Search Results

The syngo Application Software is a medical software for real-time viewing, image manipulation, communication, and storage of medical images and data on exchange media. It is used for diagnostic image viewing and post processing and for viewing and post processing during interventional procedures.

The syngo Application Software can be deployed on independent hardware such as a stand-alone diagnostic review, postprocessing, and reporting workstation. It can also be configured within a network to send and receive DICOM data.

Furthermore, the syngo Application Software can be deployed on systems Angiography system family. It provides image guided solutions in the operating room, for image guided surgery, by Image Fusion and by navigation systems, image guided solutions in interventional cardiology and electrophysiology and image guided solutions for interventional oncology, interventional radiology, and interventional neuroradiology. The syngo Application Software can also be combined with fluoroscopy systems or Radiographic systems.

The syngo Application Software can be configured with a variety of syngo or Windows-based software options, which are intended to assist the physician in diagnosis, treatment control. It includes commercially available post-processing techniques and OEM options.

Procedures that can be performed includes minimally invasive surgical procedures and minimally invasive tumor treatment.

The "syngo Application Software" (VE21) is medical diagnostic software for realtime viewing, diagnostic review, post processing, image manipulation, optimization, communication, reporting and storage of medical images and data on exchange media. It provides image guided solutions in the operating room, for image guided surgery, by Image Fusion and by navigation systems, image guided solutions in interventional cardiology and electrophysiology and image guided solutions for interventional oncology, interventional radiology, and interventional neuroradiology. It can be deployed with a variety of syngo or Windows based software options, which are intended to assist the physician in evaluation of digital radiographic examinations, including diagnosis and/or treatment planning.

Siemens "syngo Application Software" (VE21) is designed to work with digital radiographic, fluoroscopic, interventional, and angiographic systems.

This document describes the syngo Application Software (VE21), which is a medical software for viewing, manipulating, and storing medical images. The submission is for an updated version (VE21) which includes an updated feature called syngo TrueFusion.

Here's a breakdown of the requested information based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present a table of acceptance criteria with corresponding performance metrics in a quantitative format for the syngo Application Software (VE21). Instead, it describes functional changes and verification that these changes meet expected behavior.

The key acceptance criteria and reported performance for the updated syngo TrueFusion feature are described as follows:

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

The document does not provide a specific sample size for the test set used for the updated syngo TrueFusion feature. It mentions "Bench tests were conducted" and "The following test were conducted...: Overlay Images Volume and Overlay Image Change Stand X-ray." but does not quantify the number of cases or images tested.

The data provenance is not explicitly stated regarding country of origin or whether it was retrospective or prospective. Given that it refers to "Bench tests" and "software validation data," it implies internal testing rather than a clinical study with patient data.

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

The document does not mention the use of experts or the establishment of ground truth by experts for the test set. The validation appears to be based on functional testing against predefined specifications and clinical workflow expectations, rather than a diagnostic accuracy study needing expert-labeled ground truth.

4. Adjudication Method for the Test Set

No adjudication method is mentioned as there's no indication of a diagnostic accuracy study involving multiple readers and a ground truth establishment process.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and the Effect Size

No MRMC comparative effectiveness study is mentioned. The submission focuses on the functional updates of existing software and claims substantial equivalence to the predicate device based on non-clinical performance and software validation. There is no information about human readers improving with or without AI assistance.

6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) Was Done

The testing described (bench tests, software validation) focuses on the syngo Application Software (VE21) as a standalone software product's functionality in performing its specified tasks (e.g., image overlay). While it's software for human interpretation and use in interventional procedures, the performance testing discussed is of the software's functionality itself, rather than an AI algorithm's diagnostic performance in isolation on a set of cases. The document does not describe specific "algorithm-only" performance metrics in the context of, for example, a diagnostic AI.

7. The Type of Ground Truth Used

The ground truth for the functional testing appears to be based on predefined software specifications and expected clinical workflow behavior. The document states, "The test results passed and concluded that the synqo TrueFusion image overlay functionality corresponds to the clinical workflow..." This implies that the software's output was compared against what is considered correct and clinically acceptable by the developers based on internal standards and design. There is no mention of pathology, expert consensus on patient cases, or outcomes data as ground truth.

8. The Sample Size for the Training Set

The document describes an updated software feature for an existing application. It does not refer to the development or training of a new AI model with a distinct training set. If there are underlying machine learning components within syngo TrueFusion (which isn't explicitly stated but could be inferred from image fusion), the sample size for any training data is not provided. The focus is on the verification and validation of the software update itself.

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

Since there is no mention of a distinct training set or an AI model training process, there is no information on how its ground truth might have been established. The submission focuses on verifying the functional correctness of software updates rather than the performance of a newly trained AI model.

Ask a specific question about this device

ARTIS is a family of dedicated angiography systems developed for single and biplane diagnostic imaging and interventional procedures including, but not limited to, pediatric and obese patients.

Procedures that can be performed with the ARTIS family include cardiac angiography, neuro-angiography, general angiography, rotational angiography, multipurpose angiography and whole body radiographic/fluoroscopic procedures as well as procedures next to the table for i.e. patient extremities. This does not include projection radiography.

