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 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 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