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 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, 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 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 uMI Panorama has been previously cleared by FDA via K223325. The mainly modifications performed on the uMI Panorama (K223325) in this submission are due to the algorithm update of uExcel Focus (also named OncoFocus) and the addition of uKinetics. This time, uExcel Focus adds deep learning technology based on the original technology and could be performed as intended. uKinetics is a new function. which is used to generate both indirect and direct parametric images.

The provided text describes a 510(k) summary for the uMI Panorama PET/CT system, with specific modifications related to the uExcel Focus and uKinetics features. While it outlines general performance evaluations, it does not contain the detailed, quantitative acceptance criteria and the full study data typically found in a clinical study report. It primarily focuses on demonstrating substantial equivalence to a predicate device.

However, based on the information provided, we can infer some details and present them in the requested format, clearly indicating where implicit understanding or lack of specific data exists.

Here's an attempt to extract and structure the information as requested, with explicit notes about missing details:

Acceptance Criteria and Device Performance for uMI Panorama (uExcel Focus and uKinetics updates)

The performance data provided primarily aims to demonstrate substantial equivalence to the predicate device (uMI Panorama K223325) for specific new features: uExcel Focus and uKinetics. The studies performed were "bench tests" and a "clinical image evaluation."

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state quantitative acceptance criteria in numerical thresholds but rather describes the intended outcome of the features. The "reported device performance" are qualitative statements about the observed effects.

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

• Sample Size (Test Set): Not explicitly stated. For uExcel Focus, "images were compared," and for uKinetics, "Bias of area under curve (AUC) of the estimated image-derived input function (IDIF)" and "Bias of Ki and intercept in the hot spheres in the IO phantom" and "Coefficient of variation (CoV) of the background region in the IQ phantom" were assessed. This suggests phantom data for verification. The "clinical image evaluation" involved two physicians evaluating "images," but the number of patient cases or images is not provided.
• Data Provenance: Not explicitly stated. The manufacturer is based in Shanghai, China. The nature of the "clinical image evaluation" (retrospective or prospective) is not specified, but it implies real patient data. Phantom data is generated in a controlled environment.

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

• Number of Experts: For the "Clinical Image Evaluation" of uExcel Focus, Two American board-certified nuclear medicine physicians were involved.
• Qualifications of Experts: "American board-certified nuclear medicine physicians." No specific experience duration (e.g., "10 years of experience") is mentioned.

4. Adjudication Method for the Test Set

• For the "Clinical Image Evaluation" of uExcel Focus, the physicians evaluated images "independently." The document does not specify an adjudication method (e.g., 2+1, 3+1, consensus reading by a third party if there was disagreement). It merely states they evaluated independently.

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

• No, a formal MRMC comparative effectiveness study, as typically understood for quantifying human reader improvement, was not explicitly described. The "Clinical Image Evaluation" was a "blind comparison" where two nuclear medicine physicians independently evaluated images from the uMI Panorama with/without uExcel Focus. This setup is a prerequisite for an MRMC study, but the document only reports a qualitative conclusion ("sufficient for clinical diagnosis," "can reduce artifacts and improve alignment") rather than a statistical analysis of reader performance improvement (e.g., AUC, sensitivity, specificity) with AI assistance versus without.
• Effect Size of Human Reader Improvement: Not reported.

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

• The performance descriptions for both uExcel Focus (e.g., "reduce respiratory motion effects and improve the accuracy of SUV and lesion volume") and uKinetics (e.g., "provide quantitatively accurate parametric images") appear to describe the algorithm's inherent performance as measured through "bench testing" (which often involves phantoms or simulated data) or direct analysis of image metrics.
• Thus, yes, aspects of standalone performance were evaluated for both features, particularly uKinetics which focuses on quantitative accuracy of derived parameters. uExcel Focus also had non-clinical tests verifying its effects on SUV and volume accuracy.

7. The Type of Ground Truth Used

• For uExcel Focus (non-clinical/bench testing): The ground truth metrics were likely derived from known phantom configurations where true SUV, lesion volume, and motion scenarios are controlled or modeled to allow for comparison against system output (e.g., known phantom dimensions and activity concentrations).
• For uKinetics (non-clinical/bench testing): Ground truth was based on phantom properties (e.g., "hot spheres in the IO phantom," "background region in the IQ phantom") and potentially theoretical or simulated models for IDIF, Ki, and intercept values given known input.
• For uExcel Focus (clinical image evaluation): The "ground truth" for clinical sufficiency and artifact reduction appears to be expert consensus/opinion by the two American board-certified nuclear medicine physicians, rather than pathology or long-term clinical outcomes data. They judged if the images were "sufficient for clinical diagnosis."

