(88 days)
The PET scanner is intended to be used for whole body, multi-slice, Positron Emission Tomography diagnostic imaging.
The Positron Emission Tomography (PET) scanners from Neusoft Positron Medical Systems Corporation image the distribution of positron-emitting radionuclides in the human body. These software-controlled medical devices use positron emitting radioactive isotopes to create cross-sectional tomographic images that show function or metabolism, rather than anatomy, as in conventional scanning techniques.
The PET scanner's software generates quantitative images through Attenuation Correction, which corrects for loss of information due to absorption and scatter by overlying soft tissue, and through theoretical, measured, or hybrid (segmented attenuation correction) Image Reconstruction, which generates transaxial images from acquired data using a filtered back projection or iterative reconstruction process.
The PET scanner consists of Detector System, Gantry, Front-end Electronics, Patient Table, Transmission Source, Operator's Control Workstation, Image Processing Workstation and optional Remote Display Workstation.
Here's an analysis of the provided text regarding the acceptance criteria and the study conducted for Neusoft Positron Medical Systems Co., Ltd.'s PET scanner (Attrius™, Attrius L™, Truesight).
Important Note: The provided text is a 510(k) summary, which focuses on demonstrating substantial equivalence to a predicate device. It primarily describes comparisons in technological characteristics and lists various tests performed to ensure safety and effectiveness. It does not present a detailed clinical study with specific acceptance criteria metrics, sample sizes for test/training sets, expert qualifications, or MRMC study results (like an AI improvement effect size) in the way that would typically be found in a later clinical trial report for AI-powered diagnostic devices. The performance evaluation here is largely based on phantom studies (NEMA NU2) and compliance with established standards.
1. Table of Acceptance Criteria and Reported Device Performance
Given the nature of the 510(k) summary, explicit "acceptance criteria" for diagnostic performance in terms of sensitivity, specificity, or AUC against a clinical ground truth are not provided. Instead, the performance is demonstrated through compliance with established industry standards for PET scanners using phantoms.
| Acceptance Criteria Category (Implied by FDA submission) | Reported Device Performance (Summary from text) |
|---|---|
| Technological Equivalence / Performance Standards Compliance (NEMA NU2) | "The performance test data of the candidate device have been obtained using NEMA NU2 phantoms, under the test procedure of NEMA NU2 standards." |
| Safety Testing | IEC 60601-1 Safety tests, IEC 60601-1-1 Safety tests performed. |
| Electromagnetic Compatibility (EMC) | IEC 60601-1-2 Electromagnetic Compatibility test performed. |
| Software Validation | "Software validation, US FDA Software Used in Medical Devices Guidance" performed. |
| Radiation Measurement | "Radiation measurement" tests performed. |
| Substantial Equivalence (Overall Conclusion) | "All the above differences have been verified and determined to not affect safety and effectiveness of the device. We submit that the candidate device and the predicate device are substantially equivalent." |
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size (Test Set): The document does not specify a sample size of patient cases for a clinical test set. The primary performance evaluation cited is a phantom study. Phantom studies use physical objects designed to mimic human tissue for reproducible testing, not patient data.
- Data Provenance: Not applicable for a phantom study. The NEMA NU2 phantoms are standardized physical objects.
- Retrospective or Prospective: Not applicable for a phantom study.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts
- Number of Experts: Not applicable. The ground truth for NEMA NU2 phantom studies is inherently known by the phantom's design and physical properties (e.g., known radioactivity concentration, dimensions of objects). No human experts are used to establish this kind of ground truth.
- Qualifications of Experts: Not applicable.
4. Adjudication Method for the Test Set
- Adjudication Method: Not applicable. As discussed, the test set is based on NEMA NU2 phantoms, where the "ground truth" is objectively defined by the phantom itself and its preparation, not by expert consensus or adjudication.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done
- MRMC Study: No, an MRMC comparative effectiveness study is not mentioned or implied in this 510(k) summary. The summary focuses on the device's technical performance and safety, primarily through phantom testing and comparisons to a predicate device's technical specifications. This type of study would typically be performed for AI algorithms designed to assist human readers in interpretation.
- Effect Size of Human Reader Improvement: Not applicable, as no MRMC study was performed.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done
- Standalone Performance: The performance testing reported (NEMA NU2) is essentially a standalone evaluation of the PET scanner's image acquisition and reconstruction capabilities. However, this is for the imaging device itself, not for a separate AI algorithm designed for interpretation. The phrase "algorithm only" or "standalone" typically refers to the diagnostic accuracy of an AI model in performing a task (e.g., detecting lesions) without human intervention. This document describes the performance of the PET scanner as a whole system. Therefore, while technically an "algorithm" (reconstruction software) is evaluated in a standalone manner, it's not in the context of an AI-driven interpretive tool.
7. The Type of Ground Truth Used
- Type of Ground Truth: The ground truth for the performance evaluation cited is primarily physical phantom properties (NEMA NU2 phantoms). These phantoms have known geometric configurations and radioactivity distributions, allowing for objective measurement of parameters like spatial resolution, sensitivity, and image uniformity.
8. The Sample Size for the Training Set
- Training Set Sample Size: Not applicable/Not provided. This document does not describe the development or training of an AI algorithm in the contemporary sense. The PET scanner uses "3rd party OSEM image reconstruction software" and other 3rd party software (Linux, RTAI). These are established software components for image reconstruction and operating systems, not typically "trained" on a dataset in the way a modern deep learning AI model would be. Therefore, there is no mention of a dedicated training set.
9. How the Ground Truth for the Training Set Was Established
- Ground Truth for Training Set: Not applicable, as no training set for an AI algorithm is mentioned. The software components (OSEM, Linux, RTAI) would have been developed and validated by their respective creators through their own, unspecified methods, prior to being integrated into this PET scanner.
§ 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.