Search Results

Pinnacle3 Radiation Therapy Planning System is a software package intended to provide planning support for the treatment of disease processes. Pinnacle3 Radiation Therapy Planning System incorporates a number of fully integrated subsystems, including Pinnacle3 Proton, which supports proton therapy planning. The full Pinnacle Radiation Therapy Planning System software package provides planning support for the treatment of disease processes, utilizing photon, proton, electron and brachytherapy techniques.

Pinnacle3 Radiation Therapy Planning System assists the clinician in formulating a treatment plan that maximizes the dose to the treatment volume while minimizing the dose to the surrounding normal tissues. The system is capable of operating in both the forward planning and inverse planning modes. Plans generated using this system is used in the determination of the course of a patient's radiation treatment. They are to be evaluated, modified and implemented by qualified medical personnel.

Pinnacle3® Radiation Therapy Planning System (hereafter Pinnacle3 RTP) provides radiation treatment planning for the treatment of benign or malignant diseases. When using Pinnacle " RTP, qualified medical personnel may generate, review, verify, approve, print and export the radiation therapy plan prior to patient treatment. Pinnacle RTP can provide plans for various radiation therapy modalities including, utilizing photon, proton, electron and brachytherapy techniques Stereotactic Radiosurgery, and Brachytherapy.

The Proton module builds on the Pinnacle Photon Treatment Planning Solution. A substantial part of the software architecture, display, connectivity and planning tools are transferable or extensible to the Proton Treatment Planning module. Using Pinnacle® RTP as the base-line architecture will address the needs of operating and future treatment centers to seamlessly integrate photon with proton treatment planning.

Pinnacle® RTP is a software package that runs on a Oracle Server and accessed through one or more clients, or an Oracle UNIX workstation and consists of a core software module (Pinnacle') and optional software features (the Proton module requires the Oracle server and cannot be run on a workstation). These optional software features, commonly referred to as "plug-ins", are typically distributed separate from the core software product (separate CD or DVD). The device has network capability to other Pinnacle® RTP workstations, thin client, and to both input and output devices via local area network (LAN) or wide area network (WAN).

Image data is imported from CT, MR, PET, PET-CT and SPECT devices using a DICOM-compliant interface. A qualified medical professional uses the Pinnacle® RTP for functions such as viewing and analyzing the patient's anatomy, and generating a radiation therapy plan.

This 510(k) submission for the Philips Medical Systems (Cleveland), Inc. Pinnacle3 Radiation Therapy Planning System (Pinnacle3 RTP) primarily focuses on demonstrating substantial equivalence to a predicate device, the Computerized Medical Systems, Inc. Xio RTP System - Proton Spot Scanning (K102216), rather than detailing specific acceptance criteria and a study to prove they are met in a quantitative manner. Regulatory submissions for radiation therapy planning systems often rely on verification and validation activities to ensure the software performs as intended and is safe and effective when compared to a legally marketed predicate device.

However, based on the provided text, here's a breakdown of the information requested, with indications where details are not explicitly provided:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present a table of quantitative acceptance criteria for features like dose calculation accuracy or planning capabilities, nor does it provide specific device performance metrics in a pass/fail format typical of quantitative studies. Instead, it relies on demonstrating similar functionalities and computational approaches to a predicate device.

The "Non-Clinical Tests" section mentions that "Verification tests were written and executed to ensure that the system is working as designed. Pass/fail requirements and results of this testing can be found in the Thunder Core Verification Test Report, which is included in section 16 of this submission. Pinnacle3 RTP successfully passed verification testing." This suggests that internal acceptance criteria and performance thresholds existed and were met, but these specific details are not included in the provided excerpt.

The comparison table (Table 5A) highlights technological characteristics and principles of operation, implying that similarity to the predicate device in these aspects serves as a primary "acceptance criterion" for substantial equivalence.

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

• Test Set Sample Size: Not explicitly stated. The document mentions "algorithm testing was performed in a QA 'Phantom'" and "clinical orientated validation test cases were written and executed by PMS customers at External evaluation sites." However, the number of phantom configurations, patient cases (if simulated), or specific test sets used in these validations is not provided.
• Data Provenance:
  • Phantom Data: For "Algorithm testing... in a QA 'Phantom'", the data is synthetically generated or acquired in a controlled lab environment. This is typically internal, not from a specific country of origin in the clinical sense.
  • Clinical-Oriented Validation: For "clinical orientated validation test cases... executed by PMS customers at External evaluation sites," the data would likely be based on simulated or mock patient cases, or potentially anonymized clinical data provided by these "PMS customers." The countries of origin for these "External evaluation sites" are not specified, nor is whether the data was retrospective or prospective. It is implied to be retrospective or simulated to prevent patient exposure to risk.

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

• Number of Experts: Not explicitly stated.
• Qualifications of Experts: For the "clinical orientated validation test cases," it mentions "oversight by PMS customer support personnel." It also states that treatment plans "are to be evaluated, modified, and implemented by qualified medical personnel." While this implies that qualified personnel are involved in the validation, their specific roles (e.g., medical physicists, radiation oncologists, dosimetrists) and years of experience are not detailed as "experts establishing ground truth." For the QA phantom testing, the "ground truth" (measured doses) would be established by the physical measurements themselves, typically verified by medical physicists via dosimetry.

