(154 days)
Synapse 3D Base Tools is medical imaging software that is intended to provide trained medical professionals with tools to aid them in reading, interpreting, and treatment planning. Synapse 3D Base Tools accepts DICOM compliant medical images acquired from a variety of imaging devices including, CT, MR, CR, US, NM, PT, and XA, etc. This product is not intended for use with or for the primary diagnostic interpretation of Mammography images.
Synapse 3D Base Tools provides several levels of tools to the user:
Basic imaging tools for general images, including 2D viewing, volume rendering and 3D volume viewing, orthogonal / oblique / curved Multi-Planar Reconstructions (MPR), Average (RaySum) and Minimum (MinIP) Intensity Projection, 4D volume viewing, image subtraction, surface rendering, sector and rectangular shape MPR image viewing, MPR for dental images, creating and displaying multiple MPR images along an object, time-density distribution, basic image processing, noise reduction, CINE, measurements, annotations, reporting, printing, storing, distribution, and general image management and administration tools, etc.
- Tools for regional segmentation of anatomical structures within the image data, path definition through vascular and other tubular structures, and boundary detection.
-Image viewing tools for modality specific images, including CT PET fusion and ADC image viewing for MR studies. -Imaging tools for CT images including virtual endoscopic viewing and dual energy image viewing.
-Imaging tools for MR images including delayed enhancement image viewing, diffusion-weighted MRI image viewing.
The 3D image analysis software Synapse 3D Base Tools (V6.6) is medical application software running on Windows server/client configuration installed on commercial general-purpose Windows-compatible computers. It offers software tools which can be used by trained professionals to interpret medical images obtained from various medical devices, to create reports, or to develop treatment plans.
Synapse 3D Base Tools is connected through DICOM standard to medical devices such as CT, MR, CR, US, NM, PT, XA, etc. and to a PACS system storing data generated by these medical devices, and it retrieves image data via network communications based on the DICOM standard. The retrieved image data are stored on the local disk managed by Synapse 3D Base Tools (V6.6), and the associated image-related information of the image data is registered in its database and is used for display, image processing, analysis, etc. Images newly created by Synapse 3D Base Tools (V6.6) not only can be display, but also can be printed on a hardcopy using a DICOM printer or a Windows printer.
Synapse 3D Base Tools (V6.6) is a basic software module that works with other cleared clinical applications, including Synapse 3D Cardiac Tools (K200973), Synapse 3D Perfusion Analysis (K162287), Synapse 3D Lung and Abdomen Analysis (K130542), Synapse 3D Liver and Kidney Analysis (K142521), Synapse 3D Nodule Analysis (K120679), Synapse 3D Colon Analysis (K123566), Synapse 3D Tensor Analysis (K141514) and Synapse 3D Blood Flow Analysis (K191544). All these software modules consist of the Synapse 3D product family.
Synapse 3D Base Tools can be integrated with Fujifilm's Synapse PACS, and can be used as a part of a Synapse system. Synapse 3D Base Tools also can be integrated with Fujifilm's Synapse Cardiovascular for cardiology purposes.
The provided text does not contain detailed acceptance criteria and a study proving that the device meets these criteria in the typical format expected for a medical device with an AI/ML component affecting diagnostic accuracy. The device, "Synapse 3D Base Tools v6.6", is described as medical imaging software for viewing, interpreting, and planning, and its predicate device (Synapse 3D Base Tools v6.1) and other reference devices are also imaging software tools.
Instead, the submission focuses on demonstrating substantial equivalence to a predicate device, Synapse 3D Base Tools (V6.1) (K203103), by confirming similar indications for use and technical characteristics. The key performance information provided is about software development processes, verification and validation, and cybersecurity, rather than specific diagnostic performance metrics (e.g., sensitivity, specificity, AUC) for novel AI features impacting clinical decisions.
However, based on the information provided, particularly about the Dual Energy Analysis module and PixelShine, we can infer some aspects related to acceptance and performance.
Here's an analysis of the provided text in relation to your questions:
1. A table of acceptance criteria and the reported device performance
The document does not explicitly state a table of quantitative acceptance criteria for diagnostic performance metrics (e.g., sensitivity, specificity, accuracy) that the device must meet to be considered "accepted." This is likely because the device is primarily a "Medical image management and processing system" (21 CFR 892.2050) and not a primary diagnostic AI intended to make a diagnosis itself, but rather to provide "tools to aid them [trained medical professionals] in reading, interpreting, and treatment planning."
