Search Results

FUJIFILM Synapse PACS Software (client) is intended for use, as a web based application, on an off-the-shelf PC meeting or exceeding minimum specifications and networked with FUJIFILM Synapse PACS Software (Server). The FUJIFILM Synapse PACS Software is intended to serve as the primary user interface for the processing of medical images for presentation on displays appropriate to the medical task being performed. The Synapse PACS Software can process medical images from the following modality types: plane X-ray radiography, X-ray computed tomography, magnetic resonance imaging, ultrasound, nuclear medicine and images from other DICOM compliant modalities.

The FUJIFILM Synapse PACS Software enables the display, comparison of 3D (MIP/MPR) of CT, MR, PET and SPECT studies. Typical users are radiologists and clinicians. These functions (MIPMPR/Fusion) are not intended for Mammography use.

The FUJIFILM Synapse PACS Software may be used to process FUJIFILM's DICOM MG "For Processing" images and also for the display, manipulation, and interpretation of lossless compressed mammography images that have been received in the DICOM For Presentation format and displayed on FDA cleared, DICOM compatible displays for mammography.

The proposed Synapse PACS Software is an implementation that combines capabilities of Synapse Workstation software (K112439) and Synapse MPR/Fusion software (K113244) in a single system, using the current Internet standards for Web clients and servers. The Synapse PACS Software and the predicate devices, i.e., Synapse Workstation Software (K112439) and Synapse MPR Fusion Software (K113244), are picture archiving and communication systems (as defined by 21 CFR 892.2050). Synapse PACS Software is the web based (client/server) application and implementation of the Synapse Workstation Software and the Synapse MPR Fusion Software. The Synapse PACS Software (client) is intended for use, as a web based application, on an off-the-shelf PC meeting or exceeding minimum specifications and networked with Synapse PACS Software (server). The Synapse PACS Software is intended to serve as the primary user interface for the processing of medical images for presentation on displays appropriate to the medical task being performed. The Synapse PACS Software can process medical images from the following modality types: plane X-ray radiography, X-ray computed tomography, magnetic resonance imaging, ultrasound, nuclear medicine and images from other DICOM compliant modalities. Synapse PACS Software enables the display, comparison and fusion of 3D (MIP/MPR) of CT, MR, PET and SPECT studies (K113244).

In summary, this 510(k) submission introduces the Synapse PACS with the web based (client/server) application and the ability to the display, comparison and fusion of 3D (MIP/MPR) of CT, MR, PET and SPECT studies.

The provided text is a 510(k) summary for the FUJIFILM Synapse PACS (K160108). This document primarily focuses on establishing substantial equivalence to previously cleared predicate devices (Synapse Workstation K112439 and Synapse MPR Fusion K113244) rather than presenting a performance study with detailed acceptance criteria and testing methodology for a novel diagnostic algorithm.

The document describes the device, its intended use, and provides comparisons of features, technology, and specifications with the predicate devices. It also mentions general testing activities. However, it does not detail a specific study proving the device meets acceptance criteria in the way one would for a new AI/CAD device. The Synapse PACS is a picture archiving and communication system, and its "performance" is more related to its functionality, speed, and ability to display and process images, rather than the diagnostic accuracy of an interpretation algorithm.

Therefore, many of the requested elements for describing a study proving the device meets acceptance criteria for a diagnostic AI/CAD device are not applicable or not detailed in this 510(k) summary.

Here's an attempt to answer the questions based on the provided text, indicating where information is not present:

Acceptance Criteria and Study for FUJIFILM Synapse PACS (K160108)

This 510(k) submission for the Synapse PACS focuses on demonstrating substantial equivalence to predicate devices for its functionalities as a PACS system, not on proving diagnostic performance of a new AI algorithm. Therefore, the "acceptance criteria" and "study" described below are interpreted in the context of a PACS system's performance and equivalence, rather than the accuracy of an automated diagnostic output.

1. Table of Acceptance Criteria and Reported Device Performance

For a PACS system, acceptance criteria are generally related to its functionality, performance (speed, responsiveness), and ability to display and process images as intended. The document states "Pass/Fail criteria were based on the requirements and intended use of the product. Test results showed that all tests successfully passed." Specific quantitative criteria are not listed for individual functions.

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

The document mentions "actual clinical images" were used for "benchmark performance testing" but does not specify the sample size or their provenance (e.g., country of origin, retrospective/prospective collection). Given the nature of a PACS system, the "test set" would likely be a diverse range of images to ensure format compatibility and display accuracy across modalities, rather than a specific set for diagnostic accuracy assessment.

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

Not applicable. For a PACS system, "ground truth" in the diagnostic sense is not typically established by experts as the system's function is to display and process, not to provide diagnostic interpretations. The ground truth for its performance would be whether it accurately displays images, performs requested manipulations, and stores/retrieves data correctly. This would be verified through technical testing and potentially user acceptance testing by radiologists/clinicians, but not in the same way as establishing ground truth for an AI diagnostic algorithm.

4. Adjudication Method for the Test Set

Not applicable. Adjudication methods (e.g., 2+1, 3+1) are used to resolve discrepancies among expert readers when establishing ground truth for diagnostic studies. This is not relevant to the functional validation of a PACS system.

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

No. An MRMC study is typically performed to evaluate the impact of an AI algorithm on human reader performance (e.g., improved diagnostic accuracy, reduced reading time). This device is a PACS system, not a diagnostic AI algorithm, so such a study would not be applicable or expected.

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

Not applicable. This device is a PACS system, which is a tool for human interpretation and management of medical images. It does not perform standalone diagnostic interpretations.

7. The Type of Ground Truth Used

The "ground truth" for a PACS system would be the technical specifications and clinical expectations for image display, processing, and storage. For example:

• Technical Specifications: Does the system accurately render images according to DICOM standards? Are measurements correct?
• Functional Expectations: Does it perform MIP/MPR as specified? Does it retrieve images within an acceptable timeframe?
  These are assessed through verification and validation testing, not typically through pathology, expert consensus, or outcomes data in the diagnostic sense. The document refers to "benchmark performance testing using actual clinical images," which suggests an evaluation against expected display and processing quality for real-world data.

8. The Sample Size for the Training Set

Not applicable. PACS software, like the Synapse PACS, is developed based on software engineering principles and medical imaging standards (e.g., DICOM). It does not use "training sets" in the machine learning sense to learn to perform a task. It is a rule-based system designed to display and manage images.

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

Not applicable, as there is no "training set" for a PACS system in this context.

Ask a specific question about this device