Search Results

The uPMR 790 system combines magnetic resonance diagnostic devices (MRDD) and Positron Emission Tomography (PET) scanners that provide registration and fusion of high resolution physiologic and anatomic information, acquired simultaneously and iso-centrically. The combined system maintains independent functionality of the MR and PET devices, allowing for single modality MR and/or PET imaging. The MR is intended to produce sagittal, transverse, coronal, and oblique cross sectional images, and spectroscopic images, and that display internal anatomical structure and/or function of the head, body and extremities. Contrast agents may be used depending on the reqion of interest of the scan. The PET provides distribution information of PET radiopharmaceuticals within the human body to assist healthcare providers in assessing the metabolic and physiological functions. The combined system utilizes the MR for radiation-free attenuation correction maps for PET studies. The system provides inherent anatomical reference for the fused PET and MR images due to precisely aligned MR and PET image coordinate systems.

The uPMR 790 system is a combined Magnetic Resonance Diagnostic Device (MRDD) and Positron Emission Tomography (PET) scanner. It consists of components such as PET detector, 3.0T superconducting magnet, RF power amplifier, RF coils, gradient power amplifier, gradient coils, patient table, spectrometer, computer, equipment cabinets, power distribution system, internal communication system, vital signal module, and software etc.

The uPMR 790 system provides simultaneous acquisition of high resolution metabolic and anatomic information from PET and MR. PET detectors are integrated into the MR bore for simultaneous, precisely aligned whole body MR and PET acquisition. The PET subsystem supports Time of Flight (ToF). The system software is used for patient management, data management, scan control, image reconstruction, and image archive. The uPMR 790 system is designed to conform to NEMA and DICOM standards.

This traditional 510(k) is to request modifications for the cleared uPMR 790(K222540). The modifications performed on the uPMR 790 (K222540) in this submission are due to the following changes that include:

• (1) Addition of RF coils: SuperFlex Body 24, SuperFlex Large -12, SuperFlex Small -12.
• (2) Addition and modification of pulse sequences:
  • (a) New sequences: gre fine, fse arms dwi, fse dwi, fse mars sle, grase, gre_bssfp_ucs, gre_fq, gre_pass, gre_quick_4dncemra, gre_snap, gre_trass, gre_rufis, epi_dwi_msh, svs_wfs, svs_stme.
  • (b) Added Associated options for certain sequences: QScan, MultiBand, Silicon-Only Imaging, MoCap-Monitoring, T1rho, CEST, Inline T2 mapping, CASS, inline FACT, uCSR, FSP+, whole heart coronary angiography imaging, mPLD (Only output original control/labeling images and PDw(Proton Density weighted) images, no quantification images are output).
  • (c) Name change of certain sequences: gre ute(old name: gre ute sp), svs_press(old name: press),svs_steam(old name: steam), csi_press(old name: press), csi hise(old name: hise).
• (3) Addition of MR imaging processing methods: 2D Flow, 4D Flow, SNAP, CEST, T1rho, FSP+, CASS, PASS, Inline T2 Mapping and DeepRecon.
• (4) Addition and modification of PET imaging processing methods:
  • (a) The new PET imaging processing methods: Hyper DPR (also named HYPER AiR) and Digital Gating (also named Self Gating).
  • (b) The modified method: HYPER Iterative.
• (5) Addition of MR image reconstruction methods: AI-assisted Compressed Sensing (ACS).
• (6) Addition and modification of workflow features:
  • (a) The new workflow features: EasyCrop, MoCap-Monitoring and QGuard-Imaging.
  • (b) The modified workflow feature: EasyScan.
• (7) Addition Spectroscopy: Liver Spectroscopy, Breast Spectroscopy.
• (8) Additional function: MR conditional implant mode.

The provided text does not contain detailed acceptance criteria for the uPMR 790 device in the format of a table, nor does it describe a specific study proving the device meets these criteria in a comparative effectiveness study or standalone performance study as would typically be presented for an AI/ML medical device.

The document is a 510(k) summary, which focuses on demonstrating substantial equivalence to a predicate device rather than providing a detailed clinical study report with specific performance metrics against acceptance criteria.

However, based on the information available, I can extract and infer some aspects related to acceptance criteria and the performance study:

Inferred Acceptance Criteria and Reported Device Performance (based on provided text):

The device is an integrated MR-PET system. The modifications primarily involve new RF coils, pulse sequences, imaging processing methods, and workflow features. The performance data section describes non-clinical testing to verify that the proposed device met design specifications and is Substantially Equivalent (SE) to the predicate device.

While explicit quantitative acceptance criteria are not tabulated, the text implies that the performance of the modified device (uPMR 790) must be at least equivalent to, or better than, the predicate and reference devices regarding image quality and functionality.

Specifically for the new or modified features related to AI/ML (DeepRecon and ACS), the implicit acceptance criteria appear to be:

• DeepRecon:
  • Equivalence in performance to DeepRecon on the uMR Omega.
  • Better performance than NADR (No DeepRecon) in SNR and resolution.
  • Maintenance of image qualities (contrast, uniformity).
  • Significantly same structural measurements between DeepRecon and NADR images.
• ACS:
  • Equivalence in performance to ACS on the uMR Omega (K220332).
  • Better performance than CS in SNR and resolution.
  • Maintenance of image qualities (contrast, uniformity) compared to fully sampled data (golden standard).
  • Significantly same structural measurements between ACS and fully sampled images.

Table of Inferred Acceptance Criteria and Reported Device Performance:

Breakdown of the Study as described in the 510(k) Summary:

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

• DeepRecon:

  • "The testing dataset for performance testing was collected independently from the training dataset, with separated subjects and during different time periods."
  • The exact sample size (number of subjects/cases) for the DeepRecon test set is not specified beyond being "independent."
  • Data Provenance: Implied to be from UIH MRI systems, likely from clinical or volunteer scans. No specific country of origin or retrospective/prospective nature is stated for the test datasets, but training data was "collected from 264 volunteers" and "165,837 cases" using "UIH MRI systems," which suggests internal company data, likely from China where the company is based. The testing data is independently collected.

• ACS:

  • "The training and test datasets are collected from 35 volunteers, including 24 males and 11 females, ages ranging from 18 to 60. The samples from these volunteers are distributed randomly into training and test datasets."
  • "The validation dataset is collected from 15 volunteers, including 10 males and 5 females, whose ages range from 18 to 60."
  • It specifies "35 volunteers" for training+test and "15 volunteers" for validation. The text states "testing dataset for performance testing was collected independently from the training dataset," which contradicts the "distributed randomly into training and test datasets" statement for the 35 volunteers. This requires clarification, but assuming the 35 volunteers contributed to both, the total number used for testing is not explicitly broken out from the 35. The "validation dataset" of 15 volunteers seems to be an additional independent test set.
  • Data Provenance: Implied to be from UIH MRI systems. No specific country of origin or retrospective/prospective nature is stated.

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

• Expert Review: "Sample clinical images for all clinical sequences and coils were reviewed by U.S. board-certified radiologist comparing the proposed device and predicate device."
  • Number of experts: Not specified, only "radiologist" (singular or plural not clear).
  • Qualifications: "U.S. board-certified radiologist." No mention of years of experience.
• Quantitative/Objective Ground Truth: For DeepRecon and ACS, ground truth was not established by experts but rather by specific technical methods:
  • DeepRecon: "multiple-averaged images with high-resolution and high SNR were collected as the ground-truth images."
  • ACS: "Fully-sampled k-space data were collected and transformed to image space as the ground-truth."

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

• The document implies a technical assessment for AI performance (SNR, resolution, structural measurements). For the "U.S. board-certified radiologist" review, no specific adjudication method (e.g., 2+1 consensus) is mentioned.

