(49 days)
The Pulmo CT with Reference Database is intended for diagnostic imaging. It provides highly reproducible CT values for pulmonary tissue, which is essential for follow up examinations and for providing quantitative support for diagnosis.
The Pulmo CT with Reference Database enables the user to obtain CT scans at defined respiratory levels through spirometric control. The patient is asked to breath through a spirometer and when the inspiration reaches a certain percentage (e.g., 50%) of the patient's vital capacity, the CT scan is triggered.
In addition to respiratory controlled triggering of CT scans, the Pulmo CT option provides the following evaluation capabilities:
- isolation of the left and right lungs .
- . automatic and interactive segmentation of the entire lung, or of central or peripheral regions,
- . calculation and display of statistical parameters, including sub-range statistics (e.g., mean single-slice CT values),
- . calculation and display of histograms of the entire lung, as well as the left and right, and
- calculation and display of volumes and partial volumes ●
- Comparison of the patient's averaged histograms and mean CT values with the adult reference database.
The adult reference database contains a collection of lung CT values (density) acquired using existing Pulmo CT option from patients with normal lung functions.
The provided text describes a 510(k) summary for the "Pulmo CT with Reference Database Option for SOMATOM CT Systems." However, it seems to predate the common regulatory requirements for detailed acceptance criteria and validation studies as often seen for AI/ML devices today. The document describes a "reference database" as its primary distinguishing feature, which appears to be a statistical compilation rather than a predictive AI model in the modern sense.
Based on the provided text, a direct answer to your request with all specified information is not fully possible because the document does not contain the detailed validation study information, acceptance criteria, multi-reader multi-case studies, or ground truth establishment relevant to what would typically be expected for a contemporary AI/ML device.
Here's an attempt to extract and infer information based on the provided text, while also explicitly noting what is not available:
Acceptance Criteria and Reported Device Performance
The device described is more of a post-processing evaluation package that includes a reference database for comparison, rather than a predictive AI algorithm that would typically have performance metrics like sensitivity, specificity, or AUC against a ground truth.
| Acceptance Criteria | Reported Device Performance |
|---|---|
| Not explicitly stated as numerical performance metrics. The core "acceptance" is implied by its function: providing reproducible CT values and a reference for clinical evaluation of pulmonary diseases. | Functional Description: |
- Isolation of left and right lungs.
- Automatic and interactive segmentation of entire lung, or central/peripheral regions.
- Calculation and display of statistical parameters (e.g., mean single-slice CT values).
- Calculation and display of histograms.
- Calculation and display of volumes and partial volumes.
- Comparison of patient's averaged histograms and mean CT values with an adult reference database of normal lung functions. |
Study Details
The text describes a study to collect data for the reference database, not a validation study of the device's diagnostic performance against specific acceptance criteria using a test set.
2. Sample size used for the test set and the data provenance:
- Test Set Sample Size: Not applicable/not provided. The described study collected data to form the reference database, not to test the device's performance against independent ground truth.
- Data Provenance: "A multi-center clinical study was carried out in Europe to collect lung CT images from individuals with normal lung functions."
- Retrospective/Prospective: The text does not explicitly state retrospective or prospective, but the phrase "collect lung CT images" implies a prospective collection for the purpose of building the database.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- Not applicable/not provided. The study focused on collecting data from "individuals with normal lung functions" to establish a reference, rather than establishing a specific "ground truth" for diagnostic evaluation of the device. It's implied that the "normal lung functions" state was determined clinically, but the process and experts are not detailed.
4. Adjudication method (e.g., 2+1, 3+1, none) for the test set:
- Not applicable/not provided.
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. This type of study was not conducted or mentioned. The device provides a reference database, it's not described as an AI-powered diagnostic aid meant to augment human reader performance in a controlled MRMC setting.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- Partially applicable, but in a different context. The "device performance" in terms of its ability to process images, segment lungs, and calculate statistics is standalone as depicted. However, its "diagnostic utility" is as a comparison tool, which inherently involves a human interpreting the comparison. There's no evaluation of its diagnostic accuracy as a standalone diagnostic algorithm.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
- For the data collected for the reference database: The ground truth was "normal lung functions." How this was definitively established (e.g., by clinical assessment, PFTs, expert consensus on imaging) is not detailed.
8. The sample size for the training set:
- Not explicitly provided as a numerical value. The text states: "A multi-center clinical study was carried out in Europe to collect lung CT images from individuals with normal lung functions. The collected data, after statistical analysis, served as the reference database." The size of this collection, which serves as the "training" or "reference" data for the database, is not specified.
9. How the ground truth for the training set was established:
- The ground truth for the reference database was "individuals with normal lung functions." The method for establishing "normal lung functions" is not detailed (e.g., clinical assessment, pulmonary function tests, expert review criteria).
§ 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.