explicitly described for the training set in this section. General statement that "Data used for both training and validation has been collected across multiple geographical sites." The detailed "truthing process" mentioned focuses on the verification data, not the much larger training set. It's common for training data to be annotated by experts, but the specifics are not provided here.

Summary

{0}------------------------------------------------

Image /page/0/Picture/0 description: The image contains the logo of the U.S. Food and Drug Administration (FDA). On the left is the Department of Health and Human Services logo. To the right of that is a blue square with the letters "FDA" in white. To the right of the blue square is the text "U.S. FOOD & DRUG ADMINISTRATION" in blue.

GE Medical Systems Ultrasound and Primary Care Diagnostics % Bryan Behn Regulatory Affairs Director GE Medical Systems Ultrasound and Primary Care Diagnostics, LLC. 9900 Innovations Dr. WAUWATOSA WI 53226

Re: K231965

Trade/Device Name: Voluson Expert 22, Voluson Expert 20, Voluson Expert 18 Regulation Number: 21 CFR 892.1550 Regulation Name: Ultrasonic Pulsed Doppler Imaging System Regulatory Class: Class II Product Code: IYN, IYO, ITX Dated: September 29, 2023 Received: October 2, 2023

Dear Bryan Behn:

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.

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).

October 30, 2023

{1}------------------------------------------------

Your device is also subject to, among other requirements, the Quality System (OS) 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 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-reportingcombination-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.

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-reportingmdr-how-report-medical-device-problems.

For comprehensive regulatory information about mediation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/medicaldevices/device-advice-comprehensive-regulatory-assistance) and CDRH Learn (https://www.fda.gov/training-and-continuing-education/cdrh-learn). Additionally, you may contact the Division of Industry and Consumer Education (DICE) to ask a question about a specific regulatory topic. See the DICE website (https://www.fda.gov/medical-device-advice-comprehensive-regulatoryassistance/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

510(k) Number (if known) K231965

Device Name

Voluson Expert 22, Voluson Expert 20, Voluson Expert 18

Indications for Use (Describe)

Modes of operation include: B, M, PW Doppler, CW Doppler, Color M Doppler, Power 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 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 General Electric (GE) logo. The logo consists of the letters 'GE' intertwined in a stylized script, enclosed within a blue circle. The circle has a wavy, decorative border, also in blue. The logo is simple and recognizable, representing the brand identity of General Electric.

GE Healthcare

510(k) Premarket Notification Submission

510(k) Summary K231965

In accordance with 21 CFR 807.92 the following summary of information is provided:

Date: Oct 23, 2023 Submitter: GE Healthcare [GE Healthcare Austria GmbH & Co OG] Tiefenbach 15 Zipf, Austria 4871 Primary Contact Bryan Behn Regulatory Affairs Director Person:

GE Medical Systems Ultrasound and Primary Care Diagnostics, LLC 9900 Innovation Dr. Wauwatosa, WI 53226 T:(262)247-5502 F:(414)918-8275

Thomas Reisenberger Secondary Contact Sr. Regulatory Affairs Leader Person: GE Healthcare Austria GmbH & Co OG T:(+43)7682-3800-332 F:(+43)7682 3800-47
Device: Trade Voluson Expert Series Name: Models: Voluson Expert 22, Voluson Expert 20, Voluson Expert 18 Common/Usual Ultrasound system Name: Class II Classification Names: Ultrasonic Pulsed Doppler Imaging System. 21CFR 892.1550, 90-IYN Product Code: Ultrasonic Pulsed Echo Imaging System, 21CFR 892.1560, 90-IYO
Primary Predicate K220358 Voluson Expert 22, Voluson Expert 20, Voluson Expert 18 Diagnostic Ultrasound System Device(s):
Diagnostic Ultrasound Transducer, 21 CFR 892.1570, 90-ITX