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 involving human readers and AI assistance is described. The performance evaluation focuses on the technical imaging characteristics and comparison to the predicate device or baseline (NADR/CS). The "U.S. board-certified radiologist" review seems to be a qualitative assessment of diagnostic image quality rather than a structured MRMC study with quantitative outcomes.

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

• Yes, the performance tests for DeepRecon and ACS are described as standalone evaluations of the algorithms' effects on image quality (SNR, resolution, contrast, uniformity, structural measurements) by comparing them to NA (No Algorithm) or baseline (CS) methods.

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

• DeepRecon: "multiple-averaged images with high-resolution and high SNR" (objective, technical ground truth representing optimal image quality).
• ACS: "Fully-sampled k-space data" (objective, technical ground truth representing complete data).
• For the qualitative review by the radiologist, the "diagnostic quality images" from the predicate device implicitly served as a reference or ground truth for comparison.

8. The sample size for the training set:

• DeepRecon: "264 volunteers" resulting in "165,837 cases."
• ACS: "35 volunteers" (randomly distributed into training and test datasets). The exact split for training is not specified but is part of this 35.

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

• DeepRecon: "the multiple-averaged images with high-resolution and high SNR were collected as the ground-truth images." "All data were manually quality controlled before included for training."
• ACS: "Fully-sampled k-space data were collected and transformed to image space as the ground-truth." "All data were manually quality controlled before included for training."

In summary, the provided document focuses on demonstrating technical equivalence and improved image characteristics for the AI components (DeepRecon, ACS) through non-clinical testing against technically derived ground truths, rather than a clinical multi-reader study with expert consensus ground truth or outcomes data. The human reader involvement seems to be a qualitative review of diagnostic image quality rather than a formal MRMC study.

Ask a specific question about this device

The uPMR 790 system combines magnetic resonance diagnostic devices (MRDD) and Position Tomography (PET) scanners that provide registration of high resolution physiologic and anatomic information, acquired simultaneously and iso-centrically. The combined system maintains independent functionality of the MR and PET devices, allowing for single modality MR and/or PET imaging. The MR is intended to produce sagittal, transverse, coronal, and oblique cross sectional images, and that display internal anatomical structure and/or function of the head, body and extremities. Contrast agents may be used depending on the region of interest of the scan. The PET provides distribution information of PET radiopharmaceuticals within the human body to assist healthcare providers in assessing the metabolic and physiological functions. The combined system utilizes the MR for radiation-free attenuation correction maps for PET studies. The system provides inherent anatomical reference for the fused PET and MR images due to precisely aligned MR and PET image coordinate systems.

The uPMR 790 system is a combined Magnetic Resonance Diagnostic Device (MRDD) and Positron Emission Tomography (PET) scanner. It consists of components such as PET detector, 3.0T superconducting magnet, RF power amplifier, RF coils, gradient power amplifier, gradient coils, patient table, spectrometer, computer, equipment cabinets, power distribution system, internal communication system, vital signal module, and software etc. The uPMR 790 system provides simultaneous acquisition of high resolution metabolic and anatomic information from PET and MR. PET detectors are integrated into the MR bore for simultaneous, precisely aligned whole body MR and PET acquisition. The PET subsystem supports Time of Flight (ToF). The system software is used for patient management, data management, scan control, image reconstruction, and image archive. The uPMR 790 system is designed to conform to NEMA and DICOM standards.

The provided text describes modifications to the uPMR 790 system, focusing on new software features and updated specifications. The key study related to an AI module is the "WFI based head MRAC" (Water Fat Imaging based PET head attenuation correction).

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

1. Table of Acceptance Criteria and Reported Device Performance

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

• Test set for WFI-based head MRAC (AI module): 27 subjects (17 male, 10 female; Age: 15-78).
  • Provenance: All subjects were Chinese.
  • Data Independence: Test data from Center 2 (n=12) was initially excluded from the training set and from completely different subjects. Data from Center 1 (n=10) was collected almost 2 years after the training data's imaging date, also with different subjects. This confirms the test data was completely independent from the training data (prospective data collection from geographically and temporally distinct sources relative to the training set). The document implies a retrospective collection of these test cases from these two centers for the purpose of this validation.

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

• This information is not explicitly stated in the provided text for the WFI-based head MRAC study. The ground truth method is described as "three-compartment segmentation from CT images of the same person," and "image intensity threshold" for further segmentation, implying an objective, image-based ground truth rather than expert consensus on a subjective scale.

4. Adjudication Method for the Test Set

• Adjudication method is not applicable and not mentioned, as the ground truth for the AI module's performance was established via CT segmentation and image intensity thresholds rather than human readers.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done

• No, a multi-reader multi-case (MRMC) comparative effectiveness study was not conducted or reported in the provided text. The study focuses on the standalone performance of the AI module for attenuation correction, compared against CT-based ground truth (CTAC). There is no mention of human readers assisting with the AI or a comparison of human readers with and without AI assistance.

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

• Yes, a standalone performance evaluation was done for the "WFI based head MRAC" AI module. The performance was measured by comparing the SUVmean error of the AI-generated attenuation correction maps against CTAC (CT-based attenuation correction), which is considered the reference standard.

7. The Type of Ground Truth Used

• For the WFI-based head MRAC AI module, the ground truth used was "three-compartment segmentation from CT images of the same person" and subsequent separation using "image intensity threshold." This can be classified as a radiological/imaging-based ground truth derived from an existing gold standard imaging modality (CT).

8. The Sample Size for the Training Set

• Training dataset: Not explicitly stated as a single number. The text provides demographic information: Gender (76 male, 54 female), Age (17-83), Ethnicity (Chinese). This implies a total of 130 subjects in the training set (76 + 54).

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

• The ground truth for the training set for the WFI-based head MRAC AI module was established using "pairs of WFI images and three-compartment segmentation from CT images of the same person." This means that for each subject in the training set, both WFI MR images and corresponding CT images were acquired, and the CT images were segmented into three compartments (air, cortical bone, mixed compartment) to serve as the ground truth for attenuation correction mapping. The AI module (Convolution Neural Network) was then trained to generate these segmentation masks from the WFI images.

Ask a specific question about this device

The SIGNA PET/MR system combines magnetic resonance diagnostic devices (MRDD) and Positron Emission Tomography (PET) scanners that provide registration and fusion of high resolution physiologic and anatomic information, acquired simultaneously and isocentrically. The combined system maintains independent functionality of the MR and PET devices, allowing for single modality MR and / or PET imaging.

These systems are intended to be utilized by appropriately trained health care professionals to aid in the detection, localization, and diagnosis of diseases and disorders. MR is intended to produce transverse, sagittal, coronal and oblique cross-sectional MR images, spectroscopic images and/or spectra, and displays the internal structure and/or function of the human body. Other physical parameters derived from the images and/or spectra may also be produced. Depending on the region of interest, approved contrast agents may be used, as described in their labeling. This system may also be used for imaging during interventional procedures when performed with MR compatible devices, such as MR safe biopsy needles.

PET images and measures the distribution of PET radiopharmaceuticals in humans to aid the physician in determining various metabolic (molecular) and physiologic functions within the human body for evaluation of diseases and disorders such as, but not limited to, cardiovascular disease, neurological disorders and cancer.

The combined system utilizes the MR for radiation correction maps for PET studies. The system provides inherent anatomical reference for the fused PET and MR images due to precisely aligned MR and PET image coordinate systems.

