(92 days)
HERMES Medical Imaging suite that provides software applications used to process, display, and manage nuclear medicine and other medical imaging data transferred from other workstation or acquisition stations.
The base product design of Hermes Medical Imaging Suite v5.5 is the same as for the Hermes Medical Imaging Suite v5.4 (K140269). A modification has been made in the reconstruction software Hybrid Recon™ where a new feature is added to enable quantitative reconstruction. The Hermes Medical Imaging Suite provides software applications used to process, display, analyze and manage nuclear medicine and other medical imaging data transferred from other workstation or acquisition stations.
The provided text is a 510(k) summary for the Hermes Medical Imaging Suite v5.5. It focuses on demonstrating substantial equivalence to a predicate device rather than detailing extensive clinical performance studies for a novel AI device. Therefore, much of the requested information regarding AI-specific criteria (e.g., MRMC studies, training set details, expert ground truth adjudication) is not present. However, I can extract information related to the bench testing performed.
Here's a breakdown of the available information:
1. Table of Acceptance Criteria and Reported Device Performance
| Acceptance Criteria (Implicit from testing) | Reported Device Performance |
|---|---|
| Error of reconstructed activity concentration for large targets (e.g., 37mm object) | Around 5% |
| Error of reconstructed background activity concentration | Around 5% |
| Software specifications met | All software specifications met the acceptance criteria (general statement) |
2. Sample Size for the Test Set and Data Provenance
- Sample Size: The text mentions "bench testing using both Jaszczak phantom and IEC phantom." Phantoms are physical objects with known properties used for controlled testing, not human patient data. Therefore, there is no "sample size" in the conventional sense of patient cases, nor is there data provenance in terms of country of origin or retrospective/prospective status.
- Data Provenance: N/A (phantom data)
3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications
- N/A. Ground truth for phantom studies is established by the known physical properties and activity concentrations set up by the engineers/researchers conducting the test, not by expert medical review.
4. Adjudication Method for the Test Set
- N/A. Adjudication is not applicable to phantom studies where ground truth is known inherently.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done
- No, a TRMC study was not done. The document describes bench testing with phantoms, not human reader studies.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was done
- Yes, the bench testing using phantoms represents a standalone evaluation of the algorithm's performance in quantitative reconstruction, as it compares the device's output to a known ground truth without human intervention in the interpretation loop.
7. The Type of Ground Truth Used
- Phantom Gold Standard: The ground truth was established by the known "true activity" and "reconstructed activity" within different Regions of Interest (ROIs) of the Jaszczak and IEC phantoms. This is a controlled, objective ground truth based on the physical setup of the phantom experiment.
8. The Sample Size for the Training Set
- The document does not provide any information regarding a training set size. This information is typically relevant for machine learning or AI models, which are not explicitly detailed here beyond the mention of "quantitative reconstruction" capabilities.
9. How the Ground Truth for the Training Set was Established
- This information is not provided in the document.
§ 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.