(81 days)
MG ATC is indicated to improve the quality of emission SPECT images obtained on the Millennium MG dual head camera by attenuation correction.
The MG ATC attenuation correction system is an optional addition to the Millennium MG gamma camera (K962738). It comprises additional hardware and software to generate a correction map and corrected NM images for non-uniform attenuation.
The provided text describes the MG ATC: Attenuation Correction System for Dual-Head Variable-Angle Gamma Camera. Here's an analysis of the acceptance criteria and study information:
1. Acceptance Criteria and Reported Device Performance
| Acceptance Criteria | Reported Device Performance |
|---|---|
| Deliver better uniformed images than regular SPECT without attenuation correction. | Meets Criteria: "Bench data and Clinical data show that the MG ATC option delivers better uniformed images than regular SPECT without attenuation correction." |
| No significant difference compared to V TransACT images (predicate device). | Meets Criteria: "Comparison to V TransACT images shows no significant difference." |
| Substantially equivalent in terms of safety and effectiveness to the V TransACT option for the Varicam (K980959). | Meets Criteria: "In the opinion of ELGEMS Ltd., the MG ATC is substantially equivalent in terms of safety and effectiveness to the V TransACT option for the Varicam (K980959)." |
| Same intended use as the predicate device. | Meets Criteria: "The MG ATC has the same intended use as the predicate device..." |
| No new safety or effectiveness concerns raised. | Meets Criteria: "...and no new safety or effectiveness concerns are raised." |
Study Details:
The document provides a high-level summary of the studies but lacks specific quantitative details for many of the requested points.
2. Sample Size Used for the Test Set and Data Provenance:
- Sample Size for Test Set: Not specified. The document only mentions "Bench data and Clinical data."
- Data Provenance: Not specified (e.g., country of origin, retrospective or prospective).
3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications:
- Not specified.
4. Adjudication Method for the Test Set:
- Not specified.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:
- Not explicitly mentioned. The statement "Comparison to V TransACT images shows no significant difference" suggests a comparison, but it doesn't specify if human readers were part of an MRMC study or if it was an assessment based on objective metrics. Therefore, the effect size of human readers improving with AI vs. without AI assistance is not provided.
6. Standalone (Algorithm Only) Performance Study:
- The nature of the "Bench data" suggests some form of standalone evaluation of the algorithm's output (images). However, the document doesn't explicitly state a separate standalone performance study or provide specific metrics for it. The primary comparison is implied to be visual image quality and equivalence to the predicate.
7. Type of Ground Truth Used:
- The document mentions "better uniformed images" and "no significant difference" in comparison, suggesting that the ground truth was likely based on subjective image quality assessment or comparison to an established reference standard for image uniformity and accuracy in SPECT imaging. It does not mention pathology, outcomes data, or expert consensus in a structured way for ground truth creation.
8. Sample Size for the Training Set:
- Not specified. The document focuses on demonstrating equivalence to a predicate device rather than detailing model training.
9. How the Ground Truth for the Training Set Was Established:
- Not specified. As it's a device for attenuation correction, the "training" (if any, as this predates modern deep learning) would likely involve calibration data and possibly phantom studies to accurately model photon attenuation. However, no specifics are provided.
Overall Conclusion from the Provided Text:
The submission focuses heavily on demonstrating substantial equivalence to a legally marketed predicate device (V TransACT) based on the stated intended use and general performance improvements (better uniformed images compared to uncorrected SPECT). While "Bench data and Clinical data" are cited, specific details regarding sample sizes, expert involvement, and ground truth methodologies are not included in this summary document. The information is high-level for a 510(k) summary, aiming to establish equivalence rather than a detailed performance report for a novel AI algorithm.
§ 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.