Search Results

This device is indicated to acquire and display cross-sectional volumes of the whole the head. The Aquilion Precision 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.

FIRST is an iterative reconstruction algorithm intended to reduce exposure dose and improve high contrast spatial resolution for abdomen, pelvis, chest, cardiac, extremities, and head applications.

AiCE 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 Precision (TSX-304A/4) V10.14 with AiCE is an ultra-high resolution whole body multislice helical CT scanner, consisting of a gantry, couch and a console used for data processing and display. Aquilion Precision incorporates a 160-row, 0.25 mm detector, a 5.7- MHU large-capacity tube, and 0.35 s scanning, enabling wide-range scanning with short scan times to capture cross sectional volume data sets used to perform specialized studies, using indicated software/hardware, by a trained and qualified physician. In addition, the subject device incorporates the latest reconstruction technology, FIRST, intended to reduce exposure dose while maintaining and/or improving image quality as well as, AiCE (Advanced intelligent Clear-IQ Engine), intended to reduce image noise and improve image quality by utilizing Deep Convolutional Neural Network methods to 1024x1024 HR/SHR images. These methods can more fully explore the statistical properties of the signal and noise. By learning to differentiate structure from noise, the algorithm produces fast, high quality CT reconstruction.

Here's a breakdown of the acceptance criteria and the study proving the device meets them, based on the provided FDA 510(k) summary for the Aquilion Precision (TSX-304A/4) V10.14 with AiCE:

Context: The submission is for a modification to an existing device, where the AiCE (Advanced intelligent Clear-IQ Engine) noise reduction algorithm is expanded to new anatomical regions: extremities, head (brain CTA), and inner ear. Therefore, the focus of the performance testing is to demonstrate sufficient image quality and potential improvements in spatial resolution in these new applications.

1. Table of Acceptance Criteria and Reported Device Performance

The document doesn't explicitly list "acceptance criteria" as pass/fail thresholds with specific numerical values for each image quality metric. Instead, the performance testing aims to demonstrate equivalence to the predicate device and highlight quantitative improvements where applicable. The stated performance demonstrates that "AiCE is substantially equivalent to the predicate device as demonstrated by the results of the above testing" and that "the reconstructed images using the subject device were of diagnostic quality."

Implicit Acceptance Criteria & Reported Performance:

• Equivalence to predicate device in previously cleared applications. | "reconstructed images using the subject device were of diagnostic quality."
  "AiCE is substantially equivalent to the predicate device" (based on Phantom Test Results) |
  | Contrast-to-Noise Ratios (CNR) | Maintained or improved compared to predicate/baseline. | Assessed (specific values not provided, but deemed "substantially equivalent"). |
  | CT Number Accuracy | Maintained accuracy. | Assessed (specific values not provided, but deemed "substantially equivalent"). |
  | Uniformity | Maintained uniformity. | Assessed (specific values not provided, but deemed "substantially equivalent"). |
  | Slice Sensitivity Profile (SSPz) | Maintained or improved profile. | Assessed (specific values not provided, but deemed "substantially equivalent"). |
  | Modulation Transfer Function (MTF)-Wire | Maintained or improved spatial resolution. | Assessed (specific values not provided, but deemed "substantially equivalent"). |
  | Modulation Transfer Function (MTF)-Edge | Maintained or improved spatial resolution. | Assessed (specific values not provided, but deemed "substantially equivalent"). |
  | Standard Deviation of Noise (SD) | Maintained or reduced noise. | Assessed (specific values not provided, but deemed "substantially equivalent"). |
  | Noise Power Spectra (NPS) | Acceptable noise characteristics. | Assessed (specific values not provided, but deemed "substantially equivalent"). |
  | Low Contrast Detectability (LCD) | Maintained or improved detectability. | Assessed (specific values not provided, but deemed "substantially equivalent"). |
  | Pediatric conditions | Acceptable performance for pediatric imaging. | Assessed (specific values not provided, but deemed "substantially equivalent"). |
  | High Contrast Spatial Resolution (Quantitative Improvement) | Demonstrable improvement in specific applications for newly added AiCE regions. | Bone in HR mode: 5.37 lp/cm improvement (at 10% MTF and same dose).
  Inner Ear in HR mode: 7.50 lp/cm improvement (at 10% MTF and same dose).
  Brain CTA in HR mode: 11.31 lp/cm improvement (at 10% MTF and same dose). |

2. Sample Size Used for the Test Set and Data Provenance

• Sample Size: The document refers to "Representative Abdomen Bone, Brain CTA, and Inner Ear images." This implies a qualitative selection rather than a large, statistically defined sample size of clinical cases. The quantitative spatial resolution improvement was likely assessed using phantoms, not clinical images, which is common for such technical measurements.
• Data Provenance: Not explicitly stated regarding country of origin. The images were "obtained using the subject device," implying prospective acquisition for the purpose of this evaluation, but it's not explicitly stated if they were newly acquired for this submission or if they were existing images. The evaluation states "reviewed by an American Board Certified Radiologist," which might suggest clinical images from the US, but this is not definitive.
• Retrospective or Prospective: Unspecified, but the phrasing "obtained using the subject device" suggests they could be prospectively acquired.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications

• Number of Experts: One.
• Qualifications of Experts: "an American Board Certified Radiologist." No specific years of experience are provided.

4. Adjudication Method for the Test Set

No explicit adjudication method is described. The single radiologist reviewed the images and "it was confirmed that the reconstructed images using the subject device were of diagnostic quality." This implies a sole reader assessment for the qualitative clinical image evaluation.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done

No, an MRMC comparative effectiveness study involving human readers with and without AI assistance was not reported in this summary. The clinical evaluation was a single radiologist's qualitative assessment of diagnostic quality.

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

Yes, a standalone performance assessment was conducted for objective image quality metrics using phantoms. This includes:

• Contrast-to-Noise Ratios (CNR)
• CT Number Accuracy
• Uniformity
• Slice Sensitivity Profile (SSPz)
• Modulation Transfer Function (MTF)-Wire
• Modulation Transfer Function (MTF)-Edge
• Standard Deviation of Noise (SD)
• Noise Power Spectra (NPS)
• Low Contrast Detectability (LCD)
• Pediatric conditions

The quantitative spatial resolution improvement claims (5.37 lp/cm, 7.50 lp/cm, 11.31 lp/cm) are also results of standalone (algorithm only) performance tests, likely performed on phantoms.

7. The Type of Ground Truth Used

• For objective image quality metrics (phantoms): The ground truth is the known physical properties and measurements derived from the phantoms themselves (e.g., known dimensions for MTF, known densities for CT number accuracy).
• For clinical image quality: The ground truth for "diagnostic quality" was established by expert consensus / opinion from a single "American Board Certified Radiologist." There's no mention of pathology or outcomes data being used as ground truth for this aspect.

8. The Sample Size for the Training Set

The document does not provide any information about the sample size (or any details) for the training set used for the AiCE Deep Convolutional Network. This information is typically not included in FDA 510(k) summaries, as the focus is on validation and verification rather than the internal development process of the AI model.

9. How the Ground Truth for the Training Set was Established

As no information is provided about the training set, there is also no information on how its ground truth was established.

Ask a specific question about this device