4. Adjudication Method for the Test Set

Not explicitly stated. The document refers to "oversight by PMS customer support personnel" for clinical validation, but it doesn't describe any formal adjudication process for disagreements or discrepancies. For phantom testing, the "ground truth" is measured data, and the comparison is usually direct.

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

No. The document explicitly states: "Clinical trials were not performed as part of the development of this product." Therefore, a multi-reader multi-case (MRMC) comparative effectiveness study focusing on human readers' improvement with AI vs. without AI assistance was not conducted or reported. The device is a planning system, not an AI-assisted diagnostic or interpretation tool in the typical sense of MRMC studies.

6. Standalone (Algorithm Only) Performance Study

Yes, in part. "Algorithm testing was performed in a QA 'Phantom' to compare calculated against measured doses to ensure dose calculation accuracy." This constitutes a standalone performance evaluation of the dose calculation algorithm.

7. Type of Ground Truth Used

• Algorithm Testing: "Measured doses" in a QA "Phantom." This refers to physical measurements in a controlled environment as the ground truth.
• Clinical-Oriented Validation: This implicitly relies on the consensus of "qualified medical personnel" and "PMS customer support personnel" validating that the plans generated by the system are clinically appropriate and meet intended goals. However, a formal "ground truth" establishment process for these cases is not described beyond this general validation.

8. Sample Size for the Training Set

Not applicable. This device is a radiation therapy planning system that uses established physics models and algorithms (e.g., pencil beam algorithm, dose model parameter fitting to published works and measured data) rather than a machine learning model that requires a distinct "training set" in the context of deep learning or AI. The algorithms are based on fundamental physics principles and validated against measured data and published literature.

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

Not applicable, as there isn't a "training set" in the machine learning sense. The models used (e.g., pencil beam algorithm) are derived from fundamental physics and validated against "measured data... fitted to models based on published works." This fitting process uses measured physical data (e.g., Bragg Peak, Spread Out Bragg Peak, Effective SAD, Virtual SAD, Effective Source Size, CT-Number to Stopping Power Tables) as its "ground truth" for parameter derivation.

Ask a specific question about this device

The Plaque Analysis option is a non-invasive diagnostic reading software intended for use by cardiologists and radiologists as an interactive tool for viewing and analyzing cardiac CT data for determining the presence and extent of coronary plaques.

Philips' Comprehensive Cardiac Analysis (CCA) Plaque Assessment tool is a noninvasive diagnostic reading software intended to provide cardiologists and radiologists with an optimized non-invasive application to provide accurate quantification and characterization of coronary plaque. It is an interactive post-processing tool for viewing and analyzing cardiac CT image data for determining the presence and extent of coronary plaques.

The Plaque Analysis option was added to the Comprehensive Cardiac Analysis option (a.k.a. CCA) predicate device. It provides analysis of the vessel lumen and wall and makes it easier to detect findings in the coronary vessels.

The Plaque Analysis application calculates lumen and vessels contours, detects findings along the vessel wall by a single click algorithm and provides a set of measurements for all the detected findings. The option includes visualization and manual correction tools.

Outputs of the application include coronary findings segmentation and quantification.

1. Table of acceptance criteria and reported device performance:

The provided 510(k) summary (K092742) for Philips' Comprehensive Cardiac Analysis (CCA) Plaque Assessment Tool does not explicitly state specific quantitative acceptance criteria or the numerical performance results of a study designed to meet such criteria. The document focuses on demonstrating substantial equivalence to predicate devices based on safety and effectiveness considerations, rather than reporting on a specific performance study with defined metrics.

However, based on the description of the device's function, we can infer the intent of performance from the device description and indications for use. The device "provides analysis of the vessel lumen and wall and makes it easier to detect findings in the coronary vessels," and its intended use is to "provide accurate quantification and characterization of coronary plaque."

Therefore, for the purpose of this exercise, we will conceptualize the implied performance and how it might be assessed, even though the specific metrics and results are not present in the provided text.

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

The provided document does not specify the sample size used for any test set or the data provenance (e.g., country of origin, retrospective or prospective) for a performance study. The 510(k) focuses on demonstrating substantial equivalence through a comparison of technological characteristics, safety, and intended use to predicate devices, rather than presenting a detailed clinical performance study with test sets.

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

The document does not mention any ground truth establishment process, the number of experts involved, or their qualifications. As no specific performance study is detailed, the information regarding ground truth is absent.

4. Adjudication method for the test set:

Since no specific performance study or test set is described, there is no mention of an adjudication method.

5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, and the effect size of how much human readers improve with AI vs without AI assistance:

The document does not indicate that a multi-reader multi-case (MRMC) comparative effectiveness study was performed. The focus is on the device's standalone capabilities and its equivalence to other legally marketed devices, not on its assistive impact on human readers in a comparative setting.