Classification Names:	Class II
Product Code:	Ultrasonic Pulsed Doppler Imaging System. 21CFR 892.1550, 90-IYNUltrasonic Pulsed Echo Imaging System, 21CFR 892.1560, 90-IYODiagnostic Ultrasound Transducer, 21 CFR 892.1570, 90-ITX
Classification Names:Product Code:	Class IIUltrasonic Pulsed Doppler Imaging System. 21CFR 892.1550, 90-IYNUltrasonic Pulsed Echo Imaging System, 21CFR 892.1560, 90-IYODiagnostic Ultrasound Transducer, 21 CFR 892.1570, 90-ITX
Device Description:	The systems are full-featured Track 3 ultrasound systems, primarily forgeneral radiology use and specialized for OB/GYN with particularfeatures for real-time 3D/4D acquisition. They consist of a mobileconsole 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 andhave comprehensive networking and DICOM capability. They utilize avariety of linear, curved linear, matrix phased array transducersincluding mechanical and electronic scanning transducers, whichprovide highly accurate real-time three-dimensional imagingsupporting 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. The RIC12-D is a new probe and is substantially equivalent to theRIC6-12-D, it is an incremental improvement in technology.
Intended Use:	The device is a general purpose ultrasound system intended for use byqualified and trained healthcare professionals. Specific clinicalapplications remain the same as previously cleared:
	Fetal/OB; Abdominal (including GYN, pelvic and infertilitymonitoring/follicle development); Pediatric; Small Organ (breast,testes, thyroid etc.); Neonatal and Adult Cephalic; Cardiac (adult andpediatric); Musculo-skeletal Conventional and Superficial; Vascular;Transvaginal (including GYN); Transrectal
	Modes of operation include: B, M, PW Doppler, CW Doppler, ColorDoppler, Color M Doppler, Power Doppler, Harmonic Imaging, CodedPulse, 3D/4D Imaging mode, Elastography, Shear Wave Elastographyand Combined modes: B/M, B/Color, B/PWD, B/Color/PWD,B/Power/ PWD, B/Elastography. The VolusonTM Expert 18, VolusonTMExpert 20, VolusonTM Expert 22 is intended to be used in a hospital or

{4}------------------------------------------------

Image /page/4/Picture/0 description: The image shows the General Electric (GE) logo. The logo consists of the letters 'GE' intertwined in a stylized script, enclosed within a circular frame. The logo is colored in a light blue hue, providing a clean and recognizable brand representation.

K230346 Voluson SWIFT, Voluson SWIFT+ Reference Predicatee Device(s):

medical clinic.

{5}------------------------------------------------

Image /page/5/Picture/0 description: The image shows the General Electric (GE) logo. The logo consists of the letters 'GE' in a stylized, cursive font, enclosed within a blue circle. The circle has a wavy or swirling pattern around the letters, giving it a dynamic and recognizable appearance.

The Voluson Expert Series (Voluson E22/20/18) employs the same Technology: fundamental scientific technology as its predicate devices.

Determination of Comparison to Predicates

Substantial The proposed Voluson Expert 22/20/18 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 RIC6-12-D, eM6CG3 and RIC12-D. 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 22/20/18 and predicate Voluson . Expert 22/20/18 systems have the same clinical intended use.
. The proposed Voluson Expert 22/20/18 and predicate Voluson Expert 22/20/18 systems have the same imaging modes.
. The proposed Voluson Expert 22/20/18 and predicate Voluson Expert 22/20/18 system transducers are equivalent. One new transducer RIC12-D was 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.
. The proposed Voluson Expert Series 22/20/18 and predicate Expert 22/20/18 system have similar capability in terms of performing measurements, capturing digital images, reviewing and reporting studies.
. The proposed Voluson Expert Series 22/20/18 and predicate systems have been designed in compliance with approved

{6}------------------------------------------------

Image /page/6/Picture/0 description: The image shows the General Electric (GE) logo. The logo consists of the letters 'GE' in a stylized, cursive font, enclosed within a blue circle. The circle has decorative swirls around the letters, giving it a classic and recognizable appearance.

electrical and physical safety standards.

There proposed Voluson Expert Series 22/20/18 and predicate . Expert 22/20/18 system Software Features are equivalent. Some minor improvements to the existing Software features have been implemented into the proposed system.
The proposed Voluson Expert Series 22/20/18 adds additional . AI software features SonoPelvicFloor2.0 (extension of existing Feature SonoPelvicFloor) , SonoAVC2.0 (extension of existing Feature SonoAVC), Fibroid Mapping (as part of Option SonoGYN) to the system. Additional the existing features SonoLyst/ Sonolyst Live have been improved.
The proposed Voluson Expert Series 22/20/18 adds additional ● software features BSI (Blood Speckle Imaging) and Ophthalmic Artery Measurement to the system.

{7}------------------------------------------------

AI Verification Summary:

SonoAVC2.0 (also described as Auto-Caliper):

The proposed Voluson Expert Series 22/20/18 BT24 feature SonoAVC2.0 migrated from already cleared (K230346) Voluson SWIFT, Voluson SWIFT+ software feature called Auto Caliper.

