Search Results

Fibresolve is a software-only device that receives and analyzes lung computed tomography (CT) imaging data in order to provide a diagnostic subtype classification in suspected cases of interstitial lung disease (ILD). The device supplements the standard-of-care workflow by providing a qualitative, diagnostic classification output of imaging findings based on machine learning pattern recognition, in order to provide adjunctive information as part of a referral pathway to an appropriate Multidisciplinary Discussion (MDD) or as part of an MDD. Specifically, the tool is used to serve as an adjunct in the diagnosis of idiopathic pulmonary fibrosis (IPF) prior to invasive testing. The results of Fibresolve are intended to be used only by clinicians qualified in the care of lung disease, specifically in caring for patients with ILD, in conjunction with the patient's clinical history, symptoms, and other diagnostic tests, as well as the clinician's professional judgment.

The input to Fibresolve must include a DICOM-compliant lung CT scan. Clinical case eligibility includes the following criteria:

• Age > 22 years old.
• Pulmonary symptoms suggestive of possible ILD including IPF.

Fibresolve is a software system developed for qualitative disease assessment of DICOM-compliant chest computed tomography (CT) imaging. The software system is based on a machine learning model component and a Docker based HTTP/1.1 Representational State Transfer (REST) software application programming interfaces (APIs) to enable image transfer, analysis, and output of results.
The device consists of the following 3 components: (1) Image Receiver API for image acquisition in the cloud; (2) Ingestion Pipeline and Analysis System for image processing and analysis; and (3) Output API for device output transmission.
(1) The Image Receiver API is accessed via any DICOM-compliant system (e.g. PACS). The hospital or clinic either accesses the API directly via secure software integration and submits the images electronically; or the images are transmitted manually (e.g. by mail) to the device manufacturer and the case is submitted to the device through the API directly by the manufacturer. The API passes the images to the Ingestion Pipeline and Analysis System (2).
(2) (a) The Ingestion Pipeline and (b) Analysis System accept the images, select cases appropriate for processing, process the images for analysis, and analyze the images. This Analysis System includes the Fibresolve Model Inference Graph that generates the assessment for the case. The final device output report data including identifying information and technical details about the case data and a binary result stating whether the data are determined to be suggestive for the target disease state.

• The Ingestion Pipeline identifies applicable CT imaging series from the case and verifies that the series is valid, completes quality checks, and confirms adequacy for analysis.
• The Fibresolve Model Inference Graph, the core component of the Analysis System, is an ensemble 3D deep learning model developed and trained using images from multiple facilities. Analysis System algorithm development phases included model pre-training, model training to the disease target, architecture optimization, threshold determination, and validation. No segmentation is performed as part of the Analysis System.
  (3) The Output API transmits the Report data for the clinician to review. The Output API is either integrated into the hospital or clinic notification software (e.g. electronic health record) for electronic transmission or the device manufacturer transmits the Report in human-readable format directly (e.g. via fax). The clinician then incorporates the device Report as part of diagnostic decision-making.
  The system does not include an image viewer or visual output for diagnostic use. The source images are reviewed for subjective assessment prior to submission to the device using the facility's standard diagnostic viewer as part of routine standard-of-care and the source images can be reassessed by the clinical team at any time before or after submission of the case to the device. The system only assesses for the target disease described in the Intended Use and does not replace imaging interpretation generally.

The provided FDA 510(k) clearance letter and summary for Fibresolve (with PCCP) do not include the specific details of the performance study that proves the device meets acceptance criteria. The document states that "Software Verification and Validation (per IEC 62304) were performed to demonstrate safety based on current industry standards. The results of these tests indicate that the subject device is equivalent to the predicate device." However, it does not provide specific performance metrics, acceptance criteria, or details about the study design (e.g., sample size, expert review, ground truth establishment) for the original Fibresolve device.

The section on the Predetermined Change Control Plan (PCCP) mentions that "changes are evaluated via pre-specified statistical analyses in-line with those as part of the original device testing, to ensure, at minimum, non-inferior absolute performance, and potential improvements in performance, training data, or generalizability." This implies that such studies were conducted for the original device, but the details are not part of this 510(k) summary.

Therefore, while the document confirms a study was done for safety and equivalence, it does not contain the specific information requested about acceptance criteria and the detailed performance study. To answer your questions comprehensively, you would need to refer to the original 510(k) submission for the predicate device, Fibresolve (DEN220040).

Based on the provided text, I can only state that the specific details requested are NOT present in this document.

If such information were present, it would typically be found in a "Performance Data" or "Clinical Performance Testing" section, which is absent here. The document focuses on the new submission for the PCCP and compares it to the predicate device, assuming the predicate's performance data is already established.

Ask a specific question about this device