(146 days)
The Imbio CT Lung Density Analysis Software provides reproducible CT values for pulmonary tissue, which is essential for providing quantitative support for diagnosis and follow up examinations. The Imbio CT Lung Density Analysis Software can be used to support the diagnosis and documentation of pulmonary tissue images (e.g., abnormalities) from CT thoracic datasets. Three-D segmentation of sub-compartments, volumetric analysis, density evaluations and reporting tools are provided.
The Imbio CT Lung Density Analysis Software (Imbio LDA) is a set of image post-processing algorithms that perform image segmentation, registration, thresholding, and classification on CT images of human lungs. The algorithms within the Imbio CT Lung Density Analysis Software are combined into a single command-line executable program that may be run directly from the command-line or through scripting. The Imbio CT Lung Density Analysis Software program performs segmentation, then registration, then thresholding and classification. The program reads in DICOM datasets, processes the data, then writes output DICOM files to a specified directory. The Imbio CT Lung Density Analysis Software is a command-line software application that analyzes DICOM CT lung image datasets and generates reports and DICOM output that show the lungs segmented and overlaid with color-codings representing the results of its thresholding and classification rules. It has simple file management functions for input and output, and separate modules that implement the CT image-processing algorithms. Imbio CT Lung Density Analysis Software does not interface directly with any CT or data collection equipment; instead the software imports data files previously generated by such equipment.
Here's a breakdown of the acceptance criteria and study details for the Imbio CT Lung Density Analysis Software, based on the provided FDA 510(k) summary:
This device is cleared under a 510(k), which means it demonstrates substantial equivalence to a legally marketed predicate device rather than proving de novo safety and effectiveness through extensive clinical trials. Therefore, the "acceptance criteria" here refers more to the demonstration that the device's performance aligns with its specifications and is comparable to the predicate, rather than meeting specific clinical efficacy thresholds.
Study that proves the device meets the acceptance criteria:
The study primarily focused on non-clinical testing to demonstrate substantial equivalence to the predicate device (VIDA Pulmonary Workstation 2 (PW2), K083227).
1. Table of Acceptance Criteria and Reported Device Performance:
Since this is a 510(k) summary focused on substantial equivalence through non-clinical testing, specific quantitative "acceptance criteria" and "reported performance" in a typical clinical trial sense are not explicitly provided with numerical thresholds. Instead, the acceptance criteria were implicitly "functional equivalence," "accurate segmentation," and "accurate thresholding" compared to the predicate device and the ground truth derived from the datasets.
| Acceptance Criteria (Implied) | Reported Device Performance |
|---|---|
| Functional Equivalence to Predicate: Performs similar image post-processing (segmentation, registration, thresholding, classification) for CT lung images. | The Imbio CT Lung Density Analysis Software imports CT DICOM data, analyzes it, and produces reports with quantitative and graphical results, similar to the predicate. "Direct quantitative comparisons using the same CT lung scans yielded similar results." Differences (command-line interface vs. GUI, automated vs. manual inspiration/expiration registration, lack of interactive visualization, low-density cluster analysis, and airway report compared to predicate) were deemed not to affect efficacy and safety. |
| Accurate Scan Processing Completion: Software successfully processes all scans as expected. | "Direct predicate comparison for scan processing completion" was performed, indicating successful processing. |
| Accurate Segmentation: Correctly identifies and separates anatomical structures (e.g., lungs). | "Direct predicate comparison for... segmentation" was performed, indicating accurate segmentation. |
| Accurate Thresholding: Applies density thresholds correctly for classification. | "Direct predicate comparison for... thresholding" was performed, indicating accurate thresholding. |
| Specification Compliance: Software functions according to its stated specifications. | "Software verification and validation testing for each requirement specification" was conducted. |
| Algorithmic Functionality: Each algorithmic function performs as intended. | "Software verification and validation testing for each algorithmic function" was conducted. |
| System Reliability: Software operates reliably at unit, integration, and system levels. | "Software verification and validation testing at the unit, integration, and system level" was conducted. |
| Safety and Effectiveness: No new questions of safety or effectiveness are raised compared to the predicate device. | The conclusion states: "It has been shown in this 510(k) submission that the differences between the Imbio CT Lung Density Analysis Software and the VIDA PW2 (K0832277) do not raise any questions regarding safety and effectiveness." |
2. Sample Size Used for the Test Set and Data Provenance:
- Sample Size: Not explicitly stated as a number of patients or cases. The document mentions "CT datasets available upon request from the COPDGene study (www.copdgene.org) and the DIR-Lab (www.dir-lab.com)." These are large, publicly available research datasets, implying a potentially substantial number of cases were available for testing.
- Data Provenance:
- Country of Origin: Not specified for individual cases, but COPDGene is a multi-center study in the United States. DIR-Lab also sources data, often from US institutions. So, likely predominantly USA.
- Retrospective or Prospective: The use of "available upon request" datasets like COPDGene and DIR-Lab strongly suggests a retrospective analysis of existing data.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts:
- This information is not provided in the summary. Since the testing was primarily non-clinical and involved comparing software output to established datasets and a predicate device, explicit expert ground truth labeling for a test set (e.g., by radiologists) is not detailed. The "ground truth" for segmentation and density measurements would be derived from the inherent data characteristics and comparison to the predicate's outputs, which are themselves based on accepted medical imaging principles.
4. Adjudication Method for the Test Set:
- Not applicable/Not specified. Given the nature of the non-clinical testing focused on software functionality and comparison to a predicate, an expert adjudication process (like 2+1 reading) is not described. The "direct predicate comparison" served as a primary reference.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and Effect Size of Human Reader Improvement:
- No, an MRMC comparative effectiveness study was not done. The summary explicitly states: "This technology is not new, therefore a clinical study was not considered necessary prior to release. Additionally, there was no clinical testing required to support the medical device as the indications for use is equivalent to the predicate device."
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done:
- Yes, a standalone performance assessment was effectively done. The non-clinical testing detailed ("Direct predicate comparison for scan processing completion, segmentation, and thresholding," and "Software verification and validation testing for each requirement specification," "each algorithmic function," and "at the unit, integration, and system level") assesses the algorithm's performance directly, without human intervention during the processing steps.
7. The Type of Ground Truth Used:
- The primary "ground truth" for the non-clinical testing was:
- Reference standard from public datasets: The inherent, accepted characteristics of the COPDGene and DIR-Lab CT datasets regarding lung anatomy and density.
- Comparison to Predicate Device Output: The outputs of the legally marketed predicate device (VIDA PW2) on the same CT lung scans were used as a primary comparative reference, implying that the predicate's performance served as a de facto "ground truth" for equivalence.
- Software Specifications: The internal design specifications and expected behaviors of the Imbio software itself were also used as a basis for verification and validation.
8. The Sample Size for the Training Set:
- Not specified. The document mentions the use of COPDGene and DIR-Lab datasets for "non-clinical testing" and verifying function. It does not provide details on how the training of the algorithms (if applicable, for example, for segmentation models) was performed or the specific datasets and sample sizes used for that purpose. This summary is focused on the verification and validation of the final product for regulatory submission.
9. How the Ground Truth for the Training Set Was Established:
- Not specified. As the training set details are not provided, neither is the method for establishing its ground truth. However, for algorithms like segmentation and density analysis, ground truth for training would typically involve manual annotation by expert radiologists or technologists, or derived from other well-established imaging techniques or pathological correlation, depending on the algorithm's specifics.
§ 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.