The GE SIGNA PET/MR system is a combined Magnetic Resonance Diagnostic Device (MRDD) and Positron Emission Tomography (PET) scanner. The system is designed for whole body oncology, neurology and cardiology examinations. The SIGNA PET/MR system provides simultaneous acquisition of high resolution metabolic and anatomic information from the two major components of each system (MR and PET). Additional components of the system include: a detachable patient table and both the acquisition and processing workstations with associated software.

The SIGNA PET/MR includes a 3.0T superconducting magnet, gradient coil and a transmit/receive whole body radiofrequency coil. The system includes patient adaptable RF shimming capabilities. The SIGNA PET detectors are integrated into the MR bore. This allows for simultaneous, precisely aligned whole body MR and PET acquisitions. The PET subsystem supports Time of Flight (ToF) coincidence detection. The SIGNA PET/MR software is used for patient management, data management, scan control, image reconstruction and image archival and evaluation. All images conform to DICOM imaging format requirements.

The modifications to this system include the MotionFree Brain software feature, which allows users the flexibility to correct patient head motion using the acquired PET data from the exam, without the need of external tracking devices, additional MR data, or other motion tracking data schemes.

The provided text describes the 510(k) summary for the GE SIGNA PET/MR system with a specific modification: the "MotionFree Brain" software feature. This feature aims to correct patient head motion in PET data without external tracking devices or additional MR data.

Here's an analysis of the acceptance criteria and the study proving the device meets them, 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. However, it states that "Performance testing on phantoms as part of non-clinical testing demonstrated MotionFree Brain achieved performance claims for Quantitation, Temporal Resolution, and Spatial Accuracy." For clinical testing, the acceptance was based on reader preference and confirmation that the feature could be "used safely and effectively in a clinical setting."

Implicit Acceptance Criteria and Reported Performance (derived from text):

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

• Test Set Sample Size: The document does not explicitly state the numerical sample size (number of cases or patients) used for the clinical test set. It mentions "randomly labeled cases."
• Data Provenance: The document does not specify the country of origin for the data. The study was described as a "retrospective blind study."

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

• Number of Experts: The document refers to "board-certified readers" (plural), indicating more than one expert. The exact number is not provided.
• Qualifications of Experts: The experts were "board-certified readers." No further details on years of experience or specific specializations (e.g., neuroradiologist) are given.

4. Adjudication Method for the Test Set

The document states: "The readers were blinded to feature use (e.g. whether feature was enabled or disabled), report case history, as well as to the assessments made by the other readers. The readers were asked to complete an assessment, including additional commentary, and report their preference on the pair of image series presented."

This describes a blinded read comparison where readers evaluated paired images (with and without the feature). The adjudication method primarily involved readers reporting their preference rather than a formal consensus or 2+1/3+1 type of adjudication. The text implies individual reader assessment and preference reporting, not a group adjudication to establish a "ground truth" through consensus for each case regarding motion correction per se.

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

• MRMC Study: An "external reader evaluation study was performed for MotionFree Brain. The retrospective blind study involved board-certified readers who were asked to evaluate randomly labeled cases that were reconstructed with and without MotionFree Brain." This structure implies an MRMC design, where multiple readers evaluate multiple cases under different conditions (with/without AI assistance).
• Effect Size of Human Readers Improvement: The document does not quantify the effect size (e.g., AUC, sensitivity, specificity improvement) of how much human readers improved with AI (MotionFree Brain) assistance vs. without. It focuses on reader preference and overall safety/effectiveness conclusion.

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

The document describes "Performance testing on phantoms" for "Quantitation, Temporal Resolution, and Spatial Accuracy." This can be considered a form of standalone performance evaluation for the algorithm's core functionality, as it assesses the algorithm's output (reconstructed image quality metrics) on controlled phantom data, independent of human interpretation for diagnostic tasks.

7. Type of Ground Truth Used

• For Phantom Testing: The ground truth was based on the known, controlled characteristics of the phantoms used, against which the "Quantitation, Temporal Resolution, and Spatial Accuracy" were measured.
• For Clinical/Reader Study: The "ground truth" was indirectly established through the comparative assessment and preference of experienced, board-certified readers. It's not a definitive clinical outcome (e.g., pathology, long-term follow-up) but rather a relative assessment of image quality and diagnostic confidence as perceived by experts when comparing images with and without motion correction. The study design focused on assessing the impact of the feature on the interpretability by clinicians, rather than establishing a true disease status for each patient.

8. Sample Size for the Training Set

The document does not provide any information about the training set size for the MotionFree Brain software feature. This information is typically proprietary and not included in a 510(k) summary unless specifically requested or deemed critical for demonstrating substantial equivalence. Given that the feature "derives head motion information from the PET data" and "measures and incorporates the rigid-body motion information into the PET reconstruction," it likely involves algorithmic processing rather than a purely deep learning approach requiring a massive labeled training set in the conventional sense, though validation or tuning would still involve data.

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

Since no information on the training set (or its existence as a distinct "training set" in a machine learning sense) is provided, there is no description of how its ground truth was established. If the algorithm is rule-based or model-based rather than solely data-driven (e.g., deep learning), a "training set" with ground truth in the supervised learning sense might not be applicable. The description ("MotionFree Brain derives head motion information from the PET data... measures and incorporates the rigid-body motion information into the PET reconstruction, correcting the position of each coincidence event") suggests a more deterministic or model-based approach to motion correction.

Ask a specific question about this device

The Siemens MR-PET system combines magnetic resonance diagnostic devices (MRDD) and Positron Emission Tomography (PET) scanners that provide registration and fusion of high resolution physiologic and anatomic information, acquired simultaneously and isocentrically. The combined sys tem maintains independent functionality of the MR and PET devices, allowing for single modality MR and / or PET imaging.

These systems are intended to be utilized by appropriately trained health care professionals to aid in the detection, localization, and diagnosis of diseases and disorders.

The MR is intended to produce transverse, sagittal, coronal and obligue crosssectional MR images, spectroscopic images and/or spectra, and displays the internal structure and/or function of the human body. Other physical parameters derived from the images and/or spectra may also be produced. Depending on the region of interest, approved contrast agents may be used, as described in their label ing. This system may also be used for imaging during interventional procedures when performed with MR compatible devices, such as MR safe biopsy needles.

The PET images and measures the distribution of PET radiopharmaceuticals in humans to aid the physician in determining various metabolic (molecular) and physiologic functions within the human body for evaluation of diseases and disorders such as, but not limited to, cardiovascular disease, neurological disorders and cancer.

The combined system utilizes the MR for radiation-free attenuation correction maps for PET studies. The system provides inherent anatomical reference for the fused PET and MR images due to precisely aligned MR and PET image coordinate systems.

The subject device, syngo MR E11P-AP01 system software for the Biograph mMR system, is a modification of the previously cleared predicate device Biograph mMR with syngo MR E11P system software (K163234, cleared February 28, 2017). The subject device has been modified to include the new mMR 32 Head coil for combined MR-PET usage as well as improvements to the system software syngo MR E11P.

• Improvement of the SPACE pulse sequence type with:
• CAIPIRINHA acquisition technique named as CAIPIRINHA o SPACE (migrated from previously cleared reference device K173592)
• Additional magnetization preparation mode "Non-sel. T2 prep. IR" o for brain imaging with improved dark-fluid contrast.
• Implementation of "CP-only" RF transmission mode based on the । requirements of 60601-2-33 Ed. 3.2:2015.

I am unable to conduct a detailed analysis of the acceptance criteria and study as the provided text is a 510(k) summary for a medical device (Biograph mMR with syngo MR E11P-AP01 system software) and does not contain the specific information required to complete your request.