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

The 510(k) summary does not explicitly state that a standalone (algorithm-only) performance study was conducted with quantitative results. While it describes the algorithm's capabilities ("detects findings along the vessel wall by a single click algorithm" and "calculates lumen and vessels contours"), it does not provide metrics of its performance purely in an automated fashion. The device is described as an "interactive tool," implying human involvement in its intended use.

7. The type of ground truth used:

The document does not specify the type of ground truth used as no explicit performance study with ground truth is detailed.

8. The sample size for the training set:

The document does not provide any information regarding the sample size for a training set. As this is a 510(k) summary focused on substantial equivalence rather than a detailed technical report of algorithm development, such information is typically not included.

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

The document does not describe how the ground truth for a training set was established, as no training set or its associated ground truth process is mentioned.

Ask a specific question about this device

The Brilliance CT 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 supports, components and accessories.

The dual energy option allows the system to acquire two CT images of the same anatomical location using two distinct tube voltages and/or tube currents during two tube rotations. The x-ray dose will be the sum of the doses of each tube rotation at its respective tube voltage and current. Information regarding the material composition of various organs, tissues, and contrast materials may be gained from the differences in x-ray attenuation between these distinct energies. This information may also be used to reconstruct images at multiple energies within the available spectrum, and to reconstruct basis images that allow the visualization and analysis of anatomical and pathological materials.

Philips Healthcare offers a Dual Energy scanning option on the Brilliance CT Scanner. The Brilliance Dual Energy option automates the execution of sequential scanning protocols acquired during the same episode of care using two unique tube voltages and/or currents. The acquired datasets can be displayed side-by-side or overlaid and then analyzed to augment the review of anatomical and pathological structures. Dual energy imaging, by nature of differing x-ray energy values, enables the identification of attenuation differences found in those structures between the two applied energies.

This submission K090462 for the Philips Medical Systems (Cleveland) Inc. Brilliance Dual Energy option does not contain the detailed information necessary to fully address all aspects of your request regarding acceptance criteria and a study proving the device meets those criteria.

The document is a 510(k) Summary, which primarily focuses on establishing substantial equivalence to predicate devices and detailing the intended use. It does not typically include the specifics of performance studies, acceptance criteria, or ground truth establishment that would be found in a full submission or a clinical study report.

Based on the provided text:

• No specific acceptance criteria or a study demonstrating the device meets those criteria are explicitly reported. The document states that the device is "of comparable type and substantially equivalent to the legally marketed devices" (K060937 and K081105) based on "similar technological characteristics and subassemblies." This is a regulatory statement of equivalence, not a performance study result against stated acceptance criteria.

Therefore, I cannot populate the table or provide detailed answers to most of your questions based solely on the provided text.

However, I can extract information related to the device description and intended use:

1. Table of Acceptance Criteria and Reported Device Performance

Since the document does not describe a performance study with acceptance criteria, the following questions cannot be answered from the provided text:

• 2. Sample size used for the test set and the data provenance: Not mentioned.
• 3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not mentioned.
• 4. Adjudication method for the test set: Not mentioned.
• 5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done: Not mentioned.
• 6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done: Not mentioned, as this is an imaging option, not a standalone algorithm.
• 7. The type of ground truth used: Not mentioned.
• 8. The sample size for the training set: Not mentioned.
• 9. How the ground truth for the training set was established: Not mentioned.

Summary of what the document does provide:

• Device Name: Brilliance Dual Energy option
• Intended Use: To produce cross-sectional images using two distinct tube voltages and/or tube currents, aiding in material composition analysis, and reconstruction of images at multiple energies and basis images.
• Classification: Class II (21 CFR 892.1750, Product Code 90 JAK)
• Predicate Devices: Philips Brilliance Volume (K060937) and GE Lightspeed CT750 HD (K081105).
• Basis for Equivalence: Similar technological characteristics and subassemblies.

To obtain the detailed study information you're asking for, one would typically need access to the full 510(k) submission, not just the summary, or any publicly available performance reports or clinical studies related to this specific device option.

Ask a specific question about this device

The Philips MX 16-slice CT system can be used as a Head and Whole Body Computed Tomography X-ray System featuring a continuously rotating x-ray tube and detector array with multislice capability up to 16 slices simultaneously. The acquired x-ray transmission data is reconstructed by computer into cross-sectional images of the body from the same axial plane taken at different angles. The system is suitable for all patients.

The MX 16-slice CT System, phase II is a Whole Body Computed Tomography X-Rav 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 crosssectional images of the body taken at different angles and planes. This device also includes signal analysis and display equipment, patient and equipment supports. components and accessories.

The provided document is a 510(k) summary for the Philips MX 16-slice CT System. It describes the device, its intended use, and its substantial equivalence to a predicate device. However, it does not contain any information regarding specific acceptance criteria, performance studies (other than general quality assurance), sample sizes for testing or training, expert ground truth establishment, or any information about AI assistance or standalone algorithm performance.

Therefore, I cannot fulfill your request for this input based on the provided text. The document focuses on regulatory compliance and equivalence to an existing device, rather than detailed performance study results.

