Search Results

The AV Viewer is an advanced visualization software intended to process and display images and associated data in a clinical setting.

The software displays images of different modalities and timepoints, and performs digital image processing, measurement, manipulation, quantification and communication.

The AV Viewer is not to be used for mammography.

AV Viewer is an advanced visualization software which processes and displays clinical images from the following modality types: CT, CBCT – CT format, Spectral CT, MR, EMR, NM, PET, SPECT, US, XA (iXR, DXR), DX, CR and RF.

The main features of the AV Viewer are:
• Viewing of current and prior studies
• Basic image manipulation functions such as real-time zooming, scrolling, panning, windowing, and rolling/rotating.
• Advanced processing tools assisting in the interpretation of clinical images, such as 2D slice view, 2D and 3D measurements, user-defined regions of interest (ROIs), 3D segmentation and editing, 3D models visualization, MPR (multi planar Reconstructions) generation, image fusion and more.
• A finding dashboard used for capturing and displaying findings of the patient as an overview.
• Customized workflows allow the user to create their own workflows
• Tools to export customizable reports to the Radiology Information System (RIS) or PACS (Picture archiving and communication system) in different formats.

AV Viewer is based on the AV Framework, an infrastructure that provides the basis for the AV Viewer and common functionalities such as: image viewing, image editing tools, measurements tools, finding dashboard.

AV viewer can be hosted on multiple platforms and devices, such as Philips AVW, Philips CT/MR scanner console or on cloud.

The provided FDA 510(k) clearance letter for the AV Viewer device indicates that the device has met its acceptance criteria through various verification and validation activities. However, the document does not include detailed quantitative acceptance criteria (e.g., specific thresholds for accuracy, sensitivity, specificity, or measurement error) or comprehensive performance data that would typically be presented in a clinical study report. The submission focuses on demonstrating "substantial equivalence" to a predicate device rather than presenting detailed performance efficacy of the algorithm itself.

Therefore, much of the requested information regarding specific performance metrics, sample sizes for test and training sets, expert qualifications, and detailed study methodologies is not explicitly stated in this 510(k) summary. I will extract and infer what is present and explicitly state when information is missing.

Here's a breakdown based on the provided document:

Acceptance Criteria and Device Performance

The document describes comprehensive verification and validation activities, including "Bench Testing" for measurements and segmentation algorithms. However, specific quantitative acceptance criteria (e.g., "accuracy > 95%") and the reported performance values are not detailed in this summary. The general statement is that "Product requirement specifications were tested and found to meet the requirements" and "The validation objectives have been fulfilled, and the validation results provide evidence that the product meets its intended use and user requirements."

Table of Acceptance Criteria and Reported Device Performance

Note: The quantitative details for the "Acceptance Criteria" and "Reported Device Performance" for measurement accuracy and segmentation accuracy are missing from this 510(k) summary. The document only confirms that these tests were performed and the results were positive.

Study Details Based on the Provided Document:

2. Sample sizes 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 explicitly stated. The document mentions "Verification," "Validation," "Expert Test," and "Bench Testing" were performed, implying the use of test data, but no specific number of cases or images in the test set is provided.
• Data Provenance: Not explicitly stated. The document does not specify the country of origin of the data used for testing, nor does it explicitly state whether the data was 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 explicitly stated. The "Expert Test" mentions "a clinical expert" (singular) was used to test use case scenarios. It does not mention experts establishing ground truth for broader validation.
• Qualifications of Experts: The "Expert Test" mentions "a clinical expert." For intended users, the document states "trained professionals, including but not limited to, physicians and medical technicians" (Subject Device), and "trained professionals, including but not limited to radiologists" (Predicate Device). It can be inferred that the "clinical expert" would hold one of these qualifications, but specific details (e.g., years of experience, subspecialty) are not provided.

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

• Adjudication Method: Not explicitly stated. The document refers to "Expert test" where "a clinical expert" tested scenarios, implying individual assessment rather than a multi-reader adjudication process for establishing ground truth for a test set.

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: Not explicitly stated or implied. The document focuses on the device's substantial equivalence to a predicate device and its internal verification and validation. There is no mention of a human-in-the-loop MRMC study to compare reader performance with and without AV Viewer assistance. The AV Viewer is described as an "advanced visualization software" and not specifically an AI-driven diagnostic aid that would typically warrant such a study for demonstrating improved reader performance.

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

• Standalone Performance Study: The "Bench Testing" section states that it "was performed on the measurements and segmentation algorithms to validate their performance and the correctness of the various measurement functions." This implies a standalone evaluation of these specific algorithms. However, the quantitative results (e.g., accuracy, precision) of this standalone performance are not provided.

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

• Type of Ground Truth: For the "Bench Testing" of measurement and segmentation algorithms, the ground truth would likely be based on reference measurements/segmentations, possibly done manually by experts or using highly accurate, non-clinical methods. For other verification/validation activities, the ground truth would be against the pre-defined product and user requirements. However, explicit details about how this ground truth was established (e.g., expert consensus, comparison to gold standard devices/methods) are not specified.

8. The sample size for the training set

• Training Set Sample Size: Not explicitly stated. The document does not mention details about the training data used to develop the AV Viewer's algorithms. The focus is on validation for regulatory clearance. Since the product is primarily an "advanced visualization software" with general image processing tools, much of its functionality might not rely on deep learning requiring large, distinct training sets in the same way a specific AI diagnostic algorithm would.

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

• Ground Truth for Training Set: Not explicitly stated. As no training set details are provided, the method for establishing its ground truth is also not mentioned.

Summary of Missing Information:

This 510(k) summary provides a high-level overview of the device's intended use, comparison to a predicate, and the types of verification and validation activities conducted. It largely focuses on demonstrating "substantial equivalence" based on similar indications for use and technological characteristics. Critical quantitative details about the performance of specific algorithms (measurements, segmentation), the size and characteristics of the datasets used for testing, and the methodology for establishing ground truth are not included in this public summary. Such detailed performance data is typically found in the full 510(k) submission, which is not publicly released in its entirety.

