Search Filters

Search Results

Found 2 results

510(k) Data Aggregation

    K Number
    K173637
    Date Cleared
    2018-03-30

    (126 days)

    Product Code
    Regulation Number
    892.1750
    Reference & Predicate Devices
    Why did this record match?
    Device Name :

    syngo.CT Coronary Analysis; syngo.CT Vascular Analysis

    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    syngo.CT Coronary Analysis is an image analysis software package for evaluating cardiac CT angiography (CTA) volume data sets. Combining digital image processing and visualization tools (multiplanar reconstruction (MPR) thin/ thick, maximum intensity projection (MP) thin/thick, inverted MP thin/thick, volume rendering technique (VRT), curved planar reformation (CPR)), evaluation tools (coronary vessel centerline calculation, stenosis calculation and plaque analysis) and reporting tools (lesion location, lesion characteristics and key images), the software package is designed to support the physician in confirming the presence of physician-identified coronary lesions and evaluation, documentation and follow-up of any such lesion. These visualization tools allow for characterization (geometry (length, lumen diameter, cross section area, stenosis grade) and appearance (HU values)) of coronary lesions and lesion size over time, helping the physician to assess the changes in their growth. It is also designed to help the physician classify conspicuous regions of tissue.

    syngo.CT Vascular Analysis is an image analysis software package for evaluating enhanced CT images. Combining digital image processing and visualization tools (multiplanar reconstruction (MPR) thin/thick, maximum intensity projection (MIP) thin/thick, inverted MIP think, volume rendering technique (VRT), curved planar reformation (CPR), processing tools (bone removal (based both on single energy and Dual Energy), table removal) and evaluation tools (vessel centerline calculation, lumen calculation) and reporting tools (lesion location, lesion characteristics and key images), the software package is designed to support the physician in confirming the presence or absence of physician-identified lesions in blood vessels and evaluation and follow-up of any such lesion. These visualization/processing/evaluation tools allow for characterization (geometry (length, lumen diameter, cross section area, stenosis grade) and appearance (HU values)) of vascular lesions and lesion size over time, helping the physician to assess the changes in their growth. It is also designed to help the physician classify conspicuous regions of tissue.

    Device Description

    syngo.CT Coronary Analysis is an image analysis post-processing software application designed to support evaluation of the vessels of the heart. This submission describes the following modifications that were made to predicate device syngo.CT Coronary Analysis (K100637, clearance date 5/26/2010):

    1. Support of software version SOMARIS/8 VB30 which supports the following functionality:
      a. Coronary Tracing Quality Improvement
      b. Rapid Results Technology Support for Curved Vessel Ranges
    2. Update 510(k) Information
      Combining digital image processing and visualization tools (multiplanar reconstruction (MPR) thin/thick, minimum intensity projection (MIP) thin/thick, inverted MIP thin/thick, volume rendering technique (VRT), curved planar reformation (CPR)), evaluation tools (coronary vessel centerline calculation, stencils calculation and plaque analysis) and reporting tools (lesion location, lesion characteristics and kev images), the software package is designed to support the physician in confirming the presence of physician-identified coronary lesions and evaluation, documentation and follow-up of any such lesion. These visualization/evaluation tools allow for characterization of coronary lesions and lesion size over time, helping the physician to assess the changes in their growth. It is also designed to help the physician classify conspicuous regions of tissue.

    syngo.CT Vascular Analysis is a post-processing software application to support evaluation of the large vessels of the body. This submission describes the following modifications that were made to predicate device syngo.CT Vascular Analysis (K112020, clearance date 08/18/2011):

    1. Modified Indications for Use Statement
    2. Support of software version SOMARIS/8 VB30 which supports the following functionality:
      a. Rapid Results Technology Support for curved vessel ranges
      b. Bone Removal Quality Improvement
      c. Vessel Tracing Quality Improvement
    3. Update 510(k) Information
      Combining digital image processing and visualization tools (multiplanar reconstruction (MPR) thin/thick, maximum intensity projection (MIP) thin/thick, inverted MIP thin/thick, volume rendering technique (VRT), curved planar reformation (CPR), processing tools (bone removal (based both on single energy and Dual Energy), table removal) and evaluation tools (vessel centerline calculation, lumen calculation, stenosis calculation) and reporting tools (lesion location, lesion characteristics and key images), the software package is designed to support the physician in confirming the presence or absence of physician-identified lesions in blood vessels and evaluation, documentation and follow-up of any such lesion. These visualization/processing/evaluation tools allow for characterization of vascular lesions and lesion size over time, helping the physician to assess the changes in their growth. It is also designed to help the physician classify conspicuous regions of tissue.
    AI/ML Overview

    This Siemens 510(k) summary for syngo.CT Coronary Analysis and syngo.CT Vascular Analysis describes modifications to existing cleared devices rather than a completely new device. Therefore, the performance studies primarily focus on demonstrating that the modified features maintain or improve performance compared to their predicate devices.