Here's an explanation of why the requested information cannot be extracted from the provided text:

• Acceptance Criteria and Reported Device Performance: The document states that "meeting the specifications and functional requirements is demonstrated via testing," but it does not specify what those specifications or functional requirements are, nor does it provide any quantitative performance data.
• Sample Size for Test Set and Data Provenance: This information is completely absent.
• Number of Experts and Qualifications: This information is not mentioned.
• Adjudication Method: Not mentioned.
• Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study: There is no indication of such a study. The product is a CT scanner, not an AI-powered diagnostic tool.
• Standalone Performance (Algorithm Only): The device is a physical CT scanner, not an AI algorithm, so this concept does not apply in the context of this document.
• Type of Ground Truth Used: Not applicable or mentioned, as there are no diagnostic AI algorithms being evaluated.
• Sample Size for Training Set: Not applicable, as there's no mention of an AI model or training.
• How Ground Truth for Training Set Was Established: Not applicable.

The submission focuses on substantiating that the MX 16-slice CT System is substantially equivalent to a previously cleared device (Brilliance CT 16-slice, K012009) by demonstrating similar technological characteristics and adherence to general safety standards (GMP, ISO, IEC, 21 CFR Subchapter J). This type of submission generally does not require detailed clinical performance studies beyond what was established for the predicate device, unless significant changes impacting safety or effectiveness are introduced.

Ask a specific question about this device

AutoSPECT® produces images, which depict the three-dimensional distribution of radiopharmaceutical tracers in a patient. This software is intended to provide enhancements to gamma camera emission image processing by automating previously manual image processing functions, providing manual and automated motion correction, providing enhanced reconstruction algorithms that include resolution recovery, scatter correction, noise compensation, and attenuation correction via application of a transmission dataset.

AutoSPECT® is a software application that produces images, which depict the three-dimensional distribution of radiopharmaceutical tracers in a patient via automatic or manual processing. One or more cardiac SPECT, gated SPECT, or MCD cardiac data sets may be processed automatically using AutoSPECT®. Additionally, one or more non-cardiac SPECT, or MCD data sets may be processed manually. AutoSPECT® contains basic data-processing algorithms that have been cleared previously; in addition to enhanced data reconstruction algorithms that include scatter correction, resolution recovery, map-based attenuation correction, and OSEM (Astonish SPECT) reconstruction.

The AutoSPECT software option may be used on images from a gamma camera system that are DICOM 3.0 compatible. The following data sets may be used:

Cardiac, brain, or other (bone, liver, etc.) SPECT datasets .
Gated SPECT datasets .
Vantage SPECT datasets
SPECT-CT datasets ●
Total Body SPECT datasets .
MCD and MCD-AC datasets .

AutoSPECT® provides the user three options for automatically processing cardiac datasets: AutoAll, ' > Auto Recon, and Auto Reorient. Each option is described in greater detail in the Software Description section, Section 4.

AutoSPECT® also allows the user to process non-cardiac SPECT and MCD datasets. In this case, the operator manually positions the reconstruction limit lines to reconstruct transverse data sets. If necessary, the data set can be reoriented manually by positioning the azimuth, elevation, and twist lines to the desired locations.

In addition, the capability of processing groups of SPECT data sets in a batch mode fashion is provided. Once the operator has selected the datasets and determined the processing method, AutoSPECT® processes the first dataset, followed by all remaining datasets without further interaction from the user.

AutoSPECT® application runs on Microsoft Windows XP Professional environment. The minimum hardware requirements are listed:

. Intel x86/Pentium class processor > 1 GHz ;
Graphics capability must meet or exceed 1280x1024 pixels with 32 bit pixel depth; .
30 GB of disk space (minimum); .
512 MB of DRAM (minimum); .
. 10/100 BaseTX Ethernet interface;
Port capable of supporting a dongle; .
. CD drive- capable of reading and writing;
. 56 Kbps modem (minimum)

Here's a breakdown of the acceptance criteria and study details for the AutoSPECT® device, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The submission claims to expand marketing relative to half-count imaging using Astonish-AC. The acceptance criteria revolve around achieving equivalent or improved diagnostic accuracy, image quality, and interpretive certainty compared to a baseline method (full-time back projection).

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

• Sample Size: 297 patient images.
• Data Provenance: The data was acquired using Philips' imaging systems and AutoSPECT® (with Astonish & Astonish AC). It was a "multi-center evaluation" and used "previously scanned images," indicating it was retrospective and likely from various centers where Philips' equipment was used. The country of origin is not explicitly stated, but Philips Medical Systems (Cleveland), Inc. is the submitting entity.

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

The document does not explicitly state the number of experts or their specific qualifications (e.g., "radiologist with 10 years of experience") used to establish ground truth. It vaguely refers to "multi-center evaluations" and conclusions about "diagnostic accuracy" and "interpretive certainty," implying expert interpretation was involved, but details are missing.

4. Adjudication Method for the Test Set

The document does not specify an adjudication method (e.g., 2+1, 3+1, none) for the test set.

