(99 days)
Fujifilm's FDR Dual Energy Subtraction (DES) Option may be used with Fujifilm's DR X-ray Systems and is intended to be used by a qualified/trained doctor or technologist for acquiring dual energy subtraction images of human anatomy.
DES is intended to assist the physician through the visualization of anomalies by reducing the visibility of underlying / overlying anatomical structures.
This device is not intended for mammographic applications.
Dual Energy Subtraction (DES) is an advanced radiographic imaging application designed as an option to be used with our cleared FDR AcSelerate X-ray system, and will also be used in future FUJIFILM X-ray systems.
Two images are acquired at mulually different X-ray energies. These images are then subject to a weighted subtraction that can remove structures (e.g. soft tissue structures or bone structures) of a specific x-ray absorption characteristic. This results in a completed DES exam that typically consists of three processed images, (1) a standard radiographic image, (2) a soft-tissue image with the bone information removed, and (3) a bone image with the soft tissue information removed.
To suppress involuntary motion artifacts which are tvpical in dual-exposure energy subtraction, Fujifilm's DES option includes Multi-Stage Registration (MSR) which compensates for involuntary patient motion, such as the patient's heartbeat, that can produce slight differences in anatomic registration (seen as artifacts) between the first exposure (high energy image), and the second exposure (low energy image). MSR is added to suppress the motion artifacts seen in the DES image and maintains the image quality.
The Fujifilm FDR Dual Energy Subtraction (DES) Option is intended to assist physicians by visualizing anomalies through the reduction of underlying/overlying anatomical structures.
Here's an analysis of the provided text regarding acceptance criteria and the study that proves the device meets them:
1. Table of Acceptance Criteria and Reported Device Performance
The document does not explicitly state quantitative acceptance criteria or corresponding reported device performance metrics in a readily digestible table format for the device's enhanced detection capabilities in humans. Instead, it refers to a qualitative assessment.
| Acceptance Criteria | Reported Device Performance |
|---|---|
| Improved DES detectability of lung nodules | "Multi-Stage Registration feature may improve DES detectability of lung nodules in the lower right lung." |
| Effective artifact reduction | "it has been confirmed by interviews with doctors that the artifact reduction was effective." |
2. Sample Size Used for the Test Set and Data Provenance
- Test Set Sample Size: 20 subject images.
- Data Provenance: The studies were performed on the predicate device in Japan. This indicates the data is retrospective as it refers to past studies on an existing device.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications
- Number of Experts: Ten radiologists.
- Qualifications: The document only states "Ten radiologists" and does not provide further details on their experience or specific qualifications (e.g., number of years of experience, subspecialty).
4. Adjudication Method for the Test Set
The document does not specify an adjudication method like 2+1 or 3+1. It simply states that "Ten radiologists evaluated 20 subject images and concluded..." This implies a consensus or individual evaluation followed by a summary of findings rather than a structured adjudication process.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
A multi-reader multi-case (MRMC) comparative effectiveness study comparing human readers with AI assistance versus without AI assistance was not explicitly detailed in the provided text for the proposed device. The study described involved radiologists evaluating images, but it doesn't clearly articulate a comparison of human performance with and without the new DES feature, nor does it quantify an effect size of improvement. It describes the feature itself as potentially improving detectability.
6. Standalone Performance Study
A standalone (algorithm-only without human-in-the-loop performance) study was not explicitly detailed for the proposed device. The information provided focuses on the perceived improvement in images as assessed by radiologists, implying a human-in-the-loop scenario. The "Multi-Stage Registration (MSR)" is a feature of the device, but its standalone performance (e.g., in artifact reduction metrics without human interpretation) is not separately detailed beyond visual demonstration.
7. Type of Ground Truth Used
The ground truth used was expert consensus/opinion from radiologists. The document states, "Ten radiologists evaluated 20 subject images and concluded that (1) Multi-Stage Registration feature may improve DES detectability of lung nodules in the lower right lung and (2) it has been confirmed by interviews with doctors that the artifact reduction was effective." While it implies "detectability of lung nodules," it doesn't specify if there was a definitive, external ground truth (like pathology or follow-up outcomes) for these nodules in the 20 cases. It relies on the radiologists' assessment.
8. Sample Size for the Training Set
The document does not specify a sample size for the training set. It refers to "System testing," "Software Verification, bench testing," "clinical image samples," and a "literature review," but no details on training data.
9. How the Ground Truth for the Training Set Was Established
The document does not provide information on how the ground truth for any potential training set was established. It primarily discusses studies and evaluations of the device's output rather than the development or training process.
§ 892.1680 Stationary x-ray system.
(a)
Identification. A stationary x-ray system is a permanently installed diagnostic system intended to generate and control x-rays for examination of various anatomical regions. This generic type of device may include signal analysis and display equipment, patient and equipment supports, component parts, and accessories.(b)
Classification. Class II (special controls). A radiographic contrast tray or radiology diagnostic kit intended for use with a stationary x-ray system only is exempt from the premarket notification procedures in subpart E of part 807 of this chapter subject to the limitations in § 892.9.