Search Results
Found 2 results
510(k) Data Aggregation
(216 days)
FUJIFILM Synapse PACS Software is intended for use as a web-based application on an off-the shelf PC which meets or exceeds minimum specifications and is networked with a FUJIFILM Synapse PACS server.
The FUJIFILM Synapse PACS Software can process medical images from DICOM compliant modalities and non-DICOM sources.
FUJIFILM Synapse PACS Software provides toolsets for:
- Performing measurements on DICOM images
- Regional segmentation
- Importing and presenting data from modalities (DICOM and non-DICOM),
- Solving clinical calculations
- Creating and distributing structured reports
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. It enables the display, comparison, fusion, and volume rendering of studies to aid in reading, interpreting, reporting, and treatment planning.
MIP, MPR Fusion, and volume rendering are not intended for mammography use. FUJIFILM Synapse PACS Software can be used to process FUJIFILM's DICOM MG "For Processing" images and also for the display, manipulation, and interpretation of lossless compressed or non-compressed mammography images that have been received in the DICOM For Presentation format and displayed on FDA-cleared, DICOM compatible displays for mammography.
The Synapse PACS is an enterprise-wide medical information and image management software that runs on standard "off-the-shelf" PC hardware and Software (OS, browser). Synapse is intended for communication, storage, display, manipulation, measurement, printing, and processing of images and information acquired from various medical imaging and information systems. As a Software as a Medical Device (SaMD), Synapse PACS performs these purposes without being part of a hardware medical device.
FUJIFILM Synapse PACS Software is intended for use as a web-based application on an off-the shelf PC which meets or exceeds minimum specifications and is networked with a FUJIFILM Synapse PACS server.
The FUJIFILM Synapse PACS Software can process medical images from DICOM compliant modalities and non-DICOM sources.
FUJIFILM Synapse PACS Software provides toolsets for:
- Performing measurements on DICOM images
- Regional segmentation
- Importing and presenting data from modalities (DICOM and non-DICOM),
- Solving clinical calculations
- Creating and distributing structured reports
Here's a breakdown of the acceptance criteria and study details for the Synapse PACS (7.5) device, based on the provided FDA 510(k) clearance letter:
Acceptance Criteria and Reported Device Performance
The core performance study described pertains to the Bone Removal algorithm.
1. A table of acceptance criteria and the reported device performance:
Metric | Acceptance Criteria | Reported Device Performance (Mean [95% CI]) | Meets Criteria? |
---|---|---|---|
Dice Similarity Coefficient (DSC) | ≥ 0.951 | 0.959 [0.955 – 0.963] | Yes |
95% Hausdorff Distance (HD) | 0.98 mm – 7.31 mm | 1.367 mm [1.170 mm – 1.563 mm] | Yes |
Note: The acceptance thresholds for DSC and 95% HD were determined by reviewing existing bone removal models in scientific literature.
Study Details Proving Device Meets Acceptance Criteria
2. Sample size used for the test set and the data provenance:
- Test Set Sample Size: 72 patients, each with one image collected.
- Data Provenance: The document states patient demographic distribution from "Midwest" (20 patients), "Southwest" (20 patients), and "Southeast" (32 patients) regions. This indicates the images were collected from various regions within the United States. The document does not explicitly state whether the data was retrospective or prospective, but the description of "collected images" and established ground truth often implies a retrospective study using an existing image archive.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- Number of Experts: An initial bone mask was created by a "certified technologist." Then, an "independent dual-reader consensus review" was performed by two U.S. board-certified radiologists.
- Qualifications of Experts:
- Certified Technologist (specific certification details not provided)
- Two U.S. Board-Certified Radiologists (specific experience/years not provided, but "board-certified" implies a high level of qualification).
4. Adjudication method for the test set:
- Adjudication Method: A consensus review process was used. After an initial mask by a technologist, two U.S. board-certified radiologists independently evaluated the mask, recorded discrepancies, and iteratively reconciled them until consensus was achieved. This is a form of 2-reader independent reading with a consensus stage.
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:
- No, an MRMC comparative effectiveness study was not performed as part of this submission's performance testing. The study focused on the standalone performance of the bone removal algorithm against a "definitive ground truth." The document does not describe human reader performance with or without the AI assistance.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- Yes, a standalone (algorithm only) performance study was conducted for the Bone Removal feature. The performance metrics (DSC and HD) directly measure the algorithm's output against the established ground truth.
7. The type of ground truth used:
- The ground truth used was expert consensus. Specifically, after an initial mask by a technologist, it was refined and finalized through an "independent dual-reader consensus review" by two U.S. board-certified radiologists.
8. The sample size for the training set:
- The provided document does not specify the sample size for the training set. It only describes the test set. It mentions the "Bone Removal is a tool that enhances the visibility of vessels... based on an AI algorithm cleared and marketed for Synapse 3D (K221677, reference device). It was improved for Synapse PACS 7.5.0." This implies the algorithm was already trained and validated prior to this submission, and this submission focuses on its performance after potential integration and improvements within Synapse PACS 7.5.0.
9. How the ground truth for the training set was established:
- The provided document does not describe how the ground truth for the training set (if applicable to this version's training) was established. Given that the algorithm was "improved" from a previously cleared device (Synapse 3D), the initial training and ground truth establishment would have occurred during the development and clearance process for that prior version.
Ask a specific question about this device
(266 days)
RUS is medical imaging software that is intended to provide trained medical professionals with tools to aid them in reading, interpreting, reporting, and treatment planning for patients. RUS accepts DICOM compliant medical images acquired from iodine contrast-enhanced abdomen CT.