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

• Was an MRMC study done? The text describes "multi-center evaluations" that compared different processing techniques and their impact on "diagnostic accuracy" and "interpretive certainty." This strongly suggests a comparative effectiveness study, likely involving multiple readers to assess the different image sets. However, it does not explicitly label it an "MRMC study."
• Effect Size of human readers' improvement with AI vs. without AI assistance: The study compared different reconstruction techniques (Astonish, Astonish-AC, and full-time back projection) on images, not directly the improvement of human readers with AI assistance versus without AI assistance. The tools (Astonish, Astonish-AC) are enhancements to the imaging process, which then impact the diagnostic accuracy and interpretive certainty. The benefit is reported for the technique, not explicitly as a reader-AI collaboration enhancement.

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

The study evaluates the output of the AutoSPECT® software's reconstruction algorithms (Astonish and Astonish-AC) in terms of diagnostic accuracy, image quality, and interpretive certainty. Since these are measures that require human interpretation to determine against clinical outcomes or established diagnoses, the study is not a standalone (algorithm only) performance assessment. It assesses the impact of the algorithm's output on human interpretation.

7. Type of Ground Truth Used

The ground truth used is implied to be expert consensus or established clinical diagnoses/outcomes to determine "diagnostic accuracy," "sensitivity," "specificity," and "normalcy." The document does not specify how this ground truth was definitively established (e.g., based on pathology confirmation for all cases, or long-term follow-up for outcomes).

8. Sample Size for the Training Set

The document does not provide any information about the sample size used for the training set. The study detailed is an evaluation of existing reconstruction techniques and their expanded claims.

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

Since no information is provided about a training set, the method for establishing its ground truth is not mentioned.

Ask a specific question about this device

The Philips MX 16-slice CT system can be used as a Head and Whole Body Computed Tomography X-ray System featuring a continuously rotating xray tube and detector array with multislice capability up to 16 slices simultaneously. The acquired x-ray transmission data is reconstructed by computer into cross-sectional images of the body from the same axial plane taken at different angles. The system is suitable for all patients.

The "Philips MX 16 slice" is a Whole Body Computed Tomography 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 crosssectional images of the body taken at different angles and planes. This device also includes signal analysis and display equipment, patient and equipment supports, components and accessories.

This looks like a 510(k) summary for a CT scanner, a device with specific regulatory pathways that often rely on substantial equivalence to predicate devices rather than novel performance studies. As such, the document does not contain detailed acceptance criteria and a study proving those criteria are met in the same way a new medical algorithm might. Instead, it focuses on demonstrating equivalence to an already approved device.

Therefore, many of the requested fields cannot be directly extracted from this document, as the standard regulatory approach for this type of medical device at the time of this 510(k) summary did not require such detailed performance study reporting in the summary itself.

Here's an analysis based on the provided text, highlighting what is and is not present:

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

• Not present in this document. This 510(k) summary focuses on demonstrating substantial equivalence to a predicate device (Brilliance CT 16-slice, K012009). The "acceptance criteria" for this submission are fundamentally about showing that the new device has "similar technological characteristics and sub-assemblies" and adheres to relevant safety standards (GMP, ISO 13485, IEC 60601-1, 21 CFR, Subchapter J). Specific performance metrics like sensitivity, specificity, or AUC, as would be expected for an AI algorithm, are not detailed here because that was not the regulatory requirement for this type of device at this time.

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

• Not applicable/Not present. Since a specific performance study with a test set (in the context of an AI algorithm) is not detailed, this information is not provided. The substantial equivalence argument relies on comparing the device's design, intended use, and safety features to a predicate, not on a clinical performance study with patient data in the typical sense.

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/Not present. As no specific performance study on a test set (with ground truth) is described, this information is not available.

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

• Not applicable/Not present. No test set adjudication method is described.

5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance

• Not applicable/Not present. This device is a CT scanner, not an AI-assisted interpretation tool. Therefore, an MRMC study comparing human readers with and without AI assistance is not relevant to this submission.

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

• Not applicable/Not present. This device is a hardware CT scanner, not an algorithm.

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

• Not applicable/Not present. No specific performance study with ground truth data is described for this submission. The "ground truth" for this 510(k) is the established safety and effectiveness of the predicate device and adherence to recognized standards.

8. The sample size for the training set

• Not applicable/Not present. As this is a CT scanner and not an AI algorithm, there is no "training set" in the context of machine learning.

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

• Not applicable/Not present. This question is not relevant for the type of device and submission described.

Ask a specific question about this device

Software contained in the PET Application Suite process, analyze, display, and quantify medical images/data. The PET and CT images may be registered and displayed in a "fused" (overlaid in the same spatial orientation) format to provide combined metabolic and anatomical data at different angles. Trained professionals use the images in:

• The evaluation, detection and diagnosis of lesions, disease and organ function such as cancer. cardiovascular disease, and neurological disorders.
• The detection, localization, and staging of tumors and diagnosing cancer patients.
• Treatment planning and interventional radiology procedures.
  The PET Application Suite includes software that provides a quantified analysis of regional cerebral activity from PET images.
  Cardiac imaging software provides functionality for the quantification of cardiology images and datasets including but not limited to myocardial perfusion for the display of wall motion and quantification of left-ventricular function parameters from gated myocardial perfusion studies and for the 3D alignment of coronary artery images from CT coronary angiography onto the myocardium.

