Search Results

Collaboration Live is indicated for remote console access of the Philips ultrasound system for diagnostic image viewing and review, consultation, guidance, support, and education in real time. Access must be granted by the healthcare professionals operating the ultrasound system. Compliance with the technical and operator requirements specified in the User Manual is required.

It is the responsibility of the healthcare professionals at the remote client to ensure image quality, display contrast, and ambient light conditions are consistent with the generally accepted standards of the clinical application.

Collaboration Live is software-based communication feature integrated with Philips Diagnostic Ultrasound Systems. Collaboration Live, together with remote-client Reacts software, enables two-way communication of text, voice, image, and video information between an ultrasound local system operator and a remote healthcare professional on a Windows, iOS, Android, or Chrome platform. Collaboration Live-Reacts facilitates: 1) remote diagnostic viewing and review, 2) remote clinical training and education, 3) remote peer-topeer collaboration, and 4) remote service support. Collaboration Live functionality includes a remote-control feature in which the ultrasound local system operator may grant a qualified remote user control of the ultrasound system parameters via a virtual control panel and virtual touch screen. By meeting the technical, operator, and environment requirements specified in the User Manual, healthcare professionals, using Reacts, may provide clinical diagnoses from a remote location as they would directly on the ultrasound system.

The provided text describes a 510(k) premarket notification for Philips Ultrasound, Inc.'s "Collaboration Live" device, and its substantial equivalence to a predicate device. However, the document does not contain the specific details about acceptance criteria or a detailed study proving the device meets those criteria, as typically found in a clinical validation study.

The document states:

• "Validation testing was completed and produced under Philips's design controls procedures that comply with 21 CFR 820.30. Validation Testing, with pre-determined criteria, was conducted to evaluate and demonstrate the equivalency of Collaboration Live used on Windows, iOS, Android, and Chrome platforms."
• "The results of the design control activities support that the software, which expands the compatible platforms and adds three features, does not raise new questions of safety or effectiveness. In addition to labeling, testing performed demonstrates that the Collaboration Live software meets the defined requirements and performance claims and are substantially equivalent to the predicate software (K201665)."

This implies that some form of validation against pre-determined criteria was performed, but the specifics of those criteria (e.g., quantitative performance metrics like accuracy, sensitivity, specificity, resolution, latency, etc., for diagnostic image viewing and review), the study design, sample sizes, ground truth establishment, or expert involvement are not included in this FDA 510(k) summary document.

The 510(k) summary focuses on demonstrating substantial equivalence, primarily by expanding compatible platforms and adding new features (Network Indicator, Remote Image Quality, Remote User Measurement) while maintaining the original indications for use. It asserts that these changes do not raise new questions of safety or effectiveness.

Therefore, many of the requested details cannot be extracted from this document.

Here's what can be inferred or explicitly stated based on the provided text, and what is missing:

Acceptance Criteria and Device Performance:

• 1. A table of acceptance criteria and the reported device performance:
  • Acceptance Criteria: Not explicitly stated in quantitative terms within this document. The document refers to "pre-determined criteria" and "defined requirements and performance claims" but does not list them. Given the device's function (remote console access for diagnostic image viewing and review, consultation, guidance, support, and education), the acceptance criteria would likely relate to image quality (resolution, clarity, color representation), latency, reliability of connection, and functionality of remote control features, all assessed for clinical applicability.
  • Reported Device Performance: The document only states that "testing performed demonstrates that the Collaboration Live software meets the defined requirements and performance claims." Specific performance metrics are not provided.

Study Details:

• 2. Sample sizes used for the test set and the data provenance: Not provided in the document.
  • Data Provenance: Not provided.
  • Retrospective/Prospective: Not specified.
• 3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not provided. The document mentions "healthcare professionals at the remote client" being responsible for ensuring image quality, but this refers to the user's responsibility, not the study's ground truth establishment.
• 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 explicitly stated and highly unlikely for this device. This device is a remote access/collaboration tool, not an AI diagnostic algorithm intended to improve human reader performance on a diagnostic task. Its validation would focus on the fidelity and functionality of the remote access.
• 6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not applicable. This device is inherently a human-in-the-loop system for real-time collaboration. The "alone" aspect would be assessing the technical performance of the remote viewing and control, which is implied by "Validation Testing, with pre-determined criteria, was conducted to evaluate and demonstrate the equivalency of Collaboration Live used on Windows, iOS, Android, and Chrome platforms."
• 7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.): Not specified. For a device like this, ground truth would likely involve technical performance metrics (e.g., objective image quality assessments, latency measurements, functional tests of remote controls) alongside subjective assessments by clinicians regarding its usability and diagnostic adequacy when viewing images remotely.
• 8. The sample size for the training set: Not applicable and not provided. This is not an AI/ML device that requires a "training set" in the typical sense for learning patterns from data. Its development involves software engineering and functional testing.
• 9. How the ground truth for the training set was established: Not applicable and not provided.

Summary of Device and its Purpose:

• Device Name: Collaboration Live
• Manufacturer: Philips Ultrasound, Inc.
• Regulation Name: Medical image management and processing system
• Regulatory Class: Class II (Product Codes: LLZ, IYN, IYO)
• Indications for Use: Remote console access of the Philips ultrasound system for diagnostic image viewing and review, consultation, guidance, support, and education in real time. Access must be granted by the healthcare professionals operating the ultrasound system.
• Key Features (as per this submission): Expansion of compatible platforms (Windows, iOS, Android, Chrome) and addition of Network Indicator, Remote Image Quality, Remote User Measurement.
• Predicate Device: Collaboration Live – Philips Ultrasound (K201665, cleared September 15, 2020)

In conclusion, while the document confirms that validation testing demonstrating equivalency and meeting defined requirements was performed, it does not disclose the specific acceptance criteria or the detailed results of that study, which is typical for a 510(k) summary as it focuses on establishing substantial equivalence rather than providing a full clinical validation report.

