Search Results

This device is indicated to acquire and display cross sectional volumes of the whole body, to include the head. The Aquilion Serve SP has the capability to provide volume sets. These volume sets can be used to perform specialized studies, using indicated software/hardware, by a trained and qualified physician.

AiCE (Advanced Intelligent Clear-IQ Engine) is a noise reduction algorithm that improves image quality and reduces image noise by employing Deep Convolutional Network methods for abdomen, pelvis, lung, cardiac, extremities, head and inner ear applications.

Aquilion Serve SP (TSX-307B/1) V1.3 is a whole body multi-slice helical CT scanner, consisting of a gantry, couch and a console used for data processing and display. This device captures cross sectional volume data sets used to perform specialized studies, using indicated software, by a trained and qualified physician. This system is based upon the technology and materials of previously marketed Canon CT systems.

Aquilion Serve SP (TSX-307B/1) V1.3 is equipped with SilverBeam Filter which is a beam shaping filter that leverages the photon-attenuating properties of silver to selectively remove low energy photons from a polychromatic X-ray beam, leaving an energy spectrum optimized for high contrast CT applications.

The provided text is a 510(k) summary for a Computed Tomography (CT) system (Aquilion Serve SP), which focuses on demonstrating substantial equivalence to a predicate device rather than providing a detailed clinical study for a new AI algorithm's performance against acceptance criteria.

While the document mentions AiCE (Advanced Intelligent Clear-IQ Engine) as a noise reduction algorithm that improves image quality by employing Deep Convolutional Network methods, it does not provide the specifics of the study that proves this particular feature meets acceptance criteria. The performance testing section primarily describes bench testing using phantoms to assess image quality metrics and dose reduction, comparing the new device's overall performance to that of the predicate, not specifically the AI algorithm's standalone or human-in-the-loop performance.

Therefore, many of the requested details about the study proving the device (specifically its AI component, AiCE) meets acceptance criteria cannot be extracted from this text. The acceptance criteria and performance data provided are for the CT system as a whole, mainly from phantom testing.

However, based on the limited information related to performance testing in this 510(k) summary, here's what can be inferred and what is missing:

Acceptance Criteria and Device Performance (Inferred from Bench Testing Section):

The document states: "It was concluded that the performance of TSX-307B (Serve SP) was improved and/or substantially equivalent to the predicate device as demonstrated by the results of the testing." This indicates the general acceptance criterion was "improved and/or substantially equivalent" performance when compared to the predicate device, specifically across various image quality metrics and dose reduction.

Missing Information (Crucial for AI Algorithm Performance):

The provided text does not contain the detailed information for a clinical study specifically evaluating the AiCE (Advanced Intelligent Clear-IQ Engine) AI algorithm against acceptance criteria. The summary focuses on the overall CT system's substantial equivalence to a predicate.

Therefore, the following points cannot be answered from the provided text:

2. Sample size used for the test set and the data provenance: Not described for a study specifically on AiCE. The performance testing described is bench testing using phantoms.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable as no clinical test set using expert ground truth is described for AiCE.
4. Adjudication method (e.g., 2+1, 3+1, none) for the test set: Not applicable as no clinical test set is described.
5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done: Not mentioned. The focus is on technical equivalence and phantom-based image quality.
6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done: The document states AiCE improves image quality and reduces noise. This implies a standalone capability for image processing, but no specific study or metrics for this standalone performance (e.g., diagnostic accuracy on a dataset) are detailed. The "bench testing" is related to the overall CT system.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.): Not mentioned for any AI-specific performance. The stated "ground truth" for the overall CT system's performance is derived from physical phantom measurements.
8. The sample size for the training set: Not mentioned. It's only stated that AiCE uses Deep Convolutional Network methods.
9. How the ground truth for the training set was established: Not mentioned.

In summary: The provided 510(k) summary focuses on demonstrating the substantial equivalence of the Aquilion Serve SP CT system to a predicate device, primarily through bench testing using phantoms and comparing general technical specifications. While it mentions the inclusion of an AI-powered noise reduction algorithm (AiCE), the document does not detail specific studies or acceptance criteria for this AI component's performance, either standalone or in a human-in-the-loop setting, which would typically involve clinical data, expert readers, and specific accuracy metrics.

Ask a specific question about this device