K Number
K050810
Device Name
AGFA CR50.0
Manufacturer
Date Cleared
2005-04-21

(21 days)

Product Code
Regulation Number
892.1680
Panel
RA
Reference & Predicate Devices
AI/MLSaMDIVD (In Vitro Diagnostic)TherapeuticDiagnosticis PCCP AuthorizedThirdpartyExpeditedreview
Intended Use

The CR50.0 is indicated for use to provide diagnostic quality images to aid in physician diagnosis. The CR50.0 is intended to be used mainly in chest, skeletal, and gastro-intestinal x-ray imaging applications.

Device Description

The CR50.0, the predicate device, is a computed radiology imaging system. Instead of screens and photographic film for producing the diagnostic image, the CR50.0 system utilizes an "imaging plate," a plate coated with photo-stimulable storage phosphors that are sensitive to X-rays and capable of retaining a latent image. This imaging plate is inserted into a device that scans it with a laser and releases the latent image in the form of light which is converted into a digital bit stream. The bit stream of image data is stored locally, printed or sent to a Picture Archiving and Communications System (PACS) in DICOM format. The CR50.0 is very similar to the CR25.0. It has a new scanning system that improves scan time and an image plate with an improved phosphor. However, the basic principles of operation are unchanged.

AI/ML Overview

This document is a 510(k) Summary for a Device Modification (K050810), meaning it pertains to changes made to an already cleared medical device, the CR25.0 (K041701). As such, it primarily focuses on demonstrating that the modified device (CR50.0) is substantially equivalent to its predicate device and does not include a detailed study with specific acceptance criteria and performance metrics documented in the submission itself.

Here's an analysis based on the provided text, addressing your points where possible:


Acceptance Criteria and Device Performance

The document does not explicitly state specific numerical acceptance criteria or detailed performance metrics for the CR50.0 in a comparative table. This is typical for a Special 510(k) submission, where the focus is on asserting that the modifications do not negatively impact safety or effectiveness, and that any required performance testing confirms substantial equivalence.

Instead, the document states:

  • "performance data was collected, and this data demonstrates substantial equivalence." (Section D)
  • "This Special 510(k) for Device Modification submission has demonstrated Substantial Equivalence..." (Section G)
  • "The CR50.0 has been tested for proper performance to specifications through various in-house reliability and imaging performance demonstration tests." (Section F)

The "specifications" for proper performance are not detailed here, but would likely relate to image quality parameters (e.g., spatial resolution, contrast resolution, noise) that are expected to be at least equivalent to, if not better than, the predicate CR25.0. Given the description of "an image plate with an improved phosphor," it's implied that the imaging performance would be maintained or enhanced.

Therefore, a table of acceptance criteria and reported device performance cannot be generated from the provided text. The key acceptance criterion for this 510(k) was demonstrating substantial equivalence to the predicate device CR25.0.


Study Information (Based on available text):

1. A table of acceptance criteria and the reported device performance:

  • Cannot be provided as detailed in the explanation above. The submission relies on "performance data" demonstrating substantial equivalence, not specific numerical criteria presented in this summary.

2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective):

  • Not specified. The document makes no mention of specific clinical or image-based test sets, their sample sizes, or provenance. The testing mentioned in Section F ("in-house reliability and imaging performance demonstration tests") likely involved technical evaluation rather than a clinical reader study.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience):

  • Not applicable/Not specified. Given the nature of a device modification and the focus on technical performance (as opposed to diagnostic accuracy per se, which is assumed to be equivalent to the predicate), the submission does not describe a clinical ground truth establishment process or the involvement of experts for this purpose.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set:

  • Not applicable/None specified. No clinical test set requiring adjudication is described.

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. This device is a Computed Radiography imaging system and not an AI-powered diagnostic algorithm. Therefore, an MRMC study related to AI assistance would not be relevant or expected for this submission.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:

  • No. This is an imaging acquisition device, not an algorithm, so the concept of "standalone performance" in the context of an algorithm is not applicable. The device itself performs image acquisition and processing.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc):

  • Not applicable/Not specified. As explained for point 3, the submission does not detail a process for establishing a clinical "ground truth" for a test set. Technical performance metrics would be assessed against engineering specifications or benchmarks from the predicate device.

8. The sample size for the training set:

  • Not applicable/Not specified. This is a hardware/software imaging system, not a machine learning algorithm that requires a "training set" in the conventional sense. The "training" that would occur is internal software development and parameter optimization, not an AI model training process.

9. How the ground truth for the training set was established:

  • Not applicable/Not specified. As explained for point 8, there isn't a "training set" with ground truth in the context of an AI algorithm for this device.

In summary: This 510(k) is for a modification to a Computed Radiography system. It asserts substantial equivalence to a predicate device based on "performance data" from "in-house reliability and imaging performance demonstration tests." It does not involve AI, clinical reader studies, or detailed reporting of specific acceptance criteria and performance metrics within this summary document. The core of this submission is the claim of substantial equivalence due to unchanged basic principles of operation despite hardware improvements (new scanning system, improved phosphor plate).

§ 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.