(27 days)
Digital Flat Panel X-Ray Detector is indicated for digital imaging solution designed for general radiographic system for human anatomy. It is intended to replace film or screen based radiographic systems in all general purpose diagnostic procedures. Not to be used for mammography.
1717WCE, 1717WCE-HR, 1717WCE-HS, 1717WCE-GF X-ray detectors, are wired/wireless digital solid state X-ray detectors that are based on flat panel technology. The wireless LAN (IEEE 802.11 n/ac) communication signals images captured to the system and improves the user operability through high speed processing. These radiographic image detectors are processing unit consist of a scintillator coupled to an TFT sensor. The flat-panel detectors need to be integrated with an x-ray generator (not part of the submission), so it can be utilized to capture and digitize x-ray images for radiographic diagnosis.
1717WCE. 1717WCE-HR. 1717WCE-HS. 1717WCE-GF includes the software (firmware) of basic level of concern. It's the same Image Acquisition and Operating Software used for the predicate device is used but modified to include additional detector models in comparison with the predicate device. Full software documentation has been submitted, as well as the necessary sections to demonstrate device cybersecurity.
The RAW files can be further processed as DICOM compatible image files by separate consol SW (K190866, XmaruView V1 / Rayence Co.,Ltd) for a radiographic diagnosis and analysis.
1717WCE is the basic model. 1717WCE-HR is identical with the basic model except for pixel pitch not related to safety. 1717WCE-HS is identical with the basic model except for marking of sheet. 1717WCE-GF is identical with the basic model except for case color and pixel pitch.
The given text describes a 510(k) submission for a Digital Flat Panel X-ray Detector. The submission aims to demonstrate substantial equivalence to a predicate device. However, the document does not describe a study that uses an AI algorithm as a device or an AI assistance to human readers, so most of the requested information regarding AI-specific criteria (like MRMC studies, standalone AI performance, training set details, or ground truth establishment for AI) is not present.
The document focuses on the technical and clinical performance comparison of the subject device (new X-ray detector models) against a predicate device (older X-ray detector models) through non-clinical and image quality assessments by human reviewers.
Here's the available information based on the provided text, addressing the points where information is available and noting where it's not:
1. Table of acceptance criteria and reported device performance:
The document doesn't present a formal table of "acceptance criteria" for the entire device as one might see for an AI algorithm's specific performance metrics (e.g., AUC, sensitivity, specificity). Instead, it demonstrates substantial equivalence by comparing its technological characteristics and performance to a predicate device. The performance is described qualitatively through comparisons of image quality.
| Characteristic | Subject Device (1717WCE, 1717WCE-HR, 1717WCE-HS, 1717WCE-GF) | Predicate Device (1417WCE, 1417WCE-HR, 1417WCE-HS, 1417WCE-GF) | Reported Performance/Comparison |
|---|---|---|---|
| Intended Use | Digital imaging for general radiographic system, human anatomy, replaces film/screen systems. Not for mammography. | Digital imaging for general radiographic system, human anatomy, replaces film/screen systems. Not for mammography. | Same |
| Detector Type | Amorphous Silicon, TFT (1717WCE, 1717WCE-HS); Amorphous Silicon, TFT, Indium Gallium Zinc Oxide with TFT (1717WCE-HR, 1717WCE-GF) | Amorphous Silicon, TFT | Similar (some models of subject device use advanced TFT) |
| Scintillator | CsI:Tl | CsI:Tl | Same |
| Imaging Area | 17 x 17 inches | 14 x 17 inches | Similar (Subject device has larger area) |
| Pixel Pitch (WCE, HS) | 140 µm | 140 µm | Same |
| Pixel Pitch (WCE-HR, GF) | 99.9 µm | 100 µm | Same (effectively) |
| Total Pixel Matrix (WCE, HS) | 3072 x 3072 | 2500 x 3052 | Similar |
| Total Pixel Matrix (WCE-HR, GF) | 4302 x 4302 | 3534 x 4302 | Similar |
| Resolution | 3.57 lp/mm (WCE, HS); 5.00 lp/mm (WCE-HR, GF) | 3.57 lp/mm (WCE, HS); 5.00 lp/mm (WCE-HR, GF) | Same |
| DQE (@1lp/mm) | Typ. 69% (WCE, HS); Typ. 62% (WCE-HR, GF) | Typ. 63% (WCE, HS); Typ. 62% (WCE-HR, GF) | Similar (some models of subject device show improvement) |