SonoPelvicFloor2.0

Summary test statistics or acceptance criteria

Summary test statistics or other test results including acceptance criteria or other information supporting the appropriateness of the characterized performance.

· Data used for both training and validation has been collected across multiple geographical sites using different systems and probe configuration to represent the variations in target population. The distribution of test data is as follows:

Total Volumes: 94

Distribution by Systems: Voluson Expert 22 (82), Voluson E8 (8), Voluson E6 (4) -
Distribution by Probes: RAB6-D (41), RIC5-9-D (21), RM7C (32) -
-Distribution by Countries: Austria (36), U.S.A (47), South Africa (4), Czech Republic (7)

· The verification for the SonoPelvicFloor2.0 AI feature is performed by clinical experts following a specific Workflow:

1. Import the entire data pool into the Archive on the system.
1. Load the datasets one-by-one from the Archive
1. Assess and document the volume cine quality.
1. Check if the MHD plane can be found in the volume cine with clinically required quality. If the plane cannot be found/tracked, then mark the corresponding result as 'N/A'.
1. Press the Init button on the UI.
1. Enter the SonoPelvicFloor tool.
1. Draw the OmniView line to capture the MHD plane at the first frame. Start the Live tracking algorithm as follows 4D - SonoPelvicFloor - Live Tracking
1. Observe the automated placement of the MHD plane during live tracking on all frames of the cine loop.
1. If the result was not deemed 'N/A' in step 4), then document the assessment (by internal clinical expert) as Success/No result/Failure.
1. The final dataset obtained after these steps should be stored back to the archive.

Expected result: On datasets that were marked as Good in Image/Cine Quality (IQ) 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.

Our algorithm is shown to yield an accuracy of 96% on good IQ datasets and 93% on challenging IQ cases.

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 4D volume Cines in *. vol or *. 4dv data formats. This preserves the flexibility to re-process data to our needs retrospectively during scan conversion.

{8}------------------------------------------------

Our train data consists of 983 distinct volumes from 616 individual patients volume were acquired in multiple phases of examination – Rest, Contraction and/or rest. Using these 983 volumes we generated 8847 images - 3 slices from each volume with three rotation angles per image. The distribution of 983 volumes is as follows:

-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)

Demographic distribution

The data is acquired from women examined in regular clinical practice across multiple geographical sites. We do not acquire explicit information regarding age or ethnicity of each patient because of privacy constraints around PHI. Any identifying information such as age and ethnicity are removed during data anonymization step. However, acquiring data from regular practice across multiple sites/countries/clinical practices encourages implicit diversity in age and ethnicity and patient characteristics distribution in the collected datasets.

Clinical Subgroups and Confounders

The clinical subgroups/confounders present in the evaluation pool is as follows:

1. Image Quality: Good image quality and Challenging image quality The accuracy of algorithm on the above subgroups is: Good IQ: 96.2% Challenging IQ: 93.3%
1. Evaluation Phase: Rest, Contraction or Valsalva The accuracy of algorithm on the above subgroups is: Rest : 100% Contraction: 93.75% Valsalva: 96.55%

Equipment and protocols

The testing data was collected from hospital centers as well as private practices following the standard clinical protocol across multiple GE systems and probe configurations. Summary of the evaluation pool distribution is as follows:

Total Volumes: 94

Distribution by Systems: Voluson Expert 22 (82), Voluson E8 (8), Voluson E6 (4) -
Distribution by Probes: RAB6-D (41), RIC5-9-D (21), RM7C (32) -
-Distribution by Countries: Austria (36), U.S.A (47), South Africa (4), Czech Republic (7)

Independence of Test-Train data

We maintain a database containing relevant information for all datasets used during training and verification of this feature in an SQL database. The datasets contained in the collections for training and verification are mutually exclusive and stem from a mutually exclusive list of patients.

{9}------------------------------------------------

In addition, we also perform testing on data acquired from site (namely U.S.A.) which did not contribute to the training data pool. The satisfactory performance on the new/unseen data distribution from these sites indicate towards the good generalizability of our models/algorithm.

Fibroid Mapping:

Summary test statistics or acceptance criteria

Summary test statistics or other test results including acceptance criteria or other information supporting the appropriateness of the characterized performance.

· Data used for training, validation, and verification (evaluation) has been collected across multiple geographical sites using different probe configurations to represent the variations in target population.