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. The use 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. 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 subject Achieva, Intera, Ingenia 1.5T, Ingenia 3.0T, Ingenia 1.5T CX, Ingenia 3.0T CX, Ingenia Elition S, Ingenia Elition X, Ingenia Ambition S, Ingenia Ambition X and MR 5300 MR Systems are 60 cm and 70 cm bore 1.5 and 3.0 Tesla (1.5T and 3.0T) Magnetic Resonance Diagnostic Devices.
In this 510(k) submission, Philips Medical Systems Netherlands B.V. will be addressing the following software changes for the subject device since the last 510(k) submission (primary predicate device (K212673, 11/19/2021), secondary predicate device (K193215, 04/10/2020)):

• Software functionality that allows early detection of severe gradient malfunctions. The system is locked for scanning if a malfunction is detected.
• Smoke detector software support extension from Ingenia Elition S and X to all other 70cm bore systems
• SENSE XL Torso Coil workflow extensions to guide the operator on safe usage of the SENSE XL Torso Coil and monitoring of the SENSE XL Torso Coil temperature

The subject Achieva, Intera, Ingenia 1.5T, Ingenia 3.0T, Ingenia 1.5T CX, Ingenia 3.0T CX, Ingenia Elition S, Ingenia Elition X, Ingenia Ambition S, Ingenia Ambition X and MR 5300 MR Systems are intended to be marketed with the same pulse sequences and coils that are previously cleared by FDA. The accessories to be used with the subject devices have not changed compared to the predicate device.
When Philips MRI system is used in combination with the Philips MR-RT or MR-OR solutions, the user is referred to the dedicated MR-RT and MR-OR Instructions for Use for information on additional accessories that may apply.

The provided FDA 510(k) clearance letter and its associated 510(k) Summary for Philips MR Systems (K251808) DO NOT contain the detailed information required to describe the acceptance criteria and the study that proves the device meets the acceptance criteria in the manner requested.

This submission is a Special 510(k), which is used for modifications to a manufacturer's own legally marketed device where the modified device is still substantially equivalent to the cleared device, and the modifications do not raise new questions of safety and effectiveness. This type of submission often relies heavily on risk management and performance testing to demonstrate that the changes have not degraded the safety or effectiveness of the device.

The document primarily focuses on software changes related to safety-critical functions (gradient malfunction detection, smoke detector interlock, SENSE XL Torso Coil temperature monitoring) and asserts substantial equivalence to existing predicate devices.

Here's why the requested information cannot be fully extracted and what can be inferred:

Summary of Information NOT Present in the Document:

• Detailed Acceptance Criteria Table with Performance Data: The document states that "The verification and/or validation test results demonstrate that the subject... MR Systems meet the acceptance criteria and are adequate for the intended use" (Page 8), but it does not provide a specific table of these acceptance criteria nor the numerical performance data for the device against them. The information provided about the software changes focuses on their functionality and equivalence rather than quantitative performance metrics (e.g., specific thresholds for gradient malfunction detection sensitivity/specificity, or precise temperature monitoring accuracy).
• Sample Size for Test Set and Data Provenance: No specific test set sample sizes (e.g., number of patients, number of scans) are mentioned. The testing described is "Non-Clinical verification and validation tests," implying it's not based on patient data in the typical sense for clinical performance.
• Number of Experts and Qualifications for Ground Truth: Since no clinical data or diagnostic performance studies are described (only non-clinical V&V), there's no mention of experts establishing ground truth for a test set.
• Adjudication Method for Test Set: Not applicable as no clinical study with expert reads is described.
• Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study: Not mentioned as no clinical study evaluating human reader performance is described.
• Standalone (Algorithm Only) Performance: While the software features operate automatically, no quantitative standalone performance data (e.g., TPR, FPR for malfunction detection) is provided. The focus is on the functionality of the safety mechanisms (e.g., "system is locked," "enforces a cool down period").
• Type of Ground Truth Used: For the safety software functions, the "ground truth" would likely be derived from engineering specifications, simulated fault conditions, or direct sensor readings validated against known physical parameters, rather than expert consensus on medical images or pathology. The document hints at this by stating "verification and/or validation test results demonstrate that the subject... meet the acceptance criteria and are adequate for the intended use."
• Sample Size for Training Set & Ground Truth Establishment for Training Set: Since these are modifications to existing, cleared devices, and the described changes are primarily safety and workflow enhancements, it's unlikely that new deep learning models requiring large imaging training sets were developed for these specific features. If machine learning was involved in the gradient malfunction detection, the specific training methodology is not disclosed. The document implies engineering-based verification and validation rather than large-scale data-driven model training.

Information that CAN be Inferred or Directly Stated:

• Study Type: Non-clinical verification and validation tests, adhering to recognized international and FDA-recognized consensus standards (e.g., IEC 60601-1-6 for usability, IEC 62304 for software lifecycle, ISO 14971 for risk management).
• Overall Conclusion: The non-clinical testing demonstrates that the modified MR Systems "meet the acceptance criteria and are adequate for the intended use" and that "all risks are sufficiently mitigated, that no new risks are introduced, and that the overall residual risks are acceptable." This leads to the conclusion of substantial equivalence.
• Basis for Ground Truth (Implied): For the safety features, the "ground truth" is established by engineering specifications, simulated fault conditions, and internal testing to ensure the alarm/lockout mechanisms activate correctly under defined hazardous conditions and that the temperature monitoring is accurate.
• Key Software Changes and Their Demonstrated Functionality:
  • Severe Gradient Malfunction Detection: Modifies the system to lock when the frequency of gradient amplifier errors exceeds predefined thresholds, preventing severe malfunctions. The previous system only aborted individual errors and allowed continuation. The "study" here would be demonstrating that the system properly locks when these new thresholds are met and does not falsely lock otherwise.
  • Smoke Detector Software Support Extension: Extends existing 60cm MR System smoke detector interlock software to 70cm MR Systems. The "study" would show that the same logic and safety performance are maintained on the new platform.
  • SENSE XL Torso Coil Workflow Extensions: Software now enforces a cool-down period for the coil and guides the operator on temperature management. The "study" likely involved testing the logic of the cool-down enforcement and the accuracy/timing of the temperature warnings.

Based on the provided document, here's the most that can be extracted and inferred about the acceptance criteria and studies:

Device: Philips Achieva, Intera, Ingenia 1.5T, Ingenia 3.0T, Ingenia 1.5T CX, Ingenia 3.0T CX, Ingenia Elition S, Ingenia Elition X, Ingenia Ambition S, Ingenia Ambition X and MR 5300 MR Systems (software modifications).

Purpose of the Study: To demonstrate that software changes implemented for gradient malfunction detection, smoke detector interlock extension, and SENSE XL Torso Coil temperature monitoring do not raise new questions of safety and effectiveness and that the modified devices remain substantially equivalent to their predicate devices.