Ask a specific question about this device

Philips Lumify Diagnostic Ultrasound System is intended for diagnostic ultrasound imaging in B (2D), Color Doppler, Combined (B+Color), and M modes. It is indicated for diagnostic ultrasound imaging and fluid flow analysis in the following applications: Fetal/Obstetric, Abdominal, Pediatric, Cephalic, Urology, Gynecological, Cardiac Fetal Echo, Small Organ, Musculoskeletal, Peripheral Vessel, Carotid, Cardiac, Lung. Lumify is a transportable ultrasound system intended for use in environments where healthcare is provided by healthcare professionals.

Lumify Diagnostic Ultrasound System is a mobile, general, software-control medical device, which is intended to acquire high-resolution ultrasound data and to display the data in various modes of operation. It is intended to be used by trained professionals at various clinical settings including point-of-care. The Lumify Diagnostic Ultrasound System provides various imaging features including guided scan protocol for comprehensive lung exam. The introduction of the subject B-lines Feature enables the automated detection and counting of B-lines during a lung exam; the subject feature also provides the users the capabilities of reviewing the detected B-lines and editing the number of B-lines for each scanned lung zone. Clinically, B-line is a lung ultrasound artifact that can aid users in the assessment of patients with a variety of pulmonary conditions and diseases such as pneumonia, pulmonary edema, lung contusion, and acute respiratory distress syndrome (ARDS). The Lumify Diagnostic Ultrasound System includes: - A commercial off-the-shelf (COTS) mobile device l - I Philips Ultrasound software running as an app on the COTS device - I The C5-2 Curved array USB transducer - I The L12-4 Linear array USB transducer - I The S4-1 Sector array USB transducer - I The Lumify Power Module (LPM) to convert the USB interface used on the family of Lumify transducers to Apple's iAP2 Lightning interface standard used on iPhones and iPads, and to provide battery power to the transducers when using an iOS mobile device.

The provided text describes the Philips Lumify Diagnostic Ultrasound System and its new B-lines Feature. However, it does not contain specific acceptance criteria, detailed study results, or information about sample sizes, ground truth establishment, or expert qualifications for the B-lines Feature.

Instead, the document primarily focuses on regulatory approval (510(k) submission) and states generally that "all pre-determined acceptance criteria were met" and "performance test data is provided to support the introduction of the subject software algorithm."

Therefore, I cannot fulfill your request for a detailed table of acceptance criteria, reported performance, sample sizes, ground truth details, expert qualifications, or MRMC study information based solely on the provided text.

Here's what can be extracted and what is missing:

1. A table of acceptance criteria and the reported device performance:

2. Sample size used for the test set and the data provenance:

• Sample Size (Test Set): Not specified.
• Data Provenance: Not specified (e.g., 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:

• Number of Experts: Not specified.
• Qualifications of Experts: Not specified.

4. Adjudication method (e.g., 2+1, 3+1, none) for the test set:

• Not specified.

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:

• An MRMC study is not explicitly mentioned. The document states the B-lines Feature provides "automated detection and counting of B-lines," while the predicate had "manual counting," implying a standalone algorithm. However, no comparative effectiveness study with human readers and AI assistance is described, nor an effect size.

6. If a standalone (i.e. algorithm only without human-in-the loop performance) was done:

• The description of the B-lines Feature ("Automated detection and counting of B-lines from lung ultrasound images") suggests a standalone algorithm component. However, specific standalone performance metrics are not provided. The phrasing "the subject feature also provides the users the capabilities of reviewing the detected B-lines and editing the number of B-lines for each scanned lung zone" indicates a human-in-the-loop interaction, where the user can review and edit the device's output.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc):

• Not specified.

8. The sample size for the training set:

• Not specified.

9. How the ground truth for the training set was established:

• Not specified.

Summary of what is present in the document:

• The device is called the "Lumify Diagnostic Ultrasound System" with a new "B-lines Feature."
• The B-lines Feature provides "automatic detection and counting of B-lines during a lung exam."
• Users can review and edit the detected B-lines.
• Clinically, B-lines are lung ultrasound artifacts that aid in assessing pulmonary conditions.
• The study conducted was "non-clinical testing" addressing the change and performance, following Philips' internal processes (Requirements Review, Risk Analysis and Management, Product Specifications, Design Reviews, Product Performance testing).
• The conclusion states that "all pre-determined acceptance criteria were met" and the device "does not raise new questions of safety or effectiveness and is substantially equivalent to the predicate device."
• The predicate device involved "manual counting of B-lines from lung ultrasound images."

Ask a specific question about this device

The AAA Model is a software application designed to view and quantify 3D image data acquired by Philips diagnostic ultrasound systems for use in measuring the anterior diameter of abdominal aortic aneurysms. Optionally, lateral diameter, maximum diameter, and partial volume of an abdominal aortic aneurysm can also be provided. It is intended to be used by trained and qualified healthcare professionals in clinical point-of-care facilities.

AAA Model for QLAB Advanced Quantification Software is a software application designed for structural measurements of an Abdominal Aortic Aneurism (AAA), including volume measurement and diameter measurements. AAA Model is designed to assist in monitoring a previously diagnosed Abdominal Aortic Aneurisms in two ways:

1. to follow the anteroposterior (AP) maximum diameter for a Native AAA, and
2. to follow the anteroposterior (AP) maximum diameter for a post-surgical AAA.
   Philips QLAB Advanced Quantification Software (QLAB) is designed to view and quantify image data acquired on Philips ultrasound systems. QLAB is available either as a stand-alone product that can function on a standard PC, a dedicated workstation, and on-board Philips' ultrasound systems. AAA Model is compatible with the Philips EPIQ Diagnostic Ultrasound System.