| MTF (@1lp/mm) | Typ. 62% (WCE, HS); Typ. 66% (WCE-HR, GF) | Typ. 66% (WCE, HS); Typ. 61% (WCE-HR, GF) | Similar (some models of subject device show improvement) |
| A/D Conversion | 16 bits | 16 bits | Same |
| Dimensions | 460 x 460 x 15mm | 384 x 460 x 15mm | Similar |
| Weight | 3.3 kg | 2.7 kg | Similar |
| Viewer Software | XmaruView V1 (K190866/ Rayence Co.,Ltd) | XmaruView V1 (K190866/ Rayence Co.,Ltd) | Same |
Qualitative Image Quality Assessment (summarized from section 6):
- 1717WCE 99.9um vs. 1417WCE 100um: Subject device (1717WCE 99.9um) showed overall better image quality, clearer anatomical structures (bony and soft tissues of upper and lower extremities). Predicate device (1417WCE 100um) had decreased sharpness, more overexposed appearance, and higher noise.
- 1717WCE 140um vs. 1417WCE 140um: Subject device (1717WCE 140um) showed overall better image quality, clearer anatomical structures. Predicate device (1417WCE 140um) had less sharpness, more overexposed appearance, and higher noise.
- Conclusion: Both 1717WCE 140um and 1717WCE 99.9um demonstrated sufficient image quality for diagnostic purposes, with better image quality than the predicate device.
2. Sample size used for the test set and the data provenance:
- Sample Size: The document states, "After comparing a broad review of plain radiographic images taken with 1717WCE... and 1417WCE images obtained equivalent quality for the same view obtained from a similar patient." It further mentions reviewing "plain radiographic images taken with 1717WCE 99.9um and the 1417WCE 100um" and "plain radiographic images taken with 1717WCE 140um and the 1417WCE 140um." No specific numerical sample size (e.g., number of images, number of patients) is provided for this qualitative review.
- Data Provenance: Not explicitly stated (e.g., country of origin). The studies appear to be internal performance assessments rather than large-scale clinical trials. The data is retrospective in the sense that existing images were compared.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- The document mentions "Upon review of the plain radiographic images..." suggesting a human review. However, it does not specify the number of experts, their qualifications (e.g., radiologist with X years of experience), or how ground truth was established by them. The "ground truth" here seems to be subjective human judgment of image quality for diagnostic purposes rather than a definitive disease presence/absence.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set:
- No adjudication method is described. The qualitative image quality assessment is presented as a singular conclusion derived from "review."
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, an MRMC comparative effectiveness study was not done. This submission is for an X-ray detector, not an AI algorithm assisting human readers. The qualitative image review is a comparison of image detector performance, not human reader performance with or without AI.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:
- Not applicable. The device is a digital X-ray detector, which produces images. It's not a standalone AI algorithm designed to interpret those images without human involvement.
7. The type of ground truth used:
- Qualitative Human Assessment of Image Quality. The "ground truth" for the performance study is based on visual assessment by unspecified reviewers that the image quality of the subject device is "better" or "sufficient" for diagnostic purposes compared to the predicate device. It is not tied to a confirmed diagnosis (e.g., pathology, surgical findings, or long-term outcomes data). The document also mentions "non-clinical test report for the subject device were prepared and submitted to FDA... by using the identical test equipment and same analysis method described by IEC 62220-1" for metrics like MTF, DQE, and NPS, which are objective image quality measurements.
8. The sample size for the training set:
- Not applicable. This device is an X-ray detector, not an AI or machine learning model that requires a training set.
9. How the ground truth for the training set was established:
- Not applicable. As the device is not an AI/ML model, there is no "training set" or "ground truth for the training set."
§ 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.