The NexStar Liftoff PET Application Software Suite (referred to as NexStar or Liftoff within the submission) is software used to process, analyze and display medical images and may be sold with Philips nuclear medicine PET/CT Systems or systems marketed by Philips. The PET Software Application Suite is a full suite of applications, including both review and processing.
The NexStar Liftoff PET Application Software Suite is basically the same as the processing and reconstruction software cleared with the predicate device (GEMINI TF, K052640), with the extension of Image Fusion Software to include Metabolic Analysis and Cardiac Realignment.
NexStar software is a Windows®-based suite of image display and processing applications and is deployable on hardware platforms, which meet the minimum requirements needed to run the software.

The provided text is a 510(k) summary for the Philips Medical Systems' NexStar Liftoff PET Application Software Suite. It primarily focuses on demonstrating substantial equivalence to a predicate device (GEMINI Raptor System, K052640) rather than presenting a detailed study proving the device meets specific acceptance criteria in terms of clinical performance.

Therefore, much of the requested information regarding acceptance criteria and performance study details is not available in the provided document. The document explicitly states: "No performance standards have been developed for process and display applications." and "No performance standards have been developed for process and display applications." (repeated)

Here's a breakdown of what can and cannot be answered based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

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

• Sample Size: Not specified. The document does not describe a clinical test set with human cases for performance evaluation. The evaluation was primarily a comparison of technical characteristics to a predicate device.
• Data Provenance: Not applicable. No clinical data set is described for testing.

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

• Number of Experts: Not applicable. No clinical test set requiring ground truth establishment by experts is described.
• Qualifications of Experts: Not applicable.

4. Adjudication Method for the Test Set

• Adjudication Method: Not applicable. No clinical test set requiring adjudication is described.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done

• MRMC Study: No, an MRMC comparative effectiveness study was not mentioned or described in the provided document. The document focuses on technical equivalence to a predicate device rather than comparative human-AI performance.
• Effect Size of Human Readers Improve with AI vs. Without AI Assistance: Not applicable, as no such study was described.

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

• Standalone Study: No, a standalone performance study with quantifiable metrics like sensitivity, specificity, or accuracy for the algorithm itself was not described in the provided document. The submission is for application software that processes, analyzes, and displays images for use by trained professionals, implying a human-in-the-loop scenario, but no specific performance study, standalone or otherwise, is detailed.

7. The Type of Ground Truth Used

• Type of Ground Truth: Not applicable. No clinical performance study requiring a specific type of ground truth (e.g., pathology, outcomes data, expert consensus) is described. The "ground truth" for this submission was essentially the established safety and effectiveness of the predicate device, to which this device claimed substantial equivalence in its updates and changes.

8. The Sample Size for the Training Set

• Sample Size: Not specified. The document does not mention or describe a training set for machine learning or AI algorithms. The "software" described focuses on processing, analysis, and display, which typically relies on established algorithms and image processing techniques rather than a large, continuously-trained machine learning model in the context of a 2008 submission.

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

• Ground Truth Establishment: Not applicable, as no training set requiring ground truth for machine learning was described.

Ask a specific question about this device

The device is a diagnostic imaging system for fixed or mobile installations that combines Positron Emission Tomography (PET) and X-ray Computed Tomography (CT) systems. The CT subsystem produces crosssectional images of the body by computer reconstruction of x-ray transmission data. The PET subsystem produces images of the distribution of PET radiopharmaceuticals in the patient body (specific radiopharmaceuticals are used for whole body, brain, heart and other organ imaging). Attenuation correction is accomplished by CTAC. The device also provides for list mode, dynamic, and gated acquisitions.

Image processing and display workstations provide software applications to process, analyze, display, quantify and interpret medical images/data. The PET and CT images may be registered and displayed in a "fused" (overlaid in the same spatial orientation) format to provide combined metabolic and anatomical data at different angles. Trained professionals use the images in:

• The evaluation, detection and diagnosis of lesions, disease and organ function such as but not limited to cancer, cardiovascular disease, and neurological disorders.
• The detection, localization, and staging of tumors and diagnosing cancer patients.
• Treatment planning and interventional radiology procedures.

The device includes software that provides a quantified analysis of regional cerebral activity from PET images.

Cardiac imaging software provides functionality for the quantification of cardiology images and datasets including but not limited to myocardial perfusion for the display of wall motion and quantification of leftventricular function parameters from gated myocardial perfusion studies and for the 3D alignment of coronary artery images from CT coronary angiography onto the myocardium.

Both subsystems (PET and CT) can also be operated independently as fully functional, diagnostic imaging systems including application of the CT scanner as a radiation therapy simulation scanner.