8. The Sample Size for the Training Set

• Not provided. The document states that uExcel Focus "adds deep learning technology based on the original technology," which implies the use of a training set. However, the size and characteristics of this training set are not disclosed in this 510(k) summary.

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

• Not provided. Given the use of deep learning for uExcel Focus, a method to establish ground truth for training data would be crucial (e.g., expert annotations, simulated data, or other validated methods). This detail is not included in the provided text.

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, 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 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 is an extended Field of View scanner based on uMI Panorama 35. The PET system uses the detector elements that is same with the predicate device. The gantry has been designed to extend the PET detector to 504 rings, which is different from 120 rings of the uMI Panorama 35.

The CT system is UIH's commercially available uCT ATLAS Astound (K223028) with 40 mm detector, which can also be used for standalone, diagnostic CT imaging.

The patient table has 250 kg maximum load capacity which allows flexible positioning and access for all patients.

The PSC and chiller provide higher capacity to meet the extended PET system power supply and cooling requirement, compared to uMI Panorama 35.

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

Vital signal module is identical to those of the predicate device uMI Panorama 35.

The provided text describes the 510(k) summary for the uMI Panorama GS, a PET/CT system, but it primarily focuses on non-clinical performance data and its substantial equivalence to a predicate device (uMI Panorama 35). It does not include detailed acceptance criteria or a study proving the device meets those criteria, particularly in terms of clinical performance or a multi-reader multi-case (MRMC) study.

However, I can extract information related to the device's performance testing and the type of information that would be relevant to acceptance criteria.

Based on the provided text, the following information can be extracted:

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

The document mentions "Image performance test was conducted for uMI Panorama GS to verify that the proposed device met all design specifications as it is Substantially Equivalent (SE) to the predicate device." However, specific quantitative acceptance criteria (e.g., specific image quality metrics, sensitivity, specificity, resolution) and their corresponding reported device performance values are not detailed in this summary. The summary focuses on conformance to standards rather than specific performance metrics.

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

This information is not provided in the document. The summary only refers to "Image performance test" without specifying the test set characteristics or data provenance.

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

This information is not provided in the document. As there is no mention of a clinical study or human reader evaluation, no experts for ground truth establishment are discussed.

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

This information is not provided in the document.

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 was not mentioned in this summary. The document focuses on the technical specifications and non-clinical performance of the PET/CT system itself, not on an AI component or its impact on human reader performance.

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

A standalone performance study for an algorithm (without human-in-the-loop) was not mentioned in this summary. The device described is a complete PET/CT imaging system, not a standalone algorithm.

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

This information is not provided in the document. For the non-clinical image performance tests, the "ground truth" would likely be based on physical phantom measurements and known parameters, but this is not explicitly stated.

8. The sample size for the training set

This information is not provided in the document. Since this is a hardware device (PET/CT system) rather than an AI/ML algorithm-driven software device in the context of this summary, a "training set" in the typical AI sense is not applicable or discussed.

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

This information is not provided in the document, for the same reasons as #8.

Summary of what is available regarding testing and performance:

The document states that non-clinical testing was conducted for the uMI Panorama GS to verify that the proposed device met all design specifications and is substantially equivalent to the predicate device (uMI Panorama 35).

The company claims conformance to various standards and guidance documents related to:

• Electrical Safety and Electromagnetic Compatibility (EMC)
• Medical electrical equipment standards (e.g., IEC 60601 series)
• Safety of laser products (IEC 60825-1)
• Usability (IEC 60601-1-6)
• Medical device software lifecycle processes (IEC 62304)
• Performance Measurements of Positron Emission Tomographs (NEMA NU 2-2018)
• Digital Imaging and Communications in Medicine (DICOM) (NEMA PS 3.1-3.20)
• Guidance for software in medical devices and cybersecurity
• Biocompatibility (ISO 10993 series)
• Risk management (ISO 14971)
• Quality System Regulation (21 CFR Part 820)
• Radiological Health regulations (21 CFR, Subchapter J)

The conclusion is that "the uMI Panorama was found to have a safety and effectiveness profile that is similar to the predicate device." and "The proposed device is determined to be Substantially Equivalent (SE) to the predicate device." This implies that meeting these standards and demonstrating similar performance to the predicate device are the primary "acceptance criteria" for the 510(k) submission, specifically relying on non-clinical performance data.

In essence, the document presents a regulatory compliance summary rather than a detailed clinical performance study with specific acceptance criteria and outcome data as might be found for an AI diagnostic algorithm.

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