(15 days)
Agfa's Computed Radiography Systems with NX 2008 software are indicated for use in providing diagnostic quality images to aid the physiclan with diagnosis.
The systems can be used with either Musica, Musica2 or Musica2 Platinum image processing to create radiographic images of the skeleton (including skull, spinal column and extremities) chest, abdomen and other body parts.
When used with separately cleared accessories the systems can be conveniently used to generate urological, tomographic, pediatric and dental images, and for radiotherapy planning and quality control.
When used with Musica2 Platinum software the systems are indicated for creating high quality images of the thorax, abdomen or musculoskeletal regions of adult or pediatric patients.
Agfa's Computed Radiography Systems with NX 2008 software are not indicated for use in mammography.
The predicate and new devices are nearly identical computed radiography imaging systems. NX 2008 systems (new devices) have updated hardware and software that offers:
- An optional medical grade display. The display is cleared separately . by the display manufacturer.
- The capability to operate as a mixed-use system for both general . radiography and mammography (where approved or licensed). This is not the case for the USA the separately licensed mammography system is not available.
- Improved tools for installation, configuration and management. .
- The ability to receive DICOM veterinary images and data. .
The basic principles of operation of the new and predicate devices are the same. They have the same underlying technological characteristics.
The provided 510(k) summary for Agfa's Computed Radiography Systems with NX 2008 Workstations does not contain detailed information about specific acceptance criteria or a comprehensive study proving the device meets those criteria in the way typically expected for novel AI/ML devices.
Instead, this submission focuses on establishing substantial equivalence to a predicate device (Agfa's Computed Radiography Systems with NX2.0 Workstations, K071162). The core argument is that the new device has "the same underlying technological characteristics" and that any differences "do not alter the intended therapeutic/diagnostic effect."
Therefore, the information below reflects what is available in the document, and notes where specific details common to AI/ML device studies are not provided.
1. Table of Acceptance Criteria and Reported Device Performance
| Acceptance Criteria | Reported Device Performance |
|---|---|
| Proper performance to specifications | Demonstrated through "various internal tests." (Specific performance metrics and criteria are not detailed in this summary.) |
| Meet requirements of EN 60601-1-1 (Medical electrical equipment – Part 1-1: General requirements for safety – Collateral standard: Safety requirements for medical electrical systems) | Components tested and shown to meet these requirements. |
| Meet requirements of EN 60601-1-2 (Medical electrical equipment – Part 1-2: General requirements for safety – Collateral standard: Electromagnetic compatibility – Requirements and tests) | Components tested and shown to meet these requirements. |
| Substantial Equivalence to predicate device (K071162) | Demonstrated in the 510(k) submission. (This is the primary "acceptance criterion" for this type of submission.) |
2. Sample size used for the test set and the data provenance
- Not explicitly provided. The document states "various internal tests" were conducted, but does not detail a specific test set size for performance evaluation related to diagnostic image quality.
- The data provenance (e.g., country of origin, retrospective/prospective) is also not provided as clinical studies were not involved.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
- Not applicable / Not provided. The submission explicitly states, "No clinical testing was involved." Therefore, there was no separate test set requiring expert ground truth establishment in the context of diagnostic performance.
4. Adjudication method for the test set
- Not applicable / Not provided. As no clinical testing with a separate test set and expert ground truth was conducted, no adjudication method is mentioned.
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. The document explicitly states "No clinical testing was involved." This submission is for an updated Computed Radiography system, not an AI/ML diagnostic aid.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
- Not applicable. This device is a Computed Radiography system (hardware and software for image acquisition and processing), not a standalone diagnostic algorithm in the AI sense. Its "performance" is in producing diagnostic quality images for human interpretation.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
- Not applicable / Not provided. Since there was no clinical testing requiring ground truth for diagnostic performance, this information is not available. The "ground truth" for the engineering performance tests would be against established engineering specifications.
8. The sample size for the training set
- Not applicable / Not provided. This submission describes a CR imaging system, not an AI/ML algorithm that requires a "training set" in the context of machine learning. The system's image processing (Musica, Musica2, Musica2 Platinum) would have been developed and tuned using proprietary methods by Agfa, but this is not analogous to an AI/ML training set as understood for diagnostic algorithms.
9. How the ground truth for the training set was established
- Not applicable / Not provided. See explanation for point 8.
§ 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.