Search Results

syngo.via molecular imaging (MI) workflows comprise medical diagnostic applications for viewing, manipulation, quantification, analysis and comparison of medical images from single or multiple imaging modalities with one or more time-points. These workflows support functional data, such as positron emission tomography (PET) or nuclear medicine (NM), as well as anatomical datasets, such as computed tomography (CT) or magnetic resonance (MR). syngo.via MI workflows can perform harmonization of SUV (PET) across different PET systems or different PET reconstruction methods.

syngo.via MI workflows are intended to be utilized by appropriately trained health care professionals to aid in the management of diseases, including those associated with oncology, cardiology, neurology, and organ function. The images and results produced by the syngo.via MI workflows can also be used by the physician to aid in radiotherapy treatment planning.

syngo.via MI Workflows (including Scenium and syngo MBF applications) is a multi-modality post-processing software only medical device intended to aid in the management of diseases, including those associated with oncology, cardiology, neurology, and organ function. The syngo.via MI Workflows applications are part of a larger syngo.via client/server system which is intended to be installed on common IT hardware. The hardware itself is not seen as part of the syngo.via MI Workflows medical device.

The syngo.via MI Workflows software addresses the needs of the following typical users of the product:

• Reading Physician / Radiologist – Reading physicians are doctors who are trained in interpreting patient scans from PET, SPECT and other modality scanners. They are highly detail oriented and analyze the acquired images for abnormalities, enabling ordering physicians to accurately diagnose and treat scanned patients. Reading physicians serve as a liaison between the ordering physician and the technologists, working closely with both.
• Technologist – Nuclear medicine technologists operate nuclear medicine scanners such as PET and SPECT to produce images of specific areas and states of a patient's anatomy by administering radiopharmaceuticals to patients orally or via injection. In addition to administering the scan, the technologist must properly select the scan protocol, keep the patient calm and relaxed, monitor the patient's physical health during the protocol and evaluate the quality of the images. Technologists work very closely with physicians, providing them with quality-checked scan images.

The software has been designed to integrate the clinical workflow for the above users into a server-based system that is consistent in design and look with the base syngo.via platform and other syngo.via software applications. This ensures a similar look and feel for radiologists that may review multiple types of studies from imaging modalities other than Molecular Imaging, such as MR.

The syngo.via MI workflows software supports integration through DICOM transfers of positron emission tomography (PET) or nuclear medicine (NM) data, as well as anatomical datasets, such as computed tomography (CT) or magnetic resonance (MR).

Although data is automatically imported into the server based on predefined configurations through the hospital IT system, data can also be manually imported from external media, including CD, external mass storage devices, etc.

The Siemens syngo.via platform and the applications that reside on it, including syngo.via MI Workflows, are distributed via electronic medium. The Instructions for Use is also delivered via electronic medium.

syngo.via MI Workflows includes 2 workflows (syngo.MM Oncology and syngo.MI General) as well as the Scenium neurology software application and the syngo MBF cardiology software application which are launched from the OpenApps framework within the MI General workflow.

Here's a breakdown of the acceptance criteria and study details for the syngo.via MI Workflows, Scenium, and syngo MBF devices:

Acceptance Criteria and Reported Device Performance

For Lung and Lung Lobe Segmentation:

For PERCIST Liver Reference Region Placement (Binary Liver Mask, input to the algorithm):

Ask a specific question about this device

syngo.via molecular imaging (MI) workflows comprise medical diagnostic applications for viewing, manipulation, quantification, analysis and comparison of medical images from single or multiple imaging modalities with one or more time-points. These workflows support functional data, such as positron emission tomography (PET) or nuclear medicine (NM), as well as anatomical datasets, such as computed tomography (CT) or magnetic resonance (MR), syngo.via MI workflows can perform harmonization of SUV (PET) across different PET systems or different PET reconstruction methods.

syngo.via MI workflows are intended to be utilized by appropriately trained health care professionals to aid in the management of diseases, including those associated with oncology, cardiology, neurology, and organ function. The images and results produced by the syngo.via MI workflows can also be used by the physician to aid in radiotherapy treatment planning.

syngo.via MI Workflows (including Scenium and syngo MBF applications) is a multi-modality postprocessing software only medical device intended to aid in the management of diseases, including those associated with oncology, cardiology, neurology, and organ function. The syngo.via MI Workflows applications are part of a larger syngo.via client/server system which is intended to be installed on common IT hardware. The hardware itself is not seen as part of the syngo.via MI Workflows medical device.

The syngo.via MI Workflows software addresses the needs of the following typical users of the product:

• Reading Physician / Radiologist – Reading physicians are doctors who are trained in interpreting patient scans from PET, SPECT and other modality scanners. They are highly detail oriented and analyze the acquired images for abnormalities, enabling ordering physicians to accurately diagnose and treat scanned patients. Reading physicians serve as a liaison between the ordering physician and the technologists, working closely with both.
• Technologist – Nuclear medicine technologists operate nuclear medicine scanners such as PET and SPECT to produce images of specific areas and states of a patient's anatomy by administering radiopharmaceuticals to patients orally or via injection. In addition to administering the scan, the technologist must properly select the scan protocol, keep the patient calm and relaxed, monitor the patient's physical health during the protocol and evaluate the quality of the images. Technologists work very closely with physicians, providing them with quality-checked scan images.

The software has been designed to integrate the clinical workflow for the above users into a serverbased system that is consistent in design and look with the base syngo.via platform and other syngo.via software applications. This ensures a similar look and feel for radiologists that may review multiple types of studies from imaging modalities other than Molecular Imaging, such as MR.

The syngo.via MI workflows software supports integration through DICOM transfers of positron emission tomography (PET) or nuclear medicine (NM) data, as well as anatomical datasets, such as computed tomography (CT) or magnetic resonance (MR).

Although data is automatically imported into the server based on predefined configurations through the hospital IT system, data can also be manually imported from external media, including CD, external mass storage devices, etc.

The Siemens syngo.via platform and the applications that reside on it, including syngo.via MI Workflows, are distributed via electronic medium. The Instructions for Use is also delivered via electronic medium.

syngo.via MI Workflows includes 2 workflows (syngo.MM Oncology and syngo.MI General) as the Scenium neurology software application and the syngo MBF cardiology software application which are launched from the OpenApps framework within the MI General workflow.

