Search Results

The device is used for radiological guidance and visualization during diagnostic, interventional and surgical procedures on all patients. The device is to be used in health care facilities both inside the operating room, sterile as well as non-sterile environment in a variety of procedures.

Applications:

• Orthopedic
• Neuro
• Abdominal
• Vascular
• Thoracic
• Cardiac

The proposed Zenition 30 is a mobile, diagnostic X-ray imaging and viewing system. It is designed for medical use in healthcare facilities where X-ray imaging is needed. The system comprises of two main components: the C-arm stand and a Mobile View Station (MVS).

The provided text describes the K232420 submission for the Philips Zenition 30, a mobile X-ray imaging system, and compares it to a predicate device, Zenition 70 (K212813). The submission argues for substantial equivalence based on non-clinical performance data and compliance with various standards and guidance documents. There is no multi-reader multi-case (MRMC) comparative effectiveness study or standalone algorithm performance data mentioned, as the device is an imaging system and not an AI-powered diagnostic tool. The ground truth concept is not directly applicable in the context of validating an X-ray imaging system for substantial equivalence; rather, the focus is on meeting specified performance criteria and demonstrating that the new device operates similarly and as safely and effectively as its predicate.

Here's an analysis of the provided information:

Acceptance Criteria and Reported Device Performance

The acceptance criteria are implicitly derived from the comparison to the predicate device and compliance with various international and FDA-recognized consensus standards and guidance documents. The reported device performance is demonstrated by the technical characteristics listed in the comparison tables and the declaration of compliance with these standards.

Table 1: Key Performance Characteristics and Comparison (Derived from Section 7, Table 2)

• Continuous X-ray mode at 30 fps is equivalent to 30pps pulsed mode of predicate.
• Clinically acceptable image quality for intended use.
• No impact on safety and effectiveness. Substantially Equivalent. |
  | | - kV range: 40-120 kV | - kV Range: 40 to 110kV | |
  | | - Mode of operation: Pulse (with 30 pps max) | - Pulse/ Continuous: Pulsed and Continuous (15 pps max pulsed) | |
  | | - Maximum mA: 125 mA | - Maximum mA: 36mA | |
  | X-ray Tube | - Rotating Anode (e.g., RTM 780 H) | - Fixed Anode (e.g., OX 125 -0612) | - Similar target angle leads to similar field of view.
• 0.6 mm focal spot used for most applications, similar to predicate.
• No clinically significant difference in safety and clinical performance. Similar and substantially equivalent. |
  | | - Focal spot: dual (0.3 & 0.6) | - Focal spot: dual (0.6 & 1.2) | |
  | | - Target angle: 10° | - Target angle: 9° | |
  | X-ray Housing Assembly | - Minimum limiting resolution: >= 2.2 lp/mm | - Minimum limiting resolution: >= 2.2 lp/mm | - Supports minimum limiting resolution of >=2.2 lp/mm.
• Similar heat performance and safety mechanisms (thermal switch).
• Better inherent filtration.
• Complies with applicable X-ray safety standards (e.g., IEC 60601-1-3). Similar and substantially equivalent. |
  | Flat Panel Detector | - Frame rate: 30fps | - Frame rate: 30fps | - Same design, scientific technology, and image acquisition workflow.
• Similar physical size and zoom modes.
• Similar DQE (Zenition 30 slightly higher).
• Final system resolution >= 2.2 lp/mm due to similar anode angle and focal spot.
• No change in clinically relevant characteristics. Similar and substantially equivalent. |
  | | - Detector size: approx. 207mm x 207mm | - Detector size: approx. 204mm x 204mm | |
  | | - Pixel pitch: 154 μm | - Pixel pitch: 200 μm | |
  | | - DQE: 77% | - DQE: 80% | |
  | Imaging Processing Technology | Xres-3 (PC-based platform and algorithm) | Xres-3 (PC-based platform and algorithm) | Same. Substantially equivalent. |
  | Anti Scatter Grid | Removable square grid, 70% transmission | Removable square grid, 70% transmission | Same technology. Similar and substantially equivalent. |
  | Radiation Safety Features | Collimation, anti-scatter grid, fluoroscopy modes, pulsed fluoroscopy, recording/storing runs, last image hold, real-time dose monitoring. | Collimation, anti-scatter grid, fluoroscopy modes, pulsed fluoroscopy, recording/storing runs, last image hold, real-time dose monitoring. | Same features. Same and substantially equivalent. |
  | Beam Limiting Device (Collimator) | Square (round in zooming/rotation) | Square (round in zooming/rotation) | Reuses predicate's collimator; minor modification for mounting. Performance and safety parameters remain the same. Similar and substantially equivalent. |
  | C-arm Motions and Brakes | 4 axis movements (Angulation, Rotation, Longitudinal, Wigwag), 4 axis manual brakes. | 4 axis movements, 3 axis electromagnetic brakes, 1 axis manual brake. | Electromagenetic brakes improve workflow and ease of use. Usability studies and product safety assessment confirm no new risks. Similar and substantially equivalent. |
  | Geometry | Hammerhead design, 206x82x162 cm, 332 Kg (FD12), 15.3" touch screen. | New design stand, 185x82x172 cm (without push bar/surgeon arm), 210x82x162 cm (with), 295 kg, 12.1" touch screen. | Improved maneuverability, lower operating forces, slimmer UI (12.1"). Improves workflow and ease of use. Similar and substantially equivalent. |
  | System Architecture | PC Based Win 10 | PC Based Win 10 | Same. Same and substantially equivalent. |
  | Ionizing Radiation | System uses X-ray for imaging | System uses X-ray for imaging | Same X-ray technology usage. Same and substantially equivalent. |
  | Detector Laser Aiming Device | Specific model, Wavelength: 635 nm, Max output: 10mW, Beam divergence: 34 degrees. | Specific model, Wavelength: 635 nm, Max output: 10mW, Beam divergence: 34 degrees. | Same. Same and substantially equivalent. |
  | Tube Laser Aiming Device | Specific model (4598 008 4322x) | Specific model (4598 008 4322x) | Same. Same and substantially equivalent. |
  | DICOM Connectivity | Features for patient data export, unattended network transfer, local media export, multimodality viewer, improved transfer speed. | Same features for patient data export, unattended network transfer, local media export, multimodality viewer, improved transfer speed. | Same. Same and substantially equivalent. |
  | Security Features | Local user account management, username/password combination, network time synchronization, audit trail, white listing, DIACAP hardening, disk encryption, FIPS 140-2. | Same features including local user account management, username/password combination, network time synchronization, audit trail, white listing, DIACAP hardening, disk encryption, FIPS 140-2. | Same. Same and substantially equivalent. |
  | Room Interface | External x-ray and power indication interface. | External x-ray and power indication interface. | Same. Same and substantially equivalent. |
  | Audible Signals | Speaker with volume control in the Stand. | Speaker with volume control in the Stand. | Same. Same and substantially equivalent. |
  | Wired Footswitch and remote control unit | Same as predicate | Same as predicate | Same. Same and substantially equivalent. |
  | Product Name | Zenition 70 | New Product name Zenition 30 | Labeling change only; no impact on system features, safety, and effectiveness. Substantially equivalent. |

Study Information

The document describes a non-clinical performance testing study to demonstrate compliance and substantial equivalence, rather than a clinical study focused on diagnostic accuracy or AI performance.

