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 v5.7 is the same as for the Hermes Medical Imaging Suite v5.6 (K153056). The following modules have been added in this applicatio to Hybrid Viewer NM Processing: Colonic Transit, Remnant Liver, Parathyroid, Dosimetry, Classic DMSA, Oesophageal Transit/Reflux, HIDA, Salivary Gland, Bone3Phase Analysis and Uniformity.

Here's an analysis of the provided text regarding the acceptance criteria and study details for the Hermes Medical Imaging Suite v5.7:

Understanding the Device:

The device, HERMES Medical Imaging Suite v5.7, is a software application suite for processing, displaying, analyzing, and managing nuclear medicine and other medical imaging data. It has added several new modules compared to its predecessor (v5.6).

Challenges in Extracting Information:

The provided text is a 510(k) summary, which is a regulatory document focused on demonstrating substantial equivalence to a predicate device. It doesn't present a traditional "acceptance criteria" table or a single, comprehensive study report with detailed methodologies. Instead, it describes a series of comparative tests against predicate devices and manual calculations. Therefore, the "acceptance criteria" are implied by the comparisons and the statement that "the testing results supports that all the software specifications have met the acceptance criteria." The reported performance is the outcome of these comparisons.

1. Table of Acceptance Criteria and Reported Device Performance

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

• Hybrid Recon (Myocardial SPECT):

  • Sample Size: 10 subjects.
  • Data Provenance: Not explicitly stated, but implicitly retrospective as they were "compared" to a previous version and involved "stress&rest myocardial SPECT scan with Tc99m tetrofosmin." No country of origin is mentioned.

• Hybrid Recon (Phantom Studies):

  • Sample Size: Jaszczak phantom and IEC Phantom (physical phantoms, not patient data).
  • Data Provenance: Not applicable in the same way as patient data. These are controlled experimental setups.

• Classic DMSA, Colonic Transit, Oesophageal Transit/Reflux, 3Phase Bone Analysis, HIDA, Salivary Gland Analysis:

  • Sample Size: Not explicitly stated for these modules. The phrasing "compared to manual calculations" or "compared to Xeleris 3.1" does not provide the number of cases used in these comparisons.
  • Data Provenance: Not explicitly stated. Assumed to be retrospective if patient data was used, or simulated/phantom data for manual calculations.

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

• Number of Experts: Not explicitly stated.
• Qualifications of Experts: Not explicitly stated.
  • For the modules compared against "manual calculations (from first principles)," the "expert" is implied to be a human capable of performing these calculations, but specific qualifications are not provided.
  • For comparisons against predicate devices, the predicate devices themselves are the "truth" or reference, not human experts establishing ground truth for the test set.

4. Adjudication Method for the Test Set

• The document describes direct comparisons of results generated by the device (v5.7) against predicate devices (v5.6, v5.3, GE Xeleris 3.1) or against "manual calculations."
• There is no mention of an adjudication method (like 2+1 or 3+1 consensus) involving multiple human experts for determining a ground truth label for the test cases used. The reference is either an older software version or predefined manual calculation methods.

5. If a Multi Reader Multi Case (MRMC) Comparative Effectiveness Study was done

• No, an MRMC comparative effectiveness study was not done. The studies described are comparisons of one software version against another, or against manual calculations, focusing on the output consistency and accuracy of the software itself, not on how human readers perform with or without AI assistance.

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

• Yes, the described studies are standalone algorithm-only performance tests. The comparisons are between algorithm versions or between an algorithm and manually calculated results. There is no mention of a human interacting with the AI outputs as part of the performance evaluation.

7. The Type of Ground Truth Used

The ground truth used varies by the type of comparison:

• Hybrid Recon (Myocardial SPECT): The outputs from the predicate device (Hermes Medical Imaging Suite v5.6) were used as the reference for comparison.
• Hybrid Recon (Phantom Studies): The known true activity concentrations within the Jaszczak and IEC phantoms were used as the ground truth.
• Classic DMSA: The outputs from the predicate device (Classic DMSA application in Medical Imaging Suite v5.3) were used as the reference.
• Colonic Transit: The outputs from the predicate device (GE Xeleris 3.1 review and workstation) were used as the reference.
• Oesophageal Transit/Reflux, 3Phase Bone Analysis, HIDA, Salivary Gland Analysis: Manual calculations (from first principles) were used as the ground truth. This implies an established, understood method of calculation is the reference.

8. The Sample Size for the Training Set

• Not provided. The document focuses entirely on verification and validation testing, and the 510(k) summary typically does not include details about the training set for the software, especially for traditional medical imaging software (not AI/ML in the modern sense) where "training" might refer to software development and bug fixing rather than data-driven model training.

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

• Not applicable / Not provided. As no information on a training set (in the context of machine learning) is given, how its ground truth was established is also not mentioned. The software modules appear to be based on established algorithms and calculations for nuclear medicine image processing, rather than being "trained" on a dataset with external ground truth labels.

Ask a specific question about this device

The D-SPECT® Processing and Reviewing Workstation is intended for Processing, Reporting, Archiving, Display, Communication and Analysis of emission computerized tomography data using tools for imaging and automated review and quantification of Cardiac SPECT data.

The D-SPECT® Processing and Reviewing Workstation is intended to work with Spectrum Dynamics' D-SPECT® Cardiac Scanner System or as a separate standalone post processing workstation.