Here's a breakdown of the acceptance criteria and study information for the Siemens syngo.via MI Workflows, including Scenium, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

2. Sample Size and Data Provenance for Test Set

• Calibration Data:
  • Sample Size: Not explicitly stated, but "calibration of PET images and their corresponding SUVr and CL reference data were obtained from the GAAIN website." This implies a sufficiently large dataset for method calibration.
  • Provenance: GAAIN website (Global Alzheimer's Association Interactive Network) – likely a multinational, retrospective dataset of clinical trial data.
• Validation Data (ADNI):
  • Sample Size: Not explicitly stated, but "two independent datasets" were used for validation against ADNI CL values for florbetaben. ADNI (Alzheimer's Disease Neuroimaging Initiative) is a large, multi-center, prospective observational study primarily conducted in North America.
  • Provenance: ADNI (Alzheimer's Disease Neuroimaging Initiative), likely primarily from the USA and Canada. Prospective given the nature of ADNI.
• Validation Data (Visual Reading Agreement):
  • Sample Size: 162 patients (69 females, 93 males)
  • Provenance: Retrospective review of patients with Mild Cognitive Impairment (MCI) who underwent A-PET. The specific country of origin is not mentioned.

3. Number of Experts and Qualifications for Ground Truth (Test Set)

• Calibration Data (GAAIN): The "standard method" for Centiloid scale calculation (Klunk et al.²) implies a consensus-derived or established expert-validated process. The number and specific qualifications of experts involved in the original GAAIN data curation are not detailed but are assumed to be highly qualified specialists in PET imaging and Alzheimer's research.
• Validation Data (ADNI): The ADNI Centiloid values are established through rigorous, expert-driven protocols. The text states "ADNI CL values," implying the ground truth was derived from the ADNI project's established methods, which involve numerous qualified experts in neurology, radiology, and nuclear medicine.
• Validation Data (Visual Reading Agreement): Patients were classified as "negative" by consensus. The number and specific qualifications of experts involved in this consensus are not explicitly stated, but it would typically involve experienced nuclear medicine physicians or radiologists specializing in neuroimaging.

4. Adjudication Method for the Test Set

• Calibration Data (GAAIN): Not explicitly stated, but the "standard method" for Centiloid score calculation suggests an established, perhaps algorithmic, adjudication or consensus process applied to the raw data.
• Validation Data (ADNI): Not explicitly stated, but the ADNI's established protocols for data analysis and Centiloid score determination would inherently involve robust, multi-expert consensus or adjudicated methods.
• Validation Data (Visual Reading Agreement): Patients were "classified as 'negative' by consensus." This indicates that multiple experts reviewed the images and reached an agreement on the classification. The specific method (e.g., 2+1, 3+1) is not provided.

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

• No MRMC comparative effectiveness study was done comparing human readers with AI assistance vs. without AI assistance. The study primarily focuses on validating the device's output (Centiloid scores) against established standards and visual interpretations, not on human workflow improvement with AI.

6. Standalone (Algorithm Only) Performance

• Yes, standalone performance was done for the Scenium Centiloid scoring feature. The studies directly compare Scenium's calculated Centiloid scores (algorithm output) against "standard method" values (from GAAIN) and ADNI CL values. The agreement with visual reading also assesses the algorithm's standalone diagnostic accuracy in classifying patients.

7. Type of Ground Truth Used

• Expert Consensus / Established Methodology:
  • For the calibration, the ground truth was the "standard method" of Centiloid estimation as prescribed in Klunk et al.², using reference data from GAAIN, which is an established, expert-driven consortium.
  • For validation, it involved "ADNI CL values," which are considered an established ground truth in Alzheimer's research.
  • For the visual reading agreement, the ground truth was "visual-based classification" determined by expert consensus.

8. Sample Size for the Training Set

• The text does not explicitly mention a "training set" for the Scenium Centiloid scoring algorithm. The process described is a "calibration" using data from GAAIN to derive transformation equations, and then "validation" on independent datasets. It's possible the calibration data acts as a form of training/development set.
  • Calibration Data (GAAIN): Sample size not explicitly stated for the "calibration analysis" dataset.

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

• As a "training set" isn't explicitly defined, we refer to the calibration process. The ground truth for the calibration (or equations derivation) was established using "calibration of PET images and their corresponding SUVr and CL reference data obtained from the GAAIN website." This reference data itself would have been established through rigorous scientific methods and likely expert consensus within the GAAIN consortium, adhering to the "level-2 calibration analysis prescribed in Klunk et al.²" to ensure a standardized and reliable ground truth.

Ask a specific question about this device

syngo.via RT Image Suite is a 3D and 4D image visualization, multi-modality manipulation and contouring tool that helps the preparation of treatments such as, but not limited to those performed with radiation (for example, Brachytherapy, Particle Therapy, External Beam Radiation Therapy).

lt provides tools to view existing contours, create, edit, modify, copy contours of the body, such as but not limited to, skin outline, targets and organs-at-risk. It also provides functionalities to create simple geometric treatment plans. Contours, images and treatment plans can subsequently be exported to a Treatment Planning System.

The software combines the following digital image processing and visualization tools:

• Multi-modality viewing and contouring of anatomical, functional, and multi-parametric images such as but not limited to CT, PET, PET/CT, MRI, Linac CBCT images
• Multiplanar reconstruction (MPR) thin/thick, minimum intensity projection (MIP), volume rendering technique (VRT)
• Freehand and semi-automatic contouring of regions-of-interest on any orientation including oblique
• Automated Contouring on CT images
• Creation of contours on images supported by the application without prior assignment of a planning CT
• Manual and semi-automatic registration using rigid and deformable registration
• Supports the user in comparing, contouring, and adapting contours based on datasets acquired with different imaging modalities and at different time points
• Supports multi-modality image fusion
• Visualization and contouring of moving tumors and organs
• Management of points of interest including but not limited to the isocenter
• Creation of simple geometric treatment plans
• Generation of a synthetic CT based on multiple pre-define MR acquisitions

The subject device with the current software version SOMARIS/8 VB80 is an image analysis software for viewing, manipulation, 3D and 4D visualization, comparison of medical images from multiple imaging modalities and for the segmentation of tumors and organs-at-risk, prior to dosimetric planning in radiation therapy. syngo.via RT Image Suite combines routine and advanced digital image processing and visualization tools for manual and software assisted contouring of volumes of interest, identification of points of interest, sending isocenter points to an external laser system, registering images and exporting final results. syngo.via RT Image Suite supports the medical professional with tools to use during different steps in radiation therapy case preparation. The current software version SOMARIS/8 VB80 are as follows:

• Modifications in Advanced Contouring: Data for training and validation of Advanced Contouring was obtained through clinical collaborations from Asia, Australia, Europe, and America to provide variability in age, gender, geographic origin, etc. Both native and contrasted CT images are included.
• Revised User Interface

The provided text describes the regulatory clearance of "syngo.via RT Image Suite" and includes information about its performance evaluation. The focus of the performance data section is on the AI-based autocontouring feature.