1. Table of Acceptance Criteria and Reported Device Performance:

2. Sample Size Used for the Test Set and Data Provenance:
The document states "Non-Clinical verification and validation tests have been performed." This implies engineering-level testing rather than patient-based clinical studies. No specific sample sizes (e.g., number of scan instances, number of patients) are provided. The data provenance is internal Philips testing, likely performed in the Netherlands (Philips Medical Systems Nederland B.V.). It is retrospective in the sense that it evaluates modifications to existing systems.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications:
Not applicable. Ground truth for these safety software functions is based on engineering specifications and direct measurement/simulation of system states and physical parameters (e.g., gradient performance, temperature, smoke detection), not on expert interpretations of medical images.

4. Adjudication Method for the Test Set:
Not applicable. There is no mention of human readers or adjudication processes for clinical image interpretation.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done:
No, an MRMC comparative effectiveness study was not done or reported in this 510(k) summary. The nature of these software modifications (safety and workflow enhancements) does not typically necessitate such a study for 510(k) clearance, especially in a Special 510(k). The document explicitly states "the indications for use remain unchanged and there were no technological characteristics relative to the predicate device that would require clinical testing."

6. If a Standalone (Algorithm Only) Performance was done:
Yes, in the sense that the software features (e.g., gradient malfunction detection, temperature monitoring logic) are algorithms operating on system data. However, quantitative performance metrics (e.g., sensitivity, specificity, accuracy) for these algorithms are not explicitly provided in the summary. The "performance" described is functional—that the system does lock, does enforce cool-downs, etc., when conditions are met.

7. The Type of Ground Truth Used:
For the software changes described, the ground truth is primarily based on:
* Engineering Specifications: Defining thresholds for gradient errors, acceptable temperature ranges for the coil.
* Simulated Fault Conditions: Testing whether the gradient malfunction detection activates correctly under controlled, simulated error rates or conditions.
* Direct Physical Measurements: Verifying the accuracy of temperature sensors and the initiation of cool-down periods.
* Compliance with Standards: Ensuring the robust implementation of software safety features as per recognized industry standards.

8. The Sample Size for the Training Set:
The document does not specify a training set sample size. Given the nature of the software changes (safety logic and workflow enhancements) and this being a Special 510(k), it is unlikely to involve large-scale machine learning model training on medical image datasets. If any internal parameters were 'trained' (e.g., for optimal gradient error thresholds), the details are not disclosed.

9. How the Ground Truth for the Training Set Was Established:
Not explicitly stated. If there were any trainable parameters for the safety functions, the ground truth would have been established via engineering analysis, simulation, and empirical testing to define the optimal setpoints for safety interlocks and warnings.

Ask a specific question about this device

The Philips iCT CT systems is a Computed Tomography X-Ray System intended to produce images of the head and body by computer reconstruction of x-ray transmission data taken at different angles and planes. These devices may include signal analysis and display equipment, patient and equipment supports, components and accessories. The iCT is indicated for head, whole body, cardiac and vascular X-ray Computed Tomography applications in patients of all ages.

These scanners are intended to be used for diagnostic imaging and for low dose CT lung cancer screening for the early detection of lung nodules that may represent cancer*. The screening must be performed within the established inclusion criteria of programs / protocols that have been approved and published by either a governmental body or professional medical society.

*Please refer to clinical literature, including the results of the National Lung Screening Trial (N Engl J Med 2011; 365:395-409) and subsequent literature, for further information.

The Philips iCT CT System is a whole-body computed tomography (CT) X-ray system designed for diagnostic imaging. It features a continuously rotating X-ray tube and multi-slice detector gantry, enabling the acquisition of X-ray transmission data from multiple angles and planes. The system reconstructs these data into cross-sectional images using advanced image reconstruction algorithms, supporting a wide range of clinical applications.

The system consists of a gantry, which houses the rotating X-ray tube, detector array, and key imaging subsystems; a patient support couch, which moves the patient through the gantry bore in synchronization with the scan and is available in multiple configurations; an operator console, which serves as the primary user interface for system controls, image processing, and data management; and a Data Measurement System (DMS), which captures X-ray attenuation data to support high-quality image reconstruction.

The provided FDA 510(k) clearance letter for the Philips iCT CT System (K250648) focuses on demonstrating substantial equivalence to a predicate device (K162838) based on hardware and software enhancements.

However, there is no information within this document that describes specific acceptance criteria in terms of algorithm performance metrics (e.g., sensitivity, specificity, AUC) for an AI/ML-driven diagnostic task, nor does it detail a study proving the device meets such criteria in a clinical context.

The document primarily addresses:

• Physical and technical characteristics of the CT system (e.g., spatial resolution, low contrast resolution, noise, scan speeds).
• Safety and performance of system modifications (e.g., OS upgrade, cybersecurity enhancements, new phantom kit) through non-clinical verification and validation activities.
• Substantial equivalence to a predicate device based on these engineering and system-level tests.

The mention of "low dose CT lung cancer screening for the early detection of lung nodules that may represent cancer" refers to a general indication for the CT system itself, not a specific AI/ML diagnostic algorithm for nodule detection or characterization within the system. The note to "refer to clinical literature, including the results of the National Lung Screening Trial" further supports that the clinical efficacy of CT for lung screening is established and not being re-proven by this submission for a new AI feature.

Therefore, I cannot populate the requested table or answer the specific questions about AI/ML study design directly from the provided text, as this information is not present. The document focuses on the CT scanner as the device, not a specific AI-powered diagnostic algorithm within it that would require the detailed studies outlined in your request.

If the "Philips iCT CT System" were to include an AI component with an explicit diagnostic function beyond general image acquisition and display, the FDA submission would typically contain a dedicated section on its performance evaluation, including the types of studies you are asking about. This document does not describe such an AI component or its associated clinical performance study.

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. The use 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. 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 subject Ingenia, Ingenia CX, Ingenia Elition, Ingenia Ambition, BlueSeal, MR 5300 and MR 7700 MR Systems are 60 cm and 70 cm bore 1.5 and 3.0 Tesla (1.5T and 3.0T) Magnetic Resonance Diagnostic Devices.

A new optional software feature SmartSpeed Precise is contained in software R12.3 for the subject Ingenia, Ingenia CX, Ingenia Elition, Ingenia Ambition, BlueSeal, MR 5300 and MR 7700 MR Systems.

SmartSpeed Precise is a machine learning based reconstruction technique designed to increase the signal-to-noise (SNR), increase the sharpness, and reduce residual ringing artifacts in MR images.

The introduction of SmartSpeed Precise only required updates to the MR System Software.

The subject Ingenia, Ingenia CX, Ingenia Elition, Ingenia Ambition, BlueSeal, MR 5300 and MR 7700 MR Systems are intended to be marketed with the same pulse sequences and coils that are previously cleared by FDA:

The accessories to be used with the subject Ingenia, Ingenia CX, Ingenia Elition, Ingenia Ambition, BlueSeal, MR 5300 and MR 7700 MR Systems have not changed compared to the predicate device and can be found in the Instructions for Use accompanying the device.

