Search Results

The Voluson SWIFT, Voluson SWIFT+ is a general-purpose diagnostic ultrasound system intended for use by qualified and trained healthcare professionals that are legally authorized or licensed by law in the country, state or other local municipality in which he or she practices for ultrasound imaging, measurement, display and analysis of the human body and fluid. The users may or may not be working under supervision or authority of a physician. Voluson SWIFT, Voluson SWIFT+ clinical applications include: Fetal Obstetrics; Abdominal (including renal and GYN/Pelvic); Pediatio; Small Organ (Breast, Testes, Thyroid, etc.); Neonatal Cephalic; Cardiac (Adult and Pediatric); Peripheral Vascular (PV); Musculo-skeletal Conventional and Superficial; Transrectal(including UrologyProstate) (TR); Transvaginal (TV).

Mode of operation include: B, M, AMM (Anatonical M-Mode), PW Doppler, CW Doppler, Color Doppler, Color M Doppler, Power Doppler, HD-Flow (High Definition-Flow), Harmonic Imaging, Coded Pulse, 3D/4D Inaging mode, Elastography, B-Flow and Combined modes: BM, B/ Color, B/PWD, B/Power/PWD. The Voluson SWIFT / Voluson SWIFT+ are intended to be used in a hospital or medical clinic.

Device Description

The subject device is a Track 3 device, primarily intended for general-purpose radiology evaluation and specialized for OB/GYN with particular features for real-time 3D/4D acquisition. The Voluson SWIFT, Voluson SWIFT+ provide digital acquisition, processing and display capability. Voluson SWIFT, Voluson SWIFT+ consist of a mobile console with control panel, full touch monitor, optional image storage and printing devices. It provides high-performance ultrasound imaging and analysis and have comprehensive networking and DICOM capability. It utilizes a variety of linear, curved linear, matrix phased array transducer including mechanical and electronic scanning transducers which provide accurate real-time three-dimensional imaging supporting all standard acquisition modes.

AI/ML Overview

Here's a breakdown of the acceptance criteria and the study that proves the device meets them, based on the provided text:

Acceptance Criteria and Device Performance for Auto-Caliper:

Acceptance Criteria	Reported Device Performance
Success rate of the AI feature (Auto-Caliper) for 2D caliper placement is 70% or higher.	The reported success rate is not explicitly stated as a single percentage, but the aggregate data on absolute difference between AI predicted diameter and ground truth diameter can be used to infer performance. The provided table shows that 85.4% of cases have an absolute difference less than or equal to 2.0 mm (5.3 + 32.8 + 22.1 + 25.2 = 85.4%), and 5.3% of cases have an absolute difference less than 0.1mm. The study's goal was to demonstrate performance, and while a direct "success rate" percentage isn't given in relation to the 70% criteria, the detailed error distribution provides a granular view of accuracy. If "success" is defined by a certain tolerance (e.g., within 2mm), then the performance is high.

Acceptance Criteria

Reported Device Performance

Success rate of the AI feature (Auto-Caliper) for 2D caliper placement is 70% or higher.

The reported success rate is not explicitly stated as a single percentage, but the aggregate data on absolute difference between AI predicted diameter and ground truth diameter can be used to infer performance. The provided table shows that 85.4% of cases have an absolute difference less than or equal to 2.0 mm (5.3 + 32.8 + 22.1 + 25.2 = 85.4%), and 5.3% of cases have an absolute difference less than 0.1mm. The study's goal was to demonstrate performance, and while a direct "success rate" percentage isn't given in relation to the 70% criteria, the detailed error distribution provides a granular view of accuracy. If "success" is defined by a certain tolerance (e.g., within 2mm), then the performance is high.

Study Details for Auto-Caliper Feature:

2. Sample Size Used for the Test Set and Data Provenance:
* Test Set Sample Size: 67 volumes, with a total of 134 follicles evaluated (2 follicles per volume).
* Data Provenance: Data collected across multiple geographical sites: Germany, India, Spain, United Kingdom, USA. The data was collected from women examined in regular clinical practice. It was de-identified by external clinical partners.
* Retrospective/Prospective: The data appears to be retrospective, as it was "collected from patients from regular clinical practice" and then "de-identified."

