Medscape Medical NewsAll articles

Synapse 3D, Synapse 3D Base Tools v6.1

Fujifilm Corporation • Radiology • 02/09/2021

510(k)IEC 62304 Class B
FDA Summary PDF

Device Purpose

Synapse 3D Base Tools v6.1 is advanced medical imaging software intended to provide trained professionals with comprehensive tools for interpreting diverse DICOM medical images, aiding in diagnosis and treatment planning through enhanced visualization, image processing, and analysis. The system utilizes a Windows-based platform and incorporates various algorithms, including deep learning for segmentation and specialized functions for CT and MR image analysis, to improve clinical decision-making and workflow efficiency.

Summary

Synapse 3D Base Tools v6.1 is medical imaging software designed for trained medical professionals to aid in the reading, interpretation, reporting, and treatment planning processes. It accepts and processes DICOM compliant medical images from a variety of imaging modalities, including CT, MR, CR, US, NM, PT, and XA, among others, although it is not intended for the primary diagnostic interpretation of mammography images. The software operates on Windows server/client configurations, can be integrated with Fujifilm’s Synapse PACS, and serves as a basic software module that works with other cleared clinical applications in the Synapse 3D product family. Its core functionalities encompass a broad range of tools such as 2D viewing, volume rendering, 3D and 4D volume viewing, orthogonal, oblique, and curved Multi-Planar Reconstructions (MPR), Maximum/Average/Minimum Intensity Projections (MIP/RaySum/MinIP), image fusion, image subtraction, surface rendering, time-density distribution analysis, basic image processing, CINE, measurements, annotations, reporting, printing, storing, distribution, and general image management tools. Version 6.1 of Synapse 3D Base Tools introduces updated and new features, notably in advanced image analysis. These include tools for regional segmentation of anatomical structures, path definition through vascular and tubular structures, and boundary detection, with some segmentation applications implemented using deep learning methods like 'Fully Convolutional Networks' alongside existing algorithms such as 'graph cuts'. New modality-specific imaging tools have been added, including virtual endoscopic viewing for CT images, and for MR images, capabilities for ADC image viewing, delayed enhancement image viewing, and diffusion-weighted MRI data analysis. The software underwent extensive nonclinical testing, including verification and validation of system functionality, component performance, integration, usability, and risk mitigation. Benchmark performance testing using actual clinical images was conducted to demonstrate that the semi-automatic or automatic segmentation, detection, and registration functions achieved expected accuracy performance.

AI Regulatory Concerns

Powered byJev by TypeSafe AI

Jev reads the full FDA letter and returns calibrated concern probabilities per regulatory category. These are AI estimates, not regulatory advice.

Keywords

Medical Image ProcessingDICOM3D ReconstructionImage SegmentationDeep LearningMulti-Planar Reconstruction (MPR)Virtual EndoscopyMRI AnalysisCT AnalysisTreatment Planning Support

Device Metadata

Submission Number
K203103
Company
Fujifilm Corporation
Panel
Radiology
Product Code
N/A
Data Type
Images
Clinical Function
Assessment
AI Function
Analysis
AI Subclass
quantification/feature localization

Relevant Clinical Questions

  • Q1. How does the performance of the 'Fully Convolutional Network' for segmentation in Synapse 3D Base Tools v6.1 compare quantitatively (e.g., Dice coefficient, processing time) to the 'graph cuts' algorithm and previous segmentation methods across various anatomical structures and image qualities?; What specific validation metrics and datasets were used to confirm the accuracy and reliability of the new modality-specific tools, such as the Virtual Endoscopic Simulator for CT and the Diffusion-weighted MRI Data Analysis?; How does Synapse 3D Base Tools v6.1 handle the processing of large or complex DICOM datasets, particularly for 4D viewing and advanced reconstructions, in terms of system performance and potential latency on typical commercial-grade hardware?; What are the specific enhancements in user interface or workflow efficiency in v6.1 compared to v3.0, particularly for tasks involving the new segmentation and modality-specific analysis tools?; How does the software ensure traceability and reproducibility of image analysis results when multiple processing steps or tools are applied, especially when integrated with various PACS and other Synapse 3D clinical applications?

Risk Classification

ESL Analysis
FDA Device ClassII

FDA Class II via 510(k) pathway; IEC 62304 Class B (software safety classification); Authorized before §524B enforcement

Learn how Parasoft automates IEC 62304 compliance testing →

Cybersecurity Evidence

Powered by SBOMator™

Based on AI-generated device summaries, not the full FDA submission. Items not detected here may still be present in the complete submission package.

Cyber Score20/100
SBOM Evidence⚠ Not mentioned in summary
Cyber Risk Assessment⚠ Not mentioned in summary
Postmarket Plan⚠ Not mentioned in summary
§524B ApplicableNo

Supply Chain BOM Evidence

Based on the CycloneDX / OWASP ECMA-424 xBOM ecosystem. Detection is from the AI-generated summary.

SBOMSoftware Bill of Materials
- Not detected
ML-BOMMachine Learning Bill of Materials(deep learning, algorithm, dataset, annotation)
✓ Detected
SaaSBOMSoftware-as-a-Service Bill of Materials(server, network, platform)
✓ Detected
HBOMHardware Bill of Materials(hardware)
✓ Detected
CBOMCryptography Bill of Materials
- Not detected
VDR/VEXVulnerability Disclosure Report / Vulnerability Exploitability eXchange
- Not detected
OBOMOperations Bill of Materials(configuration)
✓ Detected

Analysis:

• Analysis is based on the AI-generated device summary, not the full FDA submission package. Click "Analyze Full FDA PDF" below to scan the actual submission document.

• Evidence of ML-BOM, SaaSBOM, HBOM, OBOM detected in AI-generated device summary.

• This device was authorized before §524B took effect. Cybersecurity evidence requirements were less prescriptive at the time.

• Postmarket cybersecurity monitoring plan not clearly documented in AI-generated device summary.

• Not detected in AI-generated device summary: SBOM, CBOM, VDR/VEX. These may be present in the full FDA submission.

Preparing a similar submission?

ESL takes complete ownership of your software evidence work - SBOM & CVE remediation with SBOMator™, static analysis & unit testing with Parasoft, traceability, and full IEC 62304 lifecycle support.

Assess Your Readiness →Or contact ESL directly
Synapse 3D, Synapse 3D Base Tools v6.1 - Fujifilm Corporation | ESL FDA AI Device Intelligence