Search Results

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

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.

Ask a specific question about this device

The intended use of Philips EPIQ series diagnostic ultrasound systems 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. Intra-cardiac Echo. Intra-luminal, Intraoperative (Vascular). Intraoperative (Cardiac), Musculoskeletal (Conventional), Musculoskeletal (Superficial), Other: Urology, Pediatric, Peripheral Vessel, Small Organ (Breast, Thyroid, Transesophageal (Cardiac), Transrectal, Transvaginal, Lung,

The clinical environments where Philips EPIQ 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 intended use of the Affiniti Series Diagnostic Ultrasound Systems 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), Musculoskeletal (Conventional), Musculoskeletal), Other: Urology, Pediatric, Peripheral Vessel, Small Organ (Breast, Thyroid, Testicle), Transesophageal (Cardiac), Transrectal, Transvaginal, Lung.

The clinical environments where the Affiniti Diagnostic Ultrasound Systems can be used include Clinics, and clinical point-of-care for diagnosis of patients.

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 healtheare professionals for the purposes for which they were designed. However, nothing stated in the user information reduces your responsibility for sound clinical judgment and best clinical procedure.

Philips EPIQ and Affiniti Series Diagnostic Ultrasound Systems are durable, reusable capital equipment medical devices intended for high-resolution general imaging; interventional radiology, cardiology, vascular, obstetrics, and gynecology applications; and fluid flow analysis. They are intended to be used by trained professionals at various settings of patient care such as clinical admission, periodic evaluations, prior to hospitalization discharge, and/or academic research, via maneuverable caster wheels or mobile handheld components.

The purpose of this Traditional 510(k) Pre-Market Notification is to introduce the Auto Measure software-only feature for use on the Philips EPIQ and Affiniti Series Diagnostic Ultrasound Systems. The Philips Auto Measure feature provides the end user with semiautomated functionality for a subset of 2D and Doppler measurements currently available on the Philips EPIQ and Affiniti systems when performing or reviewing an adult transthoracic echocardiography (TTE) with simultaneously acquired electrocardiogram (ECG). The AI/MLenabled algorithm is designed to produce semi-automated and editable measures.

The provided text is a 510(k) summary for the Philips EPIQ and Affiniti Ultrasound Systems with the new "Auto Measure" feature. It focuses on demonstrating substantial equivalence to predicate devices. However, the document does not contain the detailed performance data, acceptance criteria, sample sizes, expert qualifications, or ground truth establishment methods typically found in a clinical study report or a more comprehensive validation study.

The "Performance Data" section in the K211597 summary only broadly states that non-clinical testing included a "Performance Validation Study" and that "Software Verification and Validation testing were used to support substantial equivalence." It also mentions "adherence to the aforementioned Philips internal processes."

Therefore, I cannot extract the specific information requested in your prompt based on the provided text. The document clearly omits the granular details of the validation study.

Here's what the document does tell us about the study, albeit at a high level:

• Study Type: A "Performance Validation Study" was conducted for the Auto Measure software, alongside Software Verification and Validation testing.
• Purpose: To demonstrate that the Auto Measure feature meets defined requirements and performance claims, and to support substantial equivalence to the currently marketed manual measuring options.
• What was tested: The "Auto Measure" software-only feature, which provides semi-automated functionality for a subset of 2D and Doppler measurements during adult transthoracic echocardiography (TTE) with simultaneously acquired ECG. The end user can edit, accept, or reject the measurements.

Without the actual performance validation study report or more detailed information, I cannot fill in the table or answer most of your specific questions.

If this information were available, here's how I would attempt to reconstruct it:

Hypothetical Acceptance Criteria and Device Performance (Based on common FDA expectations for such devices, NOT from the provided text)

Missing Information from the Provided Document:

1. A table of acceptance criteria and the reported device performance: NOT PROVIDED. The document only states that testing demonstrated the feature "meets the defined requirements and performance claims" but does not enumerate these.
2. Sample sizes used for the test set and the data provenance: NOT PROVIDED.
   • Test Set Sample Size: Unknown
   • Data Provenance: Unknown (country of origin, retrospective or prospective)
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: NOT PROVIDED. The document refers to "manual measuring options" as a comparison, implying human expert measurements, but doesn't detail the ground truth process.
   • Number of Experts: Unknown
   • Qualifications: Unknown
4. Adjudication method (e.g., 2+1, 3+1, none) for the test set: NOT PROVIDED.
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: NOT PROVIDED. The document discusses "semi-automated and editable measures" which implies human-in-the-loop, but doesn't describe an MRMC study or effect size. It only states the AI offers "semi-automated functionality" compared to "manual" on predicate devices.
6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done: The "Auto Measure" feature is described as providing "semi-automated and editable measures," suggesting human oversight is intended. A purely standalone performance might have been part of the internal validation, but it's not explicitly detailed as a primary regulatory performance endpoint in this summary.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.): Based on the comparison to "manual measuring options," the ground truth likely involved expert human measurements (manual measurements by sonographers/cardiologists). Whether this was a single expert, consensus, or other method is NOT SPECIFIED.
8. The sample size for the training set: NOT PROVIDED.
9. How the ground truth for the training set was established: NOT PROVIDED.

In conclusion, while the document confirms that performance validation was conducted and software V&V was performed in accordance with FDA guidance, it lacks all the granular details about the study design and results that your prompt requested. This level of detail is typically found in the full 510(k) submission and supporting technical reports, not usually in the summary made publicly available.

Ask a specific question about this device