Additional procedures that can be performed include angiography in the operating room, image guided surgery by X-ray, by image fusion, and by navigation systems. The examination table as an integrated part of the system can be used for Xray imaging, surgery and interventions.

ARTIS can also support the acquisition of position triggered imaging for spatial data synthesis.

The ARTIS family include also the software option DynaCT with following indications for use:

DynaCT is an X-ray imaging software option, which allows the reconstruction of two-dimensional images acquired with a standard angiographic C-arm device into a three-dimensional image format.

DynaCT is intended for imaging both hard and soft tissues as well as other internal body structures for diagnosis, surgical planning, interventional procedures and treatment follow-up.

The ARTIS pheno (VE2) system is a multi-axis system, specifically designed to meet the growing demands of high-end imaging for interventional radiology, interventional cardiology, minimally invasive and hybrid surgery procedures. The stand allows positioning in angular, orbital, lateral, longitudinal and vertical directions, leveraging the flexible isocenter. The ARTIS pheno (VE2) system is equipped with a robotic multi-axis floor stand, C-arm, flat panel detector, x-ray tube, collimator, high voltage generator, patient table, and image post processing. The ARTIS pheno is partially coated with an optional anti-microbial coating. syngo Application Software is optional, available for the support of dedicated clinical workflows.

The ARTIS pheno (VE2) covers the complete range of angiographic applications, cardiac angiography, neuro-angiography, general angiography, surgery and surgical angiography, multipurpose angiography, rotational angiography and radiographic/ fluoroscopic procedures.

1. The following components are configured to create the ARTIS pheno VE2 system: Floor stand with C-arm, X-ray tube assembly and FD
2. Patient table
3. Display ceiling suspension with displays
4. Footswitch for releasing radiation
5. Control console for controlling the stand, patient table, collimator and imaging system.

Images and operating elements are displayed on screens. Different display variants are used to visualize image and information content. Panoramic display configurations or large displays can be used, configurable to visualize multiple images and information content in various layouts.

Post processing can be done in the exam room or in the control room that offers monitors as well, with a footswitch location in the exam room or the control room. The ARTIS pheno (VE2) System is capable of 2D and 3D imaging.

Other systems and software syngo Application Software, syngo X Workplace, Sensis, and or third-party systems may also be integrated into the ARTIS pheno (VE2) screen configuration. Different screen configurations and layouts are possible in the examination room and in the control room.

The provided text is a 510(k) summary for the ARTIS pheno (VE2) system, which is an angiography system. It primarily focuses on demonstrating substantial equivalence to predicate devices rather than proving a medical device's performance against specific acceptance criteria for a new clinical claim or an AI algorithm.

Therefore, the document does not contain the detailed information required to fill out a table of acceptance criteria and reported device performance as it would for a study proving a device meets a clinical performance claim (e.g., diagnostic accuracy of an AI algorithm). The information provided is about the safety and effectiveness of the updated angiography system in terms of hardware, software modifications, and compliance with general medical device standards.

Specifically, the document lists modifications to the ARTIS pheno (VE2) system, such as improved roadmap features, new marketing terminology, updated user interface, and hardware changes. It states that non-clinical performance testing was conducted to assess functionality and compliance with various electrical, safety, and performance standards. However, it does not present clear, quantifiable acceptance criteria or reported performance results in the format requested for a study proving device performance against specific clinical metrics.

Here's why the requested information cannot be extracted from this document:

• No specific clinical performance metrics: The document discusses improvements like "increased image quality dose ratio" and "Improved Image Quality due to improved algorithm" but without quantifiable acceptance criteria (e.g., "sensitivity > X%", "specificity > Y%", "AUC > Z%") or reported numerical results against such criteria.
• Focus on substantial equivalence: The core of a 510(k) submission is to demonstrate that a new device is "substantially equivalent" to a legally marketed predicate device, meaning it's as safe and effective. This is different from proving that a device (especially an AI-driven one making a new diagnostic claim) meets specific, pre-defined performance thresholds in a clinical study.
• No mention of AI algorithm performance: While there's talk of "improved algorithms" and "syngo DynaCT Multiphase," the document doesn't define or evaluate an AI algorithm in the way you'd expect for a device making a new AI-based diagnostic claim. It's about overall system improvements, not a groundbreaking AI diagnostic tool.
• Lack of test set details: There's no mention of a specific test set, its sample size, data provenance, or ground truth establishment for clinical performance evaluation of a new function (like an AI algorithm would require).
• No human reader studies: There is no mention of MRMC studies or human-in-the-loop performance evaluations.
• No training set details: Information about a training set for an AI algorithm (sample size, ground truth establishment) is absent.

Therefore, I cannot fulfill your request for the table and study details based on the provided text. The document describes a traditional medical device modification clearance, not a study validating an AI algorithm against specific clinical performance criteria.

Ask a specific question about this device

The Siemens Biograph Horizon PET/CT systems are combined X-Ray Computed Tomography (CT) and Positron Emission Tomography (PET) scanners that provide registration and fusion of high resolution physiologic and anatomic information.

