Search Results

The GF85 Digital X-ray Imaging System is intended for use in generating radiographic images of human anatomy by a qualified/trained doctor or technician. This device is not intended for mammographic applications.

The GF85 digital X-ray imaging system is used to capture images by transmitting X-ray to a patient's body. The X-ray passing through a patient's body is sent to the detector and then converted into electrical signals. These signals go through the process of amplification and digital data conversion in the signal process on the S-station, which is the Operation Software (OS) of Samsung Digital Diagnostic X-ray System, and save in DICOM file, a standard for medical imaging. The captured images are tuned up by an Image Post-processing Engine (IPE) which is exclusively installed in S-station, and sent to the Picture Archiving & Communication System (PACS) sever for reading images. The GF85 Digital X-ray Imaging System includes two models, namely the GF85-3P and GF85-SP. These two models differ primarily in terms of their respective configurations of High Voltage Generators (HVGs). Specifically, the GF85-3P features capacities of 80 kW, 65 kW and 50 kW with 3 phases, whereas the GF85-SP provides a capacity of 40 kW with a single phase. However, all other specifications remain consistent across both models.

The provided text describes the GF85 Digital X-ray Imaging System and its substantial equivalence to predicate devices (GC85A and GM85). The key study mentioned for demonstrating equivalence is a non-clinical phantom image evaluation.

Here's a breakdown of the requested information based on the provided text, with "N/A" for information not present:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state quantitative acceptance criteria in a table format. Instead, it relies on a comparison with predicate devices and a general statement that "All test results were satisfying the standards" and that the phantom image evaluations "found to be equivalent to the predicate device."

2. Sample size used for the test set and the data provenance

The document states "The phantom image evaluations were performed...".

• Sample size for test set: The document does not specify the number of phantom images used in the evaluation.
• Data provenance: Phantom images are synthetic data, not from human subjects. The country of origin for the data is not specified, but the submission is from Samsung Electronics Co., Ltd. in South Korea.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts

The document states, "...and were evaluated by three different professional radiologists..."

• Number of experts: Three.
• Qualifications of experts: "professional radiologists." Specific experience levels (e.g., "10 years of experience") are not provided.

4. Adjudication method for the test set

The document states the images "were evaluated by three different professional radiologists and found to be equivalent to the predicate device." It does not specify a formal adjudication method (e.g., 2+1, 3+1 consensus). It implies a collective agreement on equivalence.

5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance

• MRMC study: No. The study conducted was a non-clinical phantom image evaluation to compare the device's image quality to a predicate device, as evaluated by radiologists. It was not a comparative effectiveness study involving human readers' performance with and without AI assistance.
• Effect size of human reader improvement with AI: N/A, as no such study was conducted or reported.

6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done

• The primary evaluation described (phantom image reviews) involved human radiologists assessing images generated by the device. The device itself is an X-ray imaging system, not an AI algorithm performing diagnostic interpretation. While the software features list "Lunit INSIGHT CXR Triage" as a new feature for the GF85, the provided text does not detail any standalone performance study specifically for this AI component or any other algorithmic component of the GF85. The "phantom image evaluations" are about the device's image quality, not an algorithm's diagnostic performance.

7. The type of ground truth used

For the phantom image evaluation, the ground truth is implicitly defined by the known characteristics and standards of the phantom images themselves, as well as the comparison against the predicate device. It is not expert consensus on pathology, or outcomes data.

8. The sample size for the training set

• Training set sample size: N/A. The document describes a traditional X-ray imaging system and its non-clinical evaluation for substantial equivalence. It does not refer to a machine learning model's training set. While there are "Software Features" like "Lunit INSIGHT CXR Triage" which would involve AI, the document does not discuss their training data.

9. How the ground truth for the training set was established

• Ground truth for training set: N/A, as no training set for a machine learning model is directly discussed for the GF85 system itself in the context of its substantial equivalence.

Ask a specific question about this device