(85 days)
Radlink GPS is intended for digital image capture use in general radiographic examinations, whenever conventional screen-film systems may be used. Radlink GPS allows imaging of the pelvis, knee, skull, chest, shoulder, spine, abdomen and extremities. The digital images are transmitted from the panel or from a connection to PACS via computer networks or from a video input port to a personal computer (PC) where they may be displayed, processed, altered, overlaid with templates, compressed for archiving or transmission via computer networks to other medical facility sites. Not for mammography.
The Radlink GPS system represents the straightforward integration of digital x-ray receptor panels with their own FDA 510(k) clearance and our acquisition software that has been previously cleared by the FDA for use with our Radlink CR-Pro Solid State X-ray Imager (K052938) and Radlink LaserPro-16 (K020243). The Radlink GPS is compatible with the following digital x-ray receptor panels:
- . Vieworks VIVIX-S (K120020) and VIVIX-S Wireless (K122865)
- . Trixell Artpix Mobile EZ2GO with portable PIXIUM 3543EZ (K110849)
- -Perkin Elmer XRpad 4336 MED (K140551)
Radlink GPS is a Digital Radiography (DR) system, featuring an integrated flat panel digital detector (FPD). Radlink GPS is designed to perform digital radiographic examinations as a replacement for conventional film. This integrated platform provides the benefits of PACS with the advantages of digital radiography for a filmless environment and improves cost effectiveness. The major functions and principle of operations of the Radlink CR Pro acquisition software and PACS were not changed. The digital copies are transmitted to an internal personal computer (PC) where they may be displayed, processed for archiving or transmission via computer networks to other medical facility sites. Images can be rotated, flipped, coomed, window level, overlaid and annotated (markers, text, freestyle, line distance measurements, angles). Digital images may be received via the flat panel digital detector (FPD), from a connection to PACS via computer networks or from a video input port.
Here's an analysis of the provided text regarding the acceptance criteria and study for the Radlink GPS device:
1. Table of Acceptance Criteria and Reported Device Performance
The document does not explicitly state formal acceptance criteria with numerical targets for performance metrics (e.g., sensitivity, specificity, image quality scores). Instead, the "acceptance criteria" appear to be implicit in demonstrating that the device is "as safe and effective as products currently legally for sale in the USA" and "substantially equivalent to predicate devices."
The reported device performance primarily focuses on functionality, safety, and diagnostic quality rather than specific quantitative performance metrics.
| Acceptance Criteria (Implied) | Reported Device Performance |
|---|---|
| Functional Equivalence/Compatibility | Radlink GPS system represents the straightforward integration of digital x-ray receptor panels with existing FDA-cleared acquisition software. It is functionally equal to the predicate device and Radlink CR-Pro product (K052938). |
| Image Acquisition (Digital Panels) | Proper acquisition of digital x-ray images was verified with each of the three available digital panels (Vieworks VIVIX-S, Trixell Artpix Mobile EZ2GO, Perkin Elmer XRpad 4336 MED). All panels have already been cleared by FDA. |
| Image Quality (Diagnostic) | Human images were obtained from each of the panels. They were reviewed by a Board Certified Radiologist and found to be of good diagnostic quality. |
| Conformance to Specifications (Calibration/Resolution) | Program testing and calibration using gray-scale wedge and a line resolution phantom and has demonstrated the Radlink GPS conformance to its defined specifications. |
| Software Validation & Risk Analysis | Software validation and risk analysis was performed. The templating features software has been validated. |
| DICOM Compatibility | DICOM compatibility has been verified. (Also listed as "YES" in the Substantial Equivalence Table) |
| Electrical Safety & EMC | All panels have been tested to meet the requirements of IEC 60601-1 (Medical Device Safety) and IEC 60601-1-2 (Electromagnetic Compatibility). |
| Substantial Equivalence (Features) | Detailed comparison tables (Table 1 & 2) show that Radlink GPS software features are identical to or comparable with previous Radlink software (CR-Pro) and the predicate device (dicomPACS DX-R), with minor workflow changes and the addition of templating features. Compatible digital panels are listed. |
| Safety and Effectiveness "as legally for sale in the USA" | Concluded based on non-clinical testing, software comparison, and the fact that all proposed compatible panels have undergone successful FDA review, that it is "as safe and effective as products currently legally for sale in the USA." |
| Intended Use (General Radiographic Examinations) | The device's indications for use are consistent with conventional screen-film systems for general radiographic examinations of pelvis, knee, skull, chest, shoulder, spine, abdomen, and extremities. Not for mammography. This is consistent with the predicate. |
2. Sample Size Used for the Test Set and Data Provenance
- Test Set Sample Size: The document states that "Human images were obtained from each of the panels." It does not specify the exact number of human images or cases used for this review.
- Data Provenance: Not explicitly stated. Given the context of seeking FDA clearance in the USA, it's likely the images were acquired in a medical setting, possibly in the USA, but no specific country or retrospective/prospective nature is mentioned.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications
- Number of Experts: "a Board Certified Radiologist." (Singular)
- Qualifications of Experts: "Board Certified Radiologist." No specific number of years of experience is provided.
4. Adjudication Method for the Test Set
- Adjudication Method: "reviewed by a Board Certified Radiologist." There is no mention of multiple readers or an adjudication process (e.g., 2+1, 3+1). The assessment appears to be a single-reader evaluation.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was Done
- MRMC Study: No, an MRMC comparative effectiveness study was not done. The document focuses on demonstrating substantial equivalence primarily through functional comparison, technical performance verification, and a limited clinical review by a single radiologist. There is no mention of comparing human readers with and without AI assistance. The device itself is an image acquisition and processing system, not an AI diagnostic aid.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was Done
- Standalone Performance: The Radlink GPS is a digital radiography system, not an AI algorithm in the context typically discussed for standalone performance (e.g., detecting disease). Its "performance" is inherently linked to image acquisition and display. The "algorithm" here refers to the acquisition and processing software, and its standalone performance is tested through aspects like "conformance to its defined specifications" using phantoms, software validation, and DICOM compatibility. While not referred to as "standalone AI performance," the non-clinical testing and software validation serve a similar function for the core components of the system.
7. The Type of Ground Truth Used
- Type of Ground Truth: The ground truth for the diagnostic quality assessment was based on expert consensus (from a single Board Certified Radiologist) who evaluated the human images and found them to be of "good diagnostic quality." For other aspects like image acquisition and technical specifications, the ground truth was based on physical measurements (e.g., gray-scale wedge, line resolution phantom) against predefined technical standards.
8. The Sample Size for the Training Set
- Training Set Sample Size: Not applicable in the context of this submission. The Radlink GPS is described as an integration of existing cleared components (digital panels and acquisition software that was previously cleared). It is not an AI/machine learning model that undergoes a distinct "training phase" on a dataset in the way a diagnostic algorithm would. The software was previously cleared (K052938, K020243), implying its development and validation occurred prior to this submission.
9. How the Ground Truth for the Training Set Was Established
- Ground Truth for Training Set: Not applicable. As mentioned above, this is an integration of pre-cleared components, not a new AI algorithm requiring a dedicated training set and associated ground truth establishment for that training. The development and validation of the constituent software and hardware components would have involved their own respective "ground truths" at the time of their original clearance.
§ 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.