The CT component produces cross-sectional images of the body by computer reconstruction of X-Ray transmission data from either the same axial plane taken at different angles or spiral planes taken at different angles. The PET subsystem images and measures the distribution of PET radiopharmaceuticals in humans for the purpose of determining various metabolic (molecular) and physiologic functions within the human body and utilizes the CT for fast attenuation correction maps for PET studies and precise anatomical reference for the fused PET and CT images.

The system maintains independent functionality of the CT and PET devices, allowing for single modality CT and / or PET diagnostic imaging. These systems are intended to be utilized by appropriately trained health care professionals to aid in detecting, localizing, diagnosing, staging and re staging of lesions, tumors, disease and organ function for the evaluation of diseases and disorders such as, but not limited to, cardiovascular disease, neurological disorders and cancer. The images produced by the system can also be used by the physician to aid in radiotherapy treatment planning and interventional radiology procedures.

This CT system can be used for low dose lung cancer screening in high risk populations.*

• As defined by professional medical societies. Please refer to clinical literature, including the results of the National Lung Screening Trial (N Engl J Med 2011; 365:395-409) and subsequent literature, for further information.

The Biograph Horizon PET/CT systems are combined multi-slice X-Ray Computed Tomography and Positron Emission Tomography scanners. These systems are designed for whole body oncology, neurology and cardiology examinations. The Biograph Horizon systems provide registration and fusion of high-resolution metabolic and anatomic information from the two major components of each system (PET and CT). Additional components of the system include a patient handling system and acquisition and processing workstations with associated software.

Biograph Horizon software is a command-based program used for patient management, data management, scan control, image reconstruction and image archival and evaluation. All images conform to DICOM imaging format requirements.

The software for the Biograph Horizon systems which is the subject of this application is substantially equivalent to the commercially available Biograph Horizon software. Modifications include, corrections to software anomalies and addition of new software features, including:

• OncoFreeze
• OncoFreeze AI (Data Driven Gating)
• CardioFreeze
• FlowMotion Multi-Parametric PET AI ●
• PET FAST Planning (FlowMotion Al)
• FAST PET Workflow
• QualityGuard
• . Updates to HD FoV
• Updates to PET DICOM dose Report
• Whole Body Scatter Correction

Additionally, minor modifications have been made to the computers due to obsolescence issues and to the controllers of the PHS for cost improvement. These changes do not affect system performance characteristics and have no impact on safety or effectiveness.

The Siemens Biograph Horizon PET/CT system (K193178) underwent performance testing against NEMA NU2-2018 standards for its PET subsystem. The device also had specific evaluations for new software features: OncoFreeze AI, OncoFreeze/CardioFreeze, FlowMotion Multi-Parametric PET AI, FlowMotion AI (PET FAST Planning), QualityGuard, and Whole Body Scatter Correction.

Here's the breakdown of the acceptance criteria and study information:

1. Table of Acceptance Criteria and Reported Device Performance:

2. Sample size used for the test set and the data provenance:

• PET Testing (NEMA NU2-2018): The document implies physical phantom testing which is standard for NEMA NU2-2018. The number of samples (scans or measurements) from the phantom is not explicitly stated, but these tests are typically performed on two different configurations: a 3-ring version and a 4-ring version (TrueV). Data provenance is from physical phantom measurements on the device itself.
• OncoFreeze AI (Data Driven Gating): The document mentions "motion-corrected (OncoFreeze) images comparing Anzai based gating and deviceless gating." It does not specify the number of patient images or specific phantom studies. The provenance isn't explicitly stated as retrospective or prospective, nor a country of origin.
• FlowMotion AI (PET FAST Planning): No specific sample size (i.e., number of cases or scans) is given. The study evaluated "configuration set" effectiveness. The provenance is not explicitly stated.
• Whole Body Scatter Correction: This was a "simulation study of phantom." The sample size (number of ROIs or simulation runs) is not specified. Provenance is simulation data based on a phantom.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

• For the NEMA NU2-2018 PET testing, the ground truth for performance metrics (resolution, sensitivity, scatter fraction, image quality) is established by the known physical properties and activity concentrations of the NEMA phantom according to the standard. No human experts are involved in establishing this ground truth.
• For OncoFreeze AI, the "ground truth" for motion correction comparison is implicitly the static image or the Anzai-based gated images acting as a reference for comparison of SUV and Volume changes. No explicit expert involvement for ground truth is mentioned.
• For FlowMotion Multi-Parametric PET AI, the "ground truth" for improved noise characteristics and delineation is a comparison against the Patlak transformation performed during reconstruction without the automatic feature. This implies qualitative assessment, but no expert details are given.
• For FlowMotion AI (PET FAST Planning), the "ground truth" for correctly defined bed ranges would be based on the known or intended bed ranges. No expert involvement in establishing this ground truth is mentioned.
• For QualityGuard, the "ground truth" for time savings and exposure reduction would be direct measurement or comparison to previous workflows. No expert involvement for ground truth is mentioned.
• For Whole Body Scatter Correction, "ground truth" was established by a "simulation study of phantom," implying that the true values for activity in different regions of interest were known from the simulation setup. No human experts are involved in establishing this ground truth; it's inherent to the simulation.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set:

No adjudication method for expert review of images or data is mentioned for any of the tests described. The tests are primarily technical performance evaluations (NEMA standards, quantitative comparisons, simulation studies) or workflow efficiency observations.