1. Sample size used for the test set and the data provenance: Not applicable in the context of this submission, which relies on non-clinical testing and comparison to a predicate device's established performance parameters. The "test set" consisted of the physical device and its components undergoing engineering verification and validation tests. The provenance is internal to Philips Medical Systems Nederland B.V.
2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable. The "ground truth" for the performance of an X-ray imaging system is established through adherence to recognized international and FDA consensus standards (e.g., IEC 60601 series) and physical measurements, rather than expert consensus on medical images. The expertise would be in medical device engineering, physics, and regulatory affairs, not clinical interpretation of images.
3. Adjudication method (e.g., 2+1, 3+1, none) for the test set: Not applicable. Device performance is evaluated against quantitative engineering specifications and standard requirements, which do not typically involve an adjudication process like those used for expert review of images.
4. 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 study was done. This device is a new iteration of an X-ray imaging system, not an AI-assisted diagnostic tool or an image interpretation algorithm. The focus is on the fundamental performance and safety of the hardware and integrated software for image acquisition and display, not on assisting human readers with interpretation.
5. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done: Not applicable. The Zenition 30 is an X-ray imaging system, not an AI algorithm. Its performance is as a complete medical device intended for radiological guidance and visualization.
6. The type of ground truth used (expert consensus, pathology, outcomes data, etc.): Ground truth, in this context, refers to the established technical specifications, safety standards (e.g., radiation dose, image resolution), and functional requirements for an X-ray imaging system. It is established through recognized international standards (e.g., IEC), FDA guidance documents, and the validated performance of the predicate device. For example, a "limiting resolution of >=2.2 lp/mm" is a measurable technical specification, not something derived from expert consensus on clinical images in this submission.
7. The sample size for the training set: Not applicable. The Zenition 30 is a hardware system with integrated software, not an AI/machine learning model that requires a training set.
8. How the ground truth for the training set was established: Not applicable, as there is no training set for an AI/machine learning model. The validation and verification process involves testing the physical device and its components against predefined engineering requirements and regulatory standards.

Ask a specific question about this device

The proposed Zenition 70 is intended to be used and operated by: adequately trained, qualified and authorized health care professionals who have full understanding of the safety information and emergency procedures as well as the capabilities and functions of the device.

The device is used for radiological guidance and visualization during diagnostic, interventional and surgical procedures on all patients, except neonates (birth to one month), within the limits of the device. The device is to be used in health care facilities both inside and outside the operating room, sterile as well as non-sterile environment in a variety of procedures.

Applications:

• Orthopedic
• Neuro
• Abdominal
• Vascular
• Thoracic
• Cardiac

The proposed Zenition 70 is a mobile, diagnostic X-ray imaging and viewing system. It is designed for medical use in healthcare facilities where X-ray imaging is needed. The system comprises two main components: The C-arm stand and a mobile view station.

The provided text is a 510(k) summary for the Philips Zenition 70, a fluoroscopic X-ray system. The submission focuses on demonstrating substantial equivalence to a predicate device (previous Zenition 70 model K183040) and a reference device (Digiscan FDX K200218) by adding a new flat panel detector (FD17) and some software/UI updates.

The document states that no clinical studies were required as substantial equivalence was demonstrated through non-clinical performance testing and similarity in indications for use and technological characteristics. Therefore, the device's acceptance criteria are primarily met through compliance with recognized standards and verification of technical performance, rather than a clinical study involving human readers or a set of clinical cases with ground truth.

Here's an analysis of the provided information based on your request:

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

The document doesn't present a table of specific clinical acceptance criteria and corresponding performance metrics from a study involving clinical cases. Instead, the acceptance criteria are largely defined by adherence to a comprehensive list of international and FDA-recognized consensus standards and FDA guidance documents. The "reported device performance" is the statement that the device complies with these standards.

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

The document explicitly states: "The proposed Zenition 70 did not require clinical study since substantial equivalence to the currently marketed and predicate device Zenition 70 was demonstrated with the following attributes: Indications for use; Technological characteristics; Non-clinical performance testing; and Safety and effectiveness."
Therefore, there was no test set of clinical cases that a sample size would apply to. The testing involved non-clinical performance evaluations against standards.

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, as no clinical test set requiring expert ground truth was performed.

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

Not applicable, as no clinical test set requiring adjudication was performed.

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. This is a submission for an X-ray imaging system, not an AI-powered diagnostic device, and no MRMC study was conducted.

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

Not applicable, as this is an imaging system, not a standalone algorithm. Its performance is evaluated through technical standards.

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

The "ground truth" for this submission comes from the established and recognized international and FDA standards for medical electrical equipment and X-ray imaging devices. The performance of the new FD17 detector was compared to the predicate detectors, where "image quality performance...is compared and found to be equal." This comparison is technical/physical, not clinical.

8. The sample size for the training set

Not applicable, as this is an X-ray system. The "training" for such a device involves engineering, design, and manufacturing processes compliant with quality systems, not machine learning training on a dataset.

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

Not applicable, as there is no "training set" in the context of machine learning for this device.

Ask a specific question about this device

The Azurion series (within the limits of the Operation Room table) are intended for use to perform · Image guidance in diagnostic, interventional and minimally invasive surgery procedures for the following clinical application areas: vascular, non-vascular, cardiovascular and neuro procedures. · Cardiac imaging applications including diagnostics, interventional and minimally invasive surgery procedures. Additionally: - · The Azurion series can be used in a hybrid Operation Room · The Azurion series contain a number of features to support a flexible and patient centric procedural workflow.