When Philips MRI system is used in combination with the Philips MR-RT or MR-OR solutions, the user is referred to the dedicated MR-RT and MR-OR Instructions for Use for information on additional accessories that may apply.

This FDA 510(k) clearance letter describes the acceptance criteria and study proving the Philips MR systems meet these criteria, particularly focusing on the new SmartSpeed Precise feature.

Here's an breakdown of the requested information:

1. Table of Acceptance Criteria and Reported Device Performance

The FDA clearance letter does not provide a specific quantitative table of acceptance criteria with corresponding numerical performance metrics for the SmartSpeed Precise feature. Instead, it describes the acceptance criteria implicitly through the study design and the qualitative assessments.

The core acceptance is that the new SmartSpeed Precise feature, as implemented in the Philips MR Systems, maintains at least equivalent image quality for diagnostic purposes while providing benefits like increased SNR, sharpness, and reduced ringing artifacts, and does not negatively impact safety or effectiveness compared to the predicate device.

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

The document mentions "a reader evaluation by ABR board certified radiologists" was performed, and "qualitative image review" by application specialists. However, the specific sample size (number of cases/images) used for these evaluations (testing) is not explicitly stated in the provided text.

The data provenance is not specified regarding country of origin. It is described as non-clinical performance data, suggesting it's likely retrospective data (existing images) or phantom/simulated data, rather than prospective patient recruitment solely for this study. The phrasing "Simulated use validation was executed" further supports this.

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

• Experts for Qualitative Image Review: "application specialists" performed the qualitative review. Their specific number and detailed qualifications (e.g., years of experience, certifications beyond "application specialist") are not specified.
• Experts for Reader Evaluation: "ABR board certified radiologists" performed the reader evaluation. The number of radiologists is not specified. Their qualification is clearly stated as "ABR board certified radiologists."

4. Adjudication Method for the Test Set

The document does not explicitly describe an adjudication method (e.g., 2+1, 3+1) for resolving disagreements among readers. It states "a reader evaluation by ABR board certified radiologists was performed" and "the review evaluation shows that the proposed device is assessed as equivalent." This suggests a consensus or majority opinion might have been reached amongst them, but the process is not detailed.

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

Yes, a multi-reader multi-case comparative effectiveness study appears to have been done implicitly as part of the "reader evaluation by ABR board certified radiologists."

• Effect Size of Human Readers' Improvement with AI vs. Without AI Assistance:
  The study was designed to compare the new SmartSpeed Precise (AI-enhanced reconstruction) against the predicate device's reconstruction technology. The document states:
  "The review evaluation shows that the proposed device is assessed as equivalent for diagnosis and holds significantly better SNR and sharpness compared to the predicate reconstruction technology, also in the presence of (subtle) abnormalities and pathology."
  This indicates a positive effect size on image quality metrics (SNR, sharpness) directly impacting the interpretability for human readers. However, specific numerical effect sizes (e.g., mean difference in reader performance metrics, confidence intervals, p-values) are not provided in this summary. The primary claim is "equivalent for diagnosis" but with "significantly better SNR and sharpness."

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

The description focuses on the impact of SmartSpeed Precise on image quality for human interpretation. While a machine learning model is central to SmartSpeed Precise, the assessment is not described as a purely standalone (algorithm-only) performance evaluation independent of human interpretation. The features explicitly assessed (SNR, sharpness, CNR, artifact level) are objective image quality metrics that could be evaluated standalone, but their context in this document is in relation to human reader assessment ("radiologists have assessed the quality of the visualization of abnormalities...").

7. Type of Ground Truth Used

The ground truth for the reader evaluation appears to be based on:

• Expert Consensus/Judgment: The "ABR board certified radiologists" assessed image properties (SNR, sharpness, CNR, artifacts) and the "quality of the visualization of abnormalities and pathologies" and whether images were "of sufficient quality for diagnostic purposes." This implies their collective professional judgment formed the ground truth for diagnostic equivalence and quality assessment.
• Implicit Clinical Ground Truth: For cases with abnormalities/pathologies, the underlying clinical diagnosis (presumed to be established through other means like prior imaging, clinical follow-up, or pathology reports) would serve as the ultimate ground truth against which the visualization of these abnormalities was assessed by the radiologists. However, the specific method for establishing this clinical ground truth for the cases themselves is not detailed.

8. Sample Size for the Training Set

The document does not specify the sample size used for training the SmartSpeed Precise machine learning model. It only states that "SmartSpeed Precise is a machine learning based reconstruction technique."

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

The document does not specify how the ground truth for the training set was established. Given that it's a "machine learning based reconstruction technique" focused on improving SNR, sharpness, and reducing artifacts, the training ground truth would typically involve pairs of noisy/artifact-ridden input images and corresponding "ideal" or "truth" images (e.g., acquired with very long scan times or gold-standard techniques not feasible in routine clinical practice) against which the model learns to reconstruct improved images. However, the exact methodology is not described.

Ask a specific question about this device

The Spectral CT system is a Computed Tomography X-ray system intended to produce cross-sectional images of the body by computer reconstruction of X-ray transmission data taken at different angles and planes. This device may include signal analysis and display equipment, patient and equipment support, component parts, and accessories.

The Spectral CT system acquires one CT dataset – composed of data from a higher-energy detected X-ray spectrum and a lower- energy detected X-ray spectrum. The two spectra may be used to analyze the differences in the energy dependence of the attenuation coefficient of different materials. This allows for the generation of images at energies selected from the available spectrum and to provide information about the chemical composition of the body materials and/or contrast agents.

Additionally, materials analysis provides for the quantification and graphical display of attenuation, material density, and effective atomic number.

This information may be used by a trained healthcare professional as a diagnostic tool for the visualization and analysis of anatomical and pathological structures in patients of all ages, and to be used for diagnostic imaging in radiology, interventional radiology, and cardiology and in oncology as part of treatment preparation and radiation therapy planning. The Extended field of view images and respiratory correlated scanning (4DCT) are for treatment preparation and radiation therapy planning/simulation usage only.

This device is indicated for head, whole body, cardiac and vascular X-ray Computed Tomography applications in patients of all ages.

The system is also intended to be used for low dose CT lung cancer screening for the early detection of lung nodules that may represent cancer*. The screening must be performed within the established inclusion criteria of programs / protocols that have been approved and published by either a governmental body or professional medical society.

*Please refer to clinical literature, including the results of the National Lung Screening Trial (N Engl. J Med 2011; 365:395-409) and subsequent literature, for further information.