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 multi-reader multi-case (MRMC) comparative effectiveness study evaluating human reader improvement with AI assistance is mentioned in the provided text. The AI features mentioned (OncoFreeze AI, FlowMotion Multi-Parametric PET AI, FlowMotion AI (PET FAST Planning)) are related to image processing and workflow automation rather than direct diagnostic assistance for human readers in a comparative effectiveness setting.

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

The device itself is a diagnostic imaging system (PET/CT), not an AI algorithm that provides a diagnostic output to a human. The AI features described within the device, such as OncoFreeze AI and FlowMotion AI, are designed to improve image quality, correct for motion, or automate planning. The performance metrics focus on the output of these features (e.g., changes in SUV, bed range identification accuracy, scatter correction accuracy) as part of the overall imaging system's functionality. Therefore, these features are evaluated in a standalone manner within the machine's operation, without explicit human-in-the-loop performance studies described here.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):

• NEMA NU2-2018 PET testing: Physical phantom with known activity concentrations and physical dimensions.
• OncoFreeze AI: Comparison to static images and Anzai-based gating, which implicitly serve as a reference or "ground truth" for the motion-corrected measurements.
• FlowMotion Multi-Parametric PET AI: Comparison to non-automated Patlak transformation results.
• FlowMotion AI (PET FAST Planning): Known or intended bed ranges from the configuration setup.
• QualityGuard: Measured time and staff exposure.
• Whole Body Scatter Correction: Known values from a "simulation study of phantom."

In summary, the ground truth types are primarily known physical properties of phantoms (or simulated phantoms), comparative measurements against established methods, or direct measurements of efficiency/safety.

8. The sample size for the training set:

The document does not provide any information about the training set size for the AI features (OncoFreeze AI, FlowMotion AI).

9. How the ground truth for the training set was established:

Since no information on training sets is provided, there is also no information on how ground truth for any training sets was established.

Ask a specific question about this device

The syngo Application Software is a medical software for real-time viewing, image manipulation, communication, and storage of medical images and data on exchange media. It is used for diagnostic image viewing and post processing and for viewing and post processing during interventional procedures.

The syngo Application Software can be deployed on independent hardware such as a stand-alone diagnostic review, postprocessing, and reporting workstation. It can also be configured within a network to send and receive DICOM data.

Furthermore, the syngo Application Software can be deployed on systems of the Siemens Angiography system family. It provides image guided solutions in the operating room, for image guided surgery, by Image Fusion and by navigation systems, image guided solutions in interventional cardiology and image guided solutions for interventional oncology, interventional radiology, and interventional neuroradiology.

The syngo Application Software can also be combined with fluoroscopy systems or Radiographic systems.

The syngo Application Software can be configured with a variety of syngo or Windows-based software options, which are intended to assist the physician in diaming and treatment control. It includes commercially available post-processing techniques and OEM options.

Procedures that can be performed include: minimally invasive surgical procedures and minimally invasive turnor treatment.

The "syngo Application Software" (VE2) is medical diagnostic software for realviewing. diagnostic review. image manipulation. optimization. time communication, reporting and storage of medical images and data on exchange media. It provides image guided solutions in the operating room, for image guided surgery, by Image Fusion and by navigation systems, image guided solutions in interventional cardiology and electrophysiology and image guided solutions for interventional oncology, interventional radiology, and interventional neuroradiology. It can be deployed with a variety of syngo or Windows based software options, which are intended to assist the physician in evaluation of digital radiographic examinations, including diagnosis and/or treatment planning.

Siemens "syngo Application Software" (VE2) is designed to work with digital radiographic, fluoroscopic, interventional and angiographic systems.

Siemens Medical Solutions USA, Inc. hereby submits this Traditional 510(k) to request clearance to market the three new optional software features: 1) syngo DynaCT Sine Spin; 2).syngo DynaCT Multiphase; and 3) syngo Embolization Guidance. These new features will be added to the existing "syngo Application Software" (VD20) which was cleared in K173611 on 16/03/2018. These new software features are the subjects of this submission.

The "syngo Application Software" may be installed either on Siemens released PC hardware, on Siemens X-ray systems or on Siemens angiography systems. The "syngo Application Software" (VE2) is within the same classification regulation and the intended use and the general Indications for Use Statement for Siemens' Picture Archiving and Communications System remains the same.

The document describes the Siemens "syngo Application Software" (VE2) and its new optional software features: syngo DynaCT Sine Spin, syngo DynaCT Multiphase, and syngo Embolization Guidance. The submission aims to demonstrate substantial equivalence to the predicate device, "syngo Application Software" (VD20) (K173611).

Here's an analysis of the acceptance criteria and the study that proves the device meets them, based on the provided text:

1. A table of acceptance criteria and the reported device performance

The document doesn't provide a specific table with distinct "acceptance criteria" against which quantitative "reported device performance" is measured in a typical clinical trial format (e.g., Sensitivity X, Specificity Y). Instead, the acceptance is based on demonstrating that the new features are as safe and effective as the predicate device. The performance is reported through the results of bench testing and software validation, confirming the functionality and safety of the new features.

