(266 days)
Broncholab provides physicians with reproducible CT values for providing quantitative support for diagnosis and follow-up examination. Broncholab can be used to support physicians in the diagnosis and documentation of pulmonary tissues images (e.g., abnormalities) from CT thoracic datasets. Three-D segmentation and isolation of subcompartments, volumetric analysis, density evaluations, low density cluster analysis, fissure evaluation and reporting tools are combined with a dedicated workflow.
Broncholab is a SaMD (Software as Medical Device) which provides quantitative CT values that are intended to support the physician in the diagnosis and documentation of pulmonary tissues images (abnormalities) from CT scans. The CT scan images are transformed into 3D models of the patient-specific lungs using several image processing steps. Broncholab can be used to assess the effectiveness of therapy based on CT scan data. It is used along with the following accessories:
- Web Portal: Enables the uploading of CT scans and patient data
- Client Report: Enables the conversion of the output of Broncholab (CT values) into a desired digital format (PDF Report) and transfers this Report to the physician via email.
Inspiratory CT scan images uploaded by the users are converted into quantitative CT values using a combination of software tools. Quality checks (both manual and automated) are implemented to assure the quality of the final data. The outputs are provided as absolute values and as a percentage of the total airway volume/ lobar volume depending on the parameter. The device can be used on a computer with a web browser installed and consists of two accessories: - An online portal to upload the CT scans
- An accessory that enables the creation of the Report
The CT values include: -
- Lung and Lobar Volume is the volume of the 3D model of each lung lobe.
-
- Airway Volume is defined as the region from the trachea until the segmental bronchi.
-
- Lung Density Scores/ Volumes is defined as all the intrapulmonary voxels with Hounsfield Units between -1024 and -950 using the inspiratory scans:
- Low attenuation areas below -950 HU (LAA-950HU)
- 15th percentile of density histogram : Percentile density (PD) can also be used to express Emphysema.
- Blood vessel density : Blood vessel density can be determined through segmentation and 3-D reconstruction of the blood vessels. The segmentation is based on local geometry features and HU thresholds and is performed on the inspiratory CT scan.
-
- Fissure Analysis (fissure integrity) is the percentage of the fissure. Lung fissures are a doublefold of visceral pleura that either completely or incompletely separates the lungs into lung lobes.
CT scan images must be DICOM 3.0 compliant.
- Fissure Analysis (fissure integrity) is the percentage of the fissure. Lung fissures are a doublefold of visceral pleura that either completely or incompletely separates the lungs into lung lobes.
Here's a breakdown of the requested information regarding the acceptance criteria and study for the Broncholab device:
1. Table of Acceptance Criteria and Reported Device Performance
Note: The document provides performance results in relation to a predicate device (Vida PW2) for most metrics, and against expert segmentations for airway volume. The acceptance criteria for the comparison against the predicate are implicitly defined by similar performance to the predicate or being below specified thresholds. For airway volume, explicit thresholds are provided.
| Metric | Acceptance Criteria | Reported Device Performance |
|---|---|---|
| Lobe Volume (Relative values) | Mean difference (range) between Broncholab and predicate device less than 5% | Mean difference (range) between Broncholab and predicate device was less than 5% |
| Lobe Volume (Absolute values) | Mean difference (range) between Broncholab and predicate device less than 150mL | Mean difference (range) between Broncholab and predicate device was less than 150mL |
| Emphysema (Relative values) | Mean difference (range) between Broncholab and predicate device less than 5% | Mean difference (range) between Broncholab and predicate device was less than 5% |
| Emphysema (Absolute values) | Mean difference (range) between Broncholab and predicate device less than 150mL | Mean difference (range) between Broncholab and predicate device was less than 150mL |
| Blood Vessel Density (Relative values) | Mean difference (range) between Broncholab and predicate device less than 5% | Mean difference (range) between Broncholab and predicate device was less than 5% |
| Blood Vessel Density (Absolute values) | Mean difference (range) between Broncholab and predicate device less than 150mL | Mean difference (range) between Broncholab and predicate device was less than 150mL |
| 15th Percentile Lung Density (PD15) | Mean difference (range) between Broncholab and predicate device less than 1 HU | Mean difference (range) between Broncholab and predicate device was less than 1 HU |
| Fissure Integrity | Intraclass Correlation Coefficient (ICC) of 0.75 or higher (implicitly, based on reported value) | ICC estimate (95% CI) for comparison of fissure integrity was 0.75 (0.54, 0.87) |
| Airway Volume (Relative values) | Mean difference (range) between Broncholab and physicians less than 5% | Mean difference (range) between Broncholab and physicians was less than 5% |
| Airway Volume (Absolute values) | Mean difference (range) between Broncholab and physicians less than 150mL | Mean difference (range) between Broncholab and physicians was less than 150mL |
The document mentions "The tolerable variability for absolute and relative values are 150mL and 5%, respectively." This statement applies to the absolute and relative values across the various metrics where applicable.
2. Sample Size Used for the Test Set and Data Provenance
The document does not explicitly state the specific sample size (number of cases/patients) used for the comparison study. It refers to "datasets used for the performance testing."
Data Provenance: The CT scans used were taken from a "wide variety of scanner brands and models" including GE Healthcare, Philips, and Siemens. The specific country of origin or whether the data was retrospective or prospective is not explicitly stated in the provided text.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications
- Number of Experts: 3 physicians
- Qualifications of Experts: The document refers to them simply as "three physicians." No specific subspecialty (e.g., radiologist) or years of experience are provided.
4. Adjudication Method for the Test Set
For airway volume, the ground truth was established by "taking the mean airway volume obtained from three physicians' segmentation." This implies a form of consensus or averaging method after individual expert input, but not a formal adjudication method like 2+1 or 3+1 for discordance resolution.
For other metrics compared against the predicate device, the ground truth for the test set is implicitly the output of the predicate device itself, rather than expert consensus on individual features.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done
No. The provided text describes a head-to-head performance testing against a predicate device and against expert segmentations for airway volume. It does not describe a multi-reader, multi-case (MRMC) comparative effectiveness study to assess the improvement of human readers with AI assistance versus without. Therefore, there is no effect size reported for human readers improving with AI assistance.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done
Yes. The study described is a standalone performance evaluation of the Broncholab algorithm. It compares the algorithm's output directly against the predicate device's output and against expert segmentations (for airway volume) without the involvement of a human-in-the-loop interacting with the Broncholab device during the performance assessment phase.
7. The Type of Ground Truth Used
- For Lobe Volume, Emphysema, Blood Vessel Density, PD15, and Fissure Integrity: The ground truth was effectively the output of the predicate device (Vida Pulmonary Workstation 2 (PW2)). The study aims to show substantial equivalence to this legally marketed device.
- For Airway Volume: The ground truth was expert consensus (mean of three physicians' segmentations).
8. The Sample Size for the Training Set
The document does not provide information regarding the sample size used for the training set of the Broncholab algorithm. It focuses solely on the performance testing.
9. How the Ground Truth for the Training Set Was Established
The document does not provide information on how the ground truth for the training set was established.
§ 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.