Here's why and what's missing:

• No Explicit Acceptance Criteria: The document describes modifications to an existing device (software updates, new head coil). It states that nonclinical data "suggests that the feature bear an equivalent safety and performance profile as that of the predicate device." However, it does not define specific quantitative acceptance criteria for performance metrics (e.g., specific thresholds for image quality, signal-to-noise ratio, diagnostic accuracy, etc.) that the device must meet.
• No Detailed Study Results: While it mentions "nonclinical tests" were conducted and "clinical images are provided to support the migrated coil as well as the improved software features," it does not provide the results of these tests. It only makes a general statement that the device "performs as intended."
• Lack of Specifics for Your Questions: The text is a regulatory submission demonstrating substantial equivalence, not a detailed scientific study report. Therefore, it does not include:
  • A table of acceptance criteria and reported device performance.
  • Sample sizes for test sets, data provenance, or details about patient cohorts (e.g., country of origin, retrospective/prospective nature).
  • Number or qualifications of experts for ground truth establishment.
  • Adjudication methods.
  • Information on Multi-Reader Multi-Case (MRMC) comparative effectiveness studies or effect sizes.
  • Details of standalone algorithm performance.
  • Specific types of ground truth used (beyond general "clinical images").
  • Sample size or ground truth establishment methods for training sets.

In essence, the document confirms that testing was done to ensure the modified device is substantially equivalent to its predicate, but it does not delve into the granular details of those tests, their results, or the precise acceptance criteria used, which would be found in a more comprehensive study report or internal validation documentation.

Ask a specific question about this device

The uPMR 790 system combines magnetic resonance diagnostic devices (MRDD) and Positron Emission Tomography (PET) scanners that provide registration of high resolution physiologic and anatomic information, acquired simultaneously and iso-centrically. The combined system maintains independent functionality of the MR and PET devices, allowing for single modality MR and/or PET imaging. The MR is intended to produce sagittal, transverse, coronal, and oblique cross sectional images, and spectroscopic images, and that display internal anatomical structure and/ or function of the head, body and extremities. Contrast agents may be used depending on the region of interest of the scan. The PET provides distribution information of PET radiopharmaceuticals within the human body to assist healthcare providers in assessing the metabolic and physiological functions. The combined system utilizes the MR for radiation-free attenuation correction maps for PET studies. The system provides inherent anatomical reference for the fused PET and MR images due to precisely aligned MR and PET image coordinate systems.

The uPMR 790 system is a combined Magnetic Resonance Diagnostic Device (MRDD) and Positron Emission Tomography (PET) scanner. It consists of components such as PET detector, 3.0T superconducting magnet. RF power amplifier, RF coils, gradient power amplifier, gradient coils, patient table, spectrometer, computer, equipment cabinets, power distribution system, internal communication system, vital signal module, and software etc. The uPMR 790 system provides simultaneous acquisition of high resolution metabolic and anatomic information from PET and MR. PET detectors are integrated into the MR bore for simultaneous, precisely aligned whole body MR and PET acquisition. The PET subsystem supports Time of Flight (ToF). The system software is used for patient management, data management, scan control, image reconstruction, and image archive. The uPMR 790 system is designed to conform to NEMA and DICOM standards.

The provided text is a 510(k) summary for the uPMR 790, a combined Magnetic Resonance Diagnostic Device (MRDD) and Positron Emission Tomography (PET) scanner. This document describes the device, its intended use, and the modifications made from a previously cleared predicate device (K183014).

Based on the provided information, the 510(k) pertains to modifications of an existing device and does not describe a study involving detailed acceptance criteria and performance metrics for an AI/algorithm-driven device in the manner requested.

Here's a breakdown of why and what information is available:

1. Table of Acceptance Criteria and Reported Device Performance:

• Not Applicable. The document describes a device modification and its non-clinical testing. It does not present specific acceptance criteria in terms of accuracy, sensitivity, specificity, or other performance metrics for an AI or algorithm, nor does it report the device's performance against such criteria. The testing focused on demonstrating that the modified hardware (magnet, PET gantry, coils) maintains the expected functionality and safety of the device.

Reasons for Not Applicable:

• The 510(k) is for a combined MR/PET imaging system (hardware), not an AI/software diagnostic tool.
• The "performance data" section focuses on hardware-related tests (e.g., NEMA NU 2 for PET, Signal to Noise Ratio, Geometric Distortion, Magnetic Field Homogeneity for MR) to ensure the modified device functions similarly to its predicate. These are engineering specifications, not clinical performance metrics for an algorithm's diagnostic accuracy.

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

• Not Applicable for AI/algorithm performance. The document states, "No clinical testing was conducted on the proposed devices." The non-clinical testing involved hardware measurements and phantom studies, not a test set of patient data to evaluate an algorithm's diagnostic performance.
• Data Provenance: Not applicable as there was no clinical testing on data.

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

• Not Applicable. Since no clinical testing was conducted on patient data, there was no need for experts to establish ground truth for a test set.

4. Adjudication Method:

• Not Applicable. No clinical test set requiring adjudication was used.

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

• No. The document explicitly states: "No clinical testing was conducted on the proposed devices." Therefore, no MRMC study was performed.

6. Standalone Performance Study:

• No. The document explicitly states: "No clinical testing was conducted on the proposed devices." This implies no standalone (algorithm-only) performance testing on clinical data was performed either. The focus was on hardware modifications.

7. Type of Ground Truth Used:

• Not Applicable for AI/algorithm performance. As no clinical testing was performed, no ground truth from pathology, outcomes data, or expert consensus was used to evaluate an algorithm's performance. The "ground truth" in the context of the non-clinical testing would be the expected physical or electrical properties of the system, measured via phantoms and engineering tests.

8. Sample Size for the Training Set:

• Not Applicable. There is no mention of an AI/machine learning algorithm within the scope of this 510(k) that would require a training set. The device is a medical imaging hardware system.

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

• Not Applicable. As no training set for an AI/ML algorithm is mentioned, this information is not provided.

Summary of what the document does provide:

The document focuses on demonstrating substantial equivalence of a modified MR/PET imaging system (uPMR 790) to its predicate device (also uPMR 790, K183014) based on hardware changes. The modifications include:

• Introduction of a new magnet.
• Change in the PET gantry structure and RF shield.
• Introduction of six new receive coils and re-categorization of existing coils.

The non-clinical testing performed ensured that these hardware changes did not negatively impact the device's fundamental safety and performance characteristics, such as:

• Electrical safety (IEC 60601-1, -1-2, -2-33).
• PET performance measurements (NEMA NU 2).
• MR imaging quality (Signal to Noise Ratio, Geometric Distortion, Image Uniformity, Magnetic Field Homogeneity, Magnetic Field Decay).
• PET/MR Attenuation Correction.
• Acoustic Noise.
• Surface Heating of RF Receive Coils.

The conclusion is that the modified device remains substantially equivalent to the predicate, and introduces no new indications for use, technological characteristics, or potential hazards/safety risks.

Ask a specific question about this device

The uPMR 790 system combines magnetic resonance diagnostic devices (MRDD) and Positron Emission Tomography (PET) scanners that provide registration of high resolution physiologic and anatomic information, acquired simultaneously and iso-centrically. The combined system maintains independent functionality of the MR and PET devices, allowing for single modality MR and/or PET imaging. The MR is intended to produce sagittal, transverse, coronal, and oblique cross sectional images, and spectroscopic images, and that display internal anatomical structure and/ or function of the head, body and extremities. Contrast agents may be used depending on the region of interest of the scan. The PET provides distribution information of PET radiopharmaceuticals within the human body to assist healtheare providers in assessing the metabolic and physiological functions. The combined system utilizes the MR for radiation-free attenuation correction maps for PET studies. The system provides inherent anatomical reference for the fused PET and MR images due to precisely aligned MR and PET image coordinate systems.