This product is not intended for use with or for the primary diagnostic interpretation of Mammography images.
The software provides several categories of tools. It includes basic imaging tools for general images, including 2D viewing, volume rendering and 3D volume viewing, image fusion, surface rendering, measurements, reporting, storing, storing, general image management and administration tools, etc.
It includes a basic image processing workflow and a custom UI to segment anatomical structures, which are visible in the image data (bones, organs, vascular structures, etc.), including interactive segmentation tools, basic image filters, etc.
It also includes detection and labeling tools of organ segments, including path definition through vascular and interactive labeling.
The software is designed to be used by trained professionals (including physicians, surgeons and technicians) and is intended to assist the clinician who is solely responsible for making all final patient management decisions.
RUS uses DICOM (Digital Imaging and Communications in Medicine) standards to analyze CT images. This software provides trained medical professionals with tools to aid them in reading, interpreting, reporting, and treatment planning. By observing the medical images standard protocol (DICOM standards), this software can receive transmitted images from medical imaging devices through the h-Server and can be interfaced with PACS (Picture Archiving and Communication System).
RUS allows surgical planning by 3D modeling from patient's CT data. Surgical planning in RUS does not replace actual surgery and can only be used as an auxiliary tool.
CT is taken at the hospital, the patient's CT data is obtained from PACS, and the CT data is transferred from PACS to h-Server. When CT data and patient information are registered in the h-Server, the data is pseudonymized and anonymized and safely moved to the h-Space. If you request hu3D production by registering CT data and patient information through h-Server, hu3D will be provided within 72 hours. Then you may download the hu3D model through RUS Stomach Planning and perform Surgical planning.
RUS is a software suite and includes three software components: h-Server, h-Space, and RUS Stomach Planning.
-
h-Server
h-Server includes modules dedicated to data management and data gateway. The software is a simple tool either to anonymize or pseudonymize multidimensional digital images acquired from a variety of medical imaging modalities (DICOM images). There is no 3D data volume interpretation in this software. -
h-Space
h-Space includes data management (except for DICOM files anonymization/pseudonymization module) and 3D reconstruction. This software offers a flexible solution to help trained medical professionals with image processing knowledge (usually radiologists or radiologist technicians) in (1) the evaluation of patient's anatomy, and (2) in the creation of a 3D model of the patient's anatomy. This software proposes flexible workflow options: visualization of patient's anatomy from medical images; creation a 3D model of the patient's anatomical structures, organ segments and volumetric data; creation of an anatomical atlas (a colored image where each color represents a structure); and exports these medical data to be analyzed or reviewed later. -
RUS Stomach Planning
RUS Stomach Planning includes modules dedicated to patient & data management and surgical planning. This software offers a flexible visualization solution to help trained medical professionals (clinicians) in the evaluation of patient's anatomy to plan therapy or surgery.
Here's a breakdown of the acceptance criteria and study details for the RUS device, based on the provided document:
Acceptance Criteria and Device Performance
Feature | Acceptance Criteria | Reported Device Performance |
---|---|---|
Organ Segmentation | Dice Coefficient Score (DSC) ≥ 0.920 | 0.927 DSC |
Vessel Segmentation | Dice Coefficient Score (DSC) ≥ 0.890 | 0.920 DSC |
Pneumoperitoneum Detection | Mean Absolute Error (MAE) ≤ ± 1.083 mm | ± 0.972 mm |
Length Measurement (Ruler) | Mean difference within +/- 10% on phantom data | Accurate within a mean difference of +/- 10% |
Study Details
-
Sample Size used for the test set and data provenance:
- Test Set Sample Size: 60 imaging studies.
- Data Provenance: Not explicitly stated, but implies diverse patient population and CT system manufacturers from the statement "The data used in the device validation ensured diversity in patient population and CT system manufacturer." The document also states "No dataset contained more than one imaging study from any particular patient," and "independence of training and testing data were enforced at the level of the scanning institution, namely, studies sourced from a specific institution were used for either training or testing but could not be used for both." This suggests a multi-institutional dataset. The data includes patients with and without disease.
-
Number of experts used to establish the ground truth for the test set and their qualifications:
- The document implies ground truth was established by "medical professionals" for organ and vessel segmentations, and "3D scan data" for pneumoperitoneum.
- Expert Number: Not explicitly stated.
- Expert Qualifications: Not explicitly stated beyond "medical professionals."
-
Adjudication method for the test set: Not explicitly stated. Ground truth was established by comparing machine learning model outputs against segmentations generated by medical professionals and 3D scan data.
-
Multi-reader multi-case (MRMC) comparative effectiveness study: Not mentioned in the provided text. The study focuses on the standalone performance of the AI models.
-
Standalone (algorithm-only without human-in-the-loop) performance: Yes, this was done. The reported device performance metrics (DSC, MAE, measurement accuracy) are for the machine learning models directly, not in an assisted reading setting.
-
Type of ground truth used:
- Organ and Vessel Segmentation: Segmentations generated by medical professionals.
- Pneumoperitoneum: 3D scan data.
- Length Measurement: Phantom data and hu3D data.
-
Sample size for the training set: Not explicitly stated. The document mentions that "No imaging study used to verify performance was used for training; independence of training and testing data were enforced at the level of the scanning institution, namely, studies sourced from a specific institution were used for either training or testing but could not be used for both." However, the exact number of studies for training is not provided.
-
How the ground truth for the training set was established: Not explicitly stated, but it can be inferred that it was established similarly to the test set, i.e., likely through segmentations by medical professionals or 3D scan data, as these are the modalities against which performance was verified.
Ask a specific question about this device
Page 1 of 1