FDA 510(k) Search - By Innolitics (SaMD and AI Experts)

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.

Device Description

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.

AI/ML Overview

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.

Feature	Category	Acceptance Criteria (Implied/Qualitative)	Reported Device Performance (Qualitative)
uExcel Focus	Respiratory Motion Correction	Reduce respiratory motion effects.
Improve accuracy of SUV and lesion volume.	"The performance evaluation showed that uExcel Focus could reduce respiratory motion effects and improve the accuracy of SUV and lesion volume in comparison with no motion correction."
"Clinical evaluation shows that all images produced by uMI Panorama with uExcel Focus are sufficient for clinical diagnosis and uExcel Focus can reduce attenuation correction artifacts and improve PET-CT alignment."
uKinetics	Parametric Image Generation	Provide quantitatively accurate parametric images.	"Bench test showed that uKinetics can provide quantitatively accurate parametric images."

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.

Summary

Regulation Number and Section

§ 892.1200 Emission computed tomography system.

(a)
Identification. An emission computed tomography system is a device intended to detect the location and distribution of gamma ray- and positron-emitting radionuclides in the body and produce cross-sectional images through computer reconstruction of the data. This generic type of device may include signal analysis and display equipment, patient and equipment supports, radionuclide anatomical markers, component parts, and accessories.(b)
Classification. Class II.