Search Results

The device is a diagnostic imaging system that combines Positron Emission Tomography (PET) and X-ray Computed Tomography (CT) systems. The CT component produces crosssectional images of the body by computer reconstruction of x-ray transmission data. The PET component images the distribution of PBT radiopharmaceuticals in the patient body. The PET component utilizes CT images for attenuation correction and anatomical reference in the fused PET and CT images.

This device is to be used by a trained health care professional to gather metabolic and functional information from the distribution of the radiopharmaceutical in the body for the assessment of metabolic and physiologic functions. This information can assist in the evaluation, detection, diagnosis, therapeutic planning and therapeutic outcome assessment of {but not limited to) cancer, cardiovascular disease and brain dysfunction. Additionally, this device can be operated independently as a whole body multi-slice CT scanner.

Celesteion, PCA-9000A, is a large bore, TOF, PET-CT system, which combines a high-end CT system with a high-throughput PET system. The high-end CT system is a multi-slice helical CT scanner with a gantry aperture of 900 mm and a maximum scanning field of 700 mm. The high-throughput PET system has a time of flight (TOF) detector with temporal resolution of 450 ps. Celesteion, PCA-9000A, is intended to acquire PET images of any desired region of the whole body and CT images of the same region (to be used for attenuation correction or image fusion), to detect the location of positron emitting radiopharmaceuticals in the body with the obtained images. This device is used to gather the metabolic and functional information from the distribution of radiopharmaceuticals in the body for the assessment of metabolic and physiologic functions. This information can assist research, diagnosis, therapeutic planning, and therapeutic outcome assessment. This device can also function independently as a whole body multi-slice CT scanner.

Here's a breakdown of the acceptance criteria and study information for the Celesteion, PCA-9000A/2 device, based on the provided text:

Acceptance Criteria and Device Performance

The provided text details performance specifications for the Celesteion, PCA-9000A/2, and explicitly states that it met established specifications through phantom testing. Although the document doesn't explicitly list "acceptance criteria" as a separate table, it compares the device's measured performance against the predicate device (Gemini Raptor). We can infer that meeting comparable or improved performance to the predicate device, or meeting specified technical thresholds, constitutes the acceptance criteria.

Table of Acceptance Criteria (Inferred from Predicate Comparison and "Established Specifications") and Reported Device Performance:

Study Details

The provided text describes the testing done to support the 510(k) submission, focusing on technical performance verification.

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

   • Test Set Sample Size: The document does not specify a numerical sample size for "test sets" in terms of cases or patient data. Instead, it mentions that studies were performed using phantoms.
   • Data Provenance: The studies were phantom-based bench testing and are implicitly prospective in nature as they were conducted as part of the device's premarket submission. No information about country of origin of patient data is relevant as patient data was not used for this specific testing.

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

   • The document does not mention the use of human experts to establish ground truth for the test sets. The testing involved objective measurements of physical properties (e.g., spatial resolution, sensitivity) using phantoms, rather than subjective interpretation of diagnostic images by clinicians.

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

   • None (Not applicable): Since the described testing involved objective phantom measurements and did not use human interpretation or ground truth derived from expert consensus, an adjudication method for human readers is not relevant.

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

   • No, an MRMC comparative effectiveness study was not done. The submission focuses on the technical performance of the combined PET-CT system itself, not on a human-in-the-loop AI assistance tool.

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

   • Yes, in the context of device performance metrics. The testing described ("CT image quality metrics were performed, utilizing phantoms," and "PET image quality metrics were performed") assesses the inherent performance characteristics of the imaging device (the algorithm/hardware combined) in a standalone manner. It evaluates how well the system itself performs its core functions of image acquisition and reconstruction in terms of physical parameters. It's not an "algorithm" in the sense of a separate AI diagnostic tool, but the performance of the integrated imaging system.

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

   • Phantom-based physical measurements: The ground truth for the technical performance metrics (e.g., spatial resolution, energy resolution, sensitivity) was established using known physical properties of phantoms and standardized measurement protocols (e.g., NEMA standards implicitly for PET metrics).

7. The sample size for the training set:

   • Not applicable / Not specified. The document does not describe any machine learning or AI algorithm development that would involve a "training set" in the traditional sense. The device is a PET-CT imaging system, not a diagnostic AI software tool that requires training on a dataset of images to learn patterns.

