Search Results
Found 1 results
510(k) Data Aggregation
(194 days)
Aquilion Lightning (TSX-036A/7) V10.2 with AiCE-i
This device is indicated to acquire and display cross-sectional volumes of the whole body, to include the head.
The Aquilion Lightning has the capability to provide 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 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.
The Aquilion Lightning (TSX-036A/7) V10.2 with AiCE-i is an 80-row CT system that is a whole body, multi-slice helical CT scanner, consisting of a gantry, couch and console used for data processing and display. This device captures cross sectional volume data sets used to perform specialized studies, using indicated software/hardware, by a trained and qualified physician. This system is based upon the technology and materials of previously marketed Canon CT systems. In addition, the subject device incorporates the latest reconstruction technology, AiCE-i (Advanced intelligent Clear-IQ Engine - integrated), intended to reduce image noise and improve image quality by utilizing Deep Convolutional Network (DCNN) methods. This reconstruction algorithm is predicated on AiCE reconstruction algorithm previously 510(k) cleared per K192832 on the Canon CT scanner Aquilion Prime SP (TSX-303B/8) V10.2 with AiCE-i, which serves as a reference predicate for this submission. The DCNN 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 for every patient.
The provided text describes a 510(k) premarket notification for the "Aquilion Lightning (TSX-036A/7) V10.2 with AiCE-i" system. The acceptance criteria and the study proving the device meets them are outlined, primarily focusing on phantom studies rather than clinical performance for the new AiCE-i feature.
Here's a breakdown of the requested information:
1. Table of acceptance criteria and the reported device performance
| Acceptance Criteria Category | Specific Metric | Predicate Performance (Baseline) | Reported Device Performance (AiCE-i) |
|---|---|---|---|
| Image Quality (Phantom Study) | Contrast-to-Noise Ratios (CNR) | Not explicitly stated, inferred from predicate equivalence | Found substantially equivalent to predicate |
| CT Number Accuracy | Not explicitly stated, inferred from predicate equivalence | Found substantially equivalent to predicate | |
| Uniformity | Not explicitly stated, inferred from predicate equivalence | Found substantially equivalent to predicate | |
| Slice Sensitivity Profile (SSP) | Not explicitly stated, inferred from predicate equivalence | Found substantially equivalent to predicate | |
| Modulation Transfer Function (MTF)-Wire | Not explicitly stated, inferred from predicate equivalence | Found substantially equivalent to predicate | |
| Standard Deviation of Noise (SD) | Not explicitly stated, inferred from predicate equivalence | Found substantially equivalent to predicate | |
| Noise Power Spectra (NPS) | Not explicitly stated, inferred from predicate equivalence | Found substantially equivalent to predicate | |
| Low Contrast Detectability (LCD) | Not explicitly stated (for phantom study) | Found substantially equivalent to predicate | |
| Quantitative Spatial Resolution (Phantom Study) | High Contrast Spatial Resolution | AIDR 3D performance | Double the high contrast spatial resolution versus AIDR 3D for body (AiCE Body Sharp) |
| Quantitative Body LCD, Noise Improvement & Dose Reduction (Phantom Study) | Low Contrast Detectability (Body) | Not explicitly stated | 15% improved low contrast detectability compared to AIDR 3D (at the same dose) |
| Noise Reduction (Body) | AIDR 3D performance | 29% noise reduction compared to AIDR 3D (at the same dose) | |
| Dose Reduction | FBP performance | Up to 82.9% dose reduction, relative to FBP | |
| Noise Appearance/Texture | Noise appearance/texture | Filtered Back Projection (FBP) | Similar to filtered backprojection |
| Overall Equivalence | Substantial Equivalence to Predicate | Aquilion Lightning (TSX-036A/1) V8.4 (K170019) | Demonstrated |
| Safety and Standards Compliance | Compliance with Medical Device Standards | Various IEC, NEMA, and CFR standards | Conformance demonstrated |
| Software Validation | Software Documentation (Moderate Level of Concern) | Not applicable (new feature) | Verification and validation met |
| Cybersecurity | Cybersecurity Documentation | Not applicable (new feature) | Documentation included |
2. Sample size used for the test set and the data provenance
The document does not mention clinical test sets or human subject data. All performance claims for the AiCE-i feature are based on phantom studies. Therefore, there is no information about data provenance (country of origin, retrospective/prospective) or sample size in terms of patient numbers.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
Not applicable. The evaluation was based on phantom studies and quantitative measurements, not expert interpretation of clinical images.
4. Adjudication method for the test set
Not applicable, as the evaluation was based on phantom studies and quantitative measurements, not expert interpretation requiring adjudication.
5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance
No MRMC study was done or reported. The document explicitly states: "It was determined that representative clinical images were not necessary to demonstrate substantial equivalence of the subject device." The focus was on demonstrating the technical performance of the AiCE-i algorithm using phantoms.
6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done
Yes, the performance evaluation primarily focused on the standalone performance of the AiCE-i algorithm as applied to phantom images. The reported improvements in spatial resolution, low contrast detectability, and noise reduction are algorithm-only metrics.
7. The type of ground truth used
The ground truth used was based on phantom measurements. These are objective, reproducible physical properties measured from the phantom, rather than expert consensus, pathology, or outcomes data.
8. The sample size for the training set
The document does not specify the sample size for the training set used for the Deep Convolutional Network (DCNN) methods of AiCE-i. It mentions that AiCE-i is predicated on the AiCE reconstruction algorithm previously cleared under K192832, implying it leverages that established training.
9. How the ground truth for the training set was established
The document does not explicitly state how the ground truth for the training set was established. It describes AiCE as "learning to differentiate structure from noise" using DCNN methods. Typically, for such deep learning models, the training ground truth involves pairs of noisy and "clean" or "reference" images, where the "clean" image serves as the ground truth. This could be generated through various methods, such as extremely low-noise scans, statistical models, or simulations, but the specific method is not detailed here.
Ask a specific question about this device
Page 1 of 1