The uPMR 790 system is a combined Magnetic Resonance Diagnostic Device (MRDD) and Positron Emission Tomography (PET) scanner. It consists of components such as PET detector, 3.0T superconducting magnet, RF power amplifier, RF coils, gradient power amplifier, gradient coils, patient table, spectrometer, computer, equipment cabinets, power distribution system, internal communication system, vital signal module, and software etc. The uPMR 790 system provides simultaneous acquisition of high resolution metabolic and anatomic information from PET and MR. PET detectors are integrated into the MR bore for simultaneous, precisely aligned whole body MR and PET acquisition. The PET subsystem supports Time of Flight (ToF). The system software is used for patient management, data management, scan control, image reconstruction, and image archive. The uPMR 790 system is designed to conform to NEMA and DICOM standards.

The provided text does not contain specific acceptance criteria or details of a study that directly proves the device meets such criteria in the way a clinical performance study would for an AI-powered diagnostic device.

Instead, the document is a 510(k) summary for a combined MRDD and PET scanner (uPMR 790), asserting substantial equivalence to a predicate device (GE Healthcare's SIGNA PET/MR, K142098). The focus is on demonstrating that the new device has similar technological characteristics and performs as expected, not on specific diagnostic performance metrics (e.g., sensitivity, specificity) against a clinical ground truth.

Here's what can be inferred from the provided text regarding acceptance and testing:

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

The document lists various non-clinical standards and tests that were conducted. These standards serve as "acceptance criteria" in the sense that the device must comply with them to be considered safe and effective. The "reported device performance" is a general statement that the device "performs as expected" and the "test results demonstrated that the device performs as expected and thus, it is substantially equivalent to the predicate devices." No specific quantitative performance metrics like sensitivity, specificity, or AUC are provided as acceptance criteria or results.

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

• Sample Size: Not specified for the "sample clinical images" provided.
• Data Provenance: Not specified (e.g., country of origin, retrospective/prospective). The text only mentions "Sample clinical images were provided."

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

This information is not provided. The phrase "diagnostic quality images" implies expert evaluation, but the number or qualifications of experts are not stated.

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

Not specified.

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:

This is not an AI-powered diagnostic device, but rather a combined imaging system (PET/MR). Therefore, an MRMC study comparing human readers with and without AI assistance is not applicable and was not conducted. The study is about the performance of the imaging device itself.

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

Not applicable, as this is an imaging device, not an algorithm. The "standalone" performance here refers to the device's ability to produce images according to technical standards.

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

For the clinical images, the "ground truth" seems to be implied by the assessment of "diagnostic quality images." This would likely involve expert interpretation, but explicit details (like expert consensus, pathology, or outcomes) are not given. For the non-clinical tests, the ground truth is against specific engineering and medical device standards (e.g., NEMA NU 2-2012 for PET performance, NEMA MS series for MR performance).

8. The sample size for the training set:

Not applicable. This device is not an AI algorithm that requires a training set. It is a hardware imaging system.

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

Not applicable, as this device is not an AI algorithm.

Ask a specific question about this device

The Siemens MR-PET system combines magnetic resonance diagnostic devices (MRDD) and Positron Emission Tomography (PET) scanners that provide registration and fusion of high resolution physiologic and anatomic information, acquired simultaneously and isocentrically. The combined system maintains independent functionality of the MR and PET devices, allowing for single modality MR and / or PET imaging.

These systems are intended to be utilized by appropriately trained health care professionals to aid in the detection, localization, and diagnosis of diseases and disorders.

The MR is intended to produce transverse, sagittal, coronal and oblique crosssectional MR images, spectroscopic images and/or spectra, and displays the internal structure and/or function of the human body. Other physical parameters derived from the images and/or spectra may also be produced. Depending on the region of interest, approved contrast agents may be used, as described in their labeling. This system may also be used for imaging during interventional procedures wen performed with MR compatible devices, such as MR safe biopsy needles.

The PET images and measures the distribution of PET radiopharmaceuticals in humans to aid the physician in determining various metabolic (molecular) and physiologic functions within the human body for evaluation of diseases and disorders such as, but not limited to, cardiovascular disease, neurological disorders and cancer.

The combined system utilizes the MR for radiation correction maps for PET studies. The system provides inherent anatomical reference for the fissed PET and MR images due to precisely aligned MR and PET image coordinate systems.

The new mMR Angio Transfer Option is being introduced for the Biograph mMR system.

The new option is intended to provide a patient transfer from the SIEMENS Artis Q and Artis Q.zen (K123529) or Artis zee/zeego SW VC21 (K141574) System to the Biograph mMR and vice versa.

To achieve this functionality a Transferboard Artis (further named as Transferboard) will be used where the patient is located and transferred. This Transferboard can be adapted on the standard table of the Artis Q and Artis Q.zen (K123529) or Artis zee/zeego SW VC21 (K141574) System. The standard table is identical for all models. By swiveling the Artis Q. Artis Q.zen or Artis zee /zeego table (standard function) the Transferboard will be positioned in front of the Biograph mMR. Via the Guiding Slide Way the Transferboard is pushed manually on the Table Top of the Biograph mMR.

The Guiding Slide Way is also included in the option and is installed on the Table Top of the Biograph mMR instead of a regular patient cushion.

The Transferboard is also used to move the patient into the bore of the Biograph mMR for further diagnostic imaging.

The basic device and its functionality remain unchanged except for the following modifications:

• . Coil Adapter Cover (CAC): The Coil Adapter Cover will replace the standard mMR coil adapter cover on the foot end of the mMR tabletop to enable the overtraveling of the Transferboard (TFB).
• Guiding Slide Wav (GSW): A Guiding Slide Way (GSW) will be adapted on the ● existing Biograph mMR tabletop. This is a foldable option and can be removed for diagnostic mMR examination in case the transfer option is not needed.
• Transferboard (TFB): The Transferboard (TFB) is intended to transfer the ● patient. The patient remains on this board during the whole intraoperative procedure.
• Patient Cushion (LGH): The Patient Cushion is laid on the Transferboard (TFB) for comfortable reclining.
• Fixation Belts: The Fixation Belts are used for preventing the patient to fall of ● the Transferboard and Patient Cushion during transport, surgery and imaging,
• Transfer Support Cart (TSC): The Transfer Support Cart is part of the option. ● It ensures that both tables have the same height and that there are no vibrations during transfer due to load changes on the patient tables

The new mMR Angio Transfer Option for the Biograph mMR system requires the most recent Device Software, syngo MR E11P software cleared via 510(k) on February 28, 2017 (K163234).

This document describes a 510(k) premarket notification for the "Biograph mMR with mMR Angio Transfer Option." This submission primarily addresses changes related to a patient transfer system, not a software algorithm for disease detection or diagnosis. Therefore, much of the information typically requested for AI/ML device studies (such as diagnostic performance metrics, sample sizes for training/test sets, ground truth establishment, expert adjudication, or MRMC studies) is not applicable or present in this document.

The acceptance criteria and "study" mentioned here relate to the safety and performance of the mechanical and electrical modifications that enable patient transfer between imaging systems.

Here's the breakdown of the available information:

1. Table of Acceptance Criteria and Reported Device Performance

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

• Test Set Sample Size: Not applicable. This submission doesn't involve a test set of medical images or patient data for diagnostic performance evaluation. The "testing" refers to non-clinical performance evaluations of the mechanical and electrical components of the transfer option.
• Data Provenance: Not applicable. The "data" comes from engineering tests and evaluations of the new mechanical components and their integration with the existing Biograph mMR system, rather than patient data.

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

• Not applicable. There is no diagnostic "ground truth" or expert review of image data described, as this is not a diagnostic AI/ML device submission. The verification and validation were engineering-focused.