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

   • Not applicable. As no training set for an AI algorithm is mentioned, the method for establishing its ground truth is irrelevant to this submission.

Ask a specific question about this device

The device is a diagnostic imaging system for fixed installations that combines Positron Emission Tomography (PET) and Magnetic Resonance Iniaging (MRI). The system does not expose the patient to ionizing radiation, only the dose contribution from the PET radiopharmaceutical. The MRI subsystem produces cross-sectional images, spectroscopy images and/or spectra in any orientation of the internal structures of the whole body. The PET subsystem produces images of the distribution of PET radiopharmaceuticals in the patient body (specific pharmaceuticals are used for whole body, brain, and other organ imaging). The PET and MRI portions of the system can be used either as an integrated system or as a stand-alone MRI or PET system. The MRI subsystem provides data suitable for use in attenuation correction of the PET acquired data.

Image processing and display work stations provide software applications to process, analyze, display, quantify and interpret medical images/data via a single user interface. The PET and MRI 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 professional 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 the PET images.

The MRI provides capabilities to perform interventional procedures in the head, body, and extremities which may be facilitated by MR techniques, such as real time imaging, such procedures must be performed with MRI compatible instrumentation as selected and evaluated by the clinical user.

The Ingenuity TF PET/MR system combines the Philips Achieva MR (K063559) and the Philips GEMINI PET/CT (Raptor, K052640) technologies. The system utilizes the MR technology to obtain anatomic images of the human body and PET technology to obtain functional images of the human body. The clinical value of the both technologies is enhanced with the ability to fuse the MR and PET images using Philips fusion viewer software to create a composite image for diagnostic study and therapeutic planning. The system also provides tools for the quantification of results of the MR and PET images and provides a means for a simplified review of the fused images.

Magnetic Resonance Imaging is a medical imaging technique that is based on the principle that certain atomic nuclei present in the human body emit a weak relaxation signal when placed in a strong magnetic field and excited by a radio signal at the precession frequency. The emitted relaxation signals are analyzed by the system and a computed image reconstruction is displayed on a video screen.

Positron Emission Tomography uses radiopharmaceuticals to obtain images by measuring the internal distribution of radioactivity within organs of the body. PET technology enables the practitioner to reconstruct high resolution, three dimensional images of biochemical and metabolic processes of organs within the body.

The Ingenuity TF PET/MR system consists of two gantries integrating the MR scanner and the PET scanner, a patient table to support the patient, within the gantries, and a scanning console and viewing console at the operator's workstation.

The request asks for specific information regarding the acceptance criteria and study proving device meets acceptance criteria, based on the provided text. However, the provided text is a 510(k) summary for a PET/MR system, which focuses on device description, intended use, and substantial equivalence to predicate devices, rather than detailed performance studies or specific acceptance criteria for AI algorithms.

Therefore, much of the requested information cannot be extracted from the given document as it pertains to AI/algorithm performance studies which are not described.

Here's what can be extracted:

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

The document does not explicitly state quantitative acceptance criteria or detailed performance metrics for an AI algorithm. It mentions:

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

• Sample Size for Test Set: Not specified.
• Data Provenance: "Clinical data" is mentioned, implying real patient data, but details such as country of origin, retrospective or prospective nature are not provided.

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

Not specified in the document.

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

Not specified in the document.

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

A Multi-Reader Multi-Case (MRMC) comparative effectiveness study is not mentioned. The document primarily focuses on demonstrating substantial equivalence of the new PET/MR system to existing predicate devices (PET/CT and MRI) based on image quality and the MRAC method, not on human reader performance with or without AI assistance.

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

This document describes a diagnostic imaging system, not a standalone AI algorithm. The performance evaluation mentioned ("acceptable image quality" and "MRAC method was validated") refers to the system as a whole.

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

For the MRAC method, the ground truth was established through "phantom, simulated and clinical data." The specific nature of "ground truth" for image quality equivalence is not detailed but would typically involve visual assessment by experts against established standards or predicate images.

8. The sample size for the training set

Not applicable. The document describes a medical imaging system, not a device whose performance is based on an AI algorithm that requires a training set.

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

Not applicable.

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