(73 days)
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:
| Feature | Indication/Description | Performance (as reported) |
|---|---|---|
| HYPER Iterative | 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. | Performance evaluation report for HYPER Iterative. "Sample clinical images for HYPER Iterative and AI EFOV were reviewed by U.S. board-certified radiologist. It was shown that the proposed device can generate images as intended and the image quality is sufficient for diagnostic use." |
| AIEFOV (AI-based) | An extended field of view algorithm incorporating extrapolation and Deep Learning (DL). Project domain extrapolation ensures normal processing in convolution filter in scan field of view to reduce truncation artifact. DL technology using polar coordinate conversion in the extending region can enhance processing efficiency of deep networks and accelerate training test processing. Overall, AIEFOV does not affect CT values accuracy inside SFOV, and also increases the accuracy of CT values in the extended region. | Performance evaluation report for AI EFOV. "Sample clinical images for HYPER Iterative and AI EFOV were reviewed by U.S. board-certified radiologist. It was shown that the proposed device can generate images as intended and the image quality is sufficient for diagnostic use." "AIEFOV does not affect the CT values accuracy inside of SFOV, and also increases the accuracy of CT values in the extended region." |
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.
§ 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.