Search Results

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.

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.

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.

Ask a specific question about this device

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

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 describes a 510(k) submission for the Hermes Medical Imaging Suite v5.3. It focuses on the substantial equivalence of the new version to previously marketed predicate devices, primarily due to a change in the software's operating environment from Oracle® Solaris to Microsoft® Windows.

Although the document mentions "acceptance criteria" and "testing results supports that all the software specifications have met the acceptance criteria," it does not provide specific details on what these acceptance criteria were, what the reported device performance against those criteria was, or any clinical study details.

Therefore, many of the requested items cannot be extracted from this document.

Here's a breakdown of what can be inferred and what is explicitly missing:

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

Explanation: The document states, "The testing results supports that all the software specifications have met the acceptance criteria." However, it does not define what those specifications or acceptance criteria were, nor does it provide any quantitative performance metrics. The testing was primarily focused on demonstrating that the transfer of NM-processing applications to a new operating environment maintained the same technological characteristics and intended use as the predicate devices.

2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

• Sample Size (Test Set): Not specified.
• Data Provenance: Not specified.

Explanation: The document focuses on technical verification and validation of software functionality after an operating environment change. It does not describe a clinical study involving a test set of patient data.

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)

• Number of Experts: Not applicable, as no clinical test set for ground truth establishment is described.
• Qualifications of Experts: Not applicable.

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

• Adjudication Method: 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

• MRMC Study: No. This document describes a software update for an image processing system, not an AI-assisted diagnostic tool or a comparative effectiveness study involving human readers.
• Effect Size: Not applicable.

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

• Standalone Study: The document does not describe a standalone performance study in the context of an algorithm's diagnostic accuracy. The "testing" mentioned refers to verification and validation of software specifications, ensuring the functionality remained consistent after the platform migration.

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

• Type of Ground Truth: Not applicable, as the document does not describe a clinical study requiring ground truth for diagnostic accuracy. The testing was against design specifications and predicate device performance, not clinical ground truth.

8. The sample size for the training set

• Sample Size (Training Set): Not applicable. This device is not described as an AI/ML device that requires a training set.

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

• Ground Truth Establishment (Training Set): Not applicable.

Summary of the Study described:

The study described in the 510(k) summary is a technical verification and validation study to demonstrate that the Hermes Medical Imaging Suite v5.3, with its NM-processing applications transferred from Oracle® Solaris to Microsoft® Windows, maintains the same technological characteristics and intended use as its predicate devices. The "testing" ensured that "all the software specifications have met the acceptance criteria," and "comparisons were made between HERMES Medical Imaging Suite v5.3 and HERMES Medical Imaging Workstation (K121278), HERMES HDAQ Acquisition Station and Hermes Workstation (K021656), HERMES HDAQ Acquisition Station and Hermes Workstation (K002782) and Xeleris 2 processing and review workstation (K051673). The results showed a good compliance."

This is a regulatory submission focused on demonstrating substantial equivalence for a software update rather than a clinical performance study with specific diagnostic accuracy metrics.

Ask a specific question about this device

The system is intended for use by Nuclear Medicine (NM) or Radiology practitioners and referring physicians for display, processing, archiving, printing, reporting and networking of NM data, including planar scans (Static, Whole Body, Dynamic, Multi-Gated) and tomographic scans (SPECT, Gated SPECT, dedicated PET or Camera-Based-PET) acquired by gamma cameras or PET scanners.

The system can run on dedicated workstation or in a server-client configuration.

The NM or PET data can be coupled with registered and/or fused CT or MR scans, and with physiological signals in order to depict, localize, and/or quantify the distribution of radionuclide tracers and anatomical structures in scanned body tissue for clinical diagnostic purposes.

DaTQUANT optional application enables visual evaluation and quantification of 131ioflupane (DaTscan™)) images. DaTQUANT Normal Database option enables quantification relative to normal population databases of 1231-ioflupane (DaTscan TM) images.

These applications may assist in detection of loss of functional dopaminergic neuron terminals in the striatum, which is correlated with Parkinson disease.

The Xeleris 3.1 is a Nuclear Medicine Workstation system intended for general nuclear medicine processing & review procedures for detection of radioisotope tracer uptake in the patient body, using a variety of processing modes supported by various clinical applications types and various features designed to enhance image quality. The components of the Xeleris 3.1 NM Workstation system are: operation console, monitor and peripherals. The Xeleris 3.1 is a modification of its predicate device Xeleris 3 while providing enhanced workflow to existing operations and enabling broader access to Xeleris applications in supporting PACS and GE AW Server and in offline client server configuration. Xeleris 3.1 also enables the use of normal data base comparison together with the quantification analysis of 123I-ioflupane brain NM images. Similar functionality for NM/PET brain image analysis also resides in the predicate devices K021656 and K123528.

Here's an analysis of the provided text regarding the acceptance criteria and study for the Xeleris 3.1 Processing and Review Workstation, specifically focusing on the DaTQUANT application:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state formal acceptance criteria with specific numerical thresholds for the DaTQUANT application's accuracy. Instead, it describes a
The study for the DaTQUANT application compared "DaTQUANT analysis results to manual analysis results." The reported performance is that "DaTQUANT results were found to be as accurate as manual results."

2. Sample Size Used for the Test Set and Data Provenance

• Sample Size: The document mentions that the data used for testing was "taken from brain phantoms injected symmetrically and asymmetrically." It does not specify the number of phantoms or the number of acquisitions/images used.
• Data Provenance: The data was derived from "brain phantoms injected symmetrically and asynchronously," simulating normal and abnormal uptakes, with "different contrast levels used to simulate different signal to noise ratio levels." This indicates a controlled, artificial data set (phantoms) rather than human clinical data. It is a retrospective analysis of phantom data. The country of origin for the phantom data is not specified.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications

The ground truth in this specific test was established by "manual analysis results," which inherently implies human expert involvement. However, the document does not specify the number of experts who performed the manual analysis, nor their specific qualifications (e.g., "radiologist with 10 years of experience").

4. Adjudication Method for the Test Set

The document does not describe any specific adjudication method (e.g., 2+1, 3+1). It simply states that the DaTQUANT results were compared to "manual analysis results," implying a direct comparison without detailing how discrepancies in manual analysis (if multiple experts were involved) would have been resolved.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

No, a multi-reader multi-case (MRMC) comparative effectiveness study was not explicitly mentioned for the DaTQUANT application in this document. The testing described focuses on comparing the algorithm's output to manual analysis, not on how human readers' performance might improve with or without AI assistance.

6. Standalone Performance (Algorithm Only without Human-in-the-Loop Performance)

Yes, a standalone performance test was done for the DaTQUANT application. The description, "Testing the accuracy of using the DaTQUANT application by comparing DaTQUANT analysis results to manual analysis results," indicates that the algorithm's output (DaTQUANT results) was directly evaluated against a ground truth (manual analysis) without an explicit human-in-the-loop interaction for the DaTQUANT itself during this specific accuracy test.

7. Type of Ground Truth Used

The ground truth used for the DaTQUANT accuracy testing was expert consensus / manual analysis results derived from phantom data.

8. Sample Size for the Training Set

The document does not specify the sample size or details regarding a training set for the DaTQUANT application. The description focuses solely on the accuracy testing using phantom data.

9. How the Ground Truth for the Training Set Was Established

Since a training set is not mentioned, the method for establishing its ground truth is also not provided in this document.

Ask a specific question about this device