(94 days)
The Wireless/Wired FDR D-EVO flat panel detector system is intended to capture for display radiographic images of human anatomy. It is intended for use in general projection radiographic applications including pediatric and neonatal exams wherever conventional film/screen or CR systems may be used. The FDR D-EVO is not intended for mammography, fluoroscopy, tomography, and angiography applications.
Fujifilm's FDR D-EVO Flat Panel Detector System (DR-ID600) is a portable digital detector system that interfaces with, and acquires and digitizes x-ray exposures, from standard radiographic systems. The FDR D-EVO is designed to be used in any environment that would typically use a radiographic cassette for examinations of adults, pediatrics and neonates. The detector models support both wireless and wired/tethered data communication between the detector and the system. Detectors can be placed in a wall bucky for upright exams, a table bucky for recumbent exams, or removed from the bucky for non-grid exams.
The design modification made to the FDR D-EVO is adding Fujifilm's new post image processing algorithm called 'Virtual Grid Software'. The Virtual Grid Software is designed to improve image contrast in general radiographic images by reducing the effects of scatter radiation, primarily for exams acquired without a grid. Based on the displayed image, the user can decide whether or not to apply the Virtual Grid image processing by turning it ON or OFF as they see fit.
The provided text describes a 510(k) premarket notification for a modification to the Fujifilm FDR D-EVO Flat Panel Detector System (DR-ID600), specifically the addition of "Virtual Grid Software." This software is designed to improve image contrast by reducing scatter radiation effects, primarily for exams acquired without a physical grid.
Here's an analysis of the acceptance criteria and study information, based on the provided text:
1. Table of Acceptance Criteria and Reported Device Performance
| Feature/Metric | Acceptance Criteria | Reported Device Performance |
|---|---|---|
| Effect on Image Contrast/Quality | Improvement in image contrast/quality for images acquired without an anti-scatter grid. | Bench testing and image quality evaluation demonstrated the Virtual Grid processing algorithm yields an improvement in image contrast and quality for those images acquired without an anti-scatter grid. |
| Safety and Effectiveness | As safe and effective as the legally marketed predicate device (K132509). | Concluded to be as safe and effective as K132509 and does not raise different questions of safety and effectiveness. |
| Intended Use | Does not affect the intended use of the previous cleared device. | Adding the Virtual Grid Software does not affect the intended use. |
| Fundamental Scientific Technology | Does not alter the fundamental scientific technology of the previous cleared device. | Does not alter the fundamental scientific technology. |
| Detector Characteristics | Detector characteristics (ISS design, wireless communication) remain unchanged. | Detector characteristics remain unchanged. |
| Functional/Technical Requirements | Virtually maintains the same functional and technical requirements as the currently-cleared predicate. | Virtually maintains the same functional and technical requirements. |
| Regulatory Compliance (Non-Clinical) | Conformance to voluntary standards. | Conforms to AAMI/ANSI ES60601-1, IEC 60601-1, IEC 60601-1-2, IEC 62304, IEC 62366, IEC 62494-1, and DICOM. |
| Risk Analysis | All verification and validation activities for the Virtual Grid Software performed and satisfactory. | All verification and validation activities for the Virtual Grid Software were performed and the results were satisfactory. |
2. Sample size used for the test set and the data provenance
The document explicitly states: "Clinical Performance Data: The design modification does not require clinical studies. The substantial equivalence has been demonstrated by non-clinical studies." This indicates that no clinical test set was used for this specific modification. The evaluation relied on non-clinical data. Therefore, data provenance (country of origin, retrospective/prospective) is not applicable here in the context of a clinical test set.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
Since no clinical test set was used for establishing ground truth related to patient images, this information is not applicable. The "image quality evaluation" mentioned under non-clinical performance data likely refers to technical assessments rather than expert clinical interpretations of diagnostic images from a patient dataset.
4. Adjudication method for the test set
Not applicable as no clinical test set was used requiring expert adjudication.
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
No MRMC comparative effectiveness study was done. The document states that clinical studies were not required and that substantial equivalence was demonstrated by non-clinical studies. This modification is an image processing algorithm, not an AI-assisted diagnostic tool in the sense of improving human reader performance on a diagnostic task, but rather geared towards improving raw image quality.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
Yes, a form of standalone evaluation of the algorithm's performance on image quality was done. The document states: "Additionally the bench testing and image quality evaluation further demonstrated the Virtual Grid processing algorithm yields an improvement in image contrast and quality, for those images acquired without an antiscatter grid." This indicates that the algorithm's output was assessed for its intended effect on image characteristics.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
For the non-clinical evaluation, the "ground truth" for the image quality assessment would likely be based on technical metrics of image contrast and visual assessment agreed upon by imaging engineers or possibly radiologists on technical merits, rather than clinical expert consensus on diagnostic findings, pathology, or outcomes data. The goal was to demonstrate improved contrast, not diagnostic accuracy in a clinical setting.
8. The sample size for the training set
The document does not specify the sample size for the training set for the Virtual Grid Software.
9. How the ground truth for the training set was established
The document does not specify how the ground truth for the training set was established. It's important to note that "Virtual Grid Software" is described as a "post image processing algorithm." While some image processing algorithms can leverage machine learning and thus require training data and ground truth, the document doesn't provide details on its internal mechanisms beyond "reducing the effects of scatter radiation." If it's a rule-based or conventional signal processing algorithm, a "training set" with established ground truth in the machine learning sense might not be directly applicable. If it does involve machine learning, this information is not provided.
§ 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.