Here's a breakdown of the acceptance criteria and the study proving the device meets them, based on the provided text:

Acceptance Criteria and Reported Device Performance

The acceptance criteria for the AI-based autocontouring feature were defined based on the Dice coefficient, a commonly used overlap metric. The text states:

"All tests passed the defined acceptance criteria on the geometric overlap with the ground truth. The evaluation results confirm the clinical safety and performance of the autocontouring feature."

While the specific numerical threshold for the Dice coefficient acceptance criterion is not explicitly stated in the provided document, the statement confirms that the results met the pre-defined criteria.

Table of Acceptance Criteria and Reported Device Performance:

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

• Test Set Sample Size: 413 subjects
• Data Provenance: The test data was generated from an independent set not seen during training. It covers a wide range of CT scanners and acquisition parameters.
  • Geographic Origin: Europe (IT, PT, CH, UK, NL, DE), North America (US, CA), South America (BR), Australia, Asia (JP, IN).
  • Retrospective/Prospective: Not explicitly stated, but "obtained through clinical collaborations" suggests retrospective collection of existing clinical data.

Breakdown of Test Set Distribution (from Table 1):

• Data Source: Europe: 58, US: 165, Canada: 39, South America: 78, Australia: 28, Asia: 33, unknown: 12
• Body Region: Head&Neck: 113, Thorax&Abdomen: 216, Pelvis: 84
• Gender: Male: 188, female: 174, Unknown: 51
• Age: 70: 20, unknown: 340
• Slice thickness (in mm): 3: 19
• Manufacturer (Scanner): Siemens: 126, GE: 77, Philips: 140, unknown/others: 70

3. Number of Experts Used to Establish Ground Truth and Qualifications:

• Number of Experts: An "expert team" was used, but the specific number is not provided.
• Qualifications: "based on well accepted international contouring guidelines". The specific qualifications of the experts (e.g., radiologist with X years of experience) are not detailed.

4. Adjudication Method for the Test Set:

• The ground truth was established by an "expert team" and then followed by a "rigorous independent quality assessment." This suggests a form of review or adjudication, but the exact method (e.g., 2+1, 3+1) is not specified.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done:

• No. The provided text describes a standalone performance evaluation of the AI algorithm (autocontouring feature) against a manually annotated ground truth. It does not mention a comparative study involving human readers with and without AI assistance to measure improvement in human performance.

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

• Yes. The performance evaluation described is purely a standalone assessment of the AI-based autocontouring feature. It compares the algorithm's output directly to the "manually annotated ground truth" using the Dice coefficient.

7. The Type of Ground Truth Used:

• Expert Consensus/Manual Annotation: "Manual ground-truth segmentations were annotated by an expert team based on well accepted international contouring guidelines, followed by a rigorous independent quality assessment."

8. The Sample Size for the Training Set:

• The document states that the validation data (test set) was "20% of the available data." This implies the training set was the remaining 80% of the total available data. However, the total available data size for both training and validation is not explicitly stated. Thus, the specific numerical sample size for the training set cannot be determined from this text.

9. How the Ground Truth for the Training Set was Established:

• While not explicitly detailed for the training set, the text mentions that "Data for training and validation of Advanced Contouring was obtained through clinical collaborations from Asia, Australia, Europe, and America to provide variability in age, gender, geographic origin, etc."
• Given the method for the test set ("Manual ground-truth segmentations were annotated by an expert team"), it is highly probable that the ground truth for the training set was established through a similar process of expert manual annotation, though this is not explicitly confirmed for the training data in this section.

Ask a specific question about this device

syngo.via molecular imaging (MI) workflows comprise medical diagnostic applications for viewing, manipulation, quantification, analysis and comparison of medical images from single or multiple imaging modalities with one or more time-points. These workflows support functional data, such as positron emission tomography (PET) or nuclear medicine (NM), as well as anatomical datasets, such as computed tomography (CT) or magnetic resonance (MR). syngo.via MI workflows can perform harmonization of SUV (PET) across different PET systems or different PET reconstruction methods.

syngo via MI workflows are intended to be utilized by appropriately trained health care professionals to aid in the management of diseases, including those associated with oncology, cardiology, neurology, and organ function. The images and results produced by the syngo.via MI workflows can also be used by the physician to aid in radiotherapy treatment planning.

syngo.via MI Workflows (including Scenium and syngo MBF applications) is a multi-modality postprocessing software only medical device intended to aid in the management of diseases, including those associated with oncology, cardiology, neurology, and organ function. The syngo.via MI Workflows applications are part of a larger syngo.via client/server system which is intended to be installed on common IT hardware. The hardware itself is not seen as part of the syngo.via MI Workflows medical device.

The syngo.via MI Workflows software addresses the needs of the following typical users of the product:

• . Reading Physician / Radiologist – Reading physicians are doctors who are trained in interpreting patient scans from PET, SPECT and other modality scanners. They are highly detail oriented and analyze the acquired images for abnormalities, enabling ordering physicians to accurately diagnose and treat scanned patients. Reading physicians serve as a liaison between the ordering physician and the technologists, working closely with both.
• . Technologist – Nuclear medicine technologists operate nuclear medicine scanners such as PET and SPECT to produce images of specific areas and states of a patient's anatomy by administering radiopharmaceuticals to patients orally or via injection. In addition to administering the scan, the technologist must properly select the scan protocol, keep the patient calm and relaxed, monitor the patient's physical health during the protocol and evaluate the quality of the images. Technologists work very closely with physicians, providing them with quality-checked scan images.

The software has been designed to integrate the clinical workflow for the above users into a serverbased system that is consistent in design and look with the base syngo.via platform and other syngo.via software applications. This ensures a similar look and feel for radiologists that may review multiple types of studies from imaging modalities other than Molecular Imaging, such as MR.

syngo.via MI workflows software supports integration through DIC emission tomography (PET) or nuclear medicine (NM) data, as well as anatomical datasets, such as computed tomography (CT) or magnetic resonance (MR).