The core acceptance criterion is implicit: The new features ("syngo DynaCT Sine Spin", "syngo DynaCT Multiphase", and "syngo Embolization Guidance") must perform as intended, produce equivalent or improved image quality/functionality compared to the predicate, and not introduce any new issues of safety or effectiveness.

2. Sample sized used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

The primary testing presented involves bench testing and phantom studies. For the "syngo Embolization Guidance" a "study of randomly selected clinical cases" was performed, but the sample size is not specified. The document does not provide details on data provenance (country of origin) or whether the clinical cases were retrospective or prospective. It appears that the clinical case study for Embolization Guidance was not the primary means of validation for this 510(k), as it focuses on demonstrating safety and effectiveness mainly through non-clinical methods.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts

The document does not specify the number or qualifications of experts used to establish ground truth for any part of the test set. For the "syngo Embolization Guidance" clinical case study, it states the algorithm was "validated," implying comparison to some form of truth, but details are absent. For bench and phantom tests, ground truth would naturally be established by the physical properties of the phantoms/test setups.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set

The document does not describe any adjudication method for the test set. Given the nature of the validation (bench testing, phantom studies, and an unspecified clinical case study), a formal multi-reader adjudication process for establishing ground truth is not explicitly mentioned or implied.

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 MRMC comparative effectiveness study is described in the provided text. The submission focuses on demonstrating substantial equivalence of the software features themselves, not on the improvement of human reader performance with AI assistance. The device is a "Picture Archiving and Communications System" with features to assist physicians in image viewing and post-processing, not an AI diagnostic aid that directly impacts human reader interpretation.

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

Yes, the testing primarily focuses on the standalone performance of the algorithms and software features themselves through bench tests and phantom studies. For example, the image quality metrics (homogeneity, spatial resolution, CNR, etc.) are objective measures of the algorithm's output. The validation of the "syngo Embolization Guidance" feeder detection algorithm is also an assessment of its standalone accuracy, even if comparing against clinical cases.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)

• For syngo DynaCT Sine Spin and syngo DynaCT Multiphase: Ground truth for image quality and physical properties (e.g., homogeneity, spatial resolution, CNR, geometric distortion, z-direction resolution) would be established by the known physical properties of the phantoms and the design specifications of the system.
• For syngo Embolization Guidance: The feeder detection algorithm was "validated in a study of randomly selected clinical cases." This implies comparison to clinical ground truth, which for feeder vessels is typically established through expert review of angiographic images or potentially confirmed by intervention outcomes, though the document does not specify the exact nature of this clinical ground truth.

8. The sample size for the training set

The document does not mention a training set size. This might be because the changes are primarily functional enhancements to existing software features rather than completely new AI algorithms that require extensive training data. It states the "algorithm was not changed" for syngo Embolization Guidance, implying it was pre-existing.

9. How the ground truth for the training set was established

Since no training set is explicitly mentioned or described, the method for establishing its ground truth is not provided.

Ask a specific question about this device

Your MAGNETOM MR system is indicated for use as a magnetic resonance diagnostic device (MRDD) that produces transverse, sagittal, coronal and oblique cross sectional images, spectroscopic images and/or spectra, and that displays the internal structure and/or function of the head, body, or extremities.

Other physical parameters derived from the images and/or spectra may also be produced. Depending on the region of interest, contrast agents may be used. These images and/or spectra and the physical parameters derived from the images and/or spectra when interpreted by a trained physician yield information that may assist in diagnosis.

Your MAGNETOM MR system may also be used for imaging during interventional procedures with MR compatible devices such as in-room displays and MR Safe biopsy needles.

The subject device, MAGNETOM Avanto® with software syngo MR E11E. is a modification of the previously cleared predicate device, MAGNETOM Avanto" with software syngo MR E11C-AP04 (K173592). The software version syngo E11E for MAGNETOM Avanto™ has been modified to include the software application "Compressed Sensing (CS) Cardiac Cine." This software application was migrated unchanged from the previously cleared MAGNETOM Skyra and Aera systems with syngo MR E11C-AP02 (K163312).

The provided document is a 510(k) summary for the Siemens MAGNETOM Avanto® with software syngo MR E11E. It details the device's substantial equivalence to a predicate device, focusing on a new software feature. However, this document does not contain the specific information required to answer your detailed questions about acceptance criteria and a study proving the device meets those criteria.

The 510(k) summary states:

• No clinical tests were conducted to support the claim of substantial equivalence between the subject and predicate device (page 7).
• Nonclinical performance testing was conducted, including software verification and validation, and performance testing in accordance with FDA guidance documents (page 6). However, it does not provide details of acceptance criteria for these tests or specific results in numerical form that can be presented in a table against a predefined "acceptance criteria."
• The document implies that the "new" feature (Compressed Sensing (CS) Cardiac Cine) was migrated unchanged from a previously cleared device (MAGNETOM Skyra and Aera systems with syngo MR E11C-AP02 (K163312)). This suggests that the performance and safety of this feature were established in the clearance of the reference device, not necessarily re-tested as a new standalone study for this specific 510(k).