The Azurion R2.1 is classified as an interventional fluoroscopic X-ray system. The primary performance characteristics of the Azurion R2.1 interventional fluoroscopic X-ray system include: Real-time image visualization of patient anatomy during procedures Imaging techniques and tools to assist interventional procedures Post processing functions after interventional procedures Storage of reference/control images for patient records Compatibility to images of other modalities via DICOM Built in radiation safety controls This array of functions offers the physician the imaging information needed to perform minimally invasive interventional procedures. The Azurion R2.1 is available in comparable models and configurations as the currently marketed and predicate device Azurion R1.2. Configurations are composed of detector type (monoplane and biplane), floor or ceiling mounted geometry, standard or OR table type and available image processing. The FlexArm option is available for the 7M20 configuration in Azurion R2.1 The monoplane (single C-arm) and biplane (dual arm) X-ray system configurations are differentiated by the following features: 12 inch Flat Detector (FD12) 15 inch Flat Detector (FD15) 20 inch Flat Detector (FD20) Additionally, identical to the predicate device, Azurion R2.1 can be used in a hybrid operating room when supplied with a compatible operating room table, and can be optionally equipped with the ClarityIQ image processing algorithms.

The provided text describes the Azurion R2.1, an image-intensified fluoroscopic x-ray system, and states that it did not require clinical study data to demonstrate substantial equivalence to its predicate device, Azurion R1.2. Therefore, this document does not contain the detailed information typically found in a study proving the device meets acceptance criteria through clinical performance data.

Instead, the submission relies on demonstrating substantial equivalence based on:

• Indications for Use
• Technological Characteristics
• Non-clinical performance testing
• Safety and Effectiveness

The "study that proves the device meets the acceptance criteria" in this context refers to the non-clinical verification and validation activities summarized.

Here's an analysis of the provided text in relation to your request, noting where information is explicitly stated and where it is absent because no clinical study was conducted:

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

The document mentions that "Results demonstrated that all executed verification tests were passed" and "Results demonstrated that all executed validation protocols were passed" in the non-clinical performance and validation sections. However, it does not provide a specific table of acceptance criteria with corresponding device performance metrics. The general acceptance criteria are compliance with specified standards, user needs, and safety requirements.

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

• Test Set Sample Size: Not applicable in the context of clinical images/data for AI performance evaluation, as this submission did not involve a clinical study or AI performance evaluation on a test set of patient images. The "test set" here refers to the system itself undergoing verification and validation.
• Data Provenance: Not applicable, as no patient data was used for a clinical performance study. The tests were non-clinical verification and validation of the device system.

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)

• Number of Experts: Usability validation was performed with "both interventional radiologists / cardiologists (physicians) and nurse/technicians." The exact number is not specified.
• Qualifications of Experts: Interventional radiologists/cardiologists (physicians) and nurse/technicians. Specific years of experience are not mentioned. Their role was to validate usability and workflow in a simulated environment, not to establish ground truth for image data.

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

• Adjudication Method: Not applicable. This was not a study involving human reader interpretation of images requiring adjudication for ground truth. The "validation protocols" were executed by users, and the passing criteria would have been pre-defined operational outcomes rather than subjective interpretations needing adjudication.

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

• MRMC Study: No. The document explicitly states: "The Azurion R2.1 did not require clinical study data since substantial equivalence to the currently marketed predicate device Azurion R1.2 was demonstrated..." This device is an X-ray system, not specifically an AI algorithm for image analysis that would typically undergo an MRMC study to show human reader improvement.

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

• Standalone Performance: Not explicitly stated as a separate "algorithm only" study. The device itself is an integrated system. The "ClarityIQ image processing algorithms" are mentioned as an optional feature, but their standalone performance is not detailed in this summary, nor is it the primary focus of this 510(k) submission which deems the entire device substantially equivalent.

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

• Type of Ground Truth: Not applicable in the traditional sense of a clinical image-based study. For the verification and validation tests mentioned, the "ground truth" was compliance with established engineering specifications, risk mitigation strategies, international consensus standards, FDA guidance documents, and user needs as validated through simulated use.

8. The sample size for the training set

• Training Set Sample Size: Not applicable. This document describes a medical device (an X-ray system), not an AI algorithm that would have a "training set" of patient data in the machine learning sense.

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

• Ground Truth for Training Set: Not applicable, as there was no AI training set as described for an AI algorithm.

Ask a specific question about this device

Philips Magnetic Resonance (MR) systems are Medical Electrical Systems indicated for use as a diagnostic device. This MR system enables trained physicians to obtain cross-sectional images, spectroscopic images and/or spectra of the internal structure of the head, body or extremities, in any orientation, representing the spatial distribution of protons or other nuclei with spin.

Image appearance is determined by many different physical properties of the tissue and the anatomy, the MR scan technique applied, and presence of contrast agents for diagnostic imaging applications should be performed consistent with the approved labeling for the contrast agent.

The trained clinical user can adjust the MR scan parameters to customize image appearance, accelerate image acquisition, and synchronize with the patient's breathing or cardiac cycle.

The systems can use combinations of images to produce physical parameters, and related derived images, spectra, and measurements of physical parameters, when interpreted by a trained physician, provide information that may assist diagnosis and therapy planning. The accuracy of determined physical parameters depends on system and scan parameters, and must be controlled and validated by the clinical user.

In addition the Philips MR systems provide imaging capabilities, such as MR fluoroscopy, to guide and evaluate interventional and minimally invasive procedures in the head, body and extremities.

MR Interventional procedures, performed inside or adjacent to the Philips MR system, must be performed with MR Conditional or MR Safe instrumentation as selected and evaluated by the clinical user for use with the specific MR system configuration in the hospital. The appropriateness and use of information from a Philips MR system for a specific interventional procedure and specific MR system configuration must be validated by the clinical user.

The proposed Achieva, Intera, Ingenia, Ingenia CX, Ingenia Elition, and Ingenia Ambition MR Systems R5.7 with MultiBand SENSE software feature are provided on the 60 cm and 70 cm bore 1.5 Tesla (1.5T) and 3.0 Tesla (3.0T) Magnetic Resonance Diagnostic Devices.

Hereafter Achieva, Intera, Ingenia, Ingenia CX, Ingenia Elition, and Ingenia Ambition MR Systems R5.7 with MultiBand SENSE software feature will be referred to as the proposed Achieva, Intera, Ingenia, Ingenia CX, Ingenia Elition, and Ingenia Ambition MR Systems in this submission.

This bundled abbreviated 510(k) submission will include software modifications to the following legally marketed MR systems: Ingenia 1.5T, Ingenia 1.5T S, Ingenia 3.0T, Ingenia 1.5T CX, Ingenia 3.0T CX, Ingenia Elition S, Ingenia Elition X, Ingenia Ambition S and Ingenia Ambition X (K183063, 02/14/2019) and Achieva 1.5T, Achieva 3.0T, Intera 1.5T (K190461, 06/04/2019).

