(59 days)
The Vereos PET/CT System is a diagnostic imaging device that combines Positron Emission Tomography (PET) and Xray Computed Tomography (CT) systems. The CT subsystem images anatomical cross-sections by computer reconstruction of x-ray transmission data. The PET subsystem images the distribution of PET anatomy-specific radiopharmaceuticals in the patient. The Philips Vereos PET/CT system is used for the purpose of detecting, localizing, diagnosing, staging and follow-up for monitoring therapy response of various diseases in oncology, cardiology and neurology. The system is intended to image the whole body, heart, brain, lung, gastrointestinal, bone, lymphatic, and other major organs for a wide range of patient types, sizes, and extent of diseases. Both subsystems can also be operated as fully functional, independent diagnostic tools including application of the CT scanner for diagnosis and for use in radiation therapy planning.
The proposed Vereos PET/CT system is an integrated diagnostic X-Ray Computed Tomography (CT) and Positron Emission Tomography (PET) system designed for a wide range of diagnostic applications. Computerized Tomography (CT) is a medical imaging technique that uses X-rays to obtain cross sectional images of the head or body. The quality of the images depends on the level and amount of X-ray energy delivered to the tissue. CT imaging displays both high-density tissue, such as bone, and soft tissue. When interpreted by a trained physician, CT images provide useful diagnostic information. Positron Emission Tomography (PET) 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 imaqes of biochemical and metabolic processes of organs within the body.
The proposed Vereos PET/CT system utilizes the CT technology to obtain anatomic images of the human body and PET technology to obtain functional images of the human body. The clinical value of both technologies increases with the capability to fuse the CT and PET images using Philips fusion viewer Image Fusion software to create a composite image for therapeutic planning. The system also provides tools for quantifying results from the CT and PET images and provides the means for a simplified review of the CT, PET, and fused images. The integration of the anatomical data from CT with the metabolic data from PET gives clinicians the visual information necessary to define the severity, as well as the extent, of the disease.
The system is comprised of the following system components/subsystems: positron emission tomography (PET); X-ray computed tomography (CT); a patient table; Operating station; Reconstruction Servers. On the gantry, the main active components are the x-ray high voltage (HV) power supply, the x-ray tube, and the detection system. These components of the proposed Vereos PET/CT are identical to the currently marketed and predicate device, Vereos PET/CT (K210880) with respect to technological specifications.
The proposed Vereos PET/CT System includes a modification to the currently marketed and predicate device, Vereos PET/CT (K210880). The modification is limited to the addition of an optional Adaptive reconstruction algorithm ("PET AR") to be used as an additional reconstruction method for offline reconstructions. The interface of the PET AR with the Vereos system is additional protocols available to the user in the PET recon tool. In addition, a Software patch was released which limits the use of the PET AR reconstruction protocols for the scan type it's compatible with and enables identifying the PET AR reconstructed images with visual identifier to differentiate them from regular PET results.
Here's an analysis of the provided text regarding the acceptance criteria and the study that proves the device meets those criteria:
Device: Vereos PET/CT with PET Adaptive Reconstruction (AR) software application
Acceptance Criteria and Reported Device Performance:
The provided document does not explicitly list a table of quantitative acceptance criteria. Instead, it describes general compliance with standards and the adequacy for intended use. The core acceptance criteria for the PET AR software are that it provides low noise and improves low contrast detectability as compared to OSEM (Ordered Subsets Expectation Maximization). The overall acceptance is based on demonstrating substantial equivalence to the predicate device (Vereos PET/CT K210880) in terms of design features, indications for use, fundamental scientific technology, safety, and effectiveness.