Although data is automatically imported into the server based on predefined configurations through the hospital IT system, data can also be manually imported from external media, including CD, external mass storage devices, etc.

The Siemens syngo.via platform and the applications that reside on it, including syngo.via MI Workflows, are distributed via electronic medium. The Instructions for Use is also delivered via electronic medium.

syngo.via MI Workflows includes 2 workflows (syngo.MM Oncology and syngo.MI General) as the Scenium neurology software application and the syngo MBF cardiology software application which are launched from the OpenApps framework within the MI General workflow.

Here's a breakdown of the acceptance criteria and the study information for the Syngo.via MI Workflows, Scenium, and Syngo MBF device, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The document primarily focuses on two areas of performance evaluation: Organ Segmentation and Tau Workflow Support. The acceptance criteria for Organ Segmentation are explicitly stated, while for Tau Workflow, the criteria are implied through correlation and agreement with existing methods.

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

• Organ Segmentation: Not explicitly stated. The algorithm used was "originally cleared within syngo.via RT Image Suite (K201444) and carried into the reference predicate device (syngo.via RT Image Suite, K220783)." This suggests the data provenance for this algorithm was tied to those previous clearances. The document implies the segmentation quality was assessed, but the specific test set size for this current submission is not provided.
• Tau Workflow Support: "more than 700 flortaucipir images from ADNI".
• Data Provenance (Tau Workflow): "ADNI" (Alzheimer's Disease Neuroimaging Initiative). This is a prospective, multi-center, North American study. The exact countries of origin of the individual images are not specified but ADNI is a U.S. led initiative with international participation.

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

• Organ Segmentation: For manual ground truth annotation, the number of experts and their qualifications are not specified.
• Tau Workflow Support: The ground truth for the "MR-based method and MR-based segmentations" used for comparison is from existing methods mentioned in the references. The number and qualifications of experts involved in establishing this historical ground truth are not specified in this document.

4. Adjudication Method for the Test Set

• Organ Segmentation: An adjudication method is not explicitly stated. The process involved "comparing a manually annotated ground truth with the algorithm result." It's common for a single expert or a consensus of experts to establish manual ground truth, but the method for resolving discrepancies or reaching consensus is not detailed here.
• Tau Workflow Support: An adjudication method is not explicitly stated. The comparison was made between the device's calculated SUVRs and those from an "MR-based method and MR-based segmentations." This implies a comparison against a pre-established or validated method rather than a multi-reader adjudication specifically for this study.

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

• No MRMC comparative effectiveness study was done for this submission. The document explicitly states: "Clinical testing was not conducted for this submission." The evaluations focused on standalone performance and agreement with existing methods.

6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Performance

• Yes, standalone performance was done.
  • Organ Segmentation: The segmentation algorithm's performance (DICE coefficient and ASSD) was assessed by comparing its output directly against manually annotated ground truth. This is a standalone evaluation.
  • Tau Workflow Support: The "SUVRs calculated on individual and composite Braak VOIs using our pipeline and our masks" were compared to an "MR-based method." This directly assesses the algorithm's standalone quantification capabilities.

7. Type of Ground Truth Used

• Organ Segmentation: Expert consensus (manual annotation) is implied ("manually annotated ground truth").
• Tau Workflow Support: Reference method (MR-based method and MR-based segmentations) and potentially expert consensus that established those reference methods. The references provided suggest established research pipelines for flortaucipir processing and ADNI publications, which would typically involve expert interpretation and validation.

8. Sample Size for the Training Set

• Organ Segmentation: The document states the algorithm is the "same algorithm originally cleared within syngo.via RT Image Suite (K201444) and carried into the reference predicate device (syngo.via RT Image Suite, K220783)." The training set size for this re-used algorithm is not specified in this document, but would have been part of the original clearance.
• Tau Workflow Support: The training set size for the tau quantification workflow is not specified.

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

• Organ Segmentation: The method for establishing ground truth for the training set of the deep-learning algorithm is not specified in this document. Given it's a deep-learning algorithm, it would typically involve expert-labeled data, but the details are not provided.
• Tau Workflow Support: The method for establishing ground truth for the training set (if applicable) for the tau quantification workflow is not specified. It mentions using the AAL atlas as a basis for defining Braak regions, which is a pre-existing anatomical atlas.

Ask a specific question about this device

syngo.via View&GO is indicated for image rendering and post-processing of DICOM images to support the interpretation in the field of radiology, nuclear medicine and cardiology.

Siemens Healthcare GmbH intends to market the Medical Image Management and Processing System, syngo.via View&GO, software version VA40A. This 510(k) submission describes several modifications to the previously cleared predicate device. syngo.via View&GO, software version VA30A.

syngo.via View&GO is a software-only medical device, which is delivered by download to be installed on common IT hardware. This hardware has to fulfil the defined requirements. Any hardware platform that complies to the specified minimum hardware and software requirements and with successful installation verification and validation activities can be supported. The hardware itself is not seen as part of the medical device syngo.via View&GO and therefore not in the scope of this 510(k) submission.

syngo.via View&GO provides tools and features to cover the radiological tasks preparation for reading, reading images and support reporting. syngo.via View&GO supports DICOM formatted images and objects.

syngo.via View&GO is a standalone viewing and reading workplace. This is capable of rendering the data from the connected modalities for the post processing activities. syngo.via View&GO provides the user interface for interactive image viewing and processing with a limited short-term storage which can be interfaced with any Long-term storage (e.g. PACS) via DICOM syngo.via View&GO is based on Microsoft Windows operating systems.

syngo.via View&GO supports various monitor setups and can be adapted to a range of image types by connecting different monitor types.

The subject device and the predicate device share fundamental scientific technology. This device description holds true for the subject device. syngo.via View&GO, software version VA40A, as well as the predicate device, syngo.via View&GO, software version VA30A.

The provided text is a 510(k) summary for the syngo.via View&GO VA40A software, seeking substantial equivalence to a predicate device (syngo.via View&GO VA30A). While it details the device, its intended use, and comparisons to the predicate, it does not contain information about specific acceptance criteria or the details of a study proving the device meets those criteria.