Therefore, based solely on the provided text, I cannot extract the following information:

1. A table of acceptance criteria and the reported device performance: This document reports that testing was done and standards were conformed to, but not the specific metrics, thresholds, or measured values.
2. Sample size used for the test set and the data provenance: Clinical test data with sample sizes are not present, and for nonclinical tests, specific "test sets" in the sense of patient data are not detailed.
3. Number of experts used to establish the ground truth and their qualifications: As no clinical study is reported, this information is not applicable to the data provided.
4. Adjudication method for the test set: Not applicable without a clinical study.
5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, and effect size: The document explicitly states "No clinical tests were conducted."
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: While "performance testing" was mentioned for nonclinical data, the specifics of an algorithm-only standalone study with human-level metrics are not provided.
7. The type of ground truth used: Not specified, as clinical data and ground truth establishment methods are not detailed.
8. The sample size for the training set: This is a 510(k) for a hardware/software system, not an AI/ML device that typically has a "training set" in the context of deep learning. The new feature is a "Compressed Sensing (CS) Cardiac Cine" software application, which is a signal processing technique, not necessarily a machine learning algorithm that requires a "training set" in the conventional AI sense.
9. How the ground truth for the training set was established: Not applicable for the reasons mentioned above.

Conclusion based on the provided document:

The 510(k) summary focuses on demonstrating substantial equivalence through:

• Confirmation that the device's indications for use are the same as the predicate device.
• Confirmation that the new software feature ("Compressed Sensing (CS) Cardiac Cine") was migrated unchanged from an already cleared reference device (K163312).
• Compliance with recognized standards (IEC, ISO, NEMA) for safety and software development.
• Software verification and validation testing, and general device performance testing, all non-clinical.

The document does not contain the details of a study with specific acceptance criteria, reported performance metrics, or clinical ground truth establishment as requested in your prompt. This type of detailed performance data is typically found in accompanying test protocols and reports, which are part of the larger 510(k) submission but not always fully summarized in the publicly available 510(k) summary.

Ask a specific question about this device

Artis is a family of dedicated angiography systems developed for single and biplane diagnostic imaging and interventional procedures including, but not limited to, pediatric and obese patients.

Procedures that can be performed with the Artis family include cardiac angiography, general angiography, rotational angiography, multipurpose angiography and whole body radiographic/fluoroscopic procedures as well as procedures next to the table for i.e. patient extremities.

Additional procedures that can be performed include angiography in the operating room, image guided surgery by X-ray, by image fusion, and by navigation systems. The examination table as an integrated part of the system can be used for Xray imaging, surgery and interventions.

Artis can also support the acquisition of position triggered imaging for spatial data synthesis.

The Artis systems include also the software option DynaCT with following IFU:

DynaCT is an x-ray imaging software option, which allows the reconstruction of two-dimensional images acquired with a standard angiographic C-arm device into a three-dimensional image format.

DynaCT is intended for imaging both hard and soft tissues as well as other internal body structures for diagnosis, surgical planning, interventional procedures and treatment follow-up.

The Artis Modular Angiography systems are specialized angiography systems. In general, they are equipped with C-arm, stand, flat panel detector, x-ray tube, high voltage generator, patient table and image post-processing software.

Siemens currently markets the Artis zee / zeego (K141574) and the Artis Q / Q.zen (K123529). Siemens will provide new software VD11D for both, the Artis zee / zeego and Artis Q / Q.zen systems. The new software VD11D will support the detector Pixium 3040CV (also known as "40HDR") already cleared with Artis Q / Q.zen (K123529). Systems, Artis zee / zeego, and Artis Q / Q.zen use the cleared AEC (Automatic Exposure Control) functionality.

Siemens intends to market new claims specific to the AEC, which are provided in the product claims list. Siemens will replace the cooling unit in both systems.

The Mivabi Angio-CT configuration has been improved and will be known as and marketed as the nexaris Angio-CT configuration. Siemens nexaris Angio-CT configuration was designed to contain both Angio and CT System within close proximity or within the same environment. The CT-gantry on rails will slide towards the Angiography patient table to perform a CT scan without repositioning the patient. After the CT scan, the CT-gantry could be slide away from the patient table to use the table for Angiography C-arm acquisitions.

This 510(k) submission describes modifications made to the previously cleared predicate devices: Artis zee / zeego SW VC21 (K141574) and Artis Q / Q.zen SW Version VD10 (K123529). The modifications will be marketed as "Artis zee / zeego VD11D" and "Artis Q / Q.zen VD11."

The provided document does not contain the detailed acceptance criteria and performance study outcomes typically found in a clinical or standalone performance study report for AI-powered diagnostic devices.

Instead, this document is a 510(k) summary for Siemens Medical Solution USA, Inc.'s Artis zee/zeego & Artis Q/Q.zen angiographic X-ray systems. It primarily focuses on demonstrating substantial equivalence to previously cleared predicate devices for hardware and software modifications, rather than evaluating a novel AI algorithm's diagnostic performance against ground truth.

