(180 days)
The intended use of EPIQ Ultrasound Diagnostic System is diagnostic ultrasound imaging and fluid flow analysis of the human body, with the following indications for use:
Abdominal, Cardiac Adult, Cardiac other (Fetal), Cardiac Pediatric, Cerebral Vascular, Cephalic (Adult), Cephalic (Neonatal), Fetal/Obstetric, Gynecological, Intraoperative (Vascular), Intraoperative (Cardiac), intra-luminal, intra-cardiac echo, Musculoskeletal (Conventional), Musculoskeletal (Superficial), Ophthalmic, Other: Urology, Pediatric, Peripheral Vessel, Small Organ (Breast, Thyroid, Testicle), Transesophageal (Cardiac), Transrectal, Transvaginal, Lung.
The clinical environments where EPIQ Series Diagnostic Ultrasound Systems can be used include clinics, hospitals, and clinical point-of-care for diagnosis of patients.
When integrated with Philips EchoNavigator, the systems can assist the interventionalist and surgeon with image guidance during treatment of cardiovascular disease in which the procedure uses both live X-ray and live echo guidance.
The systems are intended to be installed, used, and operated only in accordance with the safety procedures and operating instructions given in the product user information. Systems are to be operated only by appropriately trained healthcare professionals for the purposes for which they were designed. However, nothing stated in the user information reduces your responsibility for sound clinical judgement and best clinical procedure.
The purpose of this Traditional 510(k) Pre-Market Notification is to introduce the 3D Auto TV (Tricuspid Valve) software application onto the EPIQ Series Diagnostic Ultrasound Systems.
The 3D Auto TV software enables semi-automated quantification of the tricuspid valve. At a high level, this is accomplished through automatically derived measurements from a segmented model of the tricuspid valve annulus formed by the software through model-based segmentation of the acquired ultrasound images.
The 3D Auto CFQ software provides semi-automated quantification of Mitral Requrgitation (MR) volume and peak flow rate based on 3D color flow images. This application uses a known fluid dynamic model of flow that is adapted to the acquired color information. This allows quantitative assessment of mitral valve leakage during systole. The derived result supports the assessment of mitral regurgitation volume and peak flow rate.
No hardware changes to the EPIQ systems are required when using the 3D Auto TV and 3D Auto CFQ, and existing, cleared Philips transducer(s) are used for the software applications.
The software applications are supported by all EPIQ models running software version 11.0 or higher including EPIQ CVx/CVxi. EPIQ Elite Advanced. EPIQ 7. EPIQ 5. The software applications are both associated with the cardiac adult indication.
The provided text describes two software applications, 3D Auto TV and 3D Auto CFQ, for the Philips EPIQ Series Diagnostic Ultrasound System. It details their acceptance criteria and the studies conducted to demonstrate their performance.
1. Table of Acceptance Criteria & Reported Device Performance
| Feature/Metric | Acceptance Criteria | 3D Auto TV Reported Performance | 3D Auto CFQ Reported Performance |
|---|---|---|---|
| 3D Auto TV | |||
| LoA for Annulus Size | Within ± 46% (for TEE/TTE combined) | Confidence intervals for the limits of agreement were within ± 46% | N/A |
| LoA for Annulus Shape | Within ± 52% (for TEE/TTE combined) | Confidence intervals for the limits of agreement were within ± 52% | N/A |
| Relative Bias (Distance) | Within +/- 17.37% | Met (within +/- 17.37%) | N/A |
| Relative Bias (Circumference) | Within +/- 23.68% | Met (within +/- 23.68%) | N/A |
| In-silico Phantom Mean Error | Within +/- 1% | Mean relative error of measurement primitives: within +/- 1% | N/A |
| In-silico Phantom LoA | Within +/- 5% | Limits of agreement of measurement primitives: within +/- 5% | N/A |
| 3D Auto CFQ | |||
| Maximum Allowable Difference (Δ) for Regurgitant Volume LoA | 61.6 ml | N/A | Lower LoA: -49.29; Upper LoA: 25.09. |
| 95% CI for LoA: Lower end (-58.37 - -40.20), Upper end (16.01 - 34.18). | |||
| The largest absolute difference is 58.37 mL, which is within the 61.6 mL acceptance criteria. | |||
| Mean Difference (Bias) | Within +/- 19.2 ml | N/A | Met. |
| Pearson's Correlation vs 2D PISA (Peak Regurgitant Flow) | > 0.8 (for both fully-automated and semi-automated modes) | N/A | Upper and lower bounds of the 95% confidence interval for Pearson's correlation exceeded > 0.8. |
2. Sample Size for Test Set and Data Provenance
- 3D Auto TV: The text does not explicitly state the numerical sample size (number of patients or clips) used for the test set. It mentions "cardiac clips were used" and "Subjects whose clips contributed to the study represented a broad range of demographics, body habitus, and their severity of tricuspid regurgitation." The provenance is not explicitly stated (e.g., country of origin), but it is implied to be clinical data (transthoracic and transesophageal echocardiography (TTE, TEE) cardiac clips). It is a retrospective study, as pre-recorded clips were used.