All of the aforementioned legally marketed systems will be brought up to the new baseline software R5.7. This submission addresses only software modifications, there are no hardware modifications made to any of the above legally marketed systems.

In this 510(k) submission, Philips Medical Systems Nederland B.V. will be addressing modifications to MultiBand SENSE and one labeling change to the proposed Achieva, Intera, Ingenia, Ingenia CX, Ingenia Elition and Ingenia Ambition MR Systems:

• Removal of contra-indication statement of Compressed SENSE with Gd contrast agent

This 510(k) submission will also address minor software enhancements contained in software R5.7 for the proposed Achieva, Intera, Ingenia, Ingenia CX, Ingenia Elition, and Ingenia Ambition MR Systems since the clearance of the last submission for each of the systems:

1. 4D FreeBreathing
2. MR Elastography Extension
3. EPIC Brain
4. LOVA ADC
5. Computed DWI
6. SmartShim
7. VitalScreen
8. Extended Functionality Options

The proposed Ingenia, Ingenia CX, Ingenia Elition, and Ingenia Ambition MR Systems are intended to be marketed with the following pulse sequences and coils that were previously cleared by FDA:

1. mDIXON (K102344)
2. SWIp (K131241)
3. mDIXON-Quant (K133526)
4. mDIXON XD (K143128)
5. O-MAR K143253
6. 3D APT (K172920)
7. Ingenia Coils

The proposed Achieva, Intera, Ingenia, Ingenia CX, Ingenia Elition and Ingenia Ambition MR Systems are substantially equivalent to the legally marketed predicate device Ingenia, Ingenia CX, Ingenia Elition, and Ingenia Ambition MR Systems (K183063, 02/14/2019).

In addition, the proposed Achieva, Intera, Ingenia, Ingenia CX, Ingenia Elition and Ingenia Ambition MR Systems is substantially equivalent to the following legally marketed reference devices: MultiBand SENSE software application (K162940, 12/30/2016), to support MultiBand SENSE for 1.5T and to support diffusion body imaging on 1.5T and 3.0T.Ingenia 1.5T, Ingenia 1.5T S, Ingenia 1.5T CX, Ingenia 3.0T CX, and Ingenia 3.0T CX R5.4 K173079, 04/04/2018, to support the removal of the contra-indication of the compatibility of Compressed SENSE with (dynamic) Gadolinium contrast-enhanced imaging.

The provided text is a 510(k) Summary for Philips MR Systems, primarily addressing software modifications and enhancements. It focuses on demonstrating substantial equivalence to previously cleared devices rather than presenting a novel AI/CAD device. Therefore, much of the requested information regarding acceptance criteria specifically for AI/CAD performance, MRMC studies, and detailed ground truth establishment for a test set as typically seen for AI algorithm validation is not explicitly detailed in this document.

However, based on the non-clinical performance data section, we can infer some information about "acceptance criteria" in the context of demonstrating equivalence for the software modifications.

Here's an attempt to extract and present the information based on the provided text:

Device: Achieva, Intera, Ingenia, Ingenia CX, Ingenia Elition, and Ingenia Ambition MR Systems (with software modifications R5.7, including MultiBand SENSE and Compressed SENSE with contrast among other enhancements).

Study Goal: To demonstrate substantial equivalence of the modified MR systems to legally marketed predicate devices, particularly regarding the performance of the software features.

Acceptance Criteria and Reported Device Performance

The document doesn't present a specific table of acceptance criteria with numerical performance targets typical for AI/CAD devices (e.g., sensitivity, specificity, AUC). Instead, the acceptance criteria are implicitly performance characteristics demonstrating equivalence to the predicate device and proper functioning of the new features.

Study Details

1. Sample sizes used for the test set and the data provenance:

   • For Compressed SENSE with Contrast:
     • "Bench test results (Shelley phantom)" - number of phantom acquisitions not specified.
     • "Retrospectively and prospectively sub-sampled data" - not specified if this refers to phantom or human data for prospectively sub-sampled.
     • "Data from retrospective sub-sampled CE-angio data, on 3 human subjects."
     • "Clinical data for brain perfusion in tumor classification was provided." (Number of subjects not specified, but this refers to another retrospective subsampling approach.)
   • For other features, the document states "Non-Clinical verification and or validation tests have been performed on all of the software modifications" but does not specify sample sizes for test images or subjects.
   • Data Provenance: Not explicitly stated regarding country of origin. The data appears to be retrospective (e.g., "retrospective sub-sampled CE-angio data"). It's a non-clinical submission, so no large-scale clinical trial data is expected.

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

   • No information provided regarding experts establishing ground truth for a test set. This submission focuses on demonstrating substantial equivalence based on technical and performance characteristics of the MR sequences, not on diagnostic accuracy of an AI interpreting images for specific conditions. The "ground truth" here is implied to be the established performance of the predicate device (non-accelerated acquisition) or physical properties measured by phantoms.
   • The document implies that "interpreted by a trained physician" is crucial for clinical use, but this is not about ground truth for the device's performance testing.

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

   • Not applicable/Not specified. This type of submission does not detail an adjudication process for a diagnostic interpretative task.

4. 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. An MRMC comparative effectiveness study was not performed and is not described in this 510(k) summary. This submission pertains to modifications of the MR scanner's acquisition capabilities, not an AI or CAD system that assists human readers with diagnostic interpretation.

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

   • The studies mentioned (bench tests, subsampled data comparisons) were essentially "standalone" evaluations of the image reconstruction algorithms' technical performance (e.g., temporal and spatial resolution, contrast appearance, robustness) against a reference (fully sampled or non-accelerated data). No specific metrics like sensitivity/specificity for a diagnostic task are provided, as the device is the scanner itself, not an interpretative AI.

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

   • The "ground truth" for the technical performance evaluations appears to be:
     • Phantom data: For assessing properties like time-intensity behavior (Shelley phantom).
     • Fully sampled (non-accelerated) MR acquisition data: Used as a reference for comparison with accelerated acquisition (Compressed SENSE) to assess image quality, spatial/temporal resolution, and contrast appearance.
     • Implied clinical utility/diagnostic information: The "clinical data for brain perfusion in tumor classification" might have relied on clinical diagnosis or other established medical information for the "tumor classification" aspect, but the primary comparison was the technical quality of the MR images generated by the new sequence versus the predicate.

7. The sample size for the training set:

   • Not applicable/Not specified. This document describes improvements to existing MR sequences and software, not a de novo AI model that requires a distinct "training set." The development of the algorithms would have involved internal testing and validation, but not in the sense of a machine learning training dataset for a specific diagnostic task from a large, labeled dataset.

