(64 days)
The SuperSonic Imagine AIXPLORER® ultrasound system and transducer are intended for general purpose pulse echo ultrasound imaging, Doppler fluid flow analysis of the human body, and tissue elasticity imaging of soft tissues.
The SuperSonic Imagine AIXPLORER® ultrasound system is indicated for use in the following applications: Abdominal, Small Organs, Musculoskeletal, Superficial Musculoskeletal, Vascular, Peripheral Vascular, GYN, Pelvic, Pediatric, Urology, Trans-vaginal and Neonatal Cephalic.
The system also provides the ability to measure anatomical structures (Abdominal, Small Organs, Musculoskeletal, Superficial Musculoskeletal, Peripheral Vascular, GYN, Pelvic, Pediatric, Urology, Trans-rectal, Trans-vaginal, Neonatal Cephalic).
The SuperSonic Imagine AIXPLORER® system is a cart based ultrasound imaging system used to perform invasive and non-invasive diagnostic general purpose ultrasound imaging studies. The system contains a scan converter and can be coupled to a variety of linear, curved, microconvex, and motorized linear array transducers to produce images, which are displayed on a LCD monitor. An adjustable control panel with integrated touch screen allows the user to perform an ultrasound exam quickly and efficiently in accordance with ALARA principles. The system also allows the user to perform measurements, capture images to digital memory or to an external device (such as a printer), and review diagnostic studies in the form of a report. The system functions in a manner identical to the predicate devices and transducers for the imaging modes: B-Mode, Color Flow, Pulsed Wave Doppler, Harmonic Imaging, Amplitude Doppler, 3D imaging, Panoramic Imaging and for ShearWave™ elastography. The addition of the quantification tool allows the user to read the average shear wave propagation speed.
Here's a summary of the acceptance criteria and study information for the Aixplorer® Diagnostic Ultrasound System (K132274), based on the provided text:
Acceptance Criteria and Device Performance
| Acceptance Criteria | Reported Device Performance |
|---|---|
| Shear Wave Speed Bias | Derived as the difference between the mean of five independent SWE shear wave speed measurements and the nominal shear wave speed, normalized by the nominal shear wave speed and expressed as a percentage. Specific percentage not provided, but generally expected to be low to indicate accuracy. |
| Shear Wave Speed Precision | Derived as the standard deviation of five independent SWE shear wave speed measurements normalized by the mean of the five independent SWE measurements, and expressed as a percentage. Specific percentage not provided, but generally expected to be low to indicate reproducibility. |
| QBox Measurement Accuracy (vs. Matlab) | The comparison between the SWE QBox/ROI measurements performed by the Aixplorer versus the results obtained by performing the same measurements in Matlab were within 5%. |
| Acoustic Output Limits | Complies with FDA guideline limits (September 9, 2008, 510(k) diagnostic ultrasound guidance) and NEMA UD 3 (2004), NEMA UD 2 (2004). |
- Mechanical Index: 1.9 (Maximum)
- TIS/TIB: 0.1 - 4.0 (Range)
- ISPTA(d): 720 mW/cm2
- ISPPA(d): 0 - 700 W/cm2
(Limits are the same as predicate Track 3 devices.) |
| General Safety and Electrical Standards | Designed to comply with IEC 60101 -1 (2005), IEC 60601-2-37 (2007), and IEC 60601-1-2 (2000). |
Study Information
2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
- Sample Size for Shear Wave Speed Tests: Four different cylindrical target types of a CIRS 049A Elasticity Quality Assurance phantom were used. For each target, five independent SWE shear wave speed measurements were taken. (Total of 20 measurements).
- Sample Size for QBox Measurement Tests: Not explicitly stated as a number of samples, but presumably refers to measurements performed on the same phantom targets or similar controlled environments as the shear wave speed tests.
- Data Provenance: The tests were "non clinical testing performed on the modified Aixplorer." This indicates prospective bench testing using a phantom. There is no information regarding country of origin for this test data beyond the manufacturer being in France.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)
- The ground truth for the test set was established using a CIRS 049A Elasticity Quality Assurance phantom, which has "nominal shear wave speeds" for its targets, implying a pre-defined or manufacturer-provided ground truth.
- For the QBox Measurement Tests, the comparison was against "results obtained by performing the same measurements in Matlab." This suggests the ground truth was derived from a computational standard, not expert consensus.
- Therefore, no human experts were involved in establishing the ground truth for these non-clinical performance tests.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
- No human adjudication method was used, as the study was a non-clinical, phantom-based bench test comparing device measurements to known phantom properties or computational results (Matlab).
5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance
- No MRMC comparative effectiveness study was done. This 510(k) summary focuses on the technical performance and safety of the ultrasound system itself, not on the improvement of human readers with AI assistance. The "AI" component mentioned (ShearWave™ elastography, quantification tool) is integrated into the device's imaging and measurement capabilities rather than being a separate AI-based diagnostic aid for human review.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
- Yes, the non-clinical performance data represents "standalone" algorithm performance in controlled bench tests. The tests assessed the device's ability to accurately measure shear wave speed and QBox values independently.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
- The primary type of ground truth used was phantom-based nominal values (for shear wave speed) and computational standards (comparison to Matlab for QBox measurements).
8. The sample size for the training set
- This document describes non-clinical performance testing for a diagnostic ultrasound system. It does not mention any "training set" as it would for a machine learning or AI algorithm in the typical sense of needing data to learn from. The device's "AI" functionalities (ShearWave™ elastography) are inherent in its design and physics-based measurements rather than being trained on a dataset.
9. How the ground truth for the training set was established
- As no training set is mentioned or implied for this device's submission, this question is not applicable based on the provided text.
§ 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.