The document states:

• "Non-clinical tests were conducted for the device syngo.via View&GO during product development. The modifications described in this Premarket Notification were supported with verification and validation testing." (Page 14, Section 8)
• "The testing results support that all the software specifications have met the acceptance criteria. Testing for verification and validation for the device was found acceptable to support the claims of substantial equivalence." (Page 14, Section 9)
• "Performance tests were conducted to test the functionality of the device syngo.via View&GO. These tests have been performed to assess the functionality of the subject device. Results of all conducted testing were found acceptable in supporting the claim of substantial equivalence." (Page 14, Section 10)

However, it does not provide the specific "acceptance criteria" themselves, nor does it describe the details of the "study" (beyond mentioning "non-clinical tests" and "verification and validation testing") that would demonstrate performance against these criteria.

Therefore, I cannot fulfill your request for the following information based solely on the provided text:

1. A table of acceptance criteria and the reported device performance: The acceptance criteria are not explicitly listed, nor are the specific performance results against them. The document only generally states that "all software specifications have met the acceptance criteria."
2. Sample sizes used for the test set and the data provenance: No information on sample sizes or data provenance (country, retrospective/prospective) for the test set is provided.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: As no specific study details are given, this information is not present.
4. Adjudication method for the test set: No information on adjudication is provided.
5. If a multi reader multi case (MRMC) comparative effectiveness study was done, if so, what was the effect size of how much human readers improve with AI vs without AI assistance: The document states the device is a "Medical Image Management and Processing System" and explicitly says "No automated diagnostic interpretation capabilities like CAD are included." (Page 9, CAD Functionalities table row). It is a post-processing and viewing software, not an AI/CAD system designed to directly improve human diagnostic performance via AI assistance. Therefore, an MRMC study for AI assistance would likely not be relevant or performed for this device category.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: The provided information hints at functional and software verification/validation, which are forms of standalone testing, but no specific performance metrics are given.
7. The type of ground truth used: Not specified.
8. The sample size for the training set: The document implies this is not an AI/ML algorithm that requires a "training set" in the typical sense for clinical performance. The "Imaging algorithms" section (Page 7-8) mentions "bug-fixing and minor improvements" and "No re-training or change in algorithm models was performed," suggesting that existing, validated algorithms were refined.
9. How the ground truth for the training set was established: Not applicable, as detailed above.

In summary, the provided FDA 510(k) summary focuses on demonstrating substantial equivalence to a predicate device through software verification and validation, and functional performance tests, rather than a detailed clinical study with specific acceptance criteria and performance metrics typically seen for AI/ML diagnostic aids. The changes introduced in VA40A compared to VA30A are primarily related to software architecture, operating system support (Windows 11), minor algorithm bug fixes, and user interface improvements, and the inclusion of a "Cinematic VRT" algorithm that was previously cleared. The "Imaging algorithms" section explicitly states: "The changes between the predicate device and the subject device doesn't impact the safety and effectiveness of the subject device as the necessary measures were taken for the safety and effectiveness of the subject device." This implies the focus was on ensuring the new version maintained the safety and effectiveness of the predicate, rather than proving a statistically significant improvement via a new clinical study.

Ask a specific question about this device

syngo.via View&GO is indicated for image rendering and post-processing of DICOM images to support the interpretation in the field of radiology, nuclear medicine and cardiology.

syngo.via View&GO is a software-only medical device, which is delivered by download to be installed on common IT hardware. This hardware has to fulfil the defined requirements. Any hardware platform that complies to the specified minimum hardware and software requirements and with successful installation verification and validation activities can be supported. The hardware itself is not seen as part of the medical device syngo.via View&GO and therefore not in the scope of this 510(k) submission.

syngo.via View&GO provides tools and features to cover the radiological tasks preparation for reading, reading images and support reporting. syngo.via View&GO supports DICOM formatted images and objects.

syngo.via View&GO is a standalone viewing and reading workplace. This is capable of rendering the data from the connected modalities for the post processing activities. syngo.via View&GO provides the user interface for interactive image viewing and processing with a limited short-term storage which can be interfaced with any Long-term storage (e.g. PACS) via DICOM syngo.via View&GO is based on Microsoft Windows operating systems.

syngo.via View&GO supports various monitor setups and can be adapted to a range of image types by connecting different monitor types.

The provided text is a 510(k) Summary for the Siemens Healthcare GmbH device "syngo.via View&GO" (Version VA30A). This document focuses on demonstrating substantial equivalence to a predicate device (syngo.via View&GO, Version VA20A) rather than presenting a detailed study of the device's performance against specific acceptance criteria for a novel algorithm.

The document states that the software is a Medical Image Management and Processing System, and its purpose is for "image rendering and post-processing of DICOM images to support the interpretation in the field of radiology, nuclear medicine and cardiology." It specifically states, "No automated diagnostic interpretation capabilities like CAD are included. All image data are to be interpreted by trained personnel."

Therefore, the provided text does not contain the information requested regarding acceptance criteria and a study proving an algorithm meets those criteria for diagnostic performance. It does not describe an AI/ML algorithm or its associated performance metrics.

However, based on the provided text, I can infer some aspects and highlight what information is missing if this were an AI-driven diagnostic device.

Here's an analysis based on the assumption that if this were an AI-based device, these fields would typically be addressed:

Summary of Device Performance (Based on provided text's limited scope for a general medical image processing system):

Since "syngo.via View&GO" is a medical image management and processing system without automated diagnostic interpretation capabilities, the acceptance criteria and performance data would revolve around its functionality, usability, and safety in handling and presenting medical images. The provided text primarily establishes substantial equivalence based on the lack of significant changes in core functionality and the adherence to relevant standards for medical software and imaging.

1. Table of acceptance criteria and the reported device performance:

The document doesn't provide a table of performance metrics for an AI algorithm. Instead, it describes "Non-clinical Performance Testing" focused on:

• Conformance to standards (DICOM, JPEG, ISO 14971, IEC 62304, IEC 82304-1, IEC 62366-1, IEEE Std 3333.2.1-2015).
• Software verification and validation (demonstrating continued conformance with special controls for medical devices containing software).
• Risk analysis and mitigation.
• Cybersecurity requirements.
• Functionality of the device (as outlined in the comparison table between subject and predicate device).

Reported Performance/Findings (General):

• "The testing results support that all the software specifications have met the acceptance criteria."
• "Testing for verification and validation for the device was found acceptable to support the claims of substantial equivalence."
• "Results of all conducted testing were found acceptable in supporting the claim of substantial equivalence."
• The device "does not introduce any new significant potential safety risks and is substantially equivalent to and performs as well as the predicate device."