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

   • Not applicable, as no external "training set" in the context of machine learning model development is described.

Ask a specific question about this device

The Zenition 50 device is intended to be used and operated by: adequately trained, qualified and authorized health care professionals who have full understanding of the safety information and emergency procedures as well as the capabilities and functions of the device. The device is used for radiological guidance and visualization during diagnostic, interventional and surgical procedures on all patients, except neonates (birth to one month), within the limits of the device. The device is to be used in health care facilities both inside and outside the operating room, sterile as well as non-sterile environment in a variety of procedures.

Applications:
Orthopedic
Neuro
Abdominal
Vascular
Thoracic
Cardiac

The proposed Zenition 50 is a mobile, diagnostic X-ray imaging and viewing system. It is designed for medical use in healthcare facilities where X-ray imaging is needed. The system comprises of two main components: the C-arm stand and a Mobile View Station(MVS)

The provided text describes the Philips Medical Systems Nederland BV Zenition 50, an image-intensified fluoroscopic X-ray system. The document is a 510(k) summary indicating substantial equivalence to a predicate device, the BV Pulsera.

Based on the provided document, here's a breakdown of the requested information:

1. Table of Acceptance Criteria and Reported Device Performance

The submission demonstrates substantial equivalence by showing compliance with various recognized standards and guidance documents. This largely forms the acceptance criteria for safety and performance.

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

The document primarily discusses non-clinical performance testing (verification and validation) against recognized standards. There is no mention of a clinical study or a specific "test set" of patient data for the Zenition 50 itself. The performance comparison is done against a predicate device, and improvements are assessed through non-clinical means.

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. As no clinical study or specific "test set" with a ground truth established by experts is described for the Zenition 50, this information is not provided. The evaluation relies on compliance with technical standards and comparison to a predicate device.

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

Not applicable, as no clinical test set or adjudication process for image interpretation (which would be typical for AI/algorithm performance) 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

No MRMC comparative effectiveness study is mentioned. The device is a fluoroscopic X-ray system, and the submission focuses on its safety and performance equivalence to a predicate device through non-clinical testing, not on AI assistance for human readers.

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

The document does not describe the Zenition 50 as an AI/algorithm-only device or an algorithm with standalone performance. It is a medical imaging system. Its image processing performance was compared to the predicate device and found "equal or improved" through non-clinical means (Appendix A38, not provided here).

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

For the Zenition 50, the "ground truth" for demonstrating safety and effectiveness relies on compliance with established international and FDA-recognized consensus standards and guidance documents, and by demonstrating substantial equivalence to a legally marketed predicate device (BV Pulsera). This primarily involves technical specifications, risk management, and performance testing against defined engineering and regulatory requirements, rather than clinical ground truth like pathology or outcomes data for a novel diagnostic claim.

8. The sample size for the training set

Not applicable. The document does not describe the Zenition 50 as being developed using a training set of data in the context of machine learning or AI.

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

Not applicable, as there is no mention of a training set for machine learning/AI.

Ask a specific question about this device

The Zenition 70 device is intended to be used and operated by: adequately trained, qualified and authorized health care professionals who have full understanding of the safety information and emergency procedures as well as the capabilities and functions of the device.

The device is used for radiological guidance and visualization during diagnostic, interventional and surgical procedures on all patients, except neonates (birth to one month), within the limits of the device is to be used in health care facilities both inside and outside the operating room, sterile environment in a variety of procedures.

Applications:

• Orthopedic .
• · Neuro
• · Abdominal
• . Vascular
• · Thoracic
• · Cardiac

The proposed Zenition 70 is a mobile, diagnostic X-ray imaging and viewing system. It is designed for medical use in healthcare facilities where X-ray imaging is needed. The system comprises two main components: the C-arm stand and a mobile view station

The provided text describes the regulatory clearance for the Philips Zenition 70, an image-intensified fluoroscopic x-ray system, based on substantial equivalence to a predicate device (Veradius Unity).

Here's an analysis of the acceptance criteria and supporting study information based on the provided document:

1. Table of Acceptance Criteria and Reported Device Performance:

The document does not present a table of specific quantitative acceptance criteria for device performance in the traditional sense (e.g., sensitivity, specificity, accuracy for a diagnostic task). Instead, the acceptance criteria are framed in terms of compliance with recognized standards and guidance documents. The "reported device performance" is primarily that it meets these standards and is comparable to the predicate device.

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

• Test Set (Non-clinical Performance Data): The document refers to "Non-clinical performance testing" and "Non-clinical validation testing." It states that these tests demonstrate compliance with standards and that the device meets acceptance criteria.
  • Sample Size: The document does not specify a sample size for the non-clinical tests. This type of testing typically involves engineering and bench testing, not patient-based data, so a "sample size" in the clinical sense is not applicable.
  • Data Provenance: The data comes from internal non-clinical verification and validation testing conducted by the manufacturer, Philips Medical Systems Nederland B.V. The nature of the studies implies prospective testing against engineering specifications and regulatory standards. No patient data or country of origin for such data is mentioned as this device clearance did not involve clinical studies.

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

This information is not applicable as the document explicitly states: "The Zenition 70 did not require clinical study since substantial equivalence... was demonstrated." Therefore, there was no clinical test set requiring expert ground truth establishment. The ground truth for the non-clinical tests would be the design specifications and the requirements of the standards themselves, assessed by engineers and regulatory experts.

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

This information is not applicable for the same reason as point 3. There was no clinical test set requiring image interpretation or expert adjudication.

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:

This is not applicable. The device is an image-intensified fluoroscopic x-ray system, which is a hardware device for imaging. It is not an AI-driven diagnostic assistance tool that would typically undergo an MRMC study to compare human reader performance with and without AI assistance. The clearance is based on substantial equivalence to another fluoroscopy system.

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

This is not applicable. As mentioned above, the Zenition 70 is a medical imaging hardware system, not a standalone AI algorithm.

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

For the non-clinical performance and validation tests, the "ground truth" was derived from:

• Engineering specifications and design requirements of the device.
• Requirements stipulated by the international and FDA-recognized consensus standards (e.g., IEC 60601 series for electrical safety, radiation protection; ISO 14971 for risk management; IEC 62304 for software lifecycle processes).
• FDA guidance documents relevant to X-ray imaging devices.

8. The sample size for the training set:

This is not applicable. The Zenition 70 is a hardware imaging device, not a machine learning or AI model that requires a "training set." The development process would involve traditional engineering design, manufacturing, and testing.

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

This is not applicable for the same reason as point 8.

