Search Results

The GE Omni Legend is a PET/CT system for producing attenuation corrected PET images. It is intended to be used by qualified health care professionals for imaging the distribution and localization of any positron-emitting radiopharmaceutical in a patient, for the assessment of metabolic (molecular) and physiologic function in patients, with a wide range of sizes and extent of disease, of all ages.

Omni Legend is intended to image the whole body, head, heart, brain, bone, the gastrointestinal and lymphatic systems, and other organs. The images produced by the system may be used by physicians to aid in radiotherapy treatment planning, therapy guidance and monitoring, and in interventional radiology procedures. The images may also be used for precise functional and anatomical mapping (localization, registration, and fusion).

When used with radiopharmaceuticals approved by the regulatory in the country of use, the raw and image data is an aid in; detection, localization, evaluation, diagnosis, staging, monitoring, and/or follow up, of abnormalities, lesions, tumors, inflammation, infection, organ function, disorders, and/or disease, such as, but not limited to, those in oncology, cardiology, and neurology.

Examples of which are:

Cardiology:

• Cardiovascular disease
• · Myocardial perfusion
• · Myocardial viability
• Cardiac inflammation
• · Coronary artery disease

Neurology:

· Epilepsy

· Dementia, such as Alzheimer's disease, Lewy body dementia, Parkinson's disease with dementia, and frontotemporal dementia

• · Movement disorders, such as Parkinson's and Huntington's disease
• Tumors
• · Inflammation
• · Cerebrovascular disease such as acute stroke, chronic and acute ischemia
• · Traumatic Brain Injury (TBI)
• Oncology/Cancer:
• Non-Small Cell Lung Cancer
• · Small Cell Lung Cancer
• Breast Cancer
• · Prostate Cancer
• · Hodgkin disease
• Non-Hodgkin lymphoma
• · Colorectal Cancer
• · Melanoma

Omni Legend is also intended for stand-alone, diagnostic CT imaging in accordance with the stand-alone CT system's cleared indications for use.

GE's Omni Legend is a hybrid digital PET/CT diagnostic imaging system combining a GE Positron Emission Tomography System and the commercially available GE Revolution Maxima CT System, for excellent, best-in-class imaging performance. Omni Legend is intended for CT attenuation corrected, anatomically localized PET imaging of the distribution of positron-emitting radiopharmaceuticals. It is intended to image the whole body, head, heart, brain, lung, breast, bone, the gastrointestinal and lymphatic systems, and other organs. It is also intended for stand-alone, diagnostic CT imaging.

Omni Legend's major components include the PET system, Revolution Maxima CT system, patient table, operator console, computing hardware, power distribution unit (PDU), system software, and reconstruction software.

The PET System uses the same design elements used in the predicate Discovery MI Gen2, including use of digital detection (SiPMs). The most significant difference is that the digital detection on Omni Legend uses BGO as a scintillator instead of the Lutetium-based scintillator (LYSO/LGSO) used on Discovery MI Gen2. Omni Legend's digital BGO-based detection achieves the very high sensitivity desired. The Discovery IQ reference device also uses BGO as the scintillator material for its analogic detection. Omni Legend's PET system offers scalable ring configurations (3-ring and 6-ring) to have scalable Axial Field of Views (AFOV) of 16 and 32 cm respectively, with corresponding imaging performances.

The CT System is GE's commercially available 64 detector row Revolution Maxima, which may also be used for standalone, diagnostic CT imaging.

The Operator Console and System Software control image acquisition and reconstruction, image display and post processing analysis, protocol and patient management, CT dose display, networking, filming, etc. The software carries over functionalities available on the Discovery MI Gen2 product line and is updated to support the changes introduced with Omni Legend and to bring enhancement, including ACQC, RadRx 2.0, and Express Mode.

The Patient Table and PDU are identical to those of the predicate Discovery MI Gen2.

The provided text describes the GE Omni Legend PET/CT system and its submission for FDA 510(k) clearance, asserting its substantial equivalence to a predicate device. However, the document does not contain a detailed table of specific acceptance criteria or quantitative performance metrics for the device, nor does it provide a comprehensive report of a study that directly proves the device meets specific, pre-defined acceptance criteria with numerical outcomes.

Instead, it describes the types of tests performed and the general conclusions, focusing on demonstrating equivalence to a predicate device rather than meeting absolute performance thresholds.

Therefore, for the specific request:

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

The document does not provide a specific table with numerical acceptance criteria and corresponding reported device performance values. It generally states that performance testing compliant with NEMA NU 2-2018 was conducted for various parameters.

General Performance Evaluation (as inferred from the text):

Note: The document only mentions that these tests were performed and that the results "support substantial equivalence" or "demonstrated acceptable diagnostic results," but it does not provide the specific numerical acceptance thresholds or the actual measured performance values for these metrics.