However, we can infer the acceptance for new features based on comparative testing for substantial equivalence:
| Acceptance Criterion (Inferred from Substantial Equivalence Review) | Reported Device Performance / Method of Proof |
|---|---|
| Overall Functionality and Design Specifications | "Test results showed that all tests passed successfully according to the design specifications." "All of the different components... have been stress tested to ensure that the system as a whole provides all the capabilities necessary to operate according to its intended use and in a manner substantially equivalent to the predicate devices." |
| Dual Energy Image Viewing Feature | The added "Dual Energy image viewing" feature in v6.6 is stated to be "the same as the feature available on the syngo.CT Dual Energy ('Reference Device'), which was cleared by the FDA under K133648." The module was "evaluated via comparative testing on patient data with the reference device syngo.CT Dual Energy (K133648)." |
| PixelShine Feature | The "PixelShine" feature is "the embedded functionality of previously-cleared PixelShine (cleared by CDRH via K161625)." This implies that its integration into Synapse 3D Base Tools v6.6 maintains the already cleared performance of the standalone PixelShine. |
| Software Development Process Adherence | Software development plan, hazard analysis, risk management, requirements analysis, architectural design, detailed design, unit implementation/verification, integration testing, system testing, release, and maintenance processes were followed and described. |
| Cybersecurity | Confidentiality, integrity, and availability are maintained in accordance with FDA guidance (Section 6, October 2, 2014 guidance). DICOM standard communication assures adequate protection. |
| Adherence to Performance Standards | Compliance with DICOM Set (PS 3.1-3.20) (2016), IEC 62304 Ed 1.1 2015-06, and ISO 14971:2019. |
2. Sample size used for the test set and the data provenance
The document mentions "actual clinical images" for benchmark performance testing and "patient data" for comparative testing of the Dual Energy Analysis module. However, it does not specify the sample size for these test sets, nor does it explicitly state the country of origin or whether the data was retrospective or prospective.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
The document does not provide any information regarding the number or qualifications of experts used to establish ground truth for any test set. Given the nature of the device as a processing and viewing tool, the "ground truth" for its functions would typically be the accuracy of the image processing (e.g., correct segmentation boundaries, accurate measurements compared to manual gold standard) rather than a clinical diagnosis.
4. Adjudication method for the test set
The document does not specify any adjudication method (e.g., 2+1, 3+1) for establishing ground truth or evaluating performance.
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
The document does not mention an MRMC comparative effectiveness study directly assessing human reader improvement with or without AI assistance. The comparative testing described is for the Dual Energy Analysis module against a reference device's feature, not a human reader study. The device provides "tools to aid" professionals, implying assistance, but no study is presented to quantify this aid's effect on reader performance.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
The document states: "benchmark performance testing was conducted using actual clinical images to help demonstrate that the semi-automatic or automatic segmentation, detection, and registration functions implemented in Synapse 3D Base Tools achieved the expected accuracy performance." This indicates that standalone performance testing was conducted for these specific algorithmic functions. However, it does not provide specific metrics or results for these standalone algorithms.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
The document does not explicitly state the type of ground truth. For "segmentation, detection, and registration functions," the ground truth would typically be manual delineation or measurement by experts (expert consensus or "gold standard" annotations), confirmed by visual inspection or perhaps clinical follow-up for specific detection tasks, but this is not detailed in the provided text.
8. The sample size for the training set
The document does not specify any training set sample size. This device is presented more as an update to an existing image processing software and an integration of already cleared functionalities (like PixelShine and the Dual Energy feature from K133648), rather than a new AI/ML algorithm that requires a detailed description of its training data.
9. How the ground truth for the training set was established
Since no training set information is provided, there is no information on how ground truth for any training set was established.
§ 892.2050 Medical image management and processing system.
(a)
Identification. A medical image management and processing system is a device that provides one or more capabilities relating to the review and digital processing of medical images for the purposes of interpretation by a trained practitioner of disease detection, diagnosis, or patient management. The software components may provide advanced or complex image processing functions for image manipulation, enhancement, or quantification that are intended for use in the interpretation and analysis of medical images. Advanced image manipulation functions may include image segmentation, multimodality image registration, or 3D visualization. Complex quantitative functions may include semi-automated measurements or time-series measurements.(b)
Classification. Class II (special controls; voluntary standards—Digital Imaging and Communications in Medicine (DICOM) Std., Joint Photographic Experts Group (JPEG) Std., Society of Motion Picture and Television Engineers (SMPTE) Test Pattern).