| Acceptance Criterion (Implicit) | Reported Device Performance |
|---|---|
| Compliance with International and FDA-recognized consensus standards and FDA guidance documents | Demonstrated compliance with a list of standards (IEC 60601-1, IEC 60601-1-2, IEC 60601-1-3, IEC 60601-1-6, IEC 60601-2-28, IEC 60601-2-44, IEC 60825-1, IEC 62366-1, IEC 62304, ISO 10993-1, ISO 14971) and guidance documents. Specifically, the software modification complies with IEC 62304. |
| Adequacy for intended use | Non-clinical design validation testing demonstrates the system can be used as defined in its clinical workflow and intended use. |
| Low noise as compared to OSEM | PET AR is described as an "Artificial Intelligence-powered reconstruction algorithm that provides low noise" compared to OSEM. |
| Improved low contrast detectability as compared to OSEM | PET AR is described as an "Artificial Intelligence-powered reconstruction algorithm that ... improves low contrast detectability as compared to OSEM." |
| No new risks or impact on safety and effectiveness | The PET AR modification "does not impact safety and effectiveness" and "does not introduce any new risks nor impact the safety and effectiveness" of the system. |
| Maintain good image quality | Sample clinical images were reviewed and evaluated by certified radiologists, and all images were found to have good image quality. |
Study Information:
-
Sample size used for the test set and the data provenance:
- Test Set Sample Size: The document mentions "sample clinical images" and that "External clinical images [were] reviewed by certified board radiologists." However, it does not specify the exact number of images or cases used in this external review.
- Data Provenance: Not explicitly stated. The document refers to "External clinical images," implying real patient data, but does not mention the country of origin or whether it was retrospective or prospective.
-
Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- Number of Experts: "Certified board radiologists" reviewed the external clinical images. The exact number of radiologists is not specified.
- Qualifications of Experts: "Certified board radiologists." No further details on years of experience or sub-specialty are provided.
-
Adjudication method for the test set:
- Not specified. The document only states that images were "reviewed and evaluated by certified radiologists" and that "All images were evaluated to have a good image quality." There is no mention of a consensus process (e.g., 2+1, 3+1) or any adjudication method.
-
If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:
- No. The document explicitly states: "The proposed Vereos PET/CT system did not require any clinical study." The evaluation was described as "simulated use testing" and "non-clinical testing." Therefore, an MRMC study and
effect size on human readers are not applicable here.
- No. The document explicitly states: "The proposed Vereos PET/CT system did not require any clinical study." The evaluation was described as "simulated use testing" and "non-clinical testing." Therefore, an MRMC study and
-
If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- Yes, implicitly. The performance claims regarding "low noise" and "improved low contrast detectability" compared to OSEM are inherent characteristics of the algorithm itself. While radiologists reviewed images, the performance characteristics of the reconstruction algorithm (PET AR vs. OSEM) are evaluated independently of human interpretation in terms of these intrinsic image quality metrics. The "internal PET AR image evaluation" mentioned falls under this category.
-
The type of ground truth used:
- For the "external clinical images reviewed by certified board radiologists," the implicit ground truth appears to be expert consensus/evaluation of image quality by these radiologists. They evaluated "good image quality."
- For the claims of "low noise" and "improved low contrast detectability," the ground truth likely involves quantitative metrics derived from phantoms or known datasets, compared against OSEM reconstructions. This is part of the "internal PET AR image evaluation." The document doesn't explicitly state pathology or outcomes data as ground truth for this software modification.
-
The sample size for the training set:
- Not specified. The document states PET AR is an "Artificial Intelligence-powered reconstruction algorithm" but provides no details on any training data or its sample size.
-
How the ground truth for the training set was established:
- Not specified. Since no training set details are provided, the method for establishing its ground truth is also not mentioned.
§ 892.1200 Emission computed tomography system.
(a)
Identification. An emission computed tomography system is a device intended to detect the location and distribution of gamma ray- and positron-emitting radionuclides in the body and produce cross-sectional images through computer reconstruction of the data. This generic type of device may include signal analysis and display equipment, patient and equipment supports, radionuclide anatomical markers, component parts, and accessories.(b)
Classification. Class II.