The device is a hybrid diagnostic imaging system that combines Positron Emission Tomography (PET) and X-ray Computed Tomography (CT) scanners that can be utilized in fixed installations or mobile environments. The device is comprised of the following system components/subsystems: Positron Emission Tomography (PET), X-ray Computed Tomography (CT), a patient table, gantry separation unit, and the acquisition and processing workstations.

The provided text describes the GEMINI Condor system, a combined PET/CT scanner, and its 510(k) submission. However, it does not include a detailed study proving the device meets specific acceptance criteria with performance metrics, sample sizes, expert qualifications, or adjudication methods.

The document focuses on:

• General Information: Device name, classification, predicate devices, and intended use.
• Safety and Performance Standards: Mentions adherence to 21 CFR 1020.30 & 1020.33 (Performance Standards for Ionizing Radiation Emitting Products) and NEMA NU-2 standard for device performance measurement.
• Comparison to Predicate Devices: States that the device is substantially equivalent based on similar intended use, technological comparison, and system performance, but without presenting a comparative study.
• FDA Clearance Letter: Confirms the 510(k) clearance for marketing.

Therefore, based on the provided text, I cannot complete a table of acceptance criteria and reported device performance, nor can I describe a study that explicitly proves the device meets those criteria with the requested details.

The document implies that the device performance was measured according to NEMA NU-2 standards, which are general performance standards for PET scanners (and combined PET/CT systems). To fulfill your request, specific quantitative acceptance criteria derived from these standards, and the actual measured performance values from a study, would be needed.

If the information were available in the provided text, here's how I would structure the answer:

1. Table of Acceptance Criteria and Reported Device Performance

2. Sample size used for the test set and the data provenance:
Information not available in the provided text. The document refers to "System Performance Test/ Summary of Studies" but doesn't detail specific test sets or data provenance. It only states that performance was "measured in accordance with the NEMA-NU2 standard." This standard typically involves phantom studies.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
Information not available in the provided text. As this is a performance evaluation of the imaging system itself (likely using phantoms and physical measurements), human experts for ground truth establishment are not typically involved in the initial performance characterization described here.

4. Adjudication method for the test set:
Information not available in the provided text. Not applicable for performance testing of a physical system based on physical measurements or phantom images.

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:
Information not available in the provided text. The document describes an imaging device, not an AI-assisted diagnostic tool. Therefore, an MRMC study related to AI assistance would not be expected.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
Information not available in the provided text. This is a physical imaging system, not a standalone algorithm.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
Information not available directly in the provided text, but inferred. For a performance evaluation against NEMA NU-2 and CT standards, the ground truth would be based on physical phantom measurements and known characteristics of the phantoms (e.g., known activity concentrations, known lesion sizes, known material densities).

8. The sample size for the training set:
Information not available in the provided text. The document does not describe a machine learning algorithm that requires a training set. The "software that provides a quantified analysis" and cardiac imaging software are features of the device, but there's no mention of a machine learning component requiring a distinct training set for its development.

9. How the ground truth for the training set was established:
Information not available in the provided text. Not applicable given the lack of information on a training set.

In summary, the provided 510(k) document is a regulatory submission for a medical device and confirms its substantial equivalence to predicate devices, focusing on safety, intended use, and general performance standards adherence. It does not contain the detailed study results and performance metrics requested for acceptance criteria.

Ask a specific question about this device

Bright View VCT is a gamma camera for Single Photon Emission Computed Tomography (SPECT) and integrates with an attenuation device consisting of flat panel x-ray imaging components. BrightView VCT produces non-attenuation corrected SPECT images and attenuation corrected SPECT images with x-ray transmission data that may also be used for scatter correction. The nuclear medicine images and the VCT images may be registered and displayed in a fused format (overlaid in the same orientation) to provide anatomical localization of the nuclear medicine data. The BrightView VCT Imaging System should only be used by trained healthcare professionals.

BrightView VCT is a gamma camera for Single Photon Emission Computed Tomography (SPECT) and integrates with an attenuation device consisting of flat panel x-ray imaging components. BrightView VCT is defined as a low dose, high resolution SPECT/CT system with CT-like image quality used to perform attenuation correction and localization. The overall system includes the SPECT gantry, patient table, detectors for emission, flat panel xray detector for attenuation correction and localization, acquisition system, processing workstation, image processing/analysis and fusion software, and all other accessories required for the functionality of the system.

The BrightView VCT is designed to provide extended imaging functionality relative to a ring style gantry. It is designed for single or dual detector nuclear imaging accommodating a broad range of emission computed tomography (ECT) studies. The device includes the gantry frame, display panel, two detectors, a collimator storage unit, an acquisition computer unit (with an optional customer desk), a patient imaging table (includes pallet catcher), and a hand controller. The patient imaging table (pallet) is mechanized for patient loading access and for movement during imaging studies. The table may be removed by the operator for imaging of patients in wheelchairs, beds, or gurneys. The pallet includes removable arm, leg/knee, shoulder and headrest supports for patient positioning during studies that require support. The flat panel x-ray detector can be folded into the gantry to accommodate collimator exchange or bed imaging.