4. Adjudication method for the test set

• Not applicable for the reasons stated above.

5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance.

• No, an MRMC comparative effectiveness study was not done. This device is an imaging system enhancement for patient transfer, not an AI diagnostic tool.

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

• Not applicable. This device is not an algorithm for standalone performance evaluation.

7. The type of ground truth used

• Not applicable. The "ground truth" for the non-clinical performance testing would be the engineering specifications and safety requirements defined by the referenced standards (e.g., proper mechanical function, electrical safety thresholds, risk mitigation effectiveness).

8. The sample size for the training set

• Not applicable. There is no machine learning component or training set involved in this submission.

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

• Not applicable. There is no machine learning component or training set involved in this submission.

In summary: This FDA filing (K172531) is for a modification to an existing medical imaging system (Biograph mMR) that introduces a new patient transfer option. The "study" and "acceptance criteria" discussed are related to the engineering and safety performance of these physical modifications, ensuring they meet recognized medical device standards (e.g., IEC, ISO) and do not negatively impact the safety or effectiveness of the original device. This is a typical submission for mechanical or electrical modifications to existing hardware, not for a new AI/ML diagnostic software as the questions largely imply.

Ask a specific question about this device

The Siemens MR-PET system combines magnetic resonance diagnostic devices (MRDD) and Positron Emission Tomography (PET) scanners that provide registration and fusion of high resolution physiologic and anatomic information. acquired simultaneously and isocentrically. The combined system maintains independent functionality of the MR and PET devices, allowing for single modality MR and / or PET imaging.

These systems are intended to be utilized by appropriately trained health care professionals to aid in the detection, localization, and diagnosis of diseases and disorders.

The MR is intended to produce transverse, sagittal, coronal and oblique crossectional MR images, spectroscopic inages and/or spectra, and displays the internal structure and/or function of the human body. Other physical parameters derived from the images and or spectra may also be produced. Depending on the region of interest, approved contrast agents may be used, as described in their labeling. This system may also be used for imaging during interventional procedures when performed with MR compatible devices, such as MR safe biopsy needles.

The PET images and measures the distribution of PET radiopharmaceuticals in humans to aid the physician in determining various metabolic (molecular) and physiologic functions within the human body for evaluation of diseases and disorders such as, but not limited to, cardiovascular disease, neurological disorders and cancer.

The combined system utilizes the MR for radiation-free attenuation correction maps for PET studies. The system provides inherent anatomical reference for the fised PET and MR images due to precisely aligned MR and PET image coordinate systems.

The subject device, syngo MR E11P system software, is being introduced for the Biograph mMR system.

The syngo MR E11P SW includes new sequences, new features and minor modifications of already existing features. A high level summary of the new sequences and features is included below.

Migrated sequences and features from the previously cleared secondary predicate devices MAGNETOM Verio with syngo MR D13A and Siemens E-line Software with MAGNETOM Skyra with syngo MR E11C (K153343) are not described separately as these are commercially available and no changes are introduced for this system.

Improvement in Attenuation Correction
Atlas-based bones in u-map generation
The bone attenuation map is computed based on a reqular 4-compartment (air, lung, fat, water) segmentation from a Dixon sequence. As improvement, the bone information is added to these u-maps with a model-based bone segmentation algorithm using continuous linear attenuation coefficients (LACs) for bone to represent the variation in cortical bone density in different anatomical areas.

The model consists of the most relevant bones in the body torso in terms of overall attenuation. It consists of the skull, spine, pelvis and femur bone as individual components.

MR based FoV extension for attenuation correction - (HUGE)
In this SW version syngo MR E11P the attenuation map can be improved by using an optional MR-based FoV extension technique. This technique requires an additional MR measurement optimized for distortion reduced acquisition of the patient's arms resting along the body at the edge of the FoV.

New and Modified Features
Multimodal (Elastic) Motion Correction (BodyCOMPASS)
Elastic motion correction is introduced to reduce the effect of blur induced by respiratory motion during a PET acquisition. As a basic principle, periodic motion information is collected by means of the MR as a 4D image series and used for PET to

• . bin the PET counts into separate respiratory states
• provide a mapping for each spatial position and each respiratory state to a . reference state, which can be used in the PET reconstruction

Hence, the resulting PET image combines the advantages of a gated PET image with reduced motion blur while preserving the signal-to-noise ratio of static non-gated reconstruction.

Improvement in DIXON fat water separation
In this SW version syngo MR E11P the DIXON reconstruction technique (fat/water separation) is improved. The improved algorithm is based on global optimization and thus minimizes the probability of local fat/water swaps where part of water image is wrongly assigned to fat image and/or vice versa.

Dot Cockpit (DotGO), including PET Workflow
The previously cleared DotGO with the Dot Cockpit and the MR only Dot Engines is now available on the Biograph mMR with syngo MR E11P. The configuration of PET workflows is now integrated into the Dot Cockpit for higher productivity.

This modification increases the robustness and usability for the clinical workflow with the new PET Planning Group. PET Planning Step and special reduced MR Parameter cards while still offering the full parameter access with detail views, PET and AC specific steps with their parameter cards.

Improved MR PET Workflow
With the software syngo MR E11P a set of protocols are included in order to run a clinical whole body workflow with 5 beds, AC, T1-, T2-, DWI-contrast, adjustments and SAR pauses in 45 minutes.

In this workflow the AC protocol is acquired in high resolution (1.3 mm * 1.3mm in plane) using CAIPIRINHA acceleration. Alternatively, an AC protocol in conventional resolution (2.6 mm * 2.6 mm in plane) using CAIPIRINHA acceleration is available in order to reduce the acquisition time for AC measurement in case T1-contrast is not requested from AC scan.

Other Software Improvements
NEMA NU 2:2012
As it is possible that routine NEMA testing may be required to retain ACR accreditation, Siemens has developed an optional software package which enables a Biograph mMR system user to quantify image quality for certain performances according to the most recent available NEMA standards.

Improvements in Retro Recon Task Card
In the RetroRecon Task Card of the Biograph mMR with syngo MR E11P, an additional identifier in the list of the parameter Attenuation Correction indicates gated u-Maps.

Furthermore a Tooltip for the Attenuation Correction parameter explains the identifier.

For respiratory gating a new Respiratory Curve Display shows the recorded cushion signal as well as the specified gates for some gating types.

Third Party Interface for AC
An Interface functionality is added to the synqo MR E11P software to import attenuation maps of third party components for hardware attenuation correction.

Other Modifications
Front Cover Panel Refresh for Biograph mMR
The Biograph mMR with syngo MR E11P will receive new system covers. The graphic design of the cover has been changed to give the systems an updated and more modern look to highlight the introduction of a new software version.

MaRS - technology for Biograph mMR
The modified control system of the Biograph mMR integrates the functions of the AMC (Advanced Measurement Control) and MRIR (MR Image Reconstructor) into one computer called MaRS (Measurement and Reconstruction System).

The MaRS system performs sequence control and image reconstruction without additional MRIR. The introduction of the MaRS was part of the secondary predicate device MAGNETOM Verio with syngo MR D13A (K121434). This is now updated to new computer hardware with this submission.

Physiological Monitoring Unit (PMU)
The Physiological Measurement Unit (PMU) was modified to improve the accuracy of triggers on the respiration signal. The PMU provides ECG, respiration and peripheral pulse as well as external trigger input to control of the MR imaging sequences for synchronization.

Syngo MR Software Features
Other features were included unchanged from the secondary predicate devices (K121434 and K153343). These features expand the Biograph mMR's MR scanning capabilities and update the feature set to be more similar to currently released Siemens MR software.