Here's an analysis based on the information provided, highlighting what's present and what's missing:

Acceptance Criteria and Device Performance

• No specific acceptance criteria or reported device performance metrics (e.g., sensitivity, specificity, AUC) are provided for an AI component.
• The document mentions "acceptance criteria" in the context of verification and validation testing for the software specifications and that "all software specifications have met the acceptance criteria," but these criteria are not detailed in terms. This likely refers to system-level tests for functionality, safety, and effectiveness of the updated X-ray system software, not a diagnostic performance metric.

Study Details (as far as can be inferred/is absent)

1. A table of acceptance criteria and the reported device performance:

   • Absent. There is no table detailing acceptance criteria for diagnostic performance or reported performance metrics like sensitivity, specificity, or F1-score for any AI component. The document discusses regulatory standards compliance and software verification/validation, but not diagnostic accuracy.

2. Sample size used for the test set and the data provenance:

   • Absent. The document does not describe a test set in the context of diagnostic performance evaluation for an AI algorithm. It refers to "non-clinical test data" and "clinical images and data" used for evaluating the predicate devices, but doesn't specify a test set for the modifications or an AI component.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

   • Absent. No information is provided regarding expert readers or ground truth establishment for a test set, as no diagnostic performance study for an AI algorithm is described.

4. Adjudication method (e.g., 2+1, 3+1, none) for the test set:

   • Absent. Not applicable, as there's no mention of a diagnostic test set for an AI algorithm.

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:

   • Absent. There is no mention of an MRMC study or any evaluation of human reader improvement with AI assistance. The submission is about modifications to an X-ray imaging system, not an AI diagnostic tool.

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

   • Absent. No standalone AI algorithm performance study is indicated.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):

   • Absent. No ground truth type is specified, as no diagnostic performance study is detailed.

8. The sample size for the training set:

   • Absent. There is no mention of a training set, indicating that this submission is not for an AI/ML algorithm that requires training. The "DynaCT" software option mentioned is for 3D reconstruction from 2D images, not a learned diagnostic pattern recognition system in the sense of modern AI/ML.

9. How the ground truth for the training set was established:

   • Absent. Not applicable, as no training set is mentioned.

Summary of What the Document Does Provide:

The document is a 510(k) submission for modifications to existing angiography systems. The modifications primarily involve:

• Revised Indications for Use (clarification, not new uses).
• New software version (VD11D) to support hardware.
• Support for an existing detector (Pixium 3040CV) on an additional system (Artis zee/zeego).
• A new tube cooling unit.
• Updated product claims.
• Configuration updates for the "Miyabi Angio-CT" (now "nexaris Angio-CT"), including improved collision calculation.

The regulatory review concluded that the device is "substantially equivalent" to predicate devices, based on:

• Non-clinical tests for electrical safety, performance, electromagnetic compatibility, and compliance with various international standards (listed in Table 3 on page 10).
• Software verification and validation testing, addressing the FDA's guidance documents for software in medical devices and cybersecurity. These tests demonstrated that the software modifications met acceptance criteria and did not raise new safety or effectiveness issues.
• Human Factors Usability Validation.

Key Missing Information: This document is NOT about an AI-powered diagnostic device in the modern sense that would require performance metrics like sensitivity, specificity, or a comparison against a human expert ground truth. It focuses on demonstrating the safety and effectiveness of updated hardware and software components within an imaging system.

Ask a specific question about this device

ARTIS is a family of dedicated angiography systems developed for single and biplane diagnostic imaging and interventional procedures including, but not limited to, pediatric and obese patients.

Procedures that can be performed with the ARTIS family include cardiac angiography, general angiography, rotational angiography, multipurpose angiography and whole body radiographic fluoroscopic procedures as well as procedures next to the table for i.e. patient extremities.

Additional procedures that can be performed include angiography in the operating room, image-guided surgery by X-ray, by image fusion, and by navigation systems. The examination table as an integrated part of the system can be used for Xray imaging, surgery and interventions.

ARTIS can also support the acquisition of position triggered imaging for spatial data synthesis.

The ARTIS family include also the software option DynaCT with following indications for use:

DynaCT is an X-ray imaging software option, which allows the reconstruction of two-dimensional images acquired with a standard angiographic C-arm device into a three-dimensional image format.

DynaCT is intended for imaging both hard and soft tissues as well as other internal body structures for diagnosis, surgical planning, interventional procedures and treatment follow-up.

The ARTIS pheno is a further development of the Artis Q and Artis Q.zen -Modular Angiography System. ARTIS pheno is equipped with C-arm, stand, flat panel detector, x-ray tube, high voltage generator, patient table, and image post processing. syngo Application Software is optional available for the support of dedicated clinical workflows.

The provided text describes the ARTIS pheno device and its substantial equivalence to predicate devices, but it does not contain a detailed study with specific acceptance criteria and reported device performance metrics in the format requested.

The document states that "Non-clinical tests were conducted for ARTIS pheno, during product development" and that "The modifications described in this Premarket Notification were supported with verification and validation testing." It also mentions "The performance data demonstrates continued conformance with special controls for medical devices containing software" and "The testing results support that all the software specifications have met the acceptance criteria."