Example of what a table might look like if this were an AI algorithm, along with why it's not present:

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

• Not explicitly stated for diagnostic performance, as the device does not have automated diagnostic capabilities.
• The software verification and validation activities would involve testing with various DICOM images to ensure proper rendering and processing. The exact number of images or datasets used for these software tests is not detailed.
• Data Provenance: Not specified, as it's not a clinical performance study.

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

• Not applicable / Not stated. Ground truth for diagnostic accuracy is not established for this device, as it does not perform automated diagnosis. The ground truth for software functionality would be the expected behavior of the software according to its specifications.

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

• Not applicable. No clinical adjudication method is described, as this is neither a clinical study nor an AI diagnostic device.

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 study was NOT done/described. The device explicitly states it has "No automated diagnostic interpretation capabilities like CAD are included. All image data are to be interpreted by trained personnel." Therefore, it does not offer AI assistance for diagnosis.

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

• Not applicable. The device is a "Medical Image Management and Processing System" that provides tools for human interpretation; it is not a standalone diagnostic algorithm.

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

• Not applicable for diagnostic purposes. For software functionality, the ground truth is the defined behavior as per the software specifications and design.

8. The sample size for the training set:

• Not applicable/Not stated. The document explicitly states for the "Imaging algorithms" section that "No re-training or change in algorithm models was performed." This implies that the algorithms are traditional image processing algorithms, not machine learning models that require training data in the context of diagnostic AI. If there were any minor algorithmic adjustments, the training data for such classical algorithms is typically the mathematical formulation itself rather than a dataset of clinical cases for machine learning.

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

• Not applicable. As indicated above, there is no mention of "training" in the context of machine learning. The algorithms are described as undergoing "bug-fixing and minor improvements" but no "re-training or change in algorithm models."

Ask a specific question about this device

syngo.via RT Image Suite is a 3D and 4D image visualization, multi-modality manipulation and contouring tool that helps the preparation of treatments such as, but not limited to those performed with radiation (for example, Brachytherapy, Particle Therapy, External Beam Radiation Therapy).

It provides tools to view existing contours, create, edit, modify, copy contours of regions of the body, such as but not limited to, skin outline, targets and organs-at-risk. It also provides functionalities to create simple geometric treatment plans. Contours, images and treatment plans can subsequently be exported to a Treatment Planning System.

The software combines the following digital image processing and visualization tools:

• . Multi-modality viewing and contouring of anatomical, and multi-parametric images such as but not limited to CT, PET, PET/CT, MRI, Linac CBCT images
• Multiplanar reconstruction (MPR) thin/thick, minimum intensity projection (MIP), volume rendering technique (VRT)
• . Freehand and semi-automatic contouring of regions-of-interest on any orientation including oblique
• Automated Contouring on CT images
• . Creation of contours on images supported by the application without prior assignment of a planning CT
• Manual and semi-automatic registration using rigid and deformable registration ●
• . Supports the user in comparing, contouring, and adapting contours based on datasets acquired with different imaging modalities and at different time points
• . Supports multi-modality image fusion
• . Visualization and contouring of moving tumors and organs
• Management of points of interest including but not limited to the isocenter ●
• . Creation of simple geometric treatment plans
• Generation of a synthetic CT based on multiple pre-define MR acquisitions ●

The subject device with the current software version SOMARIS/8 VB70 is an image analysis software for viewing, manipulation, 3D and 4D visualization, comparison of medical images from multiple imaging modalities and for the segmentation of tumors and organs-at-risk, prior to dosimetric planning in radiation therapy. syngo.via RT Image Suite combines routine and advanced digital image processing and visualization tools for manual and software assisted contouring of volumes of interest, identification of points of interest, sending isocenter points to an external laser system, registering images and exporting final results. syngo.via RT Image Suite supports the medical professional with tools to use during different steps in radiation therapy case preparation.

For the current software version SOMARIS/8 VB70 the following already cleared features have been modified:

• Patient Marking
• Contouring
• 4D Features ●
• Basic Features of the subject device ●

The provided text describes the acceptance criteria and a study demonstrating that the lobe-based lung ventilation algorithm within the syngo.via RT Image Suite meets these criteria.

Here's the breakdown of the requested information:

1. Table of Acceptance Criteria and Reported Device Performance

Ask a specific question about this device

syngo.via RT Image Suite is a 3D and 4D image visualization, multi-modality manipulation and contouring tool that helps the preparation of treatments such as, but not limited to those performed with radiation (for example, Brachytherapy, Particle Therapy, External Beam Radiation Therapy).

It provides tools to view existing contours, create, edit, modify, copy contours of regions of the body, such as but not limited to, skin outline, targets and organs-at-risk. It also provides functionalities to create simple geometric treatment plans. Contours, images and treatment plans can subsequently be exported to a Treatment Planning System.

The software combines the following digital image processing and visualization tools:

• . Multi-modality viewing and contouring of anatomical, and multi-parametric images such as but not limited to CT, PET, PET/CT, MRI, Linac CBCT images
• Multiplanar reconstruction (MPR) thin/thick, minimum intensity projection (MIP), volume ● rendering technique (VRT)
• . Freehand and semi-automatic contouring of regions-of-interest on any orientation including oblique
• Automated Contouring on CT images
• . Creation of contours on images supported by the application without prior assignment of a planning CT
• Manual and semi-automatic registration using rigid and deformable registration
• Supports the user in comparing, contouring, and adapting contours based on datasets acquired with different imaging modalities and at different time points
• . Supports multi-modality image fusion
• . Visualization and contouring of moving tumors and organs
• Management of points of interest including but not limited to the isocenter ●
• Creation of simple geometric treatment plans ●
• Generation of a synthetic CT based on multiple pre-define MR acquisitions ●

The subject device with the current software version SOMARIS/8 VB60 is an image analysis software for viewing, manipulation, 3D and 4D visualization, comparison of medical images from multiple imaging modalities and for the segmentation of tumors and organs-at-risk, prior to dosimetric planning in radiation therapy. syngo.via RT Image Suite combines routine and advanced digital image processing and visualization tools for manual and software assisted contouring of volumes of interest, identification of points of interest, sending isocenter points to an external laser system, registering images and exporting final results. syngo.via RT Image Suite supports the medical professional with tools to use during different steps in radiation therapy case preparation.