    1. Table of Acceptance Criteria and Reported Device Performance

    Acceptance CriteriaReported Device Performance
    For syngo.CT Coronary Analysis: Coronary Tracing Quality Improvement
    Centeredness of the Centerlines"the derived centerlines were assessed in comparison to the predicate device to demonstrate an improvement in the ability of the subject device application to more accurately follow the vessels in the lumen."
    Tracing of branches (Clinically relevant and irrelevant)"demonstrated an increased sensitivity and specificity"
    Coverage of Centerlines"improved vessel coverage for the subject device tracing feature in comparison to the predicate device."
    For syngo.CT Vascular Analysis: Vessel Tracing Quality Improvement
    Detection rate of a predetermined set of vessels"demonstrated that the subject device had a higher level of traced vessels in comparison to the predicate device, which supports an improvement of vessel tracing quality in comparison to the predicate device."
    General Software Performance (Both Devices)
    Software specifications met acceptance criteria"The testing supports that all software specifications have met the acceptance criteria."
    Conformance to performance standards (DICOM, IEC 62304, ISO 14971, IEC 62366-1, AAMI / ANSI ES60601-1)"Siemens claims conformance to the following performance standards" (lists all mentioned standards).
    Risk control implemented to mitigate identified hazards"The Risk Analysis was completed and risk control implemented to mitigate identified hazards."

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

    • syngo.CT Coronary Analysis: "a sampling of centerlines from a predetermined number of datasets were evaluated." The exact number of datasets is not specified.
    • syngo.CT Vascular Analysis: "a predetermined set of vessels was evaluated." The exact number of vessels or datasets is not specified.
    • Data Provenance: Not explicitly stated whether retrospective or prospective, or country of origin. However, given that these are modifications to existing software, it's likely that existing clinical CT angiography datasets were used.

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

    There is no mention of experts being used to establish a ground truth for these performance tests. The evaluation appears to be based on comparing algorithmic performance (e.g., centerline accuracy, branch tracing, vessel coverage) against the predicate device's performance or predefined internal metrics, rather than expert-derived ground truth.

    4. Adjudication Method for the Test Set

    No adjudication method is mentioned, as the studies are focused on comparing the algorithmic performance of the modified device against its predicate, rather than human review or consensus.

    5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

    No MRMC comparative effectiveness study was mentioned. The studies described are non-clinical performance (bench) testing, comparing the improved algorithms against their previous versions.

    6. Standalone Performance Study

    Yes, standalone (algorithm-only) performance testing was conducted for the specific improved features.

    • For syngo.CT Coronary Analysis, improvements in "Centeredness of the Centerlines," "Tracing of branches," and "Coverage of Centerlines" were evaluated.
    • For syngo.CT Vascular Analysis, the "detection rate of a predetermined set of vessels" was evaluated.
      These evaluations focused on the direct output of the algorithms.

    7. Type of Ground Truth Used

    The ground truth used for these specific performance tests appears to be internal algorithmic metrics and comparisons to the predicate device's performance.

    • For centerline centeredness, it implies an ideal path for the vessel lumen against which the derived centerlines are compared.
    • For branch tracing and coverage, it implies an objective definition of "clinically relevant" and the actual anatomical presence of branches and overall vessel extent.
    • For vessel tracing, it implies whether a vessel that is anatomically present and expected to be traced was indeed traced.
      This ground truth is not explicitly stated as expert consensus, pathology, or outcomes data, but rather as an internal standard or objective measure of algorithmic output.

    8. Sample Size for the Training Set

    The document does not provide information about the sample size used for the training set. These are modifications to existing software, and the description focuses on verification and validation of the changes, not the initial development of the underlying algorithms.

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

    The document does not provide information on how the ground truth for any training set was established.