- 3D Auto CFQ: The text does not explicitly state the numerical sample size (number of patients or clips) used for the test set. The provenance is not explicitly stated (e.g., country of origin), but it is implied to be clinical data. It is a retrospective study, as the results were compared to pre-existing Cardiac Magnetic Resonance Imaging (CMR) data.
3. Number of Experts and Qualifications for Ground Truth
- 3D Auto TV:
- Number of Experts: 3 clinical experts (reviewers).
- Qualifications: Not explicitly stated beyond "clinical experts (reviewers)."
- 3D Auto CFQ: The ground truth was Cardiac Magnetic Resonance Imaging (CMR) regurgitant volume (RVol). No human experts were used to establish this specific ground truth; rather, it's considered a gold standard imaging modality. For comparison to the PISA method, clinical experts would have performed the PISA measurements, but their number and qualifications are not specified here.
4. Adjudication Method for the Test Set
- The text does not explicitly state an adjudication method (e.g., 2+1, 3+1). For 3D Auto TV, the ground truth was established by "manual measurements by the same reviewers performed within 4D Cardio-View application (K213544)." This implies individual or consensus measurements, but a formal adjudication process is not detailed.
- For 3D Auto CFQ, the primary ground truth was CMR, which does not involve human adjudication in the same way. When compared to the 2D PISA methodology, it's implied that such measurements were collected.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
- No explicit MRMC comparative effectiveness study demonstrating improved human reader performance with AI assistance vs. without AI assistance was reported. The studies described focus on the standalone performance of the AI software against human manual measurements or other gold standard modalities.
6. Standalone (Algorithm Only) Performance Study
- Yes, standalone performance studies were conducted for both 3D Auto TV and 3D Auto CFQ.
- 3D Auto TV: The study evaluated the "automation performance of the 3D Auto TV software" and compared its results to manual measurements (ground truth) performed within the 4D Cardio-View application.
- 3D Auto CFQ: The study evaluated the "performance of the 3D Auto CFQ software" by comparing its regurgitant volume output to CMR (ground truth) and its peak flow rate output to the 2D PISA methodology.
7. Type of Ground Truth Used
- 3D Auto TV: Manual measurements performed by 3 clinical experts using the 4D Cardio-View application (K213544). This can be classified as expert consensus/manual measurement from a predicate device.
- 3D Auto CFQ:
- For regurgitant volume: Cardiac Magnetic Resonance Imaging (CMR) regurgitant volume (RVol), which is considered a clinical gold standard.
- For peak flow rate: 2D PISA methodology. While PISA is a widely accepted method in echocardiography, it is also a measurement based on assumptions and manual input, thus falling under a blend of accepted clinical methodology and manual measurement.
8. Sample Size for the Training Set
- The provided document does not specify the sample size for the training set for either 3D Auto TV or 3D Auto CFQ. It only states that the algorithms use "machine learning algorithm without user interaction" for contour generation.
9. How the Ground Truth for the Training Set Was Established
- The provided document does not explicitly describe how the ground truth for the training set was established for either 3D Auto TV or 3D Auto CFQ. It mentions "model-based segmentation" for 3D Auto TV and "machine learning algorithm" for both, implying a supervised learning approach where annotated data would have been used for training, but the specifics of that annotation process are not detailed.
§ 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.