Search Results

Agfa's DX-D Imaging Package is indicated for use in general projection radiographic applications to capture for display diagnostic quality radiographic images of human anatomy for adult, pediatric and neonatal examinations. The DX-D Imaging Package may be used wherever conventional screen-film systems, CR or DR systems may be used.

Agfa's DX-D Imaging Package is not indicated for use in mammography.

The device is a direct radiography imaging system of similar design and construction to the original (predicate) version of the device. Agfa's DX-D Imaging Package uses the company's familiar NX workstation with MUSICA2™ image processing and flat panel detectors of the scintillator-photodetector type. Flat panel detectors with scintillators of both Cesium Iodide (Csl) and Gadolinium Oxysulfide (GOS) are available. The device is used to capture and directly digitize x-ray images without a separate digitizer. This new version includes optional image processing algorithms for adult, pediatric and neonatal images that were previously cleared for use in Agfa's computed radiography systems.

The device uses a direct conversion process to convert x-rays into a digital signal. X-rays incident on the scintillator layer of the detector generate light that is absorbed by photo-detectors, converted to a digital signal and sent to the workstation the data is processed by Agfa's MUSICA image processing software. The acronym MUSICA stands for Multi-Stage-Image-Contrast-Amplification. MUSICA acts on the acquired images to preferentially enhance the diagnostically relevant, moderate and subtle contrasts.

Principles of operation and technological characteristics of the new and predicate devices are the same.

While the provided text mentions that "Performance data including laboratory image quality measurements and image comparison studies by independent radiologists are adequate to ensure equivalence," it does not provide specific acceptance criteria or detailed results of these studies. Therefore, a table of acceptance criteria and reported device performance cannot be generated with the given information.

Here's an analysis of what can be extracted and what is missing:

Acceptance Criteria and Study Details (Based on Provided Text)

The document states that the performance data from "laboratory image quality measurements" and "image comparison studies by independent radiologists" were "adequate to ensure equivalence." However, no specific metrics, targets, or results for these studies are provided.

1. Table of Acceptance Criteria and Reported Device Performance

2. Sample Size and Data Provenance for Test Set

• Sample Size: Not specified.
• Data Provenance: The document mentions "In-hospital image quality comparisons," implying diagnostic images from a clinical setting. It does not specify the country of origin.
• Retrospective/Prospective: Not specified.

3. Number of Experts and Qualifications for Ground Truth

• Number of Experts: Not specified. The document mentions "independent radiologists."
• Qualifications of Experts: The document states "qualified independent radiologists." Specific experience (e.g., "10 years of experience") is not provided.

4. Adjudication Method for Test Set

• Adjudication Method: Not specified.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

• Was it done?: Not explicitly stated as an MRMC study in the standard terminology, but the document mentions "image comparison studies by independent radiologists" and "In-hospital image quality comparisons have been conducted with qualified independent radiologists." This suggests a human reader component. However, it's unclear if this was a comparative effectiveness study involving AI assistance.
• Effect Size of Human Readers with AI vs. Without AI Assistance: Not applicable, as the document doesn't describe AI-assisted reading or its effect size. The new version includes "optional image processing algorithms," but the study described is for the device's imaging quality, not human-in-the-loop performance with new algorithms.

6. Standalone (Algorithm Only) Performance Study

• Was it done?: No. The document describes the device as an imaging system, not a standalone AI algorithm for interpretation. The "optional image processing algorithms" are part of the overall imaging package, and the performance validation is for the "complete system," not the algorithm in isolation for diagnostic accuracy.

7. Type of Ground Truth Used

• Type of Ground Truth: Implied to be expert consensus/radiologist interpretation. The document refers to "image comparison studies by independent radiologists" and "in-hospital image quality comparisons." Pathology or outcomes data are not mentioned.

8. Sample Size for Training Set

• Sample Size: Not applicable. This device is an X-ray imaging system, not a machine learning algorithm that requires a "training set" in the conventional sense for diagnostic image analysis. The "new version includes optional image processing algorithms for adult, pediatric and neonatal images that were previously cleared." These algorithms would have been developed and validated, but the document doesn't provide details on their training data.

9. How Ground Truth for Training Set Was Established

• How Ground Truth for Training Set Was Established: Not applicable (see point 8).

Ask a specific question about this device