Spectral CT system is a whole-body computed tomography (CT) X-ray system featuring a continuously rotating X-ray tube and detectors gantry, and multi slice capability. The acquired X-ray transmission data is reconstructed by computer into cross-sectional images of the body taken at different angles and planes. This system also includes signals analysis and display equipment, patient and equipment support, components, and accessories.

The Spectral CT system acquires one CT dataset – composed of data from a higher energy detected X-ray spectrum and a lower- energy detected X-ray spectrum. The two spectra may be used to analyze the differences in the energy dependence of the attenuation coefficient of different materials. This allows for the generation of images at energies selected from the available spectrum and provides information about the chemical composition of the body materials and/or contrast agents. Additionally, materials analysis provides for the quantification and graphical display of attenuation, material density, and effective atomic number.

The Spectral CT system consists of three main components – a scanner system that includes a rotating gantry, a movable patient couch, and an operator console for control and image reconstruction; a Spectral Reconstruction System; and a Spectral CT Viewer. On the gantry, the main active components are the X-ray high voltage (HV) power supply, the X-ray tube, and the detection system.

The fundamental design and characteristics of the main components used in the proposed Spectral CT system are identical to the currently marketed primary predicate device, Spectral CT system (K203020).

This document is a 510(k) clearance letter for a Spectral CT System, indicating its substantial equivalence to previously cleared predicate devices. While it focuses heavily on design features and compliance with general safety and performance standards for CT systems, it does not contain the detailed clinical study information typically found in submissions for AI/ML-based medical devices that require specific performance metrics and human reader studies.

The provided text only briefly mentions "Clinical Image Evaluation" and "Comparison of performance data against internal performance requirements" as supporting the evaluation of new features. It does not provide specific acceptance criteria or performance results for these "new features" (Pulmonary Gating 4DCT and Extended Field of View (EFOV)) in the context of a clinical study, nor does it detail how substantial equivalence was demonstrated clinically for these features beyond a generic statement.

Therefore, many of the requested items cannot be extracted from this document, as it primarily covers the device's technical specifications and regulatory compliance for a general CT system, rather than specific performance studies for new AI/ML functionalities.

Given the information provided, here's what can be extracted and what cannot:

Acceptance Criteria and Study for Spectral CT System (K244008)

Based on the provided FDA 510(k) clearance letter, the primary method for demonstrating the device meets acceptance criteria and proving its performance is through substantial equivalence to predicate devices and adherence to recognized consensus standards and guidance documents. The document does not detail specific performance metrics, acceptance criteria, or a clinical study for the new features (Pulmonary Gating 4DCT and Extended Field of View (EFOV)) in the format requested for AI/ML device performance.

The document states:

• "Non-clinical performance testing has been performed on the proposed Spectral CT system and demonstrates compliance with the following International and FDA recognized consensus standards and FDA guidance document(s)..."
• "Design verification planning and testing were conducted at the system level. The system is tested against the System Requirements Specifications (SRS)."
• "Design Validation tests the user needs and intended use that are documented in the top-level User Requirement Specification (PRS)."
• "All the validation tests as per validation plan were performed and acceptance criteria met for each of the requirements."
• "Non-clinical design validation testing demonstrates that the proposed Spectral CT system can be used as defined in its clinical workflow and intended use."
• "To support the evaluation of the new features, the submission includes: - Phantom-based image quality (IQ) testing, assessing parameters such as noise, resolution, and artifacts - A representative clinical image assessment - Comparison of performance data against internal performance requirements"

This indicates that the "acceptance criteria" are primarily framed around compliance with established engineering and regulatory standards and internal performance requirements verified through non-clinical and limited clinical assessment, rather than a specific clinical trial with defined performance endpoints for the new features.

Information Extracted from the Document:

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

   The document does not provide a table of specific quantitative acceptance criteria and corresponding reported device performance metrics from a clinical study for the new features (Pulmonary Gating 4DCT and Extended Field of View (EFOV)). Instead, it states that "All the validation tests as per validation plan were performed and acceptance criteria met for each of the requirements." without detailing these.
   The primary "performance" discussed is the technological equivalence to predicate devices. Below is a summary of the technological characteristics being presented as "met" by being identical or substantially equivalent to the predicate.

   Table: Technological Characteristics (Implicit Acceptance Criteria - Equivalence to Predicate)

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

   Not explicitly stated in the provided text. The document refers to "Phantom-based image quality (IQ) testing" and "A representative clinical image assessment" but does not give sample sizes or provenance (country/retrospective/prospective) for these.

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

   Not explicitly stated. The document refers to "A representative clinical image assessment" but does not detail how ground truth was established or the experts involved.

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

   Not explicitly stated.

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. This type of study is typically done for AI/ML diagnostic tools where human interpretation of medical images is directly affected by the AI output. This 510(k) is for a CT system itself, with new acquisition and reconstruction features (4DCT, EFOV) that are likely intended to provide better images for human interpretation, rather than an AI reading a dataset. The document's statements about "clinical image evaluation" do not elaborate on how this was conducted or whether it involved comparative effectiveness with human readers.

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

   This question is more applicable to diagnostic algorithms. For a CT system with new acquisition/reconstruction capabilities, the "standalone" performance would typically refer to the "Phantom-based image quality (IQ) testing," where the system's output (images) are assessed against objective physical metrics (noise, resolution, artifacts) without human interpretation of clinical findings. The document states this was done: "Phantom-based image quality (IQ) testing, assessing parameters such as noise, resolution, and artifacts."

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

   For the "Phantom-based IQ testing," the ground truth would be the known physical properties and measurements of the phantoms.
   For the "representative clinical image assessment," the type of ground truth is not specified.

8. The sample size for the training set:

   Not applicable. This 510(k) is for a CT hardware and software system, not an AI/ML diagnostic algorithm that would typically have a "training set" in the machine learning sense. The "new features" (Pulmonary Gating 4DCT and EFOV) are descriptions of how the system acquires and processes data, not separate AI algorithms trained on massive datasets to perform a diagnostic task.

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

   Not applicable, as there's no mention of a "training set" in the context of an AI/ML algorithm.

Ask a specific question about this device

VitalSigns Camera Medical Library is a software library that can be integrated into a customer application for use during virtual consults or health screening. It is intended for spot checking of Respiration Rate (RR) in an automatic contactless manner as a data point in the overall assessment of the patient. It is used under the supervision of a health care professional, either in the home or in a clinical environment when the subject is still and positioned properly in front of the camera (Samsung Galaxy A20e), which is placed on a stable surface in an adequately lit environment.
It is intended to be used on patients aged 22 years and older that classify as ASA I (American Society of Anesthesiologists), which is defined as a normal healthy patient, non-smoking and no or minimal alcohol use.
It is not intended for continuous patient monitoring system or as the sole method of checking the physical health of the patient, nor as an apnea monitor, but as a part of a framework which mandates periodic checks by a health care professional to ensure appropriate clinical diagnosis and treatment can be reached.