Here's a summary of the acceptance criteria and study details for the Philips AAA Model, based on the provided document:

1. Table of Acceptance Criteria and Reported Device Performance

2. Sample Sizes Used for the Test Set and Data Provenance

• Bench Testing:
  • Sample Size: 7 samples were used for each measurement (volume, AP diameter, LAT diameter, MAD diameter).
  • Data Provenance: The data was generated using "EPIQ diagnostic ultrasound system...to take 3D ultrasound images of 3 phantoms with various diameter." This indicates a controlled, simulated environment (phantom study).
• Clinical Testing:
  • Native AAA:
    • Sample Size: 91 datasets (from an initial 129 gathered) met the inclusion criteria.
    • Data Provenance: "129 Native AAA datasets were gathered from one hospital in Copenhagen, Denmark. ... All patients age > 18 years old." This indicates prospective or retrospective clinical data from Denmark.
  • Post-EVAR AAA:
    • Sample Size: 45 datasets (from an initial 77 gathered) met the inclusion criteria.
    • Data Provenance: "77 Post-EVAR AAA datasets were gathered from one hospital in Copenhagen, Denmark. ... All patients age > 18 years old." This indicates prospective or retrospective clinical data from Denmark.

3. Number of Experts Used to Establish Ground Truth and Qualifications

The document does not explicitly state the number of experts used to establish ground truth or their specific qualifications (e.g., "radiologist with 10 years of experience").

For clinical testing, the "standard of care 2D ultrasound measurement" is used as the ground truth. It is implied that these measurements would have been performed by qualified healthcare professionals (e.g., sonographers or physicians) at the hospital in Copenhagen, Denmark, as part of routine clinical practice.

4. Adjudication Method for the Test Set

The document does not explicitly describe a formal adjudication method (like 2+1 or 3+1) for establishing ground truth in either the bench testing or clinical testing.

• For bench testing, the ground truth is derived from the known dimensions of the phantoms.
• For clinical testing, the "standard of care 2D ultrasound measurement" is considered the reference. It is not specified if multiple readers were used for these reference measurements or if any discrepancies were adjudicated.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

No, a multi-reader multi-case (MRMC) comparative effectiveness study was not done. The study compared the device's measurements to a "standard of care 2D ultrasound measurement," but it was not designed to evaluate the improvement of human readers with AI assistance versus without. The device itself is described as "not a computer-assisted detection (CADe) device, and does not use artificial intelligence or machine learning."

6. Standalone Performance Study

Yes, a standalone performance study was done. The device's performance was evaluated by directly comparing its measurements (AP diameter, volume, etc.) against established ground truth (phantom measurements for bench testing, standard of care 2D ultrasound measurements for clinical testing). The description implies that the AAA Model was used as an independent tool to quantify the images.

7. Type of Ground Truth Used

• Bench Testing: Physical dimensions of phantoms (a known, manufactured standard).
• Clinical Testing: "Standard of care 2D ultrasound measurement" for abdominal aortic aneurysm AP diameter.

8. Sample Size for the Training Set

The document does not provide information regarding a separate training set or its sample size. The device is explicitly stated as "not a computer-assisted detection (CADe) device, and does not use artificial intelligence or machine learning," which suggests it may not have a traditional 'training set' in the context of machine learning. Its functionality seems to be based on pre-programmed algorithms for structural measurements rather than learned patterns from a training dataset.

9. How Ground Truth for the Training Set Was Established

As noted in point 8, the document does not mention a training set for the AAA Model, given its description as not using AI/ML. Therefore, the method for establishing ground truth for a training set is not applicable or provided.

Ask a specific question about this device

Collaboration Live is indicated for remote console access of the Philips ultrasound system for diagnostic image viewing and review, consultation, guidance, support, and education in real time. Access must be granted by the healthcare professionals operating the ultrasound system. Compliance with the technical and operator requirements specified in the User Manual is required.

It is the responsibility of the healthcare professionals at the remote client to ensure image quality, display contrast, and ambient light conditions are consistent with the generally accepted standards of the clinical application.

Collaboration Live is software-based communication feature integrated in Philips Diagnostic Ultrasound Systems. Collaboration Live together with remote-client Reacts enables two-way communication of text, voice, image, and video information between an ultrasound local system operator and a remote healthcare professional on a Windows device. Collaboration Live-Reacts facilitates: 1) remote diagnostic viewing and review, 2) remote clinical training and education, 3) remote peer collaboration, and 4) remote service support. Collaboration Live functionality includes a remote control feature in which the ultrasound local system operator may grant a qualified remote user control of the ultrasound system parameters via a virtual control panel and virtual touch screen. By meeting the technical, operator, and environment requirements specified in the User Manual, healthcare professionals using Reacts may provide clinical diagnoses from a remote location as they would directly on the ultrasound system.

Please note: The provided document is a 510(k) summary for the "Collaboration Live" device. It focuses on demonstrating substantial equivalence to a predicate device, particularly regarding the change to allow diagnostic use for remote viewing. While it mentions "validation testing with pre-determined criteria," it does not provide the specific details of the acceptance criteria or the full study report. It only states that such testing was conducted and that the labeling was updated based on the findings.

Therefore, much of the requested information regarding detailed acceptance criteria, specific reported performance, sample sizes, ground truth establishment, expert qualifications, and MRMC study details cannot be fully extracted from this document alone.