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

• Test Set Sample Size: Not explicitly stated. The document mentions "a clinically representative sample for evaluation of Omni Legend's performance."
• Data Provenance: Not explicitly stated regarding country of origin. The study was a "clinical reader study using PET/CT exams acquired on Omni Legend," implying prospective acquisition for the purpose of the study, though the specific recruitment method (e.g., patient volunteers vs. retrospective scans) is not detailed. It is highly likely, given GE's global presence and the setting of the submission (FDA), that the data was collected under ethical guidelines in a clinical setting relevant to the product development, but the specific origins are not mentioned.

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

• Number of Experts: Not precisely stated. The document says "Each image was read by NM physicians." This implies multiple physicians, but the exact number is not provided.
• Qualifications of Experts: "NM physicians" (Nuclear Medicine physicians). No specific experience level (e.g., "10 years of experience") is mentioned.

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

• Adjudication Method: Not explicitly mentioned. The statement "Each image was read by NM physicians who provided an assessment of overall diagnostic image quality using a Likert Scale. All of the physicians attested that their assessments demonstrated acceptable diagnostic results" suggests independent reads followed by a collective attestation of acceptability, rather than a formal adjudication process (like 2+1 or 3+1 for discordance resolution).

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 clinical reader study was conducted. However, the description states it was to evaluate "Omni Legend's performance" and for "assessment of overall diagnostic image quality."
• This study does not appear to be an MRMC comparative effectiveness study comparing human readers with AI assistance vs. without AI assistance. The document indicates the study was to evaluate the image quality of the system itself, not the impact of an AI algorithm on human reading performance.
• Therefore, no effect size for human readers improving with AI vs. without AI assistance is reported because that was not the stated purpose or design of the clinical reader study described.

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

• The document describes the Omni Legend as a "PET/CT system" and mentions its components and functionalities. It does not describe a specific standalone "algorithm" being assessed independently of the system's image acquisition and reconstruction. The performance testing (NEMA NU 2-2018 tests) are for the entire imaging system (e.g., sensitivity, resolution), not a separate diagnostic algorithm.
• Thus, a standalone algorithm-only performance study, as typically understood in AI/CADx submissions, is not detailed or implied for a distinct diagnostic algorithm component. The testing described is for the device as an image-generating system.

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

• The ground truth for the clinical reader study appears to be expert assessment/consensus based on the NM physicians' evaluations of "overall diagnostic image quality." There is no mention of pathology, long-term outcomes, or other objective data used as ground truth for the diagnostic image quality assessment. The physicians attested to acceptable diagnostic results.

8. The sample size for the training set:

• The document makes no mention of a training set sample size. This is because the submission is for a PET/CT imaging system, not an AI/ML algorithm that typically requires a large training set. While the system may incorporate advanced processing, the submission focuses on the hardware's performance (digital BGO detector, CT system) and its ability to produce diagnostic images, rather than a trainable AI model used for diagnosis.

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

• Since no training set is mentioned or implied for a trainable AI/ML algorithm in this submission, the establishment of ground truth for a training set is not applicable to the information provided. The "ground truth" discussed is related to the evaluation of the final image quality and diagnostic acceptability by physicians, not for training a model.

Ask a specific question about this device

The GE Discovery MI is a PET/CT system for producing attenuation corrected PET images. It is intended to be used by qualified health care professionals for imaging the distribution and localization of any positron-emitting radiopharmaceutical in a patient, for the assessment of metabolic (molecular) and physiologic function in patients, with a wide range of sizes and extent of disease, of all ages.

Discovery MI is intended to image the whole body, head, heart, brain, lung, breast, bone, the gastrointestinal and lymphatic systems, and other organs. The images produced by the system may be used by physicians to aid in radiotherapy treatment planning, therapy guidance and monitoring, and in interventional radiology procedures. The images may also be used for precise functional and anatomical mapping (localization, registration, and fusion).

When used with radiopharmaceuticals approved by the regulatory in the country of use, the raw and image data is an aid in; detection, localization, evaluation, diagnosis, staging, monitoring, and/or follow up, of abnormalities, lesions, tumors, inflammation, infection, organ function, disorders, and/or disease, such as, but not limited to, those in oncology, cardiology, and neurology. Examples of which are:

Cardiology:

• Cardiovascular disease
• Myocardial perfusion
• Myocardial viability
• Cardiac inflammation
• Coronary artery disease

Neurology:

• Epilepsy
• Dementia, such as Alzheimer's disease, Lewy body dementia, Parkinson's disease with dementia, and frontotemporal dementia.
• Movement disorders, such as Parkinson's and Huntington's disease
• Tumors
• Inflammation
• Cerebrovascular disease such as acute stroke, chronic and acute ischemia
• Traumatic Brain Injury (TBI)

Oncology/Cancer:

• Non-Small Cell Lung Cancer
• Small Cell Lung Cancer
• Breast Cancer
• Prostate Cancer
• Hodgkin disease
• Non-Hodgkin lymphoma
• Colorectal Cancer
• Melanoma

Discovery MI is also intended for stand-alone, diagnostic CT imaging in accordance with the stand-alone CT system's cleared indications for use.