For the current software version SOMARIS/8 VB60 the following already cleared features have been modified:

• . Reference Point Management
• Patient Marking ●
• Contouring / Routine Contouring
• Structure Set Management ●
• Synthetic CT
• Basic Feature of syngo,via RT Image Suite

The provided documentation relates to the Siemens syngo.via RT Image Suite, specifically describing its 510(k) premarket notification for a new software version (SOMARIS/8 VB60) that includes an AI-based algorithm for synthetic CT generation.

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

Acceptance Criteria and Reported Device Performance

The document describes performance criteria for the AI-based algorithm for generating synthetic CT images from MR images. While not presented in a formal table with specific thresholds, the text outlines the key metrics evaluated and the results.

The document states that the geometric deviation of `

Ask a specific question about this device

syngo.via molecular imaging (MI) workflows comprise medical diagnostic applications for viewing, manipulation, quantification, analysis and comparison of medical images from single or multiple imaging modalities with one or more time-points. These workflows support functional data, such as position emission tomography (PET) or nuclear medicine (NM), as well as anatomical datasets, such as computed tomography (CT) or magnetic resonance (MR), syngo.via MI workflows can perform harmonization of SUV (PET) across different PET systems or different PET reconstruction methods.

syngo.via MI workflows are intended to be utilized by appropriately trained health care professionals to aid in the management of diseases, including those associated with oncology, neurology, and organ function. The images and results produced by the syngo.via MI workflows can also be used by the physician to aid in radiotherapy treatment planning.

syngo.via MI Workflows is a multi-modality post-processing software only medical device, which is intended to be installed on common IT hardware. This hardware must fulfill the defined requirements. The hardware itself is not seen as part of the medical device.

The Siemens syngo.via platform (K191040) and the applications that reside on it are distributed via electronic medium. The Instructions for Use also delivered via electronic medium.

synqo.via molecular imaging (MI) workflows comprise medical diagnostic applications for viewing, manipulation, quantification, analysis and comparison of medical images from single or multiple imaging modalities with one or more time-points. These workflows support functional data, such as positron emission tomography (PET) or nuclear medicine (NM), as well as anatomical datasets, such as computed tomography (CT) or magnetic resonance (MR).

syngo.via MI Workflows enable visualization of information that would otherwise have to be visually compared disjointedly. syngo.via MI workflows are intended to be utilized by appropriately trained health care professionals to aid in the management of diseases, including those associated with oncology, cardiology, neurology, and organ function. The images and results produced by the syngo.via MI workflows can also be used by the physician to aid in radiotherapy treatment planning.

Scenium assists in the display and analysis of images within the MI Neurology workflow of syngo.via MI Workflows. This software enables visualization and appropriate rendering of multimodality data, providing a number of features which enable the user to process acquired image data.

Scenium consists of four workflows:

• Database Comparison
• -Striatal Analvsis
• -Cortical Analysis
• -Subtraction

The Scenium workflows are used to assist the clinician with the visual evaluation, assessment and quantification of pathologies, such as dementia (i.e., Alzheimer's), movement disorders (i.e., Parkinson's) and seizure analysis (i.e., Epilepsy),

syngo MBF is a software only product intended for visualization, assessment and quantification of medical images: specifically providing quantitative blood flow measurements of PET images. The software is launched from the OpenApps Framework within the MI Cardiology workflow within syngo.Via MI Workflows. The application supports dynamic Rubidium – PET and dynamic Ammonia – PET images. The application provides visualization and measurement tools, for qualitative and quantitative visualization and assessment of the input data. It provides automatic and manual tools to orient and segment the myocardium. The software calculates measurements of myocardial blood flow, and provides tools, such as a database comparison workflow, for the Clinician to assess these results.

The provided text describes modifications to the syngo.via MI Workflows software (specifically VB60A, Scenium VE40A, and syngo MBF VB30A versions) and asserts their substantial equivalence to a predicate device (syngo.via MI Workflows VB50A, Scenium VE30A, and syngo MBF VB20A, K201195). However, it does not contain a detailed description of acceptance criteria or a specific study proving the device meets those criteria in the typical sense of a clinical or performance validation study with quantitative metrics, expert adjudication, or MRMC data.

Instead, the document focuses on:

• Regulatory Compliance: Adherence to FDA regulations (21 CFR 892.2050, 21 CFR Part 807.87(h)), recognized standards (ISO 14971, EN ISO 13485, IEC 62304, NEMA PS 3.1-3.20, IEC 62366-1, ISO 15223-1), and cybersecurity guidelines.
• Functional Equivalence: Stating that the new features do not alter the existent technological characteristics or raise new issues of safety and effectiveness compared to the predicate device.
• Verification and Validation (V&V): A general statement that "Verification and Validation activities have been successfully performed on the software package, including assurance that functions work as designed, performance requirements and specifications have been met, and that all hazard mitigations have been fully implemented. All testing has met the predetermined acceptance values."

Without specific performance metrics and a detailed study design provided in the given text, it is not possible to fully populate all components of your request. I will extract what information is present and indicate where information is Not Provided (NP).

Acceptance Criteria and Device Performance (as inferred from the document)

The document broadly states that "All testing has met the predetermined acceptance values." However, it does not explicitly define these "predetermined acceptance values" in a quantitative table. The primary acceptance criteria appear to be substantial equivalence, functional correctness, and adherence to safety and quality standards.

Study Details:

1. Sample sizes used for the test set and the data provenance:

   • Test Set Sample Size: NP (Not provided in the document. The document refers to "Verification and Validation activities" and "All testing" but does not specify the number of cases or datasets used for these tests.)
   • Data Provenance: NP (Not provided. It is not stated where the data for testing originated from, e.g., country of origin, or if it was retrospective or prospective data.)

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

   • Number of Experts: NP (Given the nature of the modifications described – mainly functional additions and improvements to existing workflows – it's unlikely a traditional "ground truth" for disease diagnosis was established for this specific submission beyond ensuring the software performs its intended technical functions. If expert review was part of the V&V, it is not detailed.)
   • Qualifications of Experts: NP

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

   • Adjudication Method: NP (This type of adjudication is typically for establishing diagnostic ground truth, which is not the focus of the described V&V for these software updates.)

4. 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:

   • MRMC Study: No. The document describes software workflow updates for viewing, manipulation, quantification, and analysis of medical images. It does not introduce an "AI" component intended to directly assist or change clinical decision-making in a way that would necessitate an MRMC study demonstrating improved human reader performance. The software is a tool for professionals, not an AI diagnostic assistant.