Acceptance Criteria and Device Performance for Biograph mMR with syngo MR E11P system software (K163234)

Based on the provided FDA 510(k) summary, the acceptance criteria and supporting studies focus on demonstrating that the new syngo MR E11P software for the Biograph mMR system maintains the safety and effectiveness of the predicate device while introducing improvements and new features. The document highlights the substantial equivalence argument, rather than providing explicit numeric acceptance criteria and performance tables for specific clinical tasks. However, we can infer the performance goals and the studies conducted to support them.

1. Table of Acceptance Criteria and Reported Device Performance

As explicit numeric acceptance criteria and a detailed performance table are not provided in the 510(k) summary, the table below represents the implied acceptance criteria (based on the device's intended use and the nature of the modifications) and the general results reported for demonstrating substantial equivalence.

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

• Test Set Sample Size: The document does not explicitly state the numerical sample size (e.g., number of patients, cases) for the clinical images used in the comparison studies. It mentions "Sample clinical images were taken for particular new and modified sequences" and "Additionally clinical images were provided to support the substantial equivalence for the new software features of the subject device." The quantitative comparison studies also imply a dataset, but the size is not specified.
• Data Provenance: The provenance of the data (country of origin, retrospective/prospective) is not explicitly detailed. The manufacturer is Siemens Healthcare GmbH based in Erlangen, Germany, and Siemens Medical Solutions USA, Inc. is the establishment in the USA. It is common for such validation studies to involve data from internal research or collaborating institutions, but the document does not specify. The nature of "clinical images" and "quantitative comparison studies" suggests real patient data, likely retrospective or a mix, but this is not confirmed.

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

This information is not provided in the summary. While clinical images and quantitative comparisons were performed, the method of establishing ground truth and the involvement and qualifications of experts for defining "ground truth" are not described. It's likely that in the context of imaging system performance, "ground truth" for image quality and diagnostic accuracy would implicitly rely on expert assessment, but the details are omitted.

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

This information is not provided in the summary. Without details on expert involvement in ground truth establishment, no adjudication method can be inferred.

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:

A multi-reader multi-case (MRMC) comparative effectiveness study focusing on the improvement of human readers with AI assistance was not explicitly described in this 510(k) summary. The document describes improvements to the imaging system's software components (e.g., attenuation correction, motion correction, fat/water separation) that likely improve image quality and potentially diagnostic accuracy, but it doesn't quantify reader performance improvement with "AI assistance" in the sense of a decision support system. The listed studies are more focused on the technical performance and quantitative accuracy of the imaging system's outputs.

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

Yes, a form of standalone performance assessment was conducted for many of the technical improvements. The "Nonclinical Tests" section details:

• "Image quality assessments of all new/modified sequences and algorithms, were completed."
• The "Clinical Tests" section describes "Quantitative comparison study of attenuation maps of CT-based AC and MR-based AC method..." and "Quantitative comparison study of SUV estimation for MR-based AC methods..." These are direct technical evaluations of the algorithm's output (image quality, quantitative accuracy) independent of a human reader's diagnostic performance.

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

The type of ground truth used varies based on the specific study:

• For attenuation correction and SUV estimation studies: The ground truth appears to be established by comparison to established methods, specifically "reference CT AC." This implies that CT attenuation maps are considered the gold standard for comparison in these contexts.
• For general image quality and new feature performance: The "ground truth" is likely based on visual assessment by experts (implied, though not stated) combined with quantitative metrics relevant to image quality (e.g., minimizing motion blur, reducing fat/water swaps) derived from predefined technical standards or expected outcomes.

8. The sample size for the training set:

This information is not provided in the summary. The document describes modifications and improvements to existing software components and introduces new sequences and features. While these often involve internal development and testing cycles that might use various datasets, specific training set sizes for machine learning components (if any, beyond the "atlas-based bones" model) are not detailed.

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

This information is not provided in the summary. Given the nature of the improvements (e.g., atlas-based bone models, global optimization for Dixon), it's likely that internal reference datasets and expert knowledge were used, but the specifics of their ground truth establishment are not disclosed. For the "atlas-based bones in u-map generation," the "model consists of the most relevant bones in the body torso" which implies a pre-defined anatomical model or a training process that derived this model from a dataset with defined bone attenuation properties. However, details are absent.

Ask a specific question about this device

The SIGNA PET/MR system combines magnetic resonance diagnostic devices (MRDD) and Positron Emission Tomography (PET) scanners that provide registration and fusion of high resolution physiologic and anatomic information, acquired simultaneously and isocentrically. The combined system maintains independent functionality of the MR and PET devices, allowing for single modality MR and / or PET imaging. These systems are intended to be utilized by appropriately trained health care professionals to aid in the detection, localization, and diagnosis of diseases and disorders. MR is intended to produce transverse, sagittal, coronal and oblique cross-sectional MR images, spectroscopic images and/ or spectra, and displays the internal structure and/or function of the human body. Other physical parameters derived from the images and/or spectra may also be produced. Depending on the region of interest, approved contrast agents may be used, as described in their labeling. This system may also be used for imaging during interventional procedures when performed with MR compatible devices, such as MR safe biopsy needles. PET images and measures the distribution of PET radiopharmaceuticals in humans to aid the physician in determining various metabolic (molecular) and physiologic functions within the human body for evaluation of diseases and disorders such as, but not limited to, cardiovascular disease, neurological disorders and cancer. The combined system utilizes the MR for radiation-free attenuation correction maps for PET studies. The system provides inherent anatomical reference for the fused PET and MR images due to precisely aligned MR and PET image coordinate systems.

The GE SIGNA PET/MR system is a combined Magnetic Resonance Diagnostic Device (MRDD) and Positron Emission Tomography (PET) scanner. The system is designed for whole body oncology, neurology and cardiology examinations. The SIGNA PET/MR system provides simultaneous acquisition of high-resolution metabolic and anatomic information from the two major components of each system (MR and PET). Additional components of the system include: a patient table and both the acquisition and processing workstations with associated software. The SIGNA PET/MR includes a 3.0T superconducting magnet, gradient coil and body coil. The system includes dual drive capabilities. The SIGNA PET detectors are integrated into the MR bore. This allows for simultaneous, precisely aligned whole body MR and PET acquisition. The PET subsystem supports Time of Flight (ToF). The SIGNA PET/MR software is used for patient management, data management, scan control, image reconstruction and image archival and evaluation. All images conform to DICOM imaging format requirements.

Here's an analysis of the provided text to extract the requested information regarding acceptance criteria and the study proving device performance for the SIGNA PET/MR system (K163619).

Important Note: The provided document is a 510(k) premarket notification summary for a modification to an existing device (SIGNA PET/MR, K142098). Therefore, the information primarily focuses on demonstrating substantial equivalence of the modified features (MR Attenuation Correction) rather than a complete de novo study of the entire PET/MR system. As such, some specific details typically found in studies for novel devices, such as comprehensive stand-alone performance or MRMC studies for improved human reading, are not explicitly provided or may not be applicable in the same way.

1. Table of Acceptance Criteria and Reported Device Performance

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

• Test Set Sample Size: The document mentions "Sample clinical images" were used for qualitative and quantitative comparisons. However, a specific numerical sample size for this test set is not explicitly stated in the provided text.
• Data Provenance: Not explicitly stated. The document refers to "clinical images," but does not specify the country of origin or whether the data was retrospective or prospective. Given it's a 510(k) for a medical device company, it's generally assumed to be clinical data relevant to human use, potentially from multiple sites.

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

• Not explicitly stated. The document does not detail how ground truth was established for the "sample clinical images" used for comparison, nor does it mention the number or qualifications of experts involved in this specific aspect of the testing for the modified features.

4. Adjudication Method for the Test Set

• Not explicitly stated. The document focuses on demonstrating compliance with quality assurance measures and comparative testing. It does not mention an adjudication method for a test set in the context of expert review or consensus.

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

• No, an MRMC comparative effectiveness study is not mentioned. The submission describes "clinical tests" involving "sample clinical images, qualitative and quantitative comparisons compared to the predicate MR Attenuation Correction technology." This implies a comparison against the existing technology, but not necessarily an MRMC study with human readers assessing improvement with human-AI assistance. The focus is on the performance of the attenuation correction modification itself.

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

• Yes, implicitly. The reported performance relates to the "software-only features" and their engineering verification and validation ("Testing on unit level," "Integration testing," "Safety testing," "Simulated use testing"). The "qualitative and quantitative comparisons" of the modified MR Attenuation Correction also refer to the algorithmic performance in generating these corrections, independent of a human interpreting the final images. The comparative aspects focus on the technical output of the algorithm.

7. The type of ground truth used

• Regarding the "clinical tests" for the modified MR Attenuation Correction, the "ground truth" seems to be established through comparison to the predicate device's MR Attenuation Correction technology. The document states, "Sample clinical images, qualitative and quantitative comparisons compared to the predicate MR Attenuation Correction technology are included in this submission to support substantial equivalence of the modified features." This indicates the predicate's performance serves as the reference point for evaluating the new system's attenuation correction. It does not explicitly mention pathology or direct outcomes data being used as ground truth for this specific software modification.

8. The sample size for the training set

• Not explicitly stated. The document describes a software modification to an existing device. It discusses the development process using "Risk Analysis," "Requirements Reviews," and "Design Reviews" and then verification and validation testing. There is no mention of a separate "training set" in the context of machine learning model development. The focus is on demonstrating that the modified software behaves as intended and is substantially equivalent to the predicate.

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

• N/A. As no explicit "training set" for a machine learning model is mentioned, there is no information on how its ground truth was established. The document describes a development and testing process for software features, not the training of an AI model in the typical sense with labeled data.

Ask a specific question about this device

The SIGNA PET/MR system combines magnetic resonance diagnostic devices (MRDD) and Positron Emission Tomography (PET) scanners that provide registration and fusion of high resolution physiologic and anatomic information, acquired simultaneously and isocentrically. The combined system maintains independent functionality of the MR and PET devices, allowing for single modality MR and / or PET imaging. These systems are intended to be utilized by appropriately trained health care professionals to aid in the detection, and diagnosis of diseases and disorders. MR is intended to produce transverse, sagittal, coronal and oblique cross-sectional MR images and/ or spectra, and displays the internal struction of the human body. Other physical parameters derived from the images and/or spectra may also be produced. Depending on the region of interest, approved contrast agents may be used, as described in their labeling. This system may also be used for imaging during interventional procedures when performed with MR compatible devices, such as MR safe biopsy needles. PET images and measures the distribution of PET radiopharmaceuticals in humans to aid the physician in determining various metabolic (molecular) and physiologic functions within the human body for evaluation of diseases and disorders such as, but not limited to, cardiovascular disease, neurological disorders and cancer.

The combined system utilizes the MR for radiation correction maps for PET studies. The system provides inherent anatomical reference for the fused PET and MR images due to precisely aligned MR and PET image coordinate systems.

The GE SIGNA PET/MR system is a combined Magnetic Resonance Diagnostic Device (MRDD) and Positron Emission Tomography (PET) scanner. The system is designed for whole body oncology, neurology and cardiology examinations. The SIGNA PET/MR system provides simultaneous acquisition of high-resolution metabolic and anatomic information from the two major components of each system (MR and PET). Additional components of the system include: a patient table and both the acquisition and processing workstations with associated software.

The SIGNA PET/MR includes a 3.0T superconducting magnet, gradient coil, body coil and local surface RF coils based on those of the reference device Discovery MR750w 3.0T. The system includes dual drive capabilities. The SIGNA PET detectors have been modified from those of the reference device, the Discovery PET/CT 690, to allow them to be integrated into the bore of the MR. This allows for simultaneous, precisely aligned whole body MR and PET acquisition. Similar to Discovery PET/CT D690, PET supports Time of Flight (ToF). SIGNA PET/MR software is based on a combination of Discovery MR750w with Discovery PET/CT 690 software. It is used for patient management, data management, scan control, image reconstruction and image archival and evaluation. All images conform to DICOM imaging format requirements.

The SIGNA PET/MR system and surface coil suite, the subject of this application, is substantially equivalent to the commercially available devices above with modifications made to integrate the two modalities together into a whole-body system.

Here's an analysis of the provided text regarding the acceptance criteria and study for the SIGNA PET/MR device:

1. Table of Acceptance Criteria and Reported Device Performance:

The document is a 510(k) summary, which focuses on demonstrating substantial equivalence to a predicate device rather than presenting detailed acceptance criteria and performance data from a clinical trial. Therefore, specific numerical acceptance criteria and corresponding device performance metrics are not explicitly stated in this document.

However, based on the non-clinical and clinical tests mentioned, we can infer the intent of the acceptance criteria. The performance is reported in a qualitative manner, affirming compliance and confirming image quality.

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

• Test Set Sample Size: The document only states "Sample images from the SIGNA PET/MR were collected from multiple sites." It does not specify a numerical sample size for the test set used in clinical evaluation.
• Data Provenance: The data was collected "from multiple sites". The country of origin is not specified. Given it's a submission to the US FDA by a company based in the US (Waukesha, WI), it is highly probable that at least some, if not all, of the sites were in the USA, but this is not explicitly stated. The study was likely retrospective for the collected "sample images" to confirm image quality, though this is also not directly stated.

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

• Number of Experts: This information is not provided in the document.
• Qualifications of Experts: This information is not provided in the document. It only mentions that the system is intended to be used by "appropriately trained health care professionals."

4. Adjudication Method for the Test Set:

• The document does not specify any adjudication method. It notes that "sample images... were collected... to confirm simultaneous diagnostic image quality," implying some form of expert review, but details on how disagreements or consensus were reached are absent.

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

• No, an MRMC comparative effectiveness study is not mentioned. The document describes clinical evaluation to "confirm simultaneous diagnostic image quality," which is a verification of functionality, not a comparative study of human reader performance with or without AI assistance. The device itself is a diagnostic imaging system, not an AI-assisted diagnostic tool that augments human interpretation.

6. If a Standalone Study (Algorithm Only Without Human-in-the-Loop Performance) was done:

• Yes, in spirit, the clinical evaluation focused on the standalone performance of the device (SIGNA PET/MR system) in producing diagnostic image quality. The "algorithm" here refers to the entire imaging system's capability to generate images, not a separate AI algorithm that interprets those images. The statement "Sample images... were collected... to confirm simultaneous diagnostic image quality" implies an evaluation of the system's output directly.

7. The Type of Ground Truth Used:

• The document states "to confirm simultaneous diagnostic image quality." This suggests the ground truth was likely expert consensus or qualitative assessment by healthcare professionals evaluating the diagnostic utility and clarity of the acquired images. It is not pathology, outcomes data, or a quantifiable "true" diagnostic outcome in the strict sense for individual cases.

8. The Sample Size for the Training Set:

• This information is not applicable and not provided. The SIGNA PET/MR system is a medical imaging hardware device combined with imaging software, not an AI/ML algorithm that is "trained" on a dataset in the conventional sense of machine learning for classification or prediction. Its software functions (patient management, data management, scan control, image reconstruction, archival, and evaluation) are based on established engineering principles and prior device software, not iterative learning from a large training dataset.

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

• This information is not applicable and not provided for the reasons stated in point 8.

Ask a specific question about this device