Here's what can be extracted based on the provided text:

1. A table of acceptance criteria and the reported device performance

The document mentions "pre-determined criteria" for validation testing but does not explicitly list them or the quantitative reported device performance against these criteria. It broadly states that "remote display specifications and network bandwidth requirements for equivalent image quality for diagnostic viewing were determined."

Given the limited information, a hypothetical table based on the statement "equivalent image quality for diagnostic viewing" might look like this, but these are inferred and not explicitly stated criteria or performance metrics in the document:

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 test set: Not specified in the provided document.
• Data provenance: Not specified in the provided document. The document only mentions "Validation testing... was conducted."

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)

Not specified in the provided document.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set

Not specified in the provided document.

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

The document does not mention an MRMC comparative effectiveness study, nor does it refer to AI assistance. The device is a "software-based communication feature" for remote viewing and control of ultrasound systems, not an AI-driven image analysis tool.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done

The device "Collaboration Live" is explicitly designed for "remote console access" and "two-way communication... between an ultrasound local system operator and a remote healthcare professional." It's a system for human users to interact remotely with an ultrasound machine. Therefore, a "standalone algorithm only" performance study, without human involvement, would not be applicable to this type of device. The study implicitly involves human users making diagnostic decisions.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)

Not explicitly stated in the provided document beyond implying an evaluation of "equivalent image quality for diagnostic viewing." This would typically require expert assessment of image quality and diagnostic accuracy, but the specifics are not detailed.

8. The sample size for the training set

Not applicable. The "Collaboration Live" device is a software communication feature for remote access and viewing, not a machine learning or AI algorithm that requires a training set.

9. How the ground truth for the training set was established

Not applicable, as there is no training set for this type of device.

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-luminal, Intraoperative (Vascular), Intraoperative (Cardiac). Musculoskeletal (Conventional). Musculoskeletal (Superficial). Other: Urology. Pediatric. Peripheral Vessel. Small Organ (Breast, Thyroid, Testicle), Transesophageal (Cardiac), Transrectal, Transvaginal.

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, and only for the purposes for which it was designed. However, nothing stated in the user information reduces your responsibility for sound clinical judgement and best clinical procedure.

Philips EPIQ Diagnostic Ultrasound Systems are durable capital equipment / medical devices which are software-controlled and intended for high-resolution general imaging, interventional radiology, cardiology, vascular and OB/GYN 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.

Software modes/applications, scanning protocols, and pre-installed settings or functionality to create dedicated settings for imaging of specific anatomy are available with the subject Philips EPIQ Diagnostic Ultrasound Systems and may vary among model configurations.

The systems are manufactured with hardware components which consist of:

• a primary console (e.g., workstation, tablet) with built-in software components, features, and various 1) clinical applications, and
• 2. a range of compatible ultrasound transducers and ultrasound intravascular catheters.

A suite of reusable compatible transducer types are offered such as transesophageal echocardiography (TEE) transducers, non-imaging (pencil) probes, curved array and sector/phased array. Philips ultrasound transducers may be bagged into compatible transducer/probe cover sheaths, designed by other manufacturers, for each procedure to prevent cross-contamination and reduce the risk of healthcareassociated infections. Philips EPIQ Diagnostic Ultrasound Systems are also compatible with single-use diagnostic intravascular ultrasound catheters (i.e., Philips VeriSight Intracardiac Echocardiography (ICE) Catheter, VeriSight Pro Intracardiac Echocardiography (ICE) Catheter) that are intended for intracardiac and intra-luminal visualization of cardiac and great vessel anatomy and physiology as well as visualization of other devices in the heart for image guidance during cardiac interventional procedures.

Some configurations may have additional previously-cleared accessories, components and software features which are manufactured by Philips Ultrasound, Inc. or other manufacturers.

The provided FDA 510(k) summary for the Philips EPIQ Series Diagnostic Ultrasound Systems with VeriSight ICE / Pro ICE Catheters does not contain the specific acceptance criteria or the study details that prove the device meets these criteria in the format requested.

The document states that "all pre-determined acceptance criteria were met" and that "Results of these tests show that the proposed subject Philips EPIQ Series Diagnostic Ultrasound Systems with VeriSight ICE / PRO ICE Catheters meet their intended use." However, it does not explicitly list these criteria or provide detailed results from studies designed to demonstrate compliance.

Instead, the document focuses on:

• Substantial Equivalence: The primary goal of a 510(k) submission is to demonstrate that the new device is substantially equivalent to a legally marketed predicate device. This is primarily done through comparison of technological characteristics and safety standards.
• Compliance with Standards: It lists several IEC and ANSI standards that the device complies with, which are general safety and performance standards for medical electrical equipment and diagnostic ultrasound.
• Non-Clinical Verification Testing: It mentions that "Relevant non-clinical verification testing and compatibility information has been performed... to address system level requirements according to system and design specifications, and risk control measures." This implies internal testing was done, but details are not provided.
• Lack of Clinical Data: It explicitly states that "The proposed Philips EPIQ Diagnostic Ultrasound Systems did not require clinical data for determination of substantial equivalence." This means a human-in-the-loop (MRMC) study or standalone clinical performance study was not conducted or required for this 510(k) clearance.

Therefore, for the information requested in your bullet points, I can only extract general statements about compliance and the types of testing performed, not specific performance metrics against defined acceptance criteria.

Here's a breakdown of what can and cannot be derived from the provided text:

1. A table of acceptance criteria and the reported device performance

Cannot be provided from the text. The document states "all pre-determined acceptance criteria were met" and that the device meets its intended use, but it does not specify what those criteria are or report concrete performance metrics against them. The focus is on compliance with general safety and performance standards.