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

   • Standalone Performance: The V&V activities would have included testing of the software's algorithms and functions in a standalone manner to ensure they work as designed and meet specifications. However, specific metrics (e.g., accuracy, sensitivity, specificity for automated tasks) are NP for any specific algorithm. The "syngo MBF" module, for instance, calculates quantitative blood flow measurements, and its accuracy would have been part of the V&V, but no specific performance statistics are provided.

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

   • Type of Ground Truth: For the nature of these software updates, the "ground truth" would likely be technical correctness and adherence to algorithmic specifications rather than clinical outcomes or pathology. For example, ensuring that a 4D visualization works as intended, or that quantitative measurements (e.g., SUV harmonization, blood flow measurements) are mathematically correct and consistent with reference values or established methodologies. Detailed information about exactly how this "ground truth" was established (e.g., through phantom studies, simulations, or comparison with established clinical software/manual calculations) is NP.

7. The sample size for the training set:

   • Training Set Sample Size: NP. The document does not mention training sets, which implies that the updates are not based on a machine learning model that would require a distinct training phase. These are described as functional additions and improvements to existing software, not new AI/ML algorithms.

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

   • Training Set Ground Truth: NP, as no specific training set for (ML/AI) models is implied.

Ask a specific question about this device

syngo.via molecular imaging (MI) workflows comprise medical diagnostic applications for viewing, manipulation, quantification, analysis and comparison of medical images from single or multiple imaging modalities with one or more time-points. These workflows support functional data, such as positron emission tomography (PET) or nuclear medicine (NM), as well as anatomical datasets, such as computed tomography (CT) or magnetic resonance (MR). syngo.via MI workflows can perform harmonization of SUV (PET) across different PET systems or different PET reconstruction methods.

syngo.via MI workflows are intended to be utilized by appropriately trained health care professionals to aid in the management of diseases, including those associated with oncology, neurology, and organ function. The images and results produced by the syngo.via MI workflows can also be used by the physician to aid in radiotherapy treatment planning.

syngo.via MI Workflows is a software-only medical device which will be delivered on CD-ROM / DVD to be installed onto the commercially available Siemens syngo.via software platform (K191040) by trained service personnel.

syngo.via molecular imaging (MI) workflows comprise medical diagnostic applications for viewing, manipulation, quantification, analysis and comparison of medical images from single or multiple imaging modalities with one or more time-points. These workflows support functional data, such as positron emission tomography (PET) or nuclear medicine (NM), as well as anatomical datasets, such as computed tomography (CT) or magnetic resonance (MR).

synqo.via MI Workflows enable visualization of information that would otherwise have to be visually compared disjointedly. syngo.via MI workflows are intended to be utilized by appropriately trained health care professionals to aid in the management of diseases, including those associated with oncology, cardiology, neurology, and organ function. The images and results produced by the syngo.via MI workflows can also be used by the physician to aid in radiotherapy treatment planning.

Scenium is a previously cleared software device (K191309) that assists in the display and analysis of images within the MI Neurology workflow of syngo.via MI Workflows. This software enables visualization and appropriate rendering of multimodality data, providing a number of features which enable the user to process acquired image data.

Scenium consists of four workflows:

• Database Comparison -
• -Striatal Analysis
• -Cortical Analysis
• -Subtraction

The Scenium workflows are used to assist the clinician with the visual evaluation, assessment and quantification of pathologies, such as dementia (i.e., Alzheimer's), movement disorders (i.e., Parkinson's) and seizure analysis (i.e., Epilepsy).

syngo MBF is a software only product intended for visualization, assessment and quantification of medical images: specifically providing quantitative blood flow measurements of PET images. The software sites within the MI Cardiology workflow within syngo.Via MI Workflows. The application supports dynamic Rubidium - PET and dynamic Ammonia – PET images. The application provides visualization and measurement tools, for qualitative and quantitative visualization and assessment of the input data. It provides automatic and manual tools to orient and segment the myocardium. The software calculates measurements of myocardial blood flow, and provides tools, such as a database comparison workflow, for the Clinician to assess these results.

The provided text is a 510(k) Summary for the Siemens syngo.via MI Workflows VB50A. It details the device's intended use and technological characteristics but does not include a study specifically testing acceptance criteria for device performance, nor does it provide a table of acceptance criteria and reported device performance.

The document indicates that "Verification and Validation activities have been successfully performed on the software package, including assurance that functions work as designed, performance requirements and specifications have been met, and that all hazard mitigations have been fully implemented. All testing has met the predetermined acceptance values." However, it does not elaborate on what these "predetermined acceptance values" or "performance requirements and specifications" were, nor does it present the results of such testing.

Therefore, I cannot fulfill most of the requested information based on the provided text.

Here's what can be extracted based on the limitations:

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

• Cannot be provided. The document states that "All testing has met the predetermined acceptance values" but does not define these values or the specific performance metrics achieved.

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

• Cannot be provided. The document does not mention any specific test set, its size, or its provenance.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)

• Cannot be provided. The document does not describe any process for establishing ground truth using experts.

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

• Cannot be provided. The document does not describe any adjudication method.

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

• Cannot be provided. The document does not mention an MRMC comparative effectiveness study or any effect sizes related to human reader improvement with AI assistance.

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

• Cannot be provided. The document generally describes the software features but does not provide details of standalone performance testing.

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

• Cannot be provided. The document does not specify any type of ground truth used for performance evaluation.

8. The sample size for the training set

• Cannot be provided. The document does not mention any training sets or their sizes.

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

• Cannot be provided. The document does not mention any training sets or how their ground truth was established.

Summary of what the document does provide regarding testing:

• General Statement: "Verification and Validation activities have been successfully performed on the software package, including assurance that functions work as designed, performance requirements and specifications have been met, and that all hazard mitigations have been fully implemented. All testing has met the predetermined acceptance values."
• Standards Followed: Risk Management in compliance with ISO 14971, and development adhered to EN ISO 13485 and IEC 62304.
• Cybersecurity: "The Clinical Applications software has specific cybersecurity controls to prevent unauthorized access, modifications, misuse or denial of use. Additionally, controls are enabled to prevent the unauthorized use of information that is stored, accessed or transferred between the Clinical Applications software and external devices."

In conclusion, while the document indicates that verification and validation were performed and acceptance values were met, it lacks the specific details about these studies, acceptance criteria, and performance results that your request asks for. This type of detailed study information is typically found in the full 510(k) submission, not always in the public-facing 510(k) Summary.

Ask a specific question about this device