Search Results

The Pulmonx LIA software provides CT values for pulmonary tissue which is essential for providing quantitative support for diagnosis and follow up examination. The LIA software can be used to support physician in the diagnosis and documentation of pulmonary tissue images (e.g. abnormalities) from CT thoracic datasets. Three-D segmentation and isolation of sub-compartments (including lung structures), volumetric analysis, density evaluation, and reporting tools are provided.

The Lung Image Analysis (LIA) software is designed to aid in the interpretation of Computed Tomography (CT) scans of the thorax that may contain pulmonary abnormalities. Lung Image Analysis has both a graphical user interface and command-line software which can be run as a Windows application or from a command-line interpreter. The LIA software is to be used by trained professionals who are responsible for the correct and accurate use of medical images. In a typical clinical environment, the results provided by the software are used together with other clinical information by a medical professional. The software may be installed on an off-the-shelf PC computer system and is intended to be used with uncompressed digital images that are saved in DICOM format.

Here's a detailed breakdown of the acceptance criteria and the study proving the device meets them, based on the provided text:

Acceptance Criteria and Device Performance

The document doesn't explicitly list "acceptance criteria" in a dedicated table format with specific numerical thresholds (e.g., "accuracy > 90%"). Instead, it describes an equivalence study where the acceptance criteria were met if the results from the subject device (LIA) were "similar" to the predicate device (Thirona LungQ). The study compared specific measurements, implying that the LIA's ability to produce comparable values for these measurements constituted meeting the acceptance criteria.

Table of Acceptance Criteria (Inferred) and Reported Device Performance

Note: The term "similar" is subjective without defined statistical thresholds (e.g., p-value, correlation coefficient, absolute difference thresholds). However, the FDA’s clearance implies they deemed the similarity sufficient for substantial equivalence.

Study Details

1. Sample Size Used for the Test Set and Data Provenance:

   • Sample Size: 30 scans.
   • Data Provenance: Not specified in the provided text (e.g., country of origin, retrospective or prospective).

2. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of those Experts:

   • The document does not mention using experts to establish ground truth for the test set in the context of the equivalence study. The study appears to directly compare the LIA device's output to the predicate device's output, with the predicate device's output implicitly serving as a reference.

3. Adjudication Method for the Test Set:

   • Not applicable as the study compares the LIA's output directly to the predicate device's output, rather than to an expert-adjudicated ground truth.

4. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done:

   • No, a multi-reader multi-case (MRMC) comparative effectiveness study was not explicitly mentioned or described. The study focused on comparing the algorithmic measurements of the LIA to a predicate device's algorithmic measurements.

5. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was done:

   • Yes, the performance study described is a standalone (algorithm-only) study. It compares the computational output of the LIA software directly with the computational output of the predicate device (Thirona LungQ) for specific measurements (fissure calculations, lobar volumes, voxel density scores). There is no human-in-the-loop component described for this comparison study.

6. The type of ground truth used:

   • The "ground truth" for the equivalence study was effectively the measurements provided by the legally marketed predicate device (Thirona LungQ). The study's goal was to show that LIA's measurements were "similar" to those of the predicate.

7. The sample size for the training set:

   • The document does not specify the sample size used for the training set for the LIA software. The provided text only describes the validation/test set for the equivalence study.

8. How the ground truth for the training set was established:

   • The document does not specify how the ground truth for any potential training set was established. This information is typically proprietary to the manufacturer and not always included in a 510(k) summary focused on validation.

Ask a specific question about this device