The Philips VitalSigns Camera Medical Library (hereafter known as Philips VSC-MEDlib) is a software library that shall be used in conjunction with a camera which can be part of another platform or as part of a medical device. The Philips VSC-MEDlib incorporates an algorithm which allow for automatic, contactless measuring of Respiration Rate (RR). Philips VSC-MEDlib utilizes the video stream of an unobstructed view of the subject's torso captured from a camera to calculate the RR from torso motion. The video stream can be captured during a video consult or health screening which should always be conducted in the presence of a physician or other Health Care Professional (HCP). The patient must be properly positioned in front of the camera, sitting still and in an adequately lit environment. From a video stream that typically lasts 60 seconds or less, a spot measurement is taken.

Here's a breakdown of the acceptance criteria and the study proving the device meets those criteria, based on the provided FDA 510(k) clearance letter:

Acceptance Criteria and Device Performance

1. Table of Acceptance Criteria and Reported Device Performance

Note: While the predicate device had an accuracy of ±2 bpm, the Philips VSC-MEDlib's stated primary endpoint (acceptance criterion) for RMSE was ≤ 3 BPM, which it met. This suggests a slightly less stringent accuracy requirement for the new device, but the FDA still deemed it substantially equivalent based on the overall package of evidence.

2. Sample Size and Data Provenance

• Test Set Sample Size: 92 subjects were enrolled in the prospective clinical investigation. VSC-MEDlib provided a RR output for 83 subjects (93.3%).
• Data Provenance: Single center, prospective clinical investigation conducted in the Netherlands. The study explicitly states the subject population was representative of the intended U.S. population and evaluated performance under suboptimal conditions.

3. Number of Experts and Qualifications for Ground Truth

• The document states that the gold standard reference device was manually annotated capnography. It does not specify the number of experts or their qualifications for this manual annotation.

4. Adjudication Method for the Test Set

• The document does not specify an adjudication method for establishing the ground truth. It simply states "manually annotated capnography" was used as the gold standard.

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

• No, a multi-reader multi-case (MRMC) comparative effectiveness study was not reported. The study focused on the standalone performance of the device against a gold standard, not on how human readers' performance might improve with AI assistance.

6. Standalone Performance

• Yes, a standalone (algorithm only, without human-in-the-loop performance) study was performed. The clinical investigation directly evaluated the Philips VSC-MEDlib's accuracy in measuring RR against a gold standard reference.

7. Type of Ground Truth Used

• The ground truth used was manually annotated capnography. This is considered a gold standard for respiration rate measurement.

8. Sample Size for the Training Set

• The document does not provide the sample size used for the training set. It only details the clinical investigation used for performance evaluation (test set).

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

• The document does not provide information on how the ground truth was established for the training set. This is a common omission in 510(k) summaries, which tend to focus on the validation/test set performance.

Ask a specific question about this device

The Philips IntelliSite Pathology Solution (PIPS) 5.1 is an automated digital slide creation, viewing, and management system. The PIPS 5.1 is intended for in vitro diagnostic use as an aid to the pathologist to review and interpret digital images of surgical pathology slides prepared from formalin-fixed paraffin embedded (FFPE) tissue. The PIPS 5.1 is not intended for use with frozen section, cytology, or non-FFPE hematopathology specimens.

The PIPS 5.1 comprises the Imagement System (IMS) 4.2, Ultra Fast Scanner (UFS), Pathology Scanner SG20. Pathology Scanner SG60, Pathology Scanner SG300 and Philips PP27QHD display, a Beacon C411W display or a Barco MDCC-4430 display. The PIPS 5.1 is for creation and viewing of digital images of scanned glass slides that would otherwise be appropriate for manual visualization by conventional light microscopy. It is the responsibility of a qualified pathologist to employ appropriate procedures and safeguards to assure the validity of the interpretation of images obtained using PIPS 5.1.

The Philips IntelliSite Pathology Solution (PIPS) 5.1 is an automated digital slide creation, viewing, and management system. PIPS 5.1 consists of two subsystems and a display component:

• 1. A scanner in any combination of the following scanner models
  • . Ultra Fast Scanner (UFS)
  • Pathology Scanner SG with different versions for varying slide capacity . Pathology Scanner SG20, Pathology Scanner SG60, Pathology Scanner SG300
• 2. Image Management System (IMS) 4.2
• 3. Clinical display
  • PP27QHD or C411W or MDCC-4430 .

PIPS 5.1 is for creation and viewing of digital images of scanned glass slides that would otherwise be appropriate for manual visualization by conventional light microscopy. The PIPS does not include any automated image analysis applications that would constitute computer aided detection or diagnosis. The pathologists only view the scanned images and utilize the image review manipulation software in the PIPS 5.1.

This document is a 510(k) summary for the Philips IntelliSite Pathology Solution (PIPS) 5.1. It describes the device, its intended use, and compares it to a legally marketed predicate device (also PIPS 5.1, K242848). The key change in the subject device is the introduction of a new clinical display, Barco MDCC-4430.

Here's the breakdown of the acceptance criteria and study information:

1. Table of Acceptance Criteria and Reported Device Performance

The submission focuses on demonstrating substantial equivalence of the new display (Barco MDCC-4430) to the predicate's display (Philips PP27QHD). The acceptance criteria are largely derived from the FDA's "Technical Performance Assessment of Digital Pathology Whole Slide Imaging Devices" (TPA Guidance) and compliance with international consensus standards. The performance is reported as successful verification showing equivalence.

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

The document does not explicitly state a "sample size" in terms of cases or images for the non-clinical performance tests. The tests were performed on "the display of the proposed device" to verify its technological characteristics. This implies testing on representative units of the Barco MDCC-4430 display.

The data provenance is not specified in terms of country of origin or retrospective/prospective, as the tests were bench testing (laboratory-based performance evaluation of the display hardware) rather than clinical studies with patient data.

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

This information is not applicable to this submission. The tests performed were technical performance evaluations of hardware (the display), not clinical evaluations requiring expert interpretation of medical images. Ground truth for these technical tests would be established by objective measurements against specified technical standards and parameters.

4. Adjudication Method for the Test Set

This information is not applicable to this submission. As the tests were technical performance evaluations of hardware, there would not be an adjudication process involving multiple human observers interpreting results in the same way there would be for a clinical trial.