2. Sample size used for the test set and the data provenance

Cannot be provided from the text. The document does not describe a clinical test set or its provenance because it explicitly states that "The proposed Philips EPIQ Diagnostic Ultrasound Systems did not require clinical data for determination of substantial equivalence." The testing mentioned is "non-clinical verification testing and compatibility information." Details like sample size or data provenance for these internal non-clinical tests are not given.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts

Not applicable/Cannot be provided from the text. Since no clinical test set was required or described, there were no experts used to establish ground truth in the context of clinical performance.

4. Adjudication method for the test set

Not applicable/Cannot be provided from the text. As no clinical test set or ground truth establishment by experts is described, no adjudication method would have been used.

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. The document explicitly states: "The proposed Philips EPIQ Diagnostic Ultrasound Systems did not require clinical data for determination of substantial equivalence." This implies no MRMC comparative effectiveness study was conducted or needed. Furthermore, the device described is a general diagnostic ultrasound system, not explicitly an "AI" device with human-in-the-loop assistance in the context of improving reader performance.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done

No. The document states that "The proposed Philips EPIQ Diagnostic Ultrasound Systems did not require clinical data for determination of substantial equivalence." While "non-clinical verification testing" was performed, this refers to engineering and quality assurance testing against technical specifications and safety standards, not a standalone clinical performance study of an algorithm. The device is described as software-controlled, but not as an "algorithm only" device subject to standalone performance evaluation in a clinical sense.

7. The type of ground truth used

Not applicable/Cannot be provided from the text for clinical performance. For the non-clinical verification testing mentioned, the "ground truth" would likely be engineering specifications, established physical properties, and compliance with the listed safety standards (e.g., electrical safety, electromagnetic compatibility, acoustic output limits).

8. The sample size for the training set

Not applicable/Cannot be provided from the text. The document pertains to a diagnostic ultrasound system, not an AI model that undergoes a "training set" in the machine learning sense. The "software-controlled" aspect refers to the operational control of the ultrasound system itself, not necessarily an AI algorithm.

9. How the ground truth for the training set was established

Not applicable/Cannot be provided from the text. As above, this is not applicable for this type of device and submission.

In summary, the provided text from the FDA 510(k) summary demonstrates compliance by:

• Stating that "all pre-determined acceptance criteria were met" for internal non-clinical verification testing.
• Listing adherence to recognized safety and performance standards (ANSI/AAMI 60601-1, IEC 60601-1-2, IEC 60601-2-37).
• Asserting that no clinical data was required for substantial equivalence, implying that its performance is presumed to be equivalent to the predicate device based on technical and safety specifications.

Ask a specific question about this device

The PerculVav system is a stereotaxic accessory for computed tomography (CT), cone beam CT (CBCT), magnetic resonance (MR), ultrasound (US), and positron emission tomography (PET). CT, Ultrasound, PET, and MR may be fused in various combinations, such as CT with MR, MR with ultrasound, and so on. It may include instrumentation to display the simulated image of a tracked insertion tool such as a biopsy needle or probe on a computer monitor screen that shows images of the target organs and the current and the projected future path of the interventional instrument. The PerculNav system is intended for treatment planning and to assist guidance for clinical, interventional, or diagnostic procedures in a clinical setting.

The PercuNav system is also intended to supplement live imaging in clinical interventions to determine the proximity of one device relative to another.

The PercuNav system is not intended to be the sole guidance for any procedure. Procedures that can be guided by the PercuNav system adjunctively include, but are not limited to, the following:

• · Image fusion for diagnostic clinical examinations and procedures
• · Soft tissue biopsies
• · Soft tissue ablation
• Bone ablation
• · Bone biopsies
• · Nerve blocks and pain management
• · Drainage placements

The Philips PercuNav Image Fusion and Interventional Navigation System provides image-guided diagnostic and intervention that enables fusion of diagnostic images and guidance of tracked instruments to physiciandefined targets. The target can be indicated either pre-procedurally or intra-procedurally, either using images or relative to an indicated position on the patient. The system transforms two-dimensional patient images into dynamic representations that can be fused with live ultrasound or other previously acquired images. Those two-dimensional patient images, or scan sets, are derived from Ultrasound, CT, PET, PET/CT, and MRI. The resulting dynamic representation supports diagnostic review and instrument navigation.

The purpose of this Traditional 510(K) Pre-market Notification is to introduce a new semi-automated visualization tool entitled "Tumor Contouring" to the current PercuNav software system. The Tumor Contouring visualization tool is designed to aid the end user in the planning and targeting of lesions, structures, and other regions of interests prior to an interventional procedure, soft tissue ablation, etc. The Tumor Contouring tool allows the end user to generate and modify a 3D contour around a region or soft tissue structure of interest and then this contour, once accepted by the user, can be visualized and dynamically reformatted and fused in various imaging combinations for later procedures.

The provided text includes a 510(k) summary for the Philips PercuNav Image Fusion and Interventional Navigation System with a new "Tumor Contouring" visualization tool. However, it does not contain explicit acceptance criteria thresholds or detailed study results for the device's performance, as would typically be found in a clinical study report.

The document focuses on demonstrating substantial equivalence to predicate devices through technological comparison and non-clinical testing (software verification, risk analysis, product specifications, design reviews). It explicitly states: "The subject Philips PercuNav System did not require clinical data in order to make a determination for substantial equivalence when compared to the predicate device(s)."

Therefore, based on the provided text:

1. A table of acceptance criteria and the reported device performance:

2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective):

No specific sample size for a "test set" (in the context of clinical or performance data) or data provenance is mentioned. The testing described is primarily internal software verification.

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):

Not applicable. The document does not describe a study involving expert-established ground truth for performance evaluation of the Tumor Contouring tool.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set:

Not applicable. No such adjudication method is mentioned as part of the described testing.

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 or reported in this document.