    Ask a Question

    Ask a specific question about this device

    K Number
    K112020
    Date Cleared
    2011-08-18

    (35 days)

    Product Code
    Regulation Number
    892.1750
    Reference & Predicate Devices
    Why did this record match?
    Device Name :

    SYNGO.CT VASCULAR ANALYSIS

    AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
    Intended Use

    syngo.CT Vascular Analysis is an image analysis software package for evaluating enhanced CT images. Combining digital image processing and visualization tools (multiplanar reconstruction (MPR) thin/thick, maximum intensity projection (MIP) thin/thick, inverted MIP thin/thick, volume rendering technique (VRT), curved planar reformation (CPR), processing tools (bone removal (based both on single energy and Dual Energy), table removal) and evaluation toollo (vessel centerline calculation, lumen calculation, stenosis calculation) and reporting tools (lesion location, lesion characteristics and key images), the software package is designed to support the physician in confirming the presence or absence of physician-identified lesinos in blood vessels and evaluation, documentation and follow-up of any such lesion. These visualization/processing/evaluation tools allow for characterization of vascular lesions and lesion size over time, helping the physician to assess the changes in their growth. It is also designed to help the physician classify conspicuous regions of tissus.

    Device Description

    syngo.CT Vascular Analysis is an image analysis software package for evaluating enhanced CT images. Combining digital image processing and visualization tools (multiplanar reconstruction (MPR) thin/thick, maximum intensity projection (MIP) thin/thick, inverted MIP thin/thick, volume rendering technique (VRT), curved planar reformation (CPR), processing tools (bone removal (based both on single energy and Dual Energy), table removal) and evaluation tools (vessel centerline calculation, lumen calculation, stenosis calculation) and reporting tools (lesion location, lesion characteristics and key images), the software package is designed to support the physician in confirming the presence or absence of physician-identified lesions in blood vessels and evaluation, documentation and follow-up follow-up of of any such lesion. These visualization/processing/evaluation tools allow for characterization of vascular lesions and lesion size over time, helping the physician to assess the changes in their growth. It is also designed to help the physician classify conspicuous regions of tissue.

    AI/ML Overview

    Here's a breakdown of the acceptance criteria and study information, based on the provided text:

    1. Table of Acceptance Criteria and Reported Device Performance

    The provided document does not explicitly state specific quantitative acceptance criteria or detailed results of device performance metrics like sensitivity, specificity, or accuracy. Instead, it focuses on demonstrating substantial equivalence to predicate devices through functional comparison and adherence to standards.

    The document indicates that "Testing for verification and validation of the device was found acceptable to support the claims of substantial equivalence." This implies that internal acceptance criteria were met during development, but those specific criteria and their corresponding results are not disclosed in this 510(k) summary.

    Therefore, a table cannot be populated with specific acceptance criteria and reported numerical performance values from this document.

    However, based on the narrative, the device performance is implicitly claimed to be "as well as the predicate devices" due to "equivalent technological characteristics" and "current image processing algorithms."

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

    The document states: "Non clinical tests are conducted for syngo.CT Vascular Analysis software package during product development. The Risk analysis was completed and risk control implemented to mitigate identified hazards."

    • Sample Size for Test Set: Not specified.
    • Data Provenance: The document only mentions "Non clinical tests" during product development. It does not provide information on the country of origin of the data or whether the data was retrospective or prospective.

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

    The document does not provide any information regarding the number of experts used, their qualifications, or how ground truth was established for the specific "non clinical tests" mentioned.

    4. Adjudication Method for the Test Set

    The document does not provide any information regarding the adjudication method used for the test set.

    5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was Done, What was the Effect Size of How Much Human Readers Improve with AI vs Without AI Assistance

    The document does not report an MRMC comparative effectiveness study involving human readers and AI assistance. The focus is on the device's standalone functionalities and its equivalence to predicate devices.

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

    Yes, a standalone evaluation was done. The "non clinical tests" and the claim of functional equivalence to predicate devices which are also image analysis software, imply that the algorithm's performance was assessed independently. The purpose of syngo.CT Vascular Analysis is to provide "visualization/processing/evaluation tools" and "reporting tools" to support the physician, rather than to replace them or directly interact in a real-time assistive manner during interpretation, as might be evaluated in an MRMC study. The device's capabilities are described as tools for lumen/stenosis calculation, bone removal, vessel tracking, etc., which are functions of the algorithm itself.

    7. The Type of Ground Truth Used

    The document does not explicitly state the type of ground truth used for the non-clinical tests. Given the nature of the software (image processing and measurement), it's likely that ground truth would involve either:

    • Reference measurements from gold-standard techniques (if available for specific features like stenosis).
    • Expert consensus measurements.
    • Pathology (less likely for general vascular analysis measurements, more for specific findings).
    • Outcomes data (unlikely for non-clinical testing for this type of software).

    8. The Sample Size for the Training Set

    The document does not specify the sample size used for the training set. It only mentions "non clinical tests" conducted during product development, which typically follow a training/testing paradigm but the details are not provided.

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

    The document does not provide any information on how the ground truth for the training set was established.

    Ask a Question

    Ask a specific question about this device

    Page 1 of 1