Search Results

The Photon Energy Recovery (PER) Option is intended for image quality and quantification improvement by scatter reduction in planar and tomographic nuclear medicine images. This option enables Gated SPECT acquisition in multi-energy window format which allows normal GSPECT processing along with PER scatter correction on the summed data. It can be used for acquisitions of single or multi-peak isotope as well as simultaneous multi-isotope images.

The Photon Energy Recovery (PER) option is a software application for reducing the Compton scatter contribution in nuclear images. This enables scatter correction of single as well as multipeak isotope imaging. In addition it allows for the correction of cross-talk down scatter in simultaneous multiisotope imaging. The method is based on a spectral deconvolution analysis using iterative recurrent linear regressions on nuclear spectra. These spectra are broken down into multiple energy windows. This submission provides an extension on the PER features of the currently legally marketed device, GE Vision Nuclear Medicine Workstation - K012568.

The provided text describes a 510(k) submission for the GE Photon Energy Recovery (PER) Option, a software application designed to reduce Compton scatter in nuclear images for improved image quality and quantification. However, the document does not contain a detailed study proving the device meets specific acceptance criteria. Instead, it makes a general statement about substantial equivalence to a predicate device.

Here's an analysis based on the information available:

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

The document does not explicitly state acceptance criteria in the format of a table or defined metrics. It broadly states that the device is intended for "image quality and quantification improvement by scatter reduction." The "reported device performance" is summarized as:

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

The document does not provide details on the sample size used for the test set or the data provenance (e.g., country of origin, retrospective or prospective). It simply states, "Bench and clinical data show that the PER corrected simultaneous dual-isotope images are similar to the conventional single isotope images." This is a very high-level summary and lacks specifics about the study design.

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

This information is not provided in the document.

4. Adjudication method for the test set

This information is not provided 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

There is no mention of an MRMC comparative effectiveness study or any assessment of human reader improvement with or without AI assistance. The PER Option is described as a software application for image processing, not a tool for direct human-in-the-loop decision support that would typically be evaluated with an MRMC study in this context.

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

While not explicitly called a "standalone study," the statement "Bench and clinical data show that the PER corrected simultaneous dual-isotope images are similar to the conventional single isotope images" implies an assessment of the algorithm's performance in generating images. However, the specifics of this assessment (metrics, methodology) are not detailed.

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

The document does not specify the type of ground truth used. The comparison is made against "conventional single isotope images," implying that these uncorrected images might serve as a baseline or reference, but not necessarily a "ground truth" in the sense of a definitive diagnosis or outcome.

8. The sample size for the training set

The document does not provide any information about a training set since the PER Option is likely based on spectral deconvolution analysis, which might not involve machine learning training in the same way as some other AI algorithms. If there was a training phase for any parameters, it's not described.

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

As no training set is described, information on how its ground truth was established is also absent.

In summary:

The provided 510(k) summary focuses on demonstrating substantial equivalence to a predicate device and broadly describes the device's intended function. It lacks the detailed study information typically found in submissions for novel AI/ML devices that require rigorous performance evaluation against specific acceptance criteria. The claim of "similarity to conventional single isotope images" serves as the primary evidence of effectiveness, but the methodology, sample sizes, and detailed results of this comparison are not provided.

Ask a specific question about this device