Ask a specific question about this device

The Azurion series (within the limits of the used Operation Room table) are intended for use to perform:

• Image guidance in diagnostic, interventional and minimally invasive surgery procedures for the following clinical application areas: vascular, non-vascular, cardiovascular and neuro procedures.
• Cardiac imaging applications including diagnostics, interventional and minimally invasive surgery procedures.
  Additionally:
• The Azurion series can be used in a hybrid Operation Room.
• The Azurion series contains a number of features to support a flexible and patient centric procedural workflow.

The Azurion R2.0 is classified as an interventional fluoroscopic X-ray system. The primary performance characteristics of the Azurion R2.0 interventional fluoroscopic X-ray system include:

• Real-time image visualization of patient anatomy during procedures
• Imaging techniques and tools to assist interventional procedures
• Post processing functions after interventional procedures
• Storage of reference/control images for patient records
• Compatibility to images of other modalities via DICOM
• Built in radiation safety controls
  This array of functions offers the physician the imaging information needed to perform minimally invasive interventional procedures. The Azurion R2.0 is available as a single monoplane (single C-arm) configuration of the currently marketed and predicate devices Azurion series R1.2 consisting of a FD20 (frontal channel) detector with a ceiling (Clea) geometry having a standard or OR compatible table. This can optionally be configured with a horizontal L-arm which provides an extra rotation axis, with re-designed motion control software providing patient and X-ray beam positioning movement and an improved 3D roll scan time. Additionally, identical to the predicate devices, Azurion R2.0 can be used in a hybrid operating room when supplied with a compatible operating room table, and can be optionally equipped with the ClarityIQ image processing algorithms.

The provided text describes the Philips Azurion R2.0, an interventional fluoroscopic X-ray system, and its substantial equivalence to a predicate device. However, it does not contain the detailed information necessary to fully answer all aspects of your request regarding acceptance criteria and a specific study proving the device meets those criteria with granular details like sample sizes for test and training sets, number and qualifications of experts, adjudication methods, or specific comparative effectiveness study results.

The document primarily focuses on demonstrating substantial equivalence to a predicate device (Azurion series R1.2) based on similarities in indications for use, technological characteristics, and non-clinical performance testing. It states that "the Azurion series R2.0 did not require clinical study data."

Therefore, I cannot provide a table of acceptance criteria with reported device performance, sample sizes, expert qualifications, or specific study design elements as these details are not present in the provided text.

However, I can extract the information that is available:

1. Table of Acceptance Criteria and Reported Device Performance:

The document states that non-clinical performance testing "demonstrates compliance with the following International and FDA-recognized consensus standards and FDA guidance documents" and "meets the acceptance criteria and is adequate for its intended use."

While specific numerical acceptance criteria (e.g., "accuracy > 95%") are not provided, the "acceptance criteria" implicitly refer to meeting the requirements of these standards and guidance documents. The "reported device performance" is that it complies with these standards.

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

• Test Set Sample Size: Not specified. The document refers to "non-clinical performance testing," "software verification testing," and "non-clinical validation testing," including "simulated use environment" studies. No specific number of test cases, images, or subjects for these evaluations is given.
• Data Provenance: The studies are described as "non-clinical" and "simulated use," suggesting they were conducted in a controlled environment, likely by Philips Medical Systems Nederland B.V. The document does not specify the country of origin of data or if it was retrospective or prospective in detail. It does state that usability was performed with "interventional validation radiologists/cardiologists (physicians) and nurse/technicians in a simulated use environment." This indicates prospective data collection within the simulated environment.

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. The document mentions "interventional validation radiologists/cardiologists (physicians) and nurse/technicians" participated in usability and simulated use studies. However, it does not state how many of each were involved or if they established a formal "ground truth" for a test set in the traditional sense of diagnostic accuracy. Their role was to validate the device's usability and conformity to intended use.
• Qualifications of Experts: "Interventional validation radiologists/cardiologists (physicians) and nurse/technicians." Specific experience levels (e.g., "10 years of experience") are not provided.

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

• Adjudication Method: Not specified. The description of validation activities indicates that "participants executed validation protocols," and "all executed validation protocols were passed." This suggests a pass/fail assessment based on predefined criteria during the simulated use, rather than a conflict resolution/adjudication process for diagnostic ground truth.

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:

• MRMC Comparative Effectiveness Study: No. The document explicitly states: "The Azurion series R2.0 did not require clinical study data since substantial equivalence to the currently marketed predicate device Azurion series R1.1 was demonstrated..." There is no mention of an MRMC study or an assessment of human reader improvement with or without AI assistance. The device is an imaging system, and while it mentions "ClarityIQ image processing algorithms" can optionally be equipped, the focus of this submission is on the hardware and core software updates, not on a specific AI assistance feature for diagnostic improvement.

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

• Standalone Performance Study: Not applicable in the context of diagnostic accuracy for an algorithm. The device is an interventional fluoroscopic X-ray system, not a standalone AI diagnostic algorithm. Its "performance" refers to its compliance with technical and safety standards in a system context. Software verification testing was performed on "functional and non-functional requirements," which is a form of standalone testing for the software components, but not in the sense of a diagnostic accuracy study.

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

• Type of Ground Truth: For the "non-clinical validation testing," the "ground truth" was effectively established by adherence to predefined "user needs, intended use, claims, effectiveness of safety measures and instructions for use." This is not a diagnostic ground truth (like pathology or outcomes data) but rather a validation that the system functions as intended and meets safety and usability criteria within a simulated environment.

8. The sample size for the training set:

• Training Set Sample Size: Not applicable. This document describes a medical device (X-ray system) and its software updates, not a machine learning model that would typically have a distinct "training set." The software components are verified and validated against specifications.

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

• Ground Truth for Training Set: Not applicable, as this is not a machine learning model.

Ask a specific question about this device

The Interventional Workspot has the following medical purpose:
· import, export and storage of digital clinical images,
· manage the patient information associated with those images.

The Interventional Workspot is a software platform to host Interventional Tools. It provides common functionalities (e.g. import / export and data handling functions) that are required by the Interventional Tools to support the physician with performing the interventional procedure.

The provided document is a 510(k) premarket notification for a medical device called "Interventional Workspot." This device is a software platform intended to host interventional tools and provide common functionalities like importing, exporting, and managing digital clinical images and associated patient information.

Key takeaway: The document describes a "Picture archiving and communications system" that handles and displays medical images and associated patient information. It does not describe an AI medical device that provides diagnostic or prognostic insights, therefore, it does not have the kind of performance acceptance criteria typically seen for AI/ML devices.

The product is a software platform (21 CFR 892.2050 - Picture archiving and communications system) and functions primarily as a data handler and host for other interventional tools. It is an accessory to Philips Interventional X-ray systems.