· The verification was performed by clinical experts according to the following protocol:

1. Invoke Fibroid Pre Mapping Menu. 2D: Do a scan, find the mid sagittal plane and enter 3D pre and select "Fibroid Mapping" OR 3D Find mid sagittal plane in Volume, enter Volume analysis and select "Fibroid Mapping".
1. Trace uterus midline on touchscreen
1. Freeze and acquire.
1. Invoke Fibroid Mapping Main
1. Start the auto segmentation after 3D acquired.
1. Check if the segmentation is satisfying. If not return to step 2). Otherwise, select "Add to Report" to save measurements to the current exam.
1. Semi-Automated Fibroid Segmentation: Position the curser over a fibroid to be measured on the section plane and click the Add/Rem button to add or remove fibroids. Repeat for all fibroids on current plane.
1. If all fibroids in the plane are segmented correctly, adjust the sectional plane with parallel shift and repeat step 7).
1. Select "Add to Report" to save the measurements to the current exam.
1. If segmentation quality of a fibroid is not satisfactory, activate manual fibroid segmentation (Add Fibroid Manually)
1. Select measurement tool "Ellipse" or "Double Calipe". Enter the start and end point of the long and short diameter using the trackball. Measure all wanted fibroids on current plane.
1. Adjust the plane with parallel shift to achieve next slice position and continue with step 7) or 10)
1. To save measurement to the current exam select "Add to Report".
The success rate of each AI component of the feature (uterus, endometrium, and fibroid segmentation) should be 70% or higher.
. Rationale for clinical adequacy:

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 are considered appropriate.

The original verification of the feature was performed on a data pool consisting of:

Total Volumes: 78

Systems: Voluson Expert Series
Probes: RIC5-9-D, RIC6-12-D
Countries: Egypt, Greece, Korea, Philippines, Romania, USA.

{10}------------------------------------------------

Primary verification - qualitative results:

Uterus	95%
Endometrium	89%
Fibroids	88%

We then performed a secondary evaluation including a quantitative assessment as well as a stratified performance analysis per confounders as follows:

Total Volumes: 74

Systems: Voluson Expert Series -
Probes: RIC5-9-D, RIC10-D -
Countries: Austria, Egypt, Germany, Greece, Korea, Philippines, Romania, USA -

Secondary evaluation - qualitative results:

Uterus	100%
Endometrium	91%
Fibroids	88%

The clinical requirements are thus successfully met in both verification rounds.

Further details of the quantitative assessment results can be found in the dedicated subsection below. All our experiments confirm the high accuracy as well as strong generalization capabilities of the Fibroid Mapping automation feature.

Data collection

A total of 779 unique volumes are utilized to train the model. With augmentations, 7790 volumes are generated.

A total of 31 unique volumes are utilized to validate the model. With augmentations, 310 volumes are generated.

We collected training data of the following types from hospital centers as well as private practices. We provided a dedicated data collection protocol explaining the required data needs to each provider.

Systems: Voluson E10, E8, E6, S10, S8, S6, P8. -
Probes: RIC5-9-D, RIC6-12-D, RM6C, RIC5-9A-RS, RIC5-9W-RS. -
-Countries: Austria, Egypt, France, Greece, Korea, Poland, Romania, USA.

For an overview of the data used for verification (evaluation), please see the preceding subsection of this summary.

{11}------------------------------------------------

Demographic distribution

Information about clinical subgroups and confounders

We considered the following relevant confounders to analyze the performance of our algorithms on subgroups: uterus position, endometrial phase, fibroid location, probes, and geographic regions. Our analysis shows that our algorithms perform consistently well across all the subgroups.

Quantitative evaluation

The data pool for quantitative analysis consists of 74 volumes. Data is provided by external clinical partners who de-identify the data before sharing it with GE HealthCare. Original data is collected in the form of 3D volumes in *. vol data format. This preserves the flexibility to re-process data to our needs retrospectively during scan conversion. The results show high accuracy of the algorithms and a correlation between DICE scores (i.e., Dice coefficient) and qualitative assessment by independent clinical experts.

Anatomy	DICE when successful	DICE when failed
Uterus	0.89 ± 0.03	n/a
Endometrium	0.70 ± 0.18	0.29 ± 0.27
Fibroids	0.70 ± 0.13	0.48 ± 0.17

Equipment and protocols

· Data is provided by external clinical partners who de-identified the data.
· Original data is collected in the form of 3D/4D volumes to preserve the flexibility to re-process data retrospectively during scan conversion.
· A data collection protocol is provided to each site to explain the required data needs.