3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications:
* Number of Experts: Not explicitly stated as a single number. The verification for the Auto-Caliper AI feature was performed by "clinical experts" following a specific protocol. The "truthing process" for training data mentions "clinical experts" and a "senior sonographer" reviewing a random subset. It is reasonable to infer that experts with similar qualifications were used for the test set ground truth.
* Qualifications: "Clinical experts" and a "senior sonographer." Specific experience levels (e.g., "10 years of experience") are not provided.

4. Adjudication Method for the Test Set:
* Method: The outputs were evaluated by the clinical expert and the assessment was documented as Pass/No result/Fail. This suggests a qualitative assessment by individual experts rather than a specific multi-reader consensus method like 2+1 or 3+1 for resolving discrepancies. However, the quantitative evaluation involved calculating the deviation from manual measurements, which likely served as the definitive ground truth for performance metrics.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:
* Was one done? No. The document does not describe an MRMC comparative effectiveness study where human readers' performance with and without AI assistance was compared.

6. Standalone (Algorithm Only) Performance Study:
* Was one done? Yes. The provided data is a standalone performance evaluation of the Auto-Caliper AI feature, comparing its predictions against ground truth (manual measurements by experts). The evaluation directly reports the deviation of the AI predictions from the manual measurements.

7. Type of Ground Truth Used:
* Type: Expert consensus / Manual measurements. The ground truth was established by "clinical experts" who manually placed calipers following a specific protocol. The "deviation of the measurements predicted by the Auto-Caliper tool from the manual measurements" confirms that expert manual measurements served as the reference.

8. Sample Size for the Training Set:
* Sample Size: 223 volumes.

9. How the Ground Truth for the Training Set Was Established:
* Method: A "curation protocol has been developed by clinical experts to be followed by curators." Additionally, "during and after the data curation process, a senior sonographer reviewed a random subset of the curated dataset for clinical accuracy." This indicates a structured process involving clinical expert input and review to establish the ground truth for the training data.

Ask a Question

Ask a specific question about this device

K Number

K201828

Device Name

Voluson SWIFT, Voluson SWIFT+

Manufacturer

GE Medical Systems Ultrasound and Primary Care Diagnostics

Date Cleared

2020-10-11

(101 days)

Product Code

Regulation Number

Type

Panel

Reference & Predicate Devices

N/A

Intended Use

The Voluson SWIFT, Voluson SWIFT+ is a general-purpose diagnostic ultrasound system intended for use by qualified and trained healthcare professionals for ultrasound imaging, measurement, display and analysis of the human body and fluid. Voluson SWIFT, Voluson SWIFT+ clinical applications include: Fetal/Obstetrics; Abdominal (including renal and GYN/Pelvic); Pediatric; Small Organ (Breast, Thyroid, etc.); Neonatal Cephalic; Adult Cephalic; Cardiaς (Adult and Pediatric); Peripheral Vascular (PV); Musculo-skeletal Conventional and Superficial; Transrectal(including Urology/ Prostate) (TR): Transvaginal (TV).

Mode 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 and Combined modes: B/M, B/Color, B/PWD, B/ Power/PWD. The Voluson SWIFT / Voluson™ SWIFT+ are intended to be used in a hospital or medical clinic.

Device Description

AI/ML Overview

The provided text is a 510(k) summary for the GE Voluson SWIFT, Voluson SWIFT+ diagnostic ultrasound system. It outlines the device's technical characteristics, intended use, and comparison to predicate devices to establish substantial equivalence.

However, the document explicitly states that clinical studies were NOT required or performed to support the substantial equivalence of the Voluson SWIFT, Voluson SWIFT+.

Therefore, I cannot provide the detailed information requested regarding acceptance criteria and performance studies, including:

A table of acceptance criteria and reported device performance.
Sample sizes and data provenance for test sets.
Number and qualifications of experts for ground truth.
Adjudication method for the test set.
MRMC comparative effectiveness study results.
Standalone performance.
Type of ground truth used.
Sample size for the training set.
Method for establishing ground truth for the training set.

The submission focuses entirely on non-clinical tests to demonstrate safety and effectiveness, based on compliance with electrical, mechanical, and safety standards, and by showing substantial equivalence to previously cleared predicate devices through similar technology, intended use, imaging modes, and acoustic power levels.

The relevant section in the document states:
"Summary of Clinical Tests: The subject of this premarket submission. Voluson SWIFT, Voluson SWIFT+, did not require clinical studies to support substantial equivalence."

Ask a Question

Ask a specific question about this device

Page 1 of 1