Search Results

Intended for use by a qualified/trained physician or technician on both adult and pediatric subjects for taking diagnostic x-rays. Not for mammography.

This represents the straightforward combination of three devices: One of three cleared MinXray Portable HF X-ray generators: a) HF120/60H PowerPlus cleared in K040046, (and in K141885) OR b) HF100H+ cleared in K052721 OR C) HF1202 PowerPlus cleared in K153059. d) Plus: A 510(k) cleared (K153058) Digital X-Ray Receptor Panel CareView 1500C X-ray Flat Panel Detector. PLUS: the dicomPACS® software package (Same as our predicate). e) The x-ray generators are portable units which operate from 120/240V 50-60° AC. The generator unit utilizes a high frequency inverter and can be mounted to a tripod or support arm. The usual safety precautions regarding the use of x-rays must be observed by the operator. The digital panel features the Careray flat panel technology in a sleek and compact unit. The portable panel provides digital X-ray image capture for a wide range of applications. The lightweight design, generous imaging area, and fast processing times of the detector make it easy to capture high quality diagnostic images for routine diagnosis, as well as challenging trauma and bedside exams. It's a portable solution for a faster, more streamlined approach to digital radiography. The only difference between this modified device and our predicate devices is the model number of the digital x-ray receptor panel. The predicate panel can communicate either by wireless or wired connection. The subject device communicates by Ethernet only.

The provided text describes a 510(k) premarket notification for a mobile X-ray system (CMDR 2C) seeking substantial equivalence to a predicate device. This submission primarily focuses on hardware equivalence and non-clinical testing, rather than an AI/ML-based diagnostic device requiring extensive performance metrics against a clinical ground truth.

Therefore, many of the requested elements for describing "acceptance criteria and the study that proves the device meets the acceptance criteria" in the context of an AI/ML device (e.g., sample sizes for test/training sets, expert adjudication methods, MRMC studies, specific ground truth types for disease detection) are not applicable or not present in this document.

However, I can extract the information related to the device's performance through bench testing and the rationale for claiming substantial equivalence.

Here's an analysis based on the provided document:

1. Table of acceptance criteria and the reported device performance:

Since this FDA submission is for a medical device (mobile X-ray system) and not an AI/ML diagnostic tool, the "acceptance criteria" are related to established performance standards for X-ray imaging devices and demonstrating equivalence to a predicate device. The "reported device performance" is primarily about image quality and compliance with relevant safety and electrical standards.

• UL 60601-1 (2005) (Electrical medical device safety)
• IEC 60601-1-2 (2007) (Electromagnetic Compatibility)
• Additionally, the HF1202H PowerPlus generator meets IEC 60601-2-54: Medical electrical equipment - Part 2-54: Particular requirements for the basic safety and essential performance of X-ray equipment for radiography and radioscopy (not applicable to older generators).
• Risks and hazardous impacts of the device modification were analyzed by FMEA methodology. Risk control and protective measures were reviewed and implemented. "The overall assessment concluded that all identified risks and hazardous conditions were successfully mitigated and accepted." |
  | Software Compatibility: New panel compatible with existing software. | "We verified software compatibility with the new CareView Cw digital panel." The dicomPACS® software was installed on a Dell Inspiron laptop, and proper installation was verified by running the software. A Wi-Fi connection (for the predicate panel) was confirmed, and the X-ray generator was used to take test exposures with a radiographic phantom. "No modifications were necessary to any of the hardware or software other than changing the digital panel." |
  | Substantial Equivalence: Performance is as safe and effective as predicate. | "The results of bench testing indicate that the new devices are as safe and effective as the predicate devices."
  The primary difference is the digital X-ray receptor panel, with the new panel communicating via Ethernet only, while the predicate panel could communicate via wireless or wired. However, the panel's core performance characteristics (Pixel Pitch, pixels, Size, Scintillator, Spatial Resolution, A/D Resolution, MTF, DQE) are identical to the predicate panel (which was cited as the predicate in the K150929 submission). |

2. Sample size used for the test set and the data provenance:

• Sample Size: Not explicitly stated as a numerical sample size of "cases" or "patients" in the context of clinical images. The testing involved "Prototype systems covering all generator/panel combinations" and "Several test exposures" with "a radiographic phantom." This suggests a limited number of phantom images rather than a large clinical test set.
• Data Provenance: The data used for testing (phantom images) would have been generated in-house during the bench testing. The document does not specify country of origin for this testing data. The testing was non-clinical for this specific submission ("Summary of clinical testing: Clinical testing was not required to establish substantial equivalence.").

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

• Not applicable / Not specified. Given that this is a non-clinical bench study focused on physical performance and image quality of an X-ray machine rather than a diagnostic AI algorithm, there was no "ground truth" derived from expert clinical reads of patient images. The evaluation of "diagnostic quality" for phantom images would likely be performed by engineers or physicists familiar with imaging standards, but specific numbers or qualifications are not provided.

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

• Not applicable. No adjudication method for expert reads was used as no clinical images or expert reads were part of this substantiation.

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 study was not done. This device is a standard X-ray imaging system, not an AI-assisted diagnostic tool.

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

• Not applicable. This device is an X-ray machine; there is no standalone AI algorithm whose performance is being evaluated in this submission.

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

• The "ground truth" for this submission was based on physical phantom measurements and engineering standards compliance (e.g., compliance with UL, IEC standards, and the ability to produce images "of diagnostic quality" using standard test phantoