Search Results

The uMI Panorama is a diagnostic imaging system that combines two existing imaging modalities PET and CT. The quantitative distribution information of PET radiopharmaceuticals within the patient body measured by PET can assist healthcare providers in assessing metabolic and physiological functions. CT provides diagnostic tomographic anatomical information as well as photon attenuation information for the scanned region. The accurate registration and fusion of PET and CT images provides anatomical reference for the findings in the PET images.

This system is intended to be operated by qualified healthcare professionals to assist in the detection, localization, diagnosis, staging, restaging, treatment planning and treatment response evaluation for diseases, inflammation, infection and disorders in, but not limited to oncology, cardiology and neurology. The system maintains independent functionality of the CT device, allowing for single modality CT diagnostic imaging.

This CT system can be used for low dose CT lung cancer screening for the early detection of lung nodules that may represent cancer. The screening must be performed within the established inclusion criteria of programs / protocols that have been approved and published by either a governmental body or professional medical society.

The proposed device uMI Panorama GS combines a 148 cm axial field of view (FOV) PET and multi-slice CT system to provide high quality functional and anatomical images, fast PET/CT imaging and better patient experience. The system includes PET gantry, CT gantry, patient table, power supply cabinet, console and reconstruction system, chiller, vital signal module.

The uMI Panorama GS has been previously cleared by FDA via K231572. The mainly modifications performed on the uMI Panorama GS (K231572) in this submission are due to the algorithm update of AIIR, the addition of HYPER Iterative, uExcel DPR, RMC, AIEFOV, Motion Management, CT-less AC, uKinetics, Retrospective Respiratory-gated Scan, uExcel Unity and uExcel iQC.

The provided text describes the performance data for the uMI Panorama device, focusing on the AIEFOV algorithm. Here's a breakdown based on your request:

Acceptance Criteria and Reported Device Performance for AIEFOV Algorithm

Study Details Proving Device Meets Acceptance Criteria:

1. Sample Size and Data Provenance for Test Set:

   • Test Set Sample Size: 9303 images from 13 patients.
   • Data Provenance: Not explicitly stated regarding country of origin, but described as "clinical images" scanned in uMI Panorama GS. The study appears retrospective or a controlled prospective study for validation.
   • Patient Characteristics (N=13):
     • Age: 62 ± 14 years (range: 35-79)
     • Sex: 7 male, 6 female
     • BMI: 25.0 ± 3.5 kg/m² (range: 21.2-31.4)
     • Injected activity: 0.10 ± 0.01 mCi/kg (range: 0.04-0.11)

2. Number of Experts and Qualifications for Ground Truth for Test Set:

   • Number of Experts: Two (2)
   • Qualifications: "American Board qualified clinical experts"

3. Adjudication Method for Test Set:

   • The experts performed a "blind comparison" regarding image Artifacts, homogeneity of same tissue, and diagnostic confidence in PET images. Details of how disagreements were resolved (e.g., 2+1, 3+1, or if consensus was required) are not specified.

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

   • Not explicitly stated as a formal MRMC study comparing human readers with AI vs. without AI assistance. The clinical evaluation involved two experts reviewing images generated with AIEFOV for diagnostic confidence, rather than a comparative trial measuring improvement in human reader performance aided by AI. Therefore, an effect size of human reader improvement with AI vs. without AI assistance is not provided.

5. Standalone (Algorithm Only) Performance:

   • Yes, the "Bench tests" portion of the performance evaluation appears to assess the algorithm's performance directly on quantitative metrics (CT value, SUV accuracy and uniformity) using phantoms and patient studies in different truncation situations. The clinical evaluation also assessed the quality of images produced by the algorithm, implying a standalone assessment of its output for diagnostic confidence.

6. Type of Ground Truth Used:

   • For bench tests: Quantitative measurements from phantom scans and potentially patient studies where the "true" CT values and SUV could be established or inferred relative to known conditions (e.g., non-truncated scans serving as reference).
   • For clinical evaluation: Expert consensus/assessment by "American Board qualified clinical experts" regarding subjective image quality metrics (artifacts, homogeneity, diagnostic confidence).

7. Sample Size for Training Set:

   • The training data for the AIEFOV algorithm contained 506,476 images.

8. How Ground Truth for Training Set was Established:

   • "All data were manually quality controlled before included for training." This suggests a process of human review and verification to ensure the accuracy and suitability of the training images. Further details on the specific criteria or expert involvement for this manual QC are not provided.
   • It is explicitly stated that "The training dataset used for the training of AIEFOV algorithm was independent of the dataset used to test the algorithm."

Ask a specific question about this device

The uMI Panvivo is a PET/CT system designed for providing anatomical and functional images. The PET provides the distribution of specific radiopharmaceuticals. CT provides diagnostic tomographic anatomical information as well as photon attenuation information for the scanned region. PET and CT scans can be performed separately. The system is intended for assessing metabolic (molecular) and physiologic functions in various parts of the body. When used with radiopharmaceuticals approved by the requlatory authority in the country of use, the uMI Panvivo system generates images depicting the distribution of these radiopharmaceuticals. The images produced by the uMI Panvivo are intended for analysis and interpretation by qualified medical professionals. They can serve as an aid in detection, evaluation, diagnosis, staging, re-staging, monitoring, and/ or follow-up of abnormalities, lesions, tumors, inflammation, infection, disorders, and/ or diseases, in several clinical areas such as oncology, infection and inflammation, neurology. The images produced by the system can also be used by the physician to aid in radiotherapy treatment planning and interventional radiology procedures.

The CT system can be used for low dose CT lung cancer screening for the early detection of lung nodules that may represent cancer. The screening must be performed within the established inclusion criteria of programs / protocols that have been approved and published by either a governmental body or professional medical society. *

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

The proposed device uMI Panvivo combines a 295 mm axial field of view (FOV) PET and 160-slice CT system to provide high quality functional and anatomical images, fast PET/CT imaging and better patient experience. The system includes PET system, CT system, patient table, power distribution unit, control and reconstruction system (host, monitor, and reconstruction computer, system software, reconstruction software), vital signal module and other accessories.

The PET system features the following specification and technologies.

• 700 mm patient bore size. ●
• . LYSO detector with Axial Field of Views (AFOV) of 295 mm and corresponding imaging performances.
• . 250 kg maximum table load capacity allows flexible positioning and access for all patients.
• . HYPER Iterative (cleared in K193241), uses a regularized iterative reconstruction algorithm, which allows for more iterations while keeping the image noise at an acceptable level by incorporating a noise penalty term into the objective function.
• . AIEFOV is an extended field of view algorithm incorporating extrapolation and Deep Learning(DL). In this algorithm, Project domain extrapolation ensures the normal processing in convolution filter in scan field of view to reduce truncation artifact. DL technology using polar coordinate conversion in extending region can enhance the processing efficiency of deep networks and accelerate training test processing. Overall, AIEFOV does not affect the CT values accuracy inside of SFOV, and also increases the accuracy of CT values in the extended region.

The control and reconstruction system contains image acquisition and reconstruction, image display and post processing, data and patient management, CT dose display, networking, filming, etc.

This document is an FDA 510(k) clearance letter and summary for the uMI Panvivo PET/CT system. It does not contain specific acceptance criteria or a dedicated study section detailing how the device meets such criteria in the manner typically found for an AI/ML medical device.

The "Performance Data" section primarily focuses on non-clinical testing for compliance with standards (electrical safety, EMC, software, biocompatibility, risk management) and describes performance evaluations for specific features (HYPER Iterative and AI EFOV) rather than a comprehensive clinical study to prove general acceptance criteria.

However, I can extract the relevant information that is present and highlight what is missing.

1. Table of Acceptance Criteria and Reported Device Performance

Based on the provided text, specific quantitative acceptance criteria for image quality or clinical performance are not explicitly stated in a table format, nor are explicit numerical performance values against such criteria. The document states:

"Image performance test was conducted for uMI Panvivo to verify that the proposed device met all design specifications as it is Substantially Equivalent (SE) to the predicate device."

For the AI-specific features, it notes:

Missing Information Regarding Acceptance Criteria and Quantified Performance:
The document does not provide specific quantitative acceptance criteria for image quality (e.g., contrast-to-noise ratio, spatial resolution, lesion detectability thresholds) or clinical outcomes. It relies on the qualitative statement that "image quality is sufficient for diagnostic use" and "met all design specifications" in comparison to a predicate device.

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

• Test Set Sample Size: Not explicitly stated. The document mentions "Sample clinical images for HYPER Iterative and AI EFOV were reviewed." The exact number of images, cases, or patients in this "sample" is not provided.
• Data Provenance: Not explicitly stated. The document does not mention the country of origin of the data or whether the data was retrospective or prospective.

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

• Number of Experts: "a U.S. board-certified radiologist". This implies one radiologist, although it's possible it refers to a group and uses "radiologist" generically.
• Qualifications of Experts: "U.S. board-certified radiologist". No information on years of experience or specialization is provided.

4. Adjudication Method for the Test Set

• Adjudication Method: Not applicable or not described. With a single "U.S. board-certified radiologist" reviewing images, an adjudication method (like 2+1 or 3+1 for consensus) would not be performed. The radiologist's assessment served as the evaluation.

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

• MRMC Study: No, an MRMC comparative effectiveness study is not explicitly mentioned as having been done or used to demonstrate performance. The document describes a review by a single U.S. board-certified radiologist. Therefore, there is no information on the effect size of how much human readers improve with AI vs. without AI assistance.

6. Standalone Performance Study

• Standalone Performance Study: The document implies a form of standalone performance evaluation for the AI EFOV and HYPER Iterative features through "Performance evaluation report for HYPER Iterative and AI EFOV" and the review by a radiologist. However, this is presented as an evaluation of image quality generated by the device, not necessarily a quantitative standalone diagnostic performance study (e.g., sensitivity, specificity) of the AI algorithm itself in a diagnostic task. The AI EFOV is described as an algorithm that improves image quality, specifically accuracy of CT values in the extended region and reduction of truncation artifacts. The evaluation focuses on whether the generated images are "sufficient for diagnostic use" and if CT values outside the SFOV are more accurate.

7. Type of Ground Truth Used

• Type of Ground Truth: The ground truth for the review of "sample clinical images" appears to be the expert opinion of the "U.S. board-certified radiologist" that the images were "sufficient for diagnostic use." For the AIEFOV's claim of increased accuracy of CT values in the extended region, the method for establishing this accuracy (e.g., comparison to a phantom with known values or a gold standard imaging technique) is not detailed.

8. Sample Size for the Training Set

• Training Set Sample Size: Not explicitly stated. The document mentions "Deep Learning(DL) technology" for AIEFOV and says it can "accelerate training test processing," implying a training phase. However, the size of the dataset used for training the DL model is not provided.

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

• Training Set Ground Truth Establishment: Not explicitly stated. While DL is mentioned, the methodology for creating the ground truth used to train the DL model for the AIEFOV feature is not described in this document.

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 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 uEXPLORER is a diagnostic imaging system that combines two existing imaging modalities PET and CT. The quantitative distribution information of PET radiopharmaceuticals within the patient body measured by PET can assist healthcare providers in assessing metabolic and physiological functions. CT provides diagnostic tomographic anatomical information as well as photon attenuation for the scanned region. The accurate registration and fusion of PET and CT images provides anatomical reference for the findings in the PET images.

This system is intended to be operated by qualified healthcare professionals to assist in the detection, diagnosis, staging, restaging, treatment planning and treatment response evaluation for diseases, inflammation, infection and disorders in, but not limited to oncology, cardiology and neurology. The system maintains independent functionality of the CT device, allowing for single modality CT diagnostic imaging.

This CT system can be used for low dose CT lung cancer screening for the early detection of lung nodules that may represent cancer. The screening must be performed within the established inclusion criteria of programs / protocols that have been approved and published by either a governmental body or professional medical society. * * Please refer to clinical literature, including the results of the National Lung Screening Trial (N Engl J Med 2011; 365:395-409) and subsequent literature, for further information.

The proposed device uEXPLORER combines a 194 cm axial field of view (AFOV) PET and multi-slice CT system to provide high quality functional and anatomical images, fast PET/CT imaging and better patient experience. The system includes PET gantry, CT gantry, patient table, power supply cabinet, console and reconstruction system, chiller, vital signal module.

The uEXPLORER has been previously cleared by FDA via K182938. The mainly modifications performed on the uEXPLORER (K182938) in this submission are due to the addition of HYPER Iterative, HYPER DLR, Digital gating, remote assistance and CT system modification.

Details about the modifications are listed as below:

• HYPER Iterative (has been cleared in K193241), uses a regularized iterative reconstruction algorithm, which allows for more iterations while keeping the image noise at an acceptable level by incorporating a noise penalty term into the objective function.
• HYPER DLR (has been cleared in K193210), uses a deep learning technique to produce better SNR (signal-to-noise-ratio).
• Digital Gating (has been cleared in K193241), uses motion correction method to ● provide better alternatives to reduce motion effects without sacrificing image statistics.
• Remote assistance.
• PET recon matrix: 1024×1024.
• TG-66 compliant flat tabletop.
• Update the performance according to the NEMA NU 2-2018 standard.
• Update the operation system.
• CT system modification: add Low Dose CT Lung Cancer Screening, Auto ALARA kVp, Organ-Based Auto ALARA mA, EasyRange, Injector Linkage, Shuttle Perfusion, Online MPR and Dual Energy analysis function. All functions have been cleared via K230162.

This document appears to be a 510(k) Premarket Notification from Shanghai United Imaging Healthcare Co., Ltd. for their uEXPLORER device.

Here's an analysis of the provided text to extract information about the acceptance criteria and study that proves the device meets them:

Crucial Observation: The document explicitly states: "No Clinical Study is included in this submission." This means that the information typically found in an FDA submission regarding "acceptance criteria" through a clinical performance study (like an MRMC study or standalone performance) is not present here. Instead, the substantial equivalence relies on non-clinical testing and comparison to predicate devices, particularly regarding modifications to previously cleared components.

Therefore, many of the requested points below cannot be fully answered as they pertain to clinical or human-in-the-loop performance studies that were not conducted or provided in this submission for the specific device being reviewed.

However, I can extract information related to the "non-clinical testing" and the rationale for substantial equivalence.

Acceptance Criteria and Device Performance (Based on Non-Clinical Testing and Substantial Equivalence Rationale):

Given the statement "No Clinical Study is included in this submission," the acceptance criteria are primarily related to non-clinical performance, safety, and functionality demonstrating equivalence to predicate devices and adherence to relevant standards. The "reported device performance" is essentially that it met these non-clinical criteria and maintained safety/effectiveness equivalent to the predicate.

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

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

• Sample Size for Test Set: Not applicable in the context of clinical data. For non-clinical performance and algorithm testing, the "sample size" would refer to the types and number of phantoms/datasets used. The document states "Algorithm and Image performance tests were conducted," but does not specify the number or nature of these test sets.
• Data Provenance: Not specified for any test data. The company is based in China.

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)

• Not applicable, as no clinical study with expert ground truth establishment was conducted or presented in this submission.

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

• Not applicable, as no clinical study requiring adjudication was conducted or presented.

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 explicitly NOT done. The submission states: "No Clinical Study is included in this submission." The new features (HYPER Iterative, HYPER DLR, Digital Gating, and CT modifications) had "been cleared" in other predicate devices via non-clinical performance evaluations, not human reader studies.

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

• Yes, in essence, standalone performance validation of the algorithms was done, but as part of prior submissions for the predicate components. The document states "Algorithm and Image performance tests were conducted for the uEXPLORER during the product development." The key new features, HYPER Iterative, HYPER DLR, and Digital Gating, as well as the CT system modifications, are explicitly stated as having been "cleared" in previous 510(k) submissions (K193241, K193210, K230162). This implies their standalone performance was evaluated and accepted in those prior submissions through non-clinical means (e.g., phantom studies, image quality metrics like SNR, spatial resolution, noise reduction). The details of those prior standalone studies are not provided here, but the current submission leverages their previous clearance.

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

• For the non-clinical "Algorithm and Image performance tests," the ground truth would typically be established based on well-defined physical phantoms with known properties or simulated data, rather than expert consensus, pathology, or outcomes data, which are associated with clinical studies. The specific details are not provided.

8. The sample size for the training set

• Not applicable directly to this submission. The algorithms (HYPER DLR being deep learning) would have had training data, but those details pertain to their original development and previous clearances (K193210, K193241), not this particular 510(k) submission.

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

• Not applicable directly to this submission. This information would be found in the documentation for the previous 510(k) clearances for the HYPER DLR and Digital Gating algorithms if they involved supervised learning that required established ground truth. Typically, for medical imaging algorithms, this could involve large datasets with expertly annotated images, but no specifics are in this document.

Ask a specific question about this device

The uMI Panorama is a diagnostic imaging system that combines two existing imaging modalities PET and CT. The quantitative distribution information of PET radiopharmaceuticals within the patient body measured by PET can assist healthcare providers in assessing metabolic and physiological functions. CT provides diagnostic tomographic anatomical information as well as photon attenuation for the scanned region. The accurate registration and fusion of PET and CT images provides anatomical reference for the findings in the PET images.

This system is intended to be operated by qualified healthcare professionals to assist in the detection, localization, diagnosis, staging, restaging, treatment response evaluation for diseases, inflammation, infection and disorders in, but not limited to oncology and neurology. The system maintains independent functionality of the CT device, allowing for single modality CT diagnostic imaging.

This CT system can be used for low dose CT lung cancer screening for the early detection of lung nodules that may represent cancer. The screening must be performed within the established inclusion criteria of programs / protocols that have been approved and published by either a governmental body or professional medical society. * Please refer to clinical literature, including the results of the National Lung Screening Trial (N Engl J Med 2011; 365:395-409) and subsequent literature, for further information.

The proposed device uMI Panorama combines a 280 or 350 mm axial field of view (FOV) PET and 160-slice CT system to provide high quality functional and anatomical images, fast PET/CT imaging and better patient experience. The system includes PET system, CT system, patient table, power distribution unit, control and reconstruction system (host, monitor, and reconstruction computer, system software, reconstruction software), vital signal module and other accessories.

The PET system features the following specification and technologies.

• 760mm patient bore size.
• Scalable LYSO detector configurations (96-ring and 120-ring) to have scalable Axial Field of Views (AFOV) of 280 and 350mm respectively, with corresponding imaging performances.
• 318 kg maximum table load capacity allows flexible positioning and access for all patients.
• uExcel Iterative (also named HYPER Iterative, has been cleared in K193241), uses a regularized iterative reconstruction algorithm, which allows for more iterations while keeping the image noise at an acceptable level by incorporating a noise penalty term into the objective function.
• uExcel DPR (also named HYPER AiR, has been cleared in K210001), involves pre-trained neural networks in the iteration reconstruction process to reduce noise and improve contrast of fluorodeoxyglucose (FDG) PET images.
• uExcel Focus (also named HYPER Focus, has been cleared in K210418), a respiratory motion correction feature can compromise respiratory motion effects and thus improve the measurement accuracy of SUV and lesion volume.
  The CT system is UIH's 40mm detector uCT ATLAS Astound, which can also be used for standalone, diagnostic CT imaging.

The control and reconstruction system contains image acquisition and reconstruction. image display and post processing, data and patient management. CT dose display, networking, filming, etc.

I am sorry, but the provided text does not contain specific acceptance criteria, details of a clinical study demonstrating the device meets such criteria, or information on AI performance. The document is a 510(k) premarket notification summary for a medical device (uMI Panorama PET/CT system), primarily focused on proving substantial equivalence to a predicate device based on technical characteristics and non-clinical testing. It lists general indications for use and performance data from non-clinical testing for electrical safety and electromagnetic compatibility, software, and biocompatibility.

Therefore, I cannot fulfill your request to describe the acceptance criteria and the study that proves the device meets them, as this specific information is not present in the provided text.

Ask a specific question about this device

HYPER AiR is an image processing function intended to be used by radiologists and nuclear medicine physicians to reduce noise and improve contrast of fluorodeoxyglucose (FDG) PET images.

HYPER AiR is a software-only device. HYPER AiR is an image reconstruction technique which incorporates pre-trained neural networks in the iteration reconstruction process to control image noise and contrast. It is intended to be implemented on previously cleared PET/CT devices uMI 550 (K193241) and uMI 780 (K172143). HYPER AiR serves as an alternative to the existing image reconstruction algorithm that are available on the predicate devices.

The provided text describes the 510(k) summary for the HYPER AiR device, a software-only image processing function for FDG PET images. Here's a breakdown of the acceptance criteria and the study proving the device meets them, based on the information provided:

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria are implicitly defined by the performance tests and clinical image evaluation described. The device's performance is reported in terms of improvement over the conventional OSEM (Ordered Subset Expectation Maximization) algorithm.

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

• Test Set Sample Size: The exact number of cases or images in the test set for the clinical image evaluation is not specified. It only states "The clinical image evaluation was performed by comparing HYPER AiR with OSEM."
• Data Provenance: The raw datasets used for evaluation were "obtained on UH's uMI 780 and uMI 550," which are devices from United Imaging Healthcare. The country of origin of this data is not explicitly stated, but given the sponsor's location (Shanghai, China), it can be inferred that the data likely originated from China. The data was retrospective as it involved applying two different reconstruction algorithms (HYPER AiR and OSEM) to the identical raw datasets already obtained.

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

• Number of Experts: "Each image was read by three board-certified nuclear medicine physicians."
• Qualifications of Experts: "board-certified nuclear medicine physicians." No specific years of experience are mentioned.

4. Adjudication Method for the Test Set

The adjudication method is not explicitly stated. It says "Each image was read by three board-certified nuclear medicine physicians who provided an assessment of image contrast, image noise and image quality." It does not describe how discrepancies among the three readers were resolved or if a consensus mechanism was used.

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

• MRMC Study: A comparative evaluation was done with human readers comparing HYPER AiR reconstructed images to OSEM reconstructed images. This is akin to an MRMC study if the multiple readers evaluated the same cases under both conditions.
• Effect Size: The document states that "HYPER AiR produces images with better image contrast and lower image noise than OSEM while the image quality was sufficient for clinical diagnosis." However, a quantitative effect size (e.g., statistical significance of improvement, specific metrics like AUC difference, or reader confidence scores) is not provided in this summary. It's a qualitative statement of improvement. The study focuses on the standalone performance of the image processing rather than human readers improving with AI assistance vs without, although improved image quality implies potential for human improvement.

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

Yes, standalone performance was evaluated through "Engineering bench testing" where the "evaluation and analysis used the identical raw datasets obtained on UH's uMI 780 and uMI 550, and then applies both HYPER AiR and OSEM to do image reconstruction. The resultant images were then compared for: Performance on noise reduction, Performance on image contrast, Performance on contrast to noise ratio." The aim was to show HYPER AiR's intrinsic ability to improve image characteristics compared to OSEM.

7. The Type of Ground Truth Used

The ground truth used for the evaluation was expert consensus/reader assessment by three board-certified nuclear medicine physicians for the clinical image evaluation. For the non-clinical bench testing, the "ground truth" was essentially the quantitative improvement in objective image metrics (noise reduction, contrast, CNR) based on the algorithm's output compared to OSEM. This is not a "true" clinical ground truth like pathology, but rather a technical performance measure.

8. The Sample Size for the Training Set

The document does not specify the sample size used for the training set of the neural networks integrated into HYPER AiR. It only mentions "pre-trained neural networks."

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

The document does not provide information on how the ground truth for the training set was established. It merely states that HYPER AiR "incorporates pre-trained neural networks in the iteration reconstruction process to control image noise and contrast."