Independence of Test-Train data

In addition, we also perform testing on data acquired from sites (namely, in Germany and Austria) which did not contribute to the training data pool. The satisfactory performance on the new/unseen data distribution from these sites indicate towards the good generalizability of our models/algorithm.

{12}------------------------------------------------

Sonolsyt/Sonolyst Live (existing Features was improved and extended)

The basic functionality of SonoLyst Live feature were already submitted as AI feature and cleared with the submission K220358.

With this submission (K231965) the following changes occurred compared to (K220358):

-Added views
- o Lower Limb, with following criteria: Magnification, Upper leg visible, Lower leg visible, foot visible.
- Upper Limb, with following criteria: Magnification, Upper arm visible, Forearm visible o
User Interface changes -
- The sagittal spine view contained the grading criteria "Sacrum visible", "Lumbar visible", o "Thoracic visible", and "Cervical visible". In order to simply the workflow for the user, these criteria are directly accessible to the user at view level as "Spine Sacrum", "Spine Lumber" "Spine Thoracic", and "Spine Cervical", without changing the underlaying AI algorithm.
- The Lower Limb view contains the grading criteria "Upper Leg visible", "Lower leg visible", o "Foot visible". In order to simply the workflow for the user, these criteria are directly accessible to the user at view level as "Upper Leg", "Lower Leg" and "Sagittal foot", without changing the algorithm.
- o The Upper Limb view contains the grading criteria "Upper Arm visible" and "Forearm visible". In order to simply the workflow for the user, these criteria are directly accessible to the user at view level as "Upper Arm", and "Forearm", without changing the algorithm.
- Manual Indication of left/right hands/feet/extremities added. o
- Status hexagon shown also while in Scan Assistant. O
- Automatically stores images in real-time during exam. o

Summary test statistics or other test results including acceptance criteria or other information supporting the appropriateness of the characterized performance.

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 2nd 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 2nd Trimester features is based on the average agreement between a sonographer panel and the output of the algorithm regarding Traffic light quality.
The average success rate of SonoLyst 2nd Trimester IR and X and overall traffic light accuracy is ● 80% or higher.

Data Collection and Distribution:

Systems: GE Voluson V730, E6, E8, E10, Siemens Acuson 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: 2570 ●

Quantitative evaluation:

For SonoLyst 2nd Trimester IR in total 42102 images are used for quantitative evaluation

For SonoLyst 2nd Trimester X in total 10424 images are used for quantitative evaluation

For SonoLystLive 2nd Trimester in total 5666 images are used for quantitative evaluation

Information about clinical subgroups and confounders

{13}------------------------------------------------

In order to demonstrate the generalization performance of 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.

Equipment and protocols

Equipment: GE Voluson V730, E6, E8, E10, Siemens Acuson S2000 and Hitachi Aloka

Data was collected from routine clinical practice in hospitals and private practice during mid-trimester examinations, with a gestational age range of 18-24 weeks.

Information about the reference standard and dataset ("truthing process"):

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.
1. The images were sorted and graded by ScanNav AutoCapture Second Trimester. This process resulted in some images being reclassified during sorting.
1. Where they differed from the ground truth, the sorted images from step 2 were reviewed by a 5sonographer 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.

1. Where they differed from the ground truth. the graded images from step 1 were reviewed by a 5sonographer review panel, in order to determine the grading accuracy of the system.
  Conclusion: GE Healthcare considers the Voluson Expert 20 and Expert 22 to be as safe, as effective, and performance is substantially equivalent to the predicate device(s).

{14}------------------------------------------------

Image /page/14/Picture/0 description: The image shows the General Electric (GE) logo. The logo consists of the letters 'g' and 'e' intertwined in a stylized script, enclosed within a circular frame. The logo is colored in a light blue hue, and the background is white.

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 22/20/18 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 (2022a), Digital Imaging and Communications in Medicine (DICOM) Set. (Radiology)

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)

Transducer materials and other patient contact materials are biocompatible.

{15}------------------------------------------------

Image /page/15/Picture/0 description: The image shows the General Electric (GE) logo. The logo consists of the letters 'G' and 'E' intertwined in a stylized, cursive font. The logo is enclosed within a circular border, and the entire design is rendered in a light blue color.

Summary of Clinical Tests:

The subject of this premarket submission, Voluson Expert Series 22/20/18 did not require clinical studies to support substantial equivalence.

GE Healthcare considers the Voluson Expert Series 22/20/18 to be as Conclusion: safe, as effective, and performance is substantially equivalent to the predicate device(s).

Regulation Number and Section

§ 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.