The Discovery MI system is a PET/CT diagnostic imaging system combining a GE Positron Emission Tomography (PET) System and a GE Computed Tomography (CT) System.

The PET portion of the system uses a Lutetium-based Scintillator (LBS) detector. Scintillator crystal arrays are attached to Silicon Photo Multipliers (SiPM) to form detector units. The detector units are inherited from the reference device Signa PET/MR. Detector units are attached on a common support to form detector modules. The detector modules are arranged in a ring around the patient positioned inside of the PET gantry for detection of gamma rays generated as a result of PET radiopharmaceuticals injected into the patient.

The PET/CT system uses the full-featured multi-slice diagnostic CT subsystem with PET/CT post processing software to generate a map of the non-uniform attenuation in the patient. This attenuation map is then used for attenuation correction of the PET data. The CT image is also used for localization of the PET image in the patient anatomy by means of fusing the PET and CT images.

The Discovery MI system's major components are the PET gantry/detector, Revolution EVO CT system, patient table, operator console/workspace, computing hardware, power distribution unit, system software, and reconstruction software. The operator console and software provide control of the imaging (i.e. setting and confirming conditions of operation), image acquisition, dose display, reconstruction, viewing, post processing analysis, patient management, networking, and filmina. The system may include respiratory and cardiac gating capabilities, signal analysis and display equipment, patient and equipment supports, components and accessories. In addition to being installed as a complete PET/CT system, the Discovery MI may result from an upgrade to a Revolution EVO- based Discovery PET/CT 710.

The Discovery MI system provides scalable axial coverage for the PET detector. All configurations offer reference adult and pediatric protocols for both hybrid PET/CT and CT applications. The PET 3D data acquisition modes include Static, Gated, Dynamic, and Whole Body scanning. All of which can be acquired with List mode data. The system includes standard PET iterative reconstruction alqorithms. Q.Clear full-convergence, reqularized reconstruction is optionally available. Time of Flight (ToF) may be used for all PET reconstruction types.

The CT system is the commercially available 64-detector row Revolution Evo, which may also be used for stand-alone, diagnostic CT imaging. The CT system's acquisition modes include Axial, Cine, Helical (Volumetric), Cardiac, and Gated, for head, whole body, trauma, cardiac and vascular applications.

This document describes the Discovery MI, a PET/CT diagnostic imaging system. No specific acceptance criteria table or a detailed study proving the device meets acceptance criteria in the sense of a clinical trial for diagnostic performance are provided in the extracted text. The document focuses on demonstrating substantial equivalence to a predicate device, as required for a 510(k) premarket notification.

However, the text does mention non-clinical testing to substantiate product performance and claims, which effectively serve as internal performance criteria:

1. Table of Performance Claims Tested (Non-Clinical) and Device Performance (Implicitly Met):

2. Sample Size and Data Provenance for Test Set:

• Test Set (Non-Clinical): "a variety of test methods and phantoms appropriate for the performance metric/claim to be tested and evaluated." No specific sample size (e.g., number of phantoms) is provided, and the data is generated through physics and engineering analysis, not from human subjects.
• Data Provenance: Non-clinical (phantom-based, mathematical, and physics analysis). Not applicable for country of origin or retrospective/prospective as it's not human data.

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

• Not applicable as the "ground truth" for the non-clinical performance evaluations (sensitivity, NECR, resolution, lesion detectability) would be based on the known physical properties of the phantoms and the expected performance of the system as designed and measured, rather than expert consensus on clinical images.

4. Adjudication Method for Test Set:

• Not applicable, as this was non-clinical phantom testing.

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

• No MRMC comparative effectiveness study involving human readers and AI assistance is mentioned. The document explicitly states: "Given the above information and the type and scope of the changes, particularly that the new system uses PET detector modules from the cleared Signa PET/MR, and that its 510k included numerous clinical images, clinical testing is not required to demonstrate that the Discovery MI is as safe and as effective as the legally marketed predicate and reference devices."

6. Standalone (Algorithm Only) Performance Study:

• The "lesion detectability evaluation included a model observer study." This implies a standalone computational assessment of lesion detection performance, without human readers. No specific metrics (e.g., AUC, sensitivity, specificity) or detailed results from this model observer study are provided.

7. Type of Ground Truth Used (for Non-Clinical Tests):

• For non-clinical performance evaluation, the ground truth was based on the known physical properties of the phantoms and the expected performance derived from mathematical and physics analysis.

8. Sample Size for Training Set:

• Not applicable. The document does not describe the development of an AI algorithm that would typically require a training set. The "model observer study" mentioned for lesion detectability is unlikely to refer to a machine learning training set in this context but rather a computational model used to assess detectability in phantoms.

9. How Ground Truth for Training Set Was Established:

• Not applicable, as there is no mention of a machine learning training set for an AI algorithm.

Ask a specific question about this device