5. If a Multi Reader Multi Case (MRMC) Comparative Effectiveness Study was done

No, a Multi Reader Multi Case (MRMC) comparative effectiveness study was not done.

The submission explicitly states: "The proposed device with the new display did not require clinical performance data since substantial equivalence to the currently marketed predicate device was demonstrated with the following attributes: Intended Use / Indications for Use, Technological characteristics, Non-clinical performance testing, and Safety and effectiveness."

Therefore, there is no effect size reported for human readers with and without AI assistance, as AI functionality for diagnostic interpretation is not the subject of this 510(k) (the PIPS 5.1 "does not include any automated image analysis applications that would constitute computer aided detection or diagnosis").

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

This information is not applicable. The PIPS 5.1 is a digital slide creation, viewing, and management system, not an AI algorithm for diagnostic interpretation. The focus of this 510(k) is the display component. The device itself is designed for human-in-the-loop use by a pathologist.

7. The Type of Ground Truth Used

For the non-clinical performance data, the "ground truth" was based on:

• International and FDA-recognized consensus standards: This includes IEC 60601-1, IEC 60601-1-6, IEC 62471, and ISO 14971.
• TPA Guidance: The "Technical Performance Assessment of Digital Pathology Whole Slide Imaging Devices" guidance document, which specifies technical parameters for displays.
• Predicate device characteristics: Demonstrating that the new display's performance matches or is equivalent to the legally marketed predicate device's display across various technical parameters.

In essence, the ground truth was established by engineering specifications, technical performance targets, and regulatory standards for display devices.

8. The Sample Size for the Training Set

This information is not applicable. The PIPS 5.1, as described, is a system for digital pathology, not an AI algorithm that requires a training set of data. The 510(k) specifically mentions: "The PIPS does not include any automated image analysis applications that would constitute computer aided detection or diagnosis." Therefore, there is no AI training set.

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

This information is not applicable, as there is no AI training set.

Ask a specific question about this device

The Philips IntelliSite Pathology Solution (PIPS) 5.1 is an automated digital slide creation, viewing, and management system. The PIPS 5.1 is intended for in vitro diagnostic use as an aid to the pathologist to review and interpret digital images of surgical pathology slides prepared from formalin-fixed paraffin embedded (FFPE) tissue. The PIPS 5.1 is not intended for use with frozen section, cytology, or non-FFPE hematopathology specimens.

The PIPS 5.1 comprises the Imagement System (IMS) 4.2, Ultra-Fast Scanner (UFS), Pathology Scanner SG20, Pathology Scanner SG60, Pathology Scanner SG300 and Philips PP270HD display or a Beacon C411W display. The PIPS 5.1 is for creation and viewing of digital images of scanned glass slides that would otherwise be appropriate for manual visualization by conventional light microscopy. It is the responsibility of a qualified pathologist to employ appropriate procedures and safeguards to assure the validity of the interpretation of images obtained using PIPS 5.1.

The Philips IntelliSite Pathology Solution (PIPS) 5.1 is an automated digital slide creation, viewing, and management system. PIPS 5.1 consists of two subsystems and a display component:

• 1. A scanner in any combination of the following scanner models
  • . Ultra Fast Scanner (UFS)
  • . Pathology Scanner SG with different versions for varying slide capacity Pathology Scanner SG20. Pathology Scanner SG60. Pathology Scanner SG300
• 2. Image Management System (IMS) 4.2
• 3. Clinical display
  • PP27QHD or C411W

PIPS is for creation and viewing of digital images of scanned glass slides that would otherwise be appropriate for manual visualization by conventional light microscopy. The PIPS does not include any automated image analysis applications that would constitute computer aided detection or diagnosis. The pathologists only view the scanned images and utilize the image review manipulation software in the PIPS.

This document focuses on the Philips IntelliSite Pathology Solution 5.1 (PIPS 5.1) and its substantial equivalence to a predicate device, primarily due to the introduction of a new clinical display. This is a 510(k) submission, meaning it aims to demonstrate that the new device is as safe and effective as a legally marketed predicate device, rather than proving de novo effectiveness. Therefore, the study described is a non-clinical performance study to demonstrate equivalence of the new display, not a clinical effectiveness study.

Based on the provided text, a detailed breakdown of acceptance criteria and the proving study is as follows:

1. Table of Acceptance Criteria and Reported Device Performance

The document states that the evaluation was performed following the FDA's Guidance for Industry and FDA Staff entitled, "Technical Performance Assessment of Digital Pathology Whole Slide Imaging Devices" (TPA Guidance), dated April 20, 2016. The acceptance criteria are essentially defined by compliance with the tests outlined in this guidance and relevant international standards.

Reported Device Performance Summary: The non-clinical performance testing of the new display (Beacon C411W) showed that the proposed device has similar technological characteristics compared to the predicate device (using the PP27QHD display) following the TPA Guidance. It is also in compliance with the aforementioned international and FDA-recognized consensus standards. The verification and validation of existing safety, user, and system integration requirements showed that the proposed PIPS 5.1 with the new clinical display is safe and effective.

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

• Sample Size: The document does not specify a "sample size" in terms of patient cases or images for testing the display. The testing performed was bench testing ("Verification for the new display," "non-clinical performance data"). This implies that the tests were conducted on the display unit itself, measuring its physical and optical properties, and its integration with the system components, rather than on a dataset of patient images reviewed by observers.
• Data Provenance: Not applicable in the context of a display characteristic validation study. The study focused on the performance of the hardware (the new display).

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

Not applicable. This was a technical, non-clinical validation of a display unit's characteristics against engineering specifications and regulatory guidance, not a study requiring expert clinical read-outs or ground truth establishment from patient data.

4. Adjudication Method for the Test Set

Not applicable. This was a technical, non-clinical validation.

5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done

• No, an MRMC comparative effectiveness study was NOT done. The document explicitly states: "The proposed device with the new display did not require clinical performance data since substantial equivalence to the currently marketed predicate device was demonstrated with the following attributes: Intended Use / Indications for Use, Technological characteristics, Non-clinical performance testing, and Safety and effectiveness."
• The purpose of this submission was to demonstrate substantial equivalence for a minor hardware change (new display), not to show an improvement in human reader performance with AI assistance. The PIPS system itself does not include "any automated image analysis applications that would constitute computer aided detection or diagnosis." It is a whole slide imaging system for viewing and managing digital slides.

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

• Not applicable. The PIPS 5.1 is a system for creating, viewing, and managing digital slides for human pathologist review. It is not an AI algorithm that produces a diagnostic output on its own. The "standalone" performance here refers to the display's technical specifications.