6. If a standalone (i.e. algorithm only without human-in-the loop performance) was done:

The "Tumor Contouring" tool is described as "semi-automated," generating a preliminary border that the user must modify and review. This indicates it is not a standalone algorithm without human-in-the-loop performance. The document does not describe a standalone performance study.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc):

Not applicable. The document focuses on software verification against specifications and user needs rather than clinical ground truth for the Tumor Contouring feature. The closest mention of "ground truth" would be the implicit correctness against internal software design specifications.

8. The sample size for the training set:

Not applicable. There is no mention of a training set as the device's submission did not involve clinical data or machine learning model training in the context of this summary.

9. How the ground truth for the training set was established:

Not applicable, as no training set is described.

Ask a specific question about this device

The intended use of the Affiniti 30, Affiniti 70 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 (Neonatal), Fetal/Obstetric, Gynecological, Intraoperative (Vascular), Intraoperative (Cardiac), Musculoskeletal (Conventional), Musculoskeletal (Superficial), Other: Urology, Pediatric, Peripheral Vessel, Small Organ (Breast, Thyroid, Transesophageal (Cardiac), Transrectal, Transvaginal.

The clinical environments where the Affiniti Diagnostic Ultrasound Systems can be used include Clinics, 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, and only for the purposes for which it was designed. However, nothing stated in the user information reduces your responsibility for sound clinical judgment and best clinical procedure.

Philips CX50 Diagnostic Ultrasound Systems is intended for diagnostic ultrasound imaging in B (or 2- D), M-mode (including Anatomical M-mode), Pulse Wave Doppler, Continuous Wave Doppler, Color Doppler, Tissue Doppler Imaging and Harmonics (Tissue and Contrast) modes.

It is indicated for diagnostic ultrasound imaging and fluid flow analysis in the following applications: Ophthalmic Intraoperative Laparoscopic Fetal Abdominal Pediatric Small Organ Adult Cephalic Neonatal Cephalic Trans-vaginal Musculo-skeletal Gynecological Cardiac Pediatric Trans-Esoph. (Cardiac) Intracardiac echo Peripheral Vessel Other (Carotid)

The intended use of the EPIQ, EPIQ 7 is diagnostic ultrasound imaging and fluid flow analysis of the human body with the following Indications for Use: Abdominal, Cardiac other (Fetal), Cardiac Pediatric, Cerebral Vascular, Cephalic (Adult), Cephalic (Neonatal), Fetal/Obstetric, Gynecological, Intraoperative (Vascular), Intraoperative (Cardiac), Musculoskeletal (Conventional), Musculoskeletal (Superficial), Other: Urology, Pediatric, Peripheral Vessel, Small Organ (Breast, Thyroid, Testicle), Transesophageal (Cardiac), Transrectal, Transvaginal.

The clinical environments where the 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, and only for the purposes for which it was designed. However, nothing stated in the user information reduces your responsibility for sound clinical judgment and best clinical procedure.

Philips Lumify Diagnostic Ultrasound System is intended for diagnostic ultrasound imaging in B (2D), Color Doppler, Combined (B+Color), and M modes. It is indicated for diagnostic ultrasound imaging and fluid flow analysis in the following applications: Fetal/Obstetric, Abdominal, Pediatric, Cephalic, Urology, Gynecological, Cardiac Fetal Echo, Small Organ, Musculoskeletal, Peripheral Vessel, Carotid, Cardiac. Lumify is a transportable ultrasound system intended for use in environments where healthcare is provided by healthcare professionals.

QLAB Advanced Quantification Software is a software application package. It is designed to view and quantify image data acquired on Philips ultrasound systems.

Philips Sparq Diagnostic Ultrasound System is intended for diagnostic ultrasound imaging in B (or 2- D), M-mode (including Anatomical M-mode), Pulse Wave Doppler, Continuous Wave Doppler, Color Doppler, Tissue Doppler Imaging and Harmonics (Tissue and Contrast) modes. It is indicated for diagnostic ultrasound imaging and fluid flow analysis in the following applications: Ophthalmic Fetal Abdominal Pediatric Small Organ Adult Cephalic Trans-vaginal Trans-rectal Musculo-skeletal Gynecological Cardiac Adult Trans-Esoph. (Cardiac) Peripheral Vessel.

Philip Diagnostic Ultrasound Systems are durable, reusable capital equipment medical devices which are intended for high-resolution general imaging, interventional radiology, cardiology, vascular and OB/GYN 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.

Philips QLAB Advanced Quantification software (QLAB) is designed to view and quantify image data acquired on Philips ultrasound systems. QLAB is available either as a stand-alone product that can function on a standard PC, a dedicated workstation, and on-board Philips' Diagnostic Ultrasound Systems.

Software modes/applications, scanning protocols, and pre-installed settings or functionality to create dedicated settings for imaging of specific anatomy are available with the subject Philips Diagnostic Ultrasound Systems and QLAB software and may vary among model configurations.

The diagnostic ultrasound systems are manufactured with hardware components which consist of:

• a primary console (e.g., workstation, tablet) with built-in software components, features, and 1) various clinical applications, and
• 2. a range of compatible ultrasound transducers.

A suite of compatible transducer types are offered such as transesophageal echocardiography (TEE) transducers, non-imaging (pencil) probes, curved array, linear array and sector/ohased array transducer models which have a prefix "C" are designed to provide larger fields of view and penetration for e.g., consolidation between bone spaces while linear array transducer models, which can be identified with a "L" prefix model name are designed to provide shallow visualization which are optimal for tissue layer interfaces. Sector/phased array transducer models which usually have a "S" prefix model names are designed to be applied for difficult anatomical sites (e.g., cardiac intercostal space (ICS)). Other Philips ultrasound transducers may also start with the prefix "X" which is referring to the xMatrix technology for two full-resolution planes of imaging. Volumetric three-dimensional (3D) imaging functionality is also available when specific transducer models are connected to the primary console. Philips ultrasound transducers may be bagged into compatible transducer/probe cover sheaths, designed by other manufacturers, for each procedure to prevent cross-contamination and reduce the risk of healthcareassociated infections.