Ask a specific question about this device

HYPER Focus can be used to correct respiratory motion in PET images. Relative to non - corrected images, HYPER Focus can reduce respiratory motion effects and thus improve the measurement accuracy of SUV and lesion volume.

HYPER Focus is a software-only device. It is intended to be implemented on previously cleared PET/CT devices uMI 550 (K193241) and uMI 780 (K172143). HYPER Focus serves as an additional function for uMI 550 and uMI 780 to carry the respiratory correction. It uses the similar respiratory motion correction technique, non-rigid image registration, as the predicate device.

The provided text describes the regulatory clearance of a medical device called "HYPER Focus" (K210418), a software-only device designed to correct respiratory motion in PET images.

Based on the information provided, here's a breakdown of the acceptance criteria and the study that proves the device meets them:

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

The document does not explicitly state a table of quantifiable acceptance criteria with corresponding performance metrics like a typical clinical study report would. Instead, the acceptance criteria are implicitly tied to the device's ability to achieve "substantial equivalence" to a predicate device (GE Q.Freeze software, K113408) in terms of its ability to reduce respiratory motion effects and improve the accuracy of SUV and lesion volume.

The reported device performance is described qualitatively as:

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

• Sample Size: The document does not specify a numerical sample size for the test set. It mentions "identical raw datasets obtained from UIH's uMI 780 (K172143) and uMI 550 (K193241)." This suggests that existing datasets were used, but the quantity of these datasets or individual patient cases is not provided.
• Data Provenance: The data was obtained from UIH's uMI 780 and uMI 550 devices. Given that the company, Shanghai United Imaging Healthcare Co., Ltd., is based in China, it is highly probable that the data originated from China. The document does not explicitly state whether the data was retrospective or prospective, but given they are "identical raw datasets obtained" and "existing data" for bench testing, it strongly implies retrospective use of previously acquired patient data.

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)

This information is not provided in the document. The document describes "engineering bench testing" and "performance verification" using "identical raw datasets," which suggests a technical analysis rather than an expert-read clinical study to establish ground truth for the test set.

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

This information is not provided in the document. The study described appears to be a technical bench test comparing reconstructed images with and without motion correction, rather than a reader study requiring adjudication.

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 involving human readers is not described in this document. The study focuses on the device's quantitative performance (SUV and lesion volume accuracy) and its ability to reduce motion effects in comparison to non-corrected images, and on demonstrating substantial equivalence to a predicate device.

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

Yes, a standalone performance evaluation was done. The "Performance Verification" section states: "Engineering bench testing was performed to support substantial equivalence and product performance claims. The evaluation and analysis used the identical raw datasets obtained from UIH's uMI 780 (K172143) and uMI 550 (K193241), and then respectively performed image reconstruction with/without HYPER Focus." This indicates that the algorithm's performance was assessed independently of human interpretation.

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

The document primarily refers to "bench testing" and "analysis" of quantitative metrics like SUV (Standardized Uptake Value) and sphere/lesion volume accuracy. The "ground truth" for this type of test is typically based on:

• Known physical properties of phantoms: For sphere volume and potentially SUV accuracy, phantom studies with known dimensions and activity concentrations are commonly used. While not explicitly stated, "bench test" often implies phantom studies.
• Comparison to "ideal" or "reference" motion-corrected images: The document states a comparison "in comparison with no motion correction." This implies an assessment against a baseline reference, where the ground truth is the improved accuracy obtained by the algorithm. For motion correction, perfect motion-free images are the ideal ground truth, which is often approximated or modeled.
• The document implies that the "ground truth" for proving efficacy is the demonstrated improvement in SUV and lesion volume accuracy and reduction of motion effects when HYPER Focus is applied, compared to images without motion correction.

The document does not suggest the use of expert consensus, pathology, or outcomes data as a ground truth for this particular submission, which is focused on validating the technical performance of motion correction software for PET images in the context of substantial equivalence.

8. The sample size for the training set

The document does not provide any information about the sample size used for the training set of the HYPER Focus algorithm.

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

The document does not provide any information about how the ground truth for the training set was established. It focuses solely on the performance verification (testing) of the final algorithm.

Ask a specific question about this device