K Number
K140269
Date Cleared
2014-05-08

(94 days)

Product Code
Regulation Number
892.1200
Panel
RA
Reference & Predicate Devices
AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

HERMES Medical Imaging suite that provides software applications used to process, display, analyze and manage nuclear medicine and other medical imaging data transferred from other workstation or acquisition stations.

Device Description

The base product design of Hermes Medical Imaging Suite v5.4 is the same as for the Hermes Medical Imaging Suite v5.3 (K131233). A modification has been made of the product where the imaging processing application BRASS™ has been transferred from the Oracle® Solaris environment to the Microsoft® Windows environment. BRASS™ has also been updated with improved support for management and analysis of amyloid PET imaging as described in the 510(k) submission. The Hermes Medical Imaging Suite provides software applications used to process, display, analyze and manage nuclear medical imaging data transferred from other workstation or acquisition stations.

AI/ML Overview

The provided text is a 510(k) summary for the HERMES Medical Imaging Suite v5.4. It describes the device, its intended use, and substantial equivalence to predicate devices. However, it does not contain specific details about acceptance criteria, device performance metrics, or a study design with sample sizes, ground truth establishment, or expert involvement as requested.

The summary states: "The testing results supports that all the software specifications have met the acceptance criteria." but does not elaborate on what those criteria were or how performance was measured against them. It focuses on the substantial equivalence based on technological characteristics and indication for use with predicate devices.

Therefore, I cannot fulfill your request to describe the acceptance criteria and the study that proves the device meets them, nor can I provide information for most of the numbered points, as that information is not present in the provided document.

Here's a breakdown of what can and cannot be extracted from the provided text based on your request:


Acceptance Criteria and Device Performance Study (Information Not Provided in Document)

The document states that "The testing results supports that all the software specifications have met the acceptance criteria." However, it does not provide:

  • A table of acceptance criteria.
  • Reported device performance metrics.
  • Details of the study that proves the device meets the acceptance criteria.

Therefore, the following points cannot be addressed from the given text:

1. A table of acceptance criteria and the reported device performance
* Not provided in the document. The document only states that acceptance criteria were met.

2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
* Not provided in the document.

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)
* Not provided in the document.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
* 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
* Not provided in the document. The document describes a comparison to predicate devices, focusing on technological equivalence, not a comparative effectiveness study with human readers.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
* Not provided in the document.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
* Not provided in the document.

8. The sample size for the training set
* Not provided in the document. This document focuses on a 510(k) submission for a software update and comparison to predicate devices, not on the deep learning aspects of an AI model's training.

9. How the ground truth for the training set was established
* Not provided in the document.


What the document does state:

  • Device Description: The HERMES Medical Imaging Suite v5.4 is an update to v5.3 (K131233). The primary change is the transfer of the BRASS™ imaging processing application from Oracle® Solaris to Microsoft® Windows environment, with improved support for management and analysis of amyloid PET imaging.
  • Intended Use: To process, display, analyze, and manage nuclear medicine and other medical imaging data transferred from other workstations or acquisition stations.
  • Testing: "The tests for verification and validation followed Hermes Medical Solutions AB design controlled procedures. The Risk analysis was completed and risk control implemented to mitigate identified hazards. The testing results supports that all the software specifications have met the acceptance criteria."
  • Substantial Equivalence: The device is deemed substantially equivalent to predicate devices (HERMES Medical Imaging Suite v5.3 (K131233), HERMES HDAQ Acquisition Station and Hermes Workstation (K021656), Xeleris 3.1 processing and review workstation (K130884), and Scenium 3.0 (K123528)) based on similar technology, fundamental concepts, and operation, with the specific modification for BRASS™ noted. The "results showed a good compliance."

In summary, this 510(k) primarily focuses on demonstrating that a software update to an existing device, which includes transferring a feature to a new operating system and enhancing support for amyloid PET imaging, maintains substantial equivalence without introducing new safety or effectiveness concerns requiring detailed clinical performance studies to the extent of proving specific acceptance criteria with quantifiable metrics.

§ 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.