Some configurations may have additional previously-cleared accessories, components and software features which are manufactured by Philips Ultrasound, Inc. or other manufacturers.

This document is a 510(k) Premarket Notification from Philips Ultrasound, Inc. to the FDA regarding several of their diagnostic ultrasound systems and software. The primary purpose of this submission is not to present performance data for a new device that meets acceptance criteria, but rather to assert substantial equivalence to previously cleared predicate devices for expanded labeling related to COVID-19.

Therefore, the requested information regarding acceptance criteria and a study proving the device meets them, including sample sizes, ground truth establishment, expert qualifications, and comparative effectiveness studies, does not apply in the traditional sense for a new device submission with novel performance claims.

Instead, the submission states:

1. A table of acceptance criteria and the reported device performance:

• There is no specific table of acceptance criteria or reported device performance for novel features in this submission.
• The document focuses on establishing technological characteristic equivalence between the subject devices and their respective predicate devices.
• Table 1, Table 2, Table 3, Table 4, Table 5, and Table 6 (spanning pages 13-25) provide a technological comparison for each subject device (Philips Lumify, EPIQ, Affiniti, CX50, Sparq, and QLAB software) against its predicate device. For all listed "Standard Features" (Indications for Use, Reusable?, Duration of Use, Scientific Technology, Operating principles, Type of Previously-cleared Transducers, Acoustic Outputs Within Range?, Previously cleared Imaging Modes?, Biocompatibility), the comparison consistently states "Identical." This indicates that no new performance metrics or acceptance criteria beyond those already established for the predicate devices are being introduced for new functionalities.

2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective):

• Not applicable. The submission does not describe a new performance study requiring a test set. It relies on the equivalence of the subject devices to their predicate devices, which would have undergone performance testing for their initial clearances.

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):

• Not applicable. No new ground truth establishment is described in this submission.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set:

• Not applicable. No new performance study or test set requiring adjudication is described.

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 applicable. No MRMC study is mentioned. The submission is for existing ultrasound systems and software with expanded labeling, not for AI-assisted diagnostic tools requiring such studies for comparative effectiveness.

6. If a standalone (i.e. algorithm only without human-in-the loop performance) was done:

• Not applicable. While QLAB is software, the submission primarily focuses on maintaining substantial equivalence in its current functionality and expanding labeling. No new standalone algorithm performance is detailed.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc):

• Not applicable. No new ground truth is described. The established safety and effectiveness of the predicate devices implicitly relied on various forms of ground truth relevant to diagnostic ultrasound at the time of their clearance.

8. The sample size for the training set:

• Not applicable. This submission does not involve a new machine learning algorithm or a training set.

9. How the ground truth for the training set was established:

• Not applicable. This submission does not involve a new machine learning algorithm or a training set.

Summary of the Submission's Approach:

The core of this 510(k) submission is to assert that the subject devices (various Philips Diagnostic Ultrasound Systems and QLAB software) are substantially equivalent to their respective predicate devices. The significant change being addressed is the "Expanded Labeling" to include information about lung and cardiac ultrasound imaging for COVID-19 patients, based on established methods or the latest society guidelines. The submission explicitly states:

• "Relevant performance data does not apply to this submission." (Page 26)
• "There are no changes in software, hardware, and intended uses of the subject devices comparing to the predicates." (Page 26)
• "The results of the design controls activity support a determination that the subject devices do not raise new questions of safety or effectiveness and are substantially equivalent to the predicate devices." (Page 26)

Therefore, the "study" proving the device meets "acceptance criteria" is essentially the argument of identical technological characteristics and unchanged intended uses compared to the already cleared predicate devices, with the new labeling information being based on general clinical practice and guidelines rather than new device-specific performance data.

Ask a specific question about this device

The intended use of the EPIQ Diagnostic Ultrasound 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 Echo), Cardiac Pediatric, Cerebral Vascular, Cephalic (Neonatal), Fetal/Obstetric, Gynecological, Intraoperative (Vascular), Intraoperative (Cardiac), Musculoskeletal (Conventional), Musculoskeletal (Superficial), Other: Urology, Pediatric, Peripheral Vessel, Small Organ (Breast, Thyroid, Testicle), Transesophageal (Cardiac), Transrectal, Transvaginal.

The clinical environments where the Philips EPIO Diagnostic Ultrasound Systems and Philips Affiniti 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 and used 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 user responsibility for sound clinical judgement and best clinical procedure.

The proposed Philips EPIQ Series Diagnostic Ultrasound Systems are general purpose, software controlled, diagnostic ultrasound systems. Their function is to acquire ultrasound data and to display the data in various modes of operation. The devices consist of two parts: the system console and the transducers. The system console contains the user interface, a display, system electronics and optional peripherals (ECG, printers).

Transducers are connected to the system using a plug in electrical connection. Other than the introductions of the new mC12-3 Transducer, the device description, accessories and components are unchanged.

The provided text is a 510(k) summary for the Philips EPIQ Series Diagnostic Ultrasound System and mainly focuses on demonstrating substantial equivalence to a predicate device. It contains very limited information regarding acceptance criteria and performance studies in the way typically expected for an AI/ML medical device.