7. The Type of Ground Truth Used

• For the non-clinical performance data, the "ground truth" was established by engineering specifications, international consensus standards (e.g., IEC, ISO), and the FDA's TPA Guidance. The aim was to ensure the new display performed equivalently to the predicate's approved display and met relevant technical requirements.

8. The Sample Size for the Training Set

Not applicable. This was a non-clinical validation of hardware (a display), not a machine learning model requiring a training set.

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

Not applicable. (See #8)

Ask a specific question about this device

The Philips IntelliSite Pathology Solution (PIPS) is an automated digital slide creation, viewing and management, system. The PIPS is intended for in vitro diagnostic use as an aid to the pathologist to review and interpret digital images of surgical pathology slides prepared from formalin-fixed paraffin embedded (FFPE) tissue. The PIPS is not intended for use with frozen section, cytology, or non-FFPE hematopathology specimens.

The PIPS comprises the Image Management System (IMS) the Ultra Fast Scanner (UFS) and Philips PP27QHD display or a Beacon C411W display. The PIPS is for creation and viewing of digital images of scanned glass slides that would otherwise be appropriate for manual visualization by conventional light microscopy. It is the responsibility of a qualified pathologist to employ appropriate procedures and safeguards to assure the interpretation of images obtained using PIPS.

The Philips IntelliSite Pathology Solution (PIPS) is an automated digital slide creation, viewing and management, system. The PIPS comprises the Image Management System (IMS) the Ultra Fast Scanner (UFS) and Philips PP27QHD display or a Beacon C411W display.

Ask a specific question about this device

ROCC Console is intended for remote scanning, support, review, monitoring and standardization of imaging protocols of medical imaging devices. It is a multi-vendor solution allowing view-only or full access control to connected devices. ROCC Console is also intended for training of medical personnel working on connected medical imaging devices.

ROCC Console is a software device, which is part of the ROCC (Radiology Operations Command Center) system, a cloud-based solution which can connect expert radiology users located at a remote command center with onsite technologists operating an MR/CT scanner on-demand, while enabling real-time operational support/guidance for the scanner console. This ROCC system allows healthcare professionals to share expertise, even when they are not physically present in the same location. Expert users are working from remote office locations within a healthcare facility or from a home office.

ROCC Console is a multiple function device product. The medical device functions include the ability to console of a connected MR/CT scanner from a remote location, and a Protocol Management mode, which can be used to manage updates / harmonize scan protocols across connected MR/CT scanners.

ROCC Console is vendor neutral. It is intended to be used in healthcare environments including imaging modalities (MR or CT) with digital output (DP, DVI, and HDMI) which are either fixed to one location or are in mobile (truck) environments where medical imaging services are provided.

ROCC Console supports three connection methods to exchange the KVM (Keyboard, Video and Mouse) information between the expert user and the technologist. The proprietary software KVM connection includes two applications: a "Console Transmitter App" for use by the technologist on the scanner side, and a "Console Receiver App" for use by the remotely located expert user. The Console Transmitter App is a native Windows application installed on a desktop system, which sends the console video stream over the internet to the Console Receiver App. The Console Receiver App is a web-application that can run on a web browser, and receives and displays the video stream to the remotely located expert user edits the scanner console through mouse and keyboard entries, it sends these keyboard and mouse entries back to the Console Transmitter App, which subsequently sends the scanner console. Additionally, ROCC Console supports off-the-shelf HW/SW KVM switch or VNC. ROCC Console can be used with 3 MR/CT console connections concurrently.

When a patient is to be scanned, the on-site technologist must remain present at all times and retains full control over the MR/CT scanner console and can terminate the editing authorization at any time. For CT connections, full access is limited to what is available in the software associated with the modality workspace and is not applicable to physical switches controlling the radiation exposure.

The Protocol Management mode allows access to the MR/CT scanner console without a technologist on site. It is only intended for protocol management and harmonization and not for any remote imaging support.

The ROCC Console is a Medical Image Management and Processing System (MIMPS) that allows remote scanning, support, review, monitoring, and standardization of imaging protocols for medical imaging devices (MR/CT scanners). It is a multi-vendor solution and can be used for training.

Here's an analysis of the acceptance criteria and the study proving the device meets them:

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

The provided document does not explicitly list specific numerical acceptance criteria for performance metrics like latency, accuracy, or specific functionality tests, alongside their reported performance. Instead, it states broadly that:

• "All pre-specified performance metrics have been met as demonstrated within the software verification and validation."
• "V&V activities were performed on the proposed ROCC Console and demonstrated that the predetermined acceptance criteria were successfully met and no different questions in terms of safety and effectiveness were raised."
• "The ROCC Console performs as intended."

However, it does mention one specific performance characteristic and its relation to the predicate device:

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 does not provide details on the sample size used for the test set or the data provenance (country of origin, retrospective/prospective). It refers to "software verification and validation documents" as the source of this information, which are not included in this extract.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g., radiologist with 10 years of experience)

The document does not specify the number of experts used and their qualifications for establishing ground truth in the test set.

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

The document does not describe any adjudication method used for the test set.

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

A Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not conducted in this context. The ROCC Console is a system for remote control and management of imaging devices, not an AI-powered diagnostic tool directly assisting human readers in interpreting medical images. Therefore, the concept of "human readers improving with AI vs without AI assistance" does not directly apply here. The claim of substantial equivalence is based on non-clinical performance testing.

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

The ROCC Console is a software device that facilitates remote control and management of medical imaging devices, with a human technologist present on-site during scanning in most cases (except for Protocol Management mode). Its primary function involves human operators. The document does not describe a "standalone" or "algorithm only" performance study in the traditional sense of an AI model providing automated results. Performance testing would likely focus on the reliability, responsiveness, and accuracy of the remote control and data transmission functionalities.

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

The document does not specify the type of ground truth used. Given the nature of the device (remote control and management), ground truth would likely relate to the accurate transmission of KVM information, successful execution of remote commands, consistency of protocol management, and overall system functionality without compromising image acquisition or patient safety. This would likely be assessed through functional testing and comparison against expected system behavior.

8. The sample size for the training set

The document does not provide information regarding a training set sample size. The ROCC Console is described as a "software device" and does not explicitly mention the use of machine learning or deep learning algorithms that typically require a distinct training set. The term "training set" is usually applied to AI/ML product validation, which doesn't seem to be the primary validation approach for this device's stated functions.

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

As there is no mention of a training set or the use of AI/ML, the document does not describe how ground truth for a training set was established.

Ask a specific question about this device