Search Results

The Millennium MT and MG systems are designed to acquire data for whole body and multi-slice images. The Millennium MT and MG are intended for use as diagnostic imaging devices. When used with appropriate pharmaceuticals, they produce images representative of the internal distribution of radioactivity in head or body. These systems allow you to acquire data for high resolution three dimensional, static gated or dynamic images of biochemical and metabolic processes.

Millennium MT Nuclear Medicine System will be used for general purpose applications planar, whole body and SPECT (Single Photon Emission Computed Tomography). It will support two Digital CSE (correlated signal enhancement) rectangular detectors in 180 degree (opposed) geometry (DH position). Whole body studies will be accomplished through the gantry ring. The gantry/detector assembly will support step-and-shoot tomography, continuous tomography, elliptical tomography, simultaneous anterior/ posterior whole body and whole body contour applications. Prone/supine/sitting/sideways patient studies will be accommodated by the gantry/detector assembly.

In addition to the Millennium MT capabilities, the Millenneum MG provides a 101.25 degree cardiac detector angulation (VG position) functionality implemented through the addition of a locking motor, additional software to automate the positioning and set up protocols.

The MT system can be upgraded to a MG system by adding a locking motor to the gantry and removing software locks to enable all of the MG software functionality

The provided text is a Summary of Safety and Effectiveness for the GE Millennium MT and MG Nuclear Medicine Systems, submitted as part of a 510(k) premarket notification. This document focuses on demonstrating substantial equivalence to predicate devices rather than proving performance against specific acceptance criteria for an AI or imaging algorithm.

Therefore, the requested information cannot be fully extracted as it pertains to AI-specific evaluation metrics and study designs that are not typically found in a traditional 510(k) for a general nuclear medicine imaging system from 1996.

Here's an analysis based on the absence of the requested information, and what can be inferred from the document:

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

• Acceptance Criteria: Not explicitly stated as performance metrics in this document. The "acceptance criteria" for a 510(k) of this nature is generally "substantial equivalence" to predicate devices, meaning it performs as well as or better than existing devices without raising new safety or efficacy concerns.
• Reported Device Performance: No specific quantitative performance metrics (e.g., sensitivity, specificity, accuracy, resolution numbers) are provided or compared. The document states that the systems "acquire data for whole body and multi-slice images" and "produce images representative of the internal distribution of radioactivity."

2. Sample sized 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 in the document. The filing is for a general-purpose nuclear medicine system, and the "studies" mentioned are not clinical trials or performance evaluations against a specific diagnostic task with a test set of patient data as understood in AI/algorithm evaluations. The "Summary of Studies" section generally refers to the capabilities of the device (planar, whole body, SPECT, tomographic, cardiac imaging) rather than a study with a defined test set.

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 and is not applicable to this type of 510(k) submission. "Ground truth" for an imaging system from this era would typically refer to the physical and technical specifications of the device's image acquisition and reconstruction, not expert interpretation of images for diagnostic accuracy in a clinical study.

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

• This information is not present and is not applicable.

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. MRMC studies are used to evaluate human reader performance, especially with AI assistance. The device described is a raw imaging system, not an AI-powered diagnostic tool, and the filing dates back to 1996, preceding widespread AI in medical imaging.

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

• This information is not present. The device is an imaging system; it is not an algorithm, and the concept of "standalone performance" for an algorithm separate from human input wasn't central to this type of device submission.

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

• This information is not present in the AI/diagnostic algorithm sense. For a nuclear medicine system, "ground truth" might refer to phantoms used for calibration or physical measurements of detector performance, but these are not clinical "ground truths."

8. The sample size for the training set

• This information is not present. The device is a hardware system; it does not have a "training set" in the context of machine learning.

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

• This information is not present and is not applicable.

In summary: The provided document is a 510(k) premarket notification from 1996 for a nuclear medicine imaging system. It focuses on demonstrating "substantial equivalence" to existing predicate devices by comparing intended use and design, and stating that it raises no new safety or effectiveness concerns. It does not contain the specific information requested regarding acceptance criteria, study methodologies, reader studies, or AI algorithm performance, as these concepts and requirements were either not relevant to this type of device at that time or are specific to AI/software as a medical device (SaMD) evaluations.

Ask a specific question about this device