Specifically, the document does not describe:

• A table of acceptance criteria for algorithm performance and reported device performance.
• Sample sizes used for a test set or its provenance.
• The number or qualifications of experts used for ground truth establishment.
• Adjudication methods for a test set.
• Whether a multi-reader multi-case (MRMC) comparative effectiveness study was done or the effect size of AI assistance for human readers.
• Whether a standalone (algorithm only) performance study was done.
• The type of ground truth used (e.g., pathology, outcomes data).
• The sample size for a training set or how its ground truth was established.

The document states:

• "Non-Clinical verification testing has been performed addressing system level requirements according to system and design specifications, and risk control measures." (Page 6)
• "The proposed Philips EPIQ Series Diagnostic Ultrasound System did not require clinical data for determination of substantial equivalence." (Page 6)
• "For testing, all pre-determined acceptance criteria were met. Results of these tests show that the proposed Philips EPIQ Series Diagnostic Ultrasound Systems with the new mC12-3 transducer meet their intended use." (Page 7)

This suggests that the "testing" mentioned refers primarily to non-clinical performance data related to the safety and fundamental operation of the ultrasound system and its new transducer (mC12-3), rather than the performance of an AI/ML algorithm that predicts or classifies outcomes. The acceptance criteria met were likely related to electrical safety, electromagnetic compatibility, acoustic output, and biocompatibility, as listed under "Nonclinical Performance Data" on page 6.

Therefore, based solely on the provided text, it is not possible to answer the detailed questions about acceptance criteria and study design for an AI/ML component, as the submission appears to be for a traditional ultrasound system and transducer, not an AI/ML-driven diagnostic device.

Ask a specific question about this device

The intended use of the EPIQ 5, EPIQ 7, Affiniti 30, Affiniti 70 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 (Superficial), Other: Urology, Pediatric, Peripheral Vessel, Small Organ (Breast, Thyroid, Testicle), Transesophageal (Cardiac), Transrectal, Transvaginal.

The proposed Philips EPIQ Diagnostic Ultrasound Systems and Philips Affiniti Diagnostic Ultrasound Systems are general purpose, software controlled, diagnostic ultrasound systems. Their function is to acquire ultrasound data and to display the data in various modes of operation. The devices consist of two parts: the system console and the transducers. The system console contains the user interface, a display, system electronics and optional peripherals (ECG, printers).

The removable transducers are connected to the system using a standard technology, multi-pin connectors. Other than the introductions of the two new transducers, the device description, accessories and components are unchanged, reference table 1.

Here's the breakdown of the acceptance criteria and supporting studies for the Philips EPIQ and Affiniti Diagnostic Ultrasound Systems based on the provided text:

Important Note: The provided text is a 510(k) summary, which focuses on demonstrating substantial equivalence to a predicate device rather than presenting a detailed clinical study for the device's original clearance. Therefore, information regarding specific clinical performance metrics (like sensitivity, specificity, accuracy) from a de novo study is not present. Instead, the document emphasizes compliance with standards and equivalence to a previously cleared device.

1. Table of Acceptance Criteria and Reported Device Performance

The document describes the device meeting safety and performance standards rather than specific clinical performance metrics like sensitivity/specificity for a novel algorithm.

Ask a specific question about this device

Philips Xperius Ultrasound system is intended for diagnostic Ultrasound imaging in B (2D), Color Doppler, M-Mode, and Color Power Angio (CPA) modes. It is indicated for diagnostic ultrasound imaging, and fluid flow analysis in the following applications: Abdominal Peripheral Vessel MSK Small Organ Pediatric

The modified/proposed Xperius Ultrasound System is a general purpose, software controlled, diagnostic ultrasound system. Its function is to acquire ultrasound data and to display the data in various modes of operation.

The provided text is a 510(k) summary for the Philips Xperius Ultrasound System (K182529). It details the device's indications for use and compares its technological characteristics to predicate devices. However, it explicitly states that no clinical studies were required or performed to determine substantial equivalence. Therefore, it is not possible to provide information about acceptance criteria, device performance from a test set, sample sizes, expert qualifications, adjudication methods, MRMC studies, or standalone performance, as these items are typically derived from clinical or performance studies.

The document indicates that substantial equivalence was demonstrated through non-clinical performance data and attributes such as design features, indications for use, and fundamental scientific technology.

Here's a breakdown of the requested information based only on the provided document:

1. Table of Acceptance Criteria and Reported Device Performance

This information is not available in the provided document. The submission explicitly states "The proposed Xperius Ultrasound System did not require clinical studies since substantial equivalence to the currently marketed predicate devices... was demonstrated with the following attributes: Design features; Indication for use; Fundamental scientific technology; Non-clinical performance testing; and Safety and effectiveness." As such, there are no reported device performance metrics against specific acceptance criteria from a clinical or performance study.

2. Sample Size Used for the Test Set and Data Provenance

This information is not available in the provided document. No clinical or performance test set was used according to the submission.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications

This information is not available in the provided document. No clinical or performance test set was used, and therefore no experts were involved in establishing ground truth for such a test set.

4. Adjudication Method for the Test Set

This information is not available in the provided document. No clinical or performance test set was used.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and the Effect Size

This information is not available in the provided document. No clinical studies, including MRMC studies, were performed.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done

This information is not available in the provided document. The device is an ultrasound system with various modes, not an AI algorithm. No standalone performance study of an algorithm was mentioned.

7. The Type of Ground Truth Used

This information is not applicable as there were no clinical or performance studies generating results that would require ground truth for comparison. Substantial equivalence was based on non-clinical performance data and comparison to predicate devices, not on a new clinical evaluation requiring ground truth.

8. The Sample Size for the Training Set

This information is not available in the provided document. The document describes an ultrasound system, not a device that underwent machine learning training with a specific training set.

9. How the Ground Truth for the Training Set Was Established

This information is not applicable as there is no mention of a training set for a machine learning model.

Ask a specific question about this device