Based on the provided information, the device is not an AI/ML diagnostic or prognostic device. It does not perform tasks such as detecting abnormalities, classifying diseases, or predicting outcomes based on image analysis. Therefore, the questions related to "acceptance criteria" in the context of diagnostic performance (e.g., sensitivity, specificity, AUC), sample sizes for test/training sets, expert ground truth, MRMC studies, or standalone algorithm performance are not applicable to this device.

The study referenced focuses on demonstrating substantial equivalence to a predicate device (Interventional Workspot Release 1.0, K121296) by showing that the new version (1.4.5.1) has similar indications for use, technological characteristics, and safety and effectiveness, despite some minor updates (e.g., operating system, hardware support, bug fixes, security features).

The acceptance criteria for this device are related to its functional performance, safety, and compliance with relevant standards, rather than diagnostic accuracy.

Here's a breakdown of the available information relevant to "acceptance criteria" and the "study" (non-clinical performance testing) conducted:

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

The document does not present a formal table of quantitative acceptance criteria for diagnostic or prognostic performance, as it is not an AI/ML diagnosis/prognosis device. Instead, the acceptance criteria are implicitly tied to a series of verification and validation tests demonstrating the device's functional integrity, safety, and compliance with standards.

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

• Sample Size: Not applicable. The "test set" here refers to the software verification and validation activities, which involve structured testing scenarios rather than a dataset of clinical cases for diagnostic performance evaluation. The document states: "Software verification testing has been performed to verify the modifications as per predetermined System Requirements Specification and acceptance criteria. The verification tests and acceptance criteria were identified based on Risk Assessent. Verification tests were performed to verify safety risk control measures from the Detailed Risk Management Matrix and to verify the Privacy and Security requirements for Interventional Workspot 1.4.5.1 have been implemented."
• Data Provenance: Not applicable. No clinical image data or patient data was used for a performance study. "Clinical images are not necessary to establish substantial equivalence based on the modifications to the predicate device (note that the Interventional Workspot software is strongly based on the predicate). Non-clinical performance data provides sufficient evidence that the subject device works as intended."

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

• Not applicable. There is no "ground truth" in the clinical diagnostic sense for this device. The testing involved verifying that the software performs its intended functions (e.g., import/export images, manage patient info) correctly and securely, and complies with engineering and quality standards.

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

• Not applicable. No diagnostic "test set" requiring expert adjudication.

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. This is not an AI-assisted diagnostic device.

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

• Not applicable. This device is a software platform, not an algorithm that performs a standalone clinical task.

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

• Not applicable. The "ground truth" for this device's validation is adherence to functional requirements, safety specifications, and recognized industry standards (e.g., DICOM compatibility, cybersecurity, usability engineering).

8. The sample size for the training set:

• Not applicable. This device does not use machine learning or AI that requires a training set.

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

• Not applicable. No training set for an AI/ML model.

Ask a specific question about this device

The Azurion series (within the limits of the used Operation Room table) are intended for use to perform:

· Image guidance in diagnostic, interventional and minimally invasive surgery procedures for the following clinical application areas: vascular, non-vascular, cardiovascular and neuro procedures,

· Cardiac imaging applications including diagnostics, interventional and minimally invasive surgery procedures.

Additionally:

• · The Azurion series can be used in a hybrid Operation Room.
  · The Azurion series contain a number of features to support a flexible and patient centric procedural workflow.

The Azurion series R1.2 is classified as an interventional fluoroscopic X-ray system. The primary performance characteristics of the Azurion series R1.2 interventional fluoroscopic X-ray system include:

• Real-time image visualization of patient anatomy during procedures ●
• Imaging techniques and tools to assist interventional procedures ●
• Post processing functions after interventional procedures o
• Storage of reference/control images for patient records ●
• Compatibility to images of other modalities via DICOM o
• Built in radiation safety controls ●

This array of functions offers the physician the imaging information needed to perform minimally invasive interventional procedures.

The Azurion series R1.2 is available in a comparable set of configurations for monoplane models as the currently marketed and predicate devices Allura Xper R9.

Configurations are composed of detector type. (monoplane) geometry, table type and available image processing. The monoplane (single C-arm) and biplane (dual arm) systems are categorized into X-ray systems and the configurations are differentiated by the following features:

• 12 inch Flat detector (FD12)
• 15 inch Flat detector (FD15)
• 20 inch Flat detector (FD20) ●

Additionally, identical to the predicate devices, all configurations of the Azurion series R1.2 can be used in a hybrid operating room when supplied with a compatible operating room table, and can be optionally equipped with the ClarityIQ image processing algorithms.

Here's an analysis of the provided text regarding the Azurion series R1.2 device, focusing on acceptance criteria and the study that proves the device meets those criteria:

1. Table of Acceptance Criteria and Reported Device Performance

The provided text describes the Azurion series R1.2 as an interventional fluoroscopic X-ray system intended for image guidance and cardiac imaging applications. It indicates that the device's performance is demonstrated through its compliance with various international and FDA-recognized consensus standards and guidance documents, as well as software verification and non-clinical validation testing. However, the document does not explicitly state specific, quantifiable acceptance criteria (e.g., "minimum resolution of X lp/mm," "contrast-to-noise ratio of Y"). Instead, it focuses on demonstrating equivalence to a predicate device and compliance with established standards.

Therefore, the "acceptance criteria" can be inferred as successful completion of the listed tests and compliance with the relevant standards, aiming for performance that is "substantially equivalent" to the predicate device.

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

The document does not specify a "test set" in the context of patient data or image datasets. The performance validation is based on:

• Software verification testing: Performed to cover system-level requirements and risk control measures. The "sample size" here would refer to the number of software test cases, which is not provided.
• Non-clinical validation testing: Performed to cover intended use, claims, user needs, etc. The "sample size" is not specified here either, as this refers to device-level validation activities rather than a dataset.
• Lack of clinical study data: The document explicitly states: "The Azurion series R1.2 did not require clinical study data since substantial equivalence to the currently marketed predicate device Allura Xper R9 was demonstrated..."

Therefore, there is no information about a "test set" sample size or data provenance in the sense of patient data or images used for algorithmic performance evaluation.

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

Since no clinical study data or image-based test set with ground truth is mentioned for the Azurion series R1.2 in this document, there is no information regarding experts used to establish ground truth or their qualifications. The device is evaluated for substantial equivalence based on technical specifications and non-clinical testing.

4. Adjudication Method for the Test Set

As there is no mention of a clinical test set or human interpretation of images requiring ground truth adjudication, no adjudication method is described.