The system is intended for use by the Nuclear Medicine (NM), Radiology or Electro Physiology practitioners and referring physicians for display, processing, archiving, printing, reporting and networking of NMI data, including planar scans (Static, Dynamic, Multi-Gated) and tomographic three-dimensional scans (SPECT, Gated SPECT) acquired by gamma cameras. The system can run on a dedicated workstation or as part of Spectrum Dynamics' D-SPECT® Cardiac Scanner System. The NM data can be coupled with registered and/or fused X-Ray 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. "SUMO" optional application enables visual evaluation and assessment of the sympathetic innervation system of the heart by quantification of uptake ratios between regions of interest, identifying discreet uptake areas of mIBG I-123 (AdreView tm Iobenguane I-123 Injection) or similar agents within the heart.

D-SPECT® Processing and Reviewing Workstation is intended for acceptance, transfer, display, storage, and processing of images for detection of radioisotope tracer uptakes in the patient's body. The device using various processing modes supported by the various clinical applications and various features designed to enhance image quality. The emission computerized tomography data can be coupled with registered and/or fused CT/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. Visualization tools include segmentation, color coding, and polar maps. Analysis tools include Quantitative Perfusion SPECT (QPS), Quantitative Gated SPECT (QGS) and Quantitative Blood Pool Gated SPECT (QBS) measurements, Multi Gated Acquisition (MUGA) and Heart-to-Mediastinum activity ratio (H/M). It also includes reporting tools for formatting findings and user selected areas of interest. It is capable of processing and displaying the acquired information in traditional formats, as well as in three-dimensional renderings, and in various forms of animated sequences, showing kinetic attributes of the imaged organs.

D-SPECT® Processing and Reviewing Workstation is based on Windows operating system. Due to special customer requirements and the clinical focus the D-SPECT® Processing and Reviewing Workstation can be configured in the same way as the predicate device with different combinations of Windows OS based software options and clinical applications which are intended to assist the physician in diagnosis and/or treatment planning. This includes commercially available post-processing software packages.

D-SPECT® Processing and Reviewing Workstation is a processing workstation primarily intended for, but not limited to cardiac applications. The workstation can be a part of the FDA cleared D-SPECT® Cardiac Scanner System (K110507) or integrated to a separate standalone post processing station. "SUMO" optional application enables visual evaluation and assessment of the sympathetic innervation system of the heart by quantification of uptake ratios between regions of interest, identifying discreet uptake areas within the heart of mIBG I-123 (AdreView™ Iobenguane I-123 Injection) or similar agents.

The D-SPECT® Processing and Reviewing Workstation, a nuclear medicine workstation, underwent testing to demonstrate its safety and effectiveness.

Here's an analysis based on the provided document:

1. Acceptance Criteria and Reported Device Performance

The document states that "The performance tests indicate that the D-SPECT® Processing and Reviewing Workstation meets the specification requirements." However, specific quantitative acceptance criteria (e.g., sensitivity, specificity, accuracy thresholds) and reported device performance metrics are not explicitly listed in the provided text. The document focuses on demonstrating substantial equivalence to predicate devices and compliance with relevant standards.

Table of Acceptance Criteria and Reported Device Performance:

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

The document mentions that a "overall performance study using a simulated phantom and a dataset of subjects" was performed.

• Test Set Sample Size: The exact number of subjects in the "dataset of subjects" is not specified.
• Data Provenance: The country of origin for the data is not specified. The document indicates the study was performed in accordance with FDA guidance for Computer-Assisted Detection Devices. It is a pre-clinical study utilizing both a simulated phantom and a dataset of subjects. It appears to be retrospective as data collection usually precedes such studies for regulatory submission.

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

This information is not provided in the document. The document mentions "automated review and quantification," but does not detail how ground truth for the subject dataset was established or if it involved expert interpretation or consensus.

4. Adjudication Method for the Test Set

The adjudication method (e.g., 2+1, 3+1, none) for establishing ground truth on the test set is not specified in the provided text.

5. If a Multi Reader Multi Case (MRMC) Comparative Effectiveness Study Was Done

A Multi-Reader Multi-Case (MRMC) comparative effectiveness study comparing human readers with AI assistance versus without AI assistance was not explicitly mentioned or described. The study described ("overall performance study") focuses on the device's standalone performance validating its safety and effectiveness against specifications. The document also states that the device is intended for "automated review and quantification."

6. If a Standalone Study Was Done

Yes, a standalone study was done. The document states: "To demonstrate and validate the safety, effectiveness and clinical use of the modified D-SPECT® Processing and Reviewing Workstation using SUMO application, Spectrum Dynamics performed a number of validation and verification tests including overall performance study using a simulated phantom and a dataset of subjects..." This describes a study evaluating the performance of the algorithm/workstation itself.

7. The Type of Ground Truth Used

The type of ground truth used for the subject dataset is not explicitly stated. It would typically involve clinical diagnosis, often based on expert interpretation of imaging, pathology, or other clinical outcomes, but this is not detailed in the provided text. The mention of "simulated phantom" suggests a known, controlled ground truth for that part of the study.

8. The Sample Size for the Training Set

The sample size for any training set is not specified. The document describes performance tests and validation, but does not detail the development or training of any machine learning components (if present and if requiring a training set), beyond stating "automated review and quantification."

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

The method for establishing ground truth for any potential training set is not specified, as the document does not elaborate on the development or training process for the automated review and quantification tools.

Ask a specific question about this device

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