However, it does not provide the actual acceptance criteria or the specific numerical performance results achieved by the device in a table format. It only lists various standards the device complies with (e.g., ES60601-1:2005/(R)2012) and general statements about the tests being passed.

Therefore, I cannot populate the requested table or provide detailed answers to questions 2 through 9 based on the provided text. The document refers to "non-clinical performance testing" and "verification and validation testing" but does not elaborate on the specific methodologies, sample sizes, ground truth establishment, or expert involvement for these tests.

Summary of available information regarding performance:

• Acceptance Criteria/Reported Performance: Not explicitly stated in a quantifiable manner or table. The document generally states that "all tests were passed" and that "all the software specifications have met the acceptance criteria."
• Sample size for test set and data provenance: No information provided.
• Number of experts and qualifications for ground truth: No information provided.
• Adjudication method: No information provided.
• MRMC comparative effectiveness study: No information provided.
• Standalone (algorithm only) performance: No information provided the software is a component of the interventional fluoroscopic x-ray system, not a standalone AI device with specific algorithmic performance metrics.
• Type of ground truth used: "Non-clinical performance testing" and "software specifications" are mentioned, suggesting internal validation against defined functional requirements and safety standards. No mention of expert consensus, pathology, or outcomes data for performance evaluation in the context of diagnostic accuracy.
• Sample size for training set: No information provided.
• How ground truth for training set was established: No information provided.

The document primarily focuses on demonstrating substantial equivalence to predicate devices based on technological characteristics, adherence to safety and performance standards for an interventional fluoroscopic x-ray system, and successful completion of verification and validation activities. It does not provide the kind of detailed study results one might expect for a novel AI/CAD device.

Ask a specific question about this device

The syngo Application Software is a medical software for real-time viewing, image manipulation, communication, and storage of medical images and data on exchange media. It is used for diagnostic image viewing and post processing and for viewing and post processing during interventional procedures.

The syngo Application Software can be deployed on independent hardware such as a stand-alone diagnostic review, post-processing, and reporting workstation. It can also be configured within a network to send and receive DICOM data. Furthermore, the syngo Application Software can be deployed on systems Angiography system family. It provides image guided solutions in the operating room, for image guided surgery, by Image Fusion and by navigation systems, image guided solutions in interventional cardiology and image guided solutions for interventional oncology, interventional radiology, and interventional neuroradiology.

The syngo Application Software can also be combined with fluoroscopy systems or Radiographic systems.

The syneo Application Software can be configured with a variety of syngo or Windows-based software options, which are intended to assist the physician in diagnosis, treatment control. It includes commercially available post-processing techniques and OEM options.

Procedures that can be performed include: minimally invasive surgical procedures and minimally invasive tumor treatment.

The syngo Application Software is medical diagnostic software for real-time viewing, diagnostic review, post-processing, image manipulation, optimization, communication, reporting and storage of medical images and data on exchange media. It provides image guided solutions in the operating room, for image guided surgery, by Image Fusion and by navigation systems, image guided solutions in interventional cardiology and electrophysiology and image guided solutions for interventional oncology, interventional radiology, and interventional neuroradiology. It can be deployed with a variety of syngo or Windows based software options, which are intended to assist the physician in evaluation of digital radiographic examinations, including diagnosis and/or treatment planning.

Siemens syngo Application Software is designed to work with digital radiographic, fluoroscopic, interventional and angiographic systems. The software platform with common software architecture, syngo application packages and basic services is the same as used with the syngo Application Software cleared in K162541.

Siemens Medical Solutions USA, Inc. hereby submits this Traditional 510(k) to request clearance for new software features to the syngo Application Software.

Proposed Device Modifications:

• 1. Enhanced syngo Embolization Guidance
• 2. Proposed new product claims associated with device.

The "syngo Application Software" may be installed either on Siemens released PC hardware, on Siemens X-ray systems or on Siemens Angiography Systems. The combination of syngo Application Software and the Siemens released PC Hardware will be marketed as components of the syngo X Workplace.

The syngo Application Software is within the same classification regulation and the intended use and the general Indications for Use Statement for Siemens' Picture Archiving and Communications System.

The document provided is a 510(k) premarket notification for the "syngo Application Software," specifically focusing on enhancements to the "syngo Embolization Guidance" feature. While the document mentions performance testing and results, it does not detail acceptance criteria with specific thresholds or a formal study design that would typically contain all the requested information for a comprehensive study proving the device meets acceptance criteria.

However, based on the provided text, we can glean some information regarding the performance evaluation of the syngo Embolization Guidance algorithm. The primary focus of the performance data section is on the detection rate of vessels, specifically in the context of embolization guidance for hepatic arteries.

Here's an attempt to extract and infer the requested information:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state acceptance criteria in a table format with clear threshold values for key performance metrics. It only provides reported performance metrics related to the syngo Embolization Guidance algorithm. The implicit acceptance criterion would be that the performance is "clinically accepted by a board certified radiologist."

Ask a specific question about this device