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

No MRMC comparative effectiveness study is mentioned. The submission explicitly states that clinical study data was not required.

6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study

The device itself is an X-ray imaging system, not an AI algorithm designed for standalone diagnostic interpretation. Its "performance" is inherently tied to producing images for human interpretation and guiding procedures. Therefore, the concept of a "standalone" algorithmic performance study as typically understood for AI/CAD devices does not directly apply here. The software verification and non-clinical validation assess the system's operational integrity and image generation capabilities.

7. Type of Ground Truth Used

Given the nature of the device (an X-ray imaging system) and the emphasis on non-clinical testing and substantial equivalence, the "ground truth" for its evaluation would primarily involve:

• Technical specifications and engineering standards: Compliance with IEC, ISO, and FDA guidance documents serves as a form of "ground truth" that the device meets defined safety and performance benchmarks.
• Predicate device features and performance: The Allura Xper R9 serves as the primary "ground truth" reference for substantial equivalence, meaning the Azurion series R1.2 is evaluated against the established and cleared performance and safety profile of the predicate device.
• Internal functional requirements: Software verification tests against defined functional and non-functional requirements.

There is no mention of pathology, expert consensus on patient images, or outcomes data being used as ground truth in this 510(k) summary.

8. Sample Size for the Training Set

No information is provided about a training set. This device is an imaging system, not an AI/ML algorithm that would typically require a training set of data. While the device may incorporate image processing algorithms (like ClarityIQ), the document doesn't detail their development or any associated training sets.

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

As no training set is mentioned in the context of this device's submission, there is no information on how its ground truth would have been established.

Ask a specific question about this device

Dynamic Coronary Roadmap is intended to assist the physician during percutaneous coronary interventions in correlating the device position to the coronary vasculature, by providing a motion compensated overlay of this coronary vasculature. Dynamic Coronary Roadmap is suitable for use with the entire adult human population.

Dynamic Coronary Roadmap is a software medical device and does not come in contact with a human subject.

The Dynamic Coronary Roadmap is a software medical device intended to provide a real-time and dynamic angiographic roadmap of coronary arteries. The angiographic roadmap is automatically generated from previously acquired diagnostic coronary angiograms during the same procedure.

Dynamic Coronary Roadmap uses coronary angiograms, acquired during a PCI procedure, to automatically generate a dynamic angiographic roadmap of the coronary vasculature. This roadmap is then overlaid on the live fluoroscopy images during device navigation. Dynamic Coronary Roadmap works in combination with a Philips interventional X-ray system. The user interface of Dynamic Coronary Roadmap guides the physician through the workflow and minimal additional user interaction from the tableside is required. The following design features support the physician with this:

• Dynamic angiographic roadmap creation; this technique allows the physician to automatically construct a 2D dynamic angiographic roadmap of the coronary vasculature from a diagnostic coronary angiogram.
• Live guidance; this technique provides continuous overlay of the dynamic angiographic roadmap on live fluoroscopic images.
• X-ray system integration; this provides the physician with a seamless integration with the Philips interventional X-ray system. The clinical product supports:
  • Automatic power ON or OFF; this allows the software medical device to always be available by automatically powering ON and OFF with the X-ray system.
  • 3D Automatic Position Control (APC); this allows the C-arm to automatically move to a nearby available dynamic angiographic roadmap to be able to reuse this for live guidance.
  • Table-side control; this provides the physician with an efficient workflow during interventional procedures. The most frequently used functions that require additional user interaction next to the normal x-ray system interaction can be controlled from the tableside of the Xray system.

Here's a breakdown of the acceptance criteria and the study information for the Dynamic Coronary Roadmap, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present a table of quantitative acceptance criteria with corresponding performance metrics. Instead, it describes general categories of testing and validation, concluding that the device "passed" and "conforms" to requirements.

2. Sample Size for the Test Set and Data Provenance

The document states:

• Test Set Description: "Standard angiographic and fluoroscopy x-ray data" was used for algorithm verification and expert opinion validation, allowing for evaluation of "a wide range of variance e.g. region to treat, detector format, patient, acquisition angles."
• Sample Size: The exact number of cases or data points in the test set is not specified.
• Data Provenance: The document does not explicitly state the country of origin or whether the data was retrospective or prospective. It only mentions "standard angiographic and fluoroscopy x-ray data."

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

• Number of Experts: The document states that "certified interventional cardiologists" participated in the Expert Opinion Validation. While it mentions "the expert" (singular) evaluating, it implicitly suggests a group of experts due to the nature of validation. However, the exact number of experts is not specified.
• Qualifications: "Certified interventional cardiologists." No specific years of experience are mentioned.
• For In-house Simulated Validation: "Experienced Clinical Marketing Specialists with clinical knowledge gained from work experience and hospital visits." These test participants "have experience in the relevant clinical area and therefore are considered equivalent to the intended operator profiles."

4. Adjudication Method for the Test Set

The document does not describe a formal adjudication method (e.g., 2+1, 3+1, none) for the test set. The "Expert Opinion Validation" involved experts evaluating performance, but the process for resolving disagreements or establishing a single ground truth from multiple expert opinions is not detailed.

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

• Was it done? No, the document does not mention a multi-reader multi-case (MRMC) comparative effectiveness study.
• Effect Size: Therefore, no effect size of AI assistance versus without AI assistance is reported.

6. Standalone Performance Study (Algorithm Only)

Yes, a standalone performance assessment of the algorithm was part of the "Algorithm Verification Testing." This testing was performed "with standard angiographic and fluoroscopy x-ray data to ensure sufficient functioning of the algorithms." It specifically focused on "registration of the catheter tip and the guide wire," implying an evaluation of the algorithm's output independently.

7. Type of Ground Truth Used

The concept of "ground truth" seems to be established through:

• Expert Consensus/Opinion: For the "Expert Opinion Validation," the performance of the device was evaluated against the assessment of certified interventional cardiologists in a simulated environment. This implies that their collective judgment served as the benchmark.
• Internal Validation/Simulated Clinical Setting: For the "In-house Simulated Validation," established protocols representing clinical user needs and safety mitigations were used, with evaluation performed by experienced clinical marketing specialists. This suggests a pre-defined set of expected outcomes or correct performance against which the device was measured.
• System Requirements/Risk Control Measures: For "General Verification Testing," the device's performance was measured against "system level requirements" and "identified risk control measures."

8. Sample Size for the Training Set

The document does not specify the sample size used for the training set. It focuses on verification and validation data.

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

The document does not describe how the ground truth for any training set was established, as it does not elaborate on the development or training of the algorithms, only their verification and validation.

Ask a specific question about this device