(179 days)
Adaptive Motion Correction (AMC) software is intended to be used as an adjunct to the current cardiac reconstruction methods in cases where motion of the coronary arteries creates artifacts. This software can be applied to these images, without additional dose to the patient, to enhance the visibility of the coronary arteries.
4D Airways Analysis is a post processing software that may be used in conjunction with chest CT images to provide automatic (semi-automatic) segmentation of the bronchial tree. This software may aid in the diagnosis and follow-up treatment of bronchial diseases.
Adaptive Motion Correction (AMC), CSMC-001A, is a reconstruction method available on 320 row Aquilion ONE CT systems, which have system software V7.0 or later installed, to aid physicians in analysis of CT coronary angiography images for diagnosis and treatment planning.
4D Airways Analysis, CSAA-001A, is a post-processing software used on 320 row Aquillion ONE CT systems, which have system software V7.0 or later installed, to aid physicians in analysis of chest CT images for diagnosis and treatment planning.
The provided text describes two software features: Adaptive Motion Correction (AMC) and 4D Airways Analysis. Since the details for each are somewhat distinct, I will present the information separately where appropriate.
Adaptive Motion Correction (AMC), CSMC-001A
1. Table of Acceptance Criteria and Reported Device Performance:
| Acceptance Criteria | Reported Device Performance |
|---|---|
| Improved visualization of coronary arteries | Demonstrated improved visualization of the coronary arteries with the exception of RCA (Right Coronary Artery). |
2. Sample size used for the test set and the data provenance:
- Test Set Sample Size: Not explicitly stated.
- Data Provenance: Not explicitly stated, though referred to as "clinical evaluations." It's common for such evaluations to use retrospective data from existing patient scans.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- Number of Experts: Not explicitly stated, described as "qualified users."
- Qualifications of Experts: "Qualified users" - specific qualifications (e.g., radiologist with X years of experience) are not provided.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set:
- Adjudication Method: Not explicitly stated. The text only mentions "clinical evaluations were performed by qualified users."
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:
- MRMC Study: Not explicitly stated as an MRMC study. The evaluation focused on improved visualization, which can be part of qualitative MRMC-like assessments, but the methodology is not detailed enough to confirm.
- Effect Size: Not provided.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- Standalone Performance: Not explicitly stated. The description implies that the software is used as an "adjunct," suggesting human-in-the-loop, where AMC enhances images for physician review.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
- Type of Ground Truth: The improved visualization was likely based on subjective expert assessment (clinical evaluation by qualified users) of image quality and artifact reduction, rather than a definitive "ground truth" like pathology for diagnosis.
8. The sample size for the training set:
- Training Set Sample Size: Not provided.
9. How the ground truth for the training set was established:
- Ground Truth Establishment (Training Set): Not provided.
4D Airways Analysis, CSAA-001A
1. Table of Acceptance Criteria and Reported Device Performance:
| Acceptance Criteria | Reported Device Performance |
|---|---|
| Reduce user variability in measurements | Demonstrated that the user variability associated with this type of measurement was reduced. |
| Provide automatic (semi-automatic) segmentation of the bronchial tree | Yes (implied by device description) |
2. Sample size used for the test set and the data provenance:
- Test Set Sample Size: Not explicitly stated.
- Data Provenance: Not explicitly stated, though referred to as "clinical evaluations." It's common for such evaluations to use retrospective data from existing patient scans.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- Number of Experts: Not explicitly stated, described as "qualified users."
- Qualifications of Experts: "Qualified users" - specific qualifications are not provided.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set:
- Adjudication Method: Not explicitly stated. The text only mentions "clinical evaluations were performed by qualified users."
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:
- MRMC Study: Not explicitly stated as an MRMC study. The evaluation focused on "reduced user variability," which suggests a quantitative assessment that might involve multiple readers, but the methodology is not detailed enough to confirm an MRMC study or an effect size for human reader improvement with AI assistance.
- Effect Size: Not provided.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- Standalone Performance: The software provides "automatic (semi-automatic) segmentation." While the core segmentation might be algorithmic, the assessment focused on "user variability associated with this type of measurement," suggesting human interaction and measurement following the segmentation. It does not explicitly describe a standalone algorithm-only performance assessment against a ground truth without human interaction.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
- Type of Ground Truth: The reduction in user variability implies a comparison of measurements made by different users, possibly against a reference measurement or an agreed-upon standard for bronchial tree segmentation and measurement. This would likely involve expert consensus or established anatomical landmarks/measurements.
8. The sample size for the training set:
- Training Set Sample Size: Not provided.
9. How the ground truth for the training set was established:
- Ground Truth Establishment (Training Set): Not provided.
General Notes for Both Devices:
- The document is a 510(k) summary, which provides a high-level overview for substantial equivalence. It is not typically a detailed scientific publication. As such, many specific methodological details common in research papers (like exact sample sizes, detailed ground truth establishment, or specific expert qualifications) are often not included.
- The emphasis in a 510(k) is on demonstrating substantial equivalence to a predicate device and safety/effectiveness rather than a comprehensive efficacy trial.
- "Verification/validation and performance testing conducted through bench testing" and "Software Documentation for a Moderate Level of Concern" were also part of the submission, indicating adherence to general software development and testing standards.
§ 892.1750 Computed tomography x-ray system.
(a)
Identification. A computed tomography x-ray system is a diagnostic x-ray system intended to produce cross-sectional images of the body by computer reconstruction of x-ray transmission data from the same axial plane taken at different angles. This generic type of device may include signal analysis and display equipment, patient and equipment supports, component parts, and accessories.(b)
Classification. Class II.