The BrightView VCT is designed to allow acquisition of a broad range of imaging studies using single or dual detectors. When using either a single detector or dual detectors placed in a relative 90-degree or relative 180-degree positions (as study appropriate), BrightView VCT can be used to perform static, dynamic, gated, total body, circular-orbit and non-circular orbit SPECT studies, gated SPECT (circular and non-circular) studies. A flat panel x-ray detector and x-ray tube are mounted to the SPECT gantry to provide attenuation correction and localization capability.

This document provides information from a 510(k) premarket notification for the Philips Medical Systems (Cleveland) Inc. BrightView VCT Imaging System. The primary purpose of this submission is to demonstrate substantial equivalence to predicate devices, rather than an independent study proving performance against specific acceptance criteria.

The submission claims substantial equivalence based on identical indications for use, technological comparison, and overall system performance. However, it does not present a detailed study with specific acceptance criteria and metrics of device performance. Instead, it focuses on comparing the new device's features and intended use with previously cleared devices.

Therefore, many of the requested details about acceptance criteria, sample sizes, expert involvement, and ground truth establishment are not present in this 510(k) summary. The document is primarily a regulatory filing for market clearance, not a scientific publication of a performance study.

Here's an attempt to answer the questions based only on the provided text, highlighting what is not available:

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

The provided text does not contain a table of explicit acceptance criteria with corresponding device performance metrics. The submission argues for "overall system performance" being substantially equivalent to predicate devices, but no quantitative performance data is present in this summary.

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

This information is not provided in the document. The submission does not detail a specific "test set" for performance evaluation in the manner of a clinical study. It focuses on technological comparison and indications for use.

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)

This information is not provided in the document. No "ground truth" establishment by experts for a test set is described.

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

This information is not provided in the document. No adjudication method is mentioned, as no specific test set or study design is detailed in this regulatory summary.

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

There is no indication that a multi-reader multi-case (MRMC) comparative effectiveness study was conducted or reported in this document. The device is a diagnostic imaging system, not an AI assistance tool for human readers in the traditional sense discussed by this question. The submission focuses on the imaging system's capabilities for attenuation correction and localization.

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

The document describes the device as an "imaging system" that produces images for "trained healthcare professionals" to use. It inherently involves a human-in-the-loop for interpretation and diagnosis. The primary "algorithm only" aspect would be image reconstruction and correction, which is part of the system's function, but not typically evaluated as a "standalone" performance metric in this context. The focus is on the integrated system's capabilities.

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

This information is not provided in the document. The filing does not describe a performance study with an established ground truth.

8. The sample size for the training set

This information is not provided in the document. The filing does not mention a "training set" in the context of an algorithm's development or evaluation.

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

This information is not provided in the document. As no training set is mentioned, the method for establishing its ground truth is also absent.

Ask a specific question about this device

The "Brilliance Volume" 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 supports, components and accessories.

The "Brilliance Volume" is a Whole Body Computed Tomography 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 crosssectional images of the body taken at different angles and planes. This device also includes signal analysis and display equipment, patient and equipment supports, components and accessories.

This 510(k) summary for the "Brilliance Volume" CT scanner does not contain the detailed information required to describe acceptance criteria and a study that proves the device meets those criteria, as typically found in a clinical performance study report.

The document focuses on demonstrating substantial equivalence to a predicate device based on similar technological characteristics and adherence to general safety and quality standards. There is no mention of specific performance metrics, clinical studies, or an evaluation of an AI algorithm's performance.

Therefore, I cannot provide a table of acceptance criteria and reported device performance or answer most of your specific questions. However, I can extract information relevant to your inquiry based on the provided text, highlighting what is missing.

Here's an analysis of the provided text in relation to your questions:

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

This information is not present in the provided document. The 510(k) summary focuses on demonstrating substantial equivalence to a predicate device (Philips Plus K033326) by stating that "Brilliance Volume" has "similar technological characteristics and sub-assemblies." There are no reported performance metrics (e.g., sensitivity, specificity, accuracy) or explicit acceptance criteria for a new device's performance.

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

This information is not present. The document does not describe any specific test set or data used to evaluate the device's performance.

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):

This information is not present. Since no test set or performance evaluation is described, there's no mention of experts or ground truth establishment.

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

This information is not present.

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 information is not present. There is no mention of an MRMC study, human readers, or AI assistance. This device is a CT scanner, not explicitly an AI-driven image analysis tool in the context of this 2006 submission.

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

This information is not present. The document describes a CT scanner, a hardware device, not an algorithm being evaluated in a standalone capacity for diagnostic performance.

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

This information is not present.

8. The sample size for the training set:

This information is not present.

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

This information is not present.

Summary of available information related to your questions (mostly noting what is absent):

In conclusion, the K060937 submission for the "Brilliance Volume" CT scanner is a typical 510(k) summary from 2006, demonstrating substantial equivalence through technological comparison and adherence to general safety and quality standards, rather than providing a detailed clinical performance study with defined acceptance criteria and proven device performance metrics. Such in-depth clinical studies and AI algorithm evaluations, as implied by your questions, became much more common and detailed in regulatory submissions in later years, especially with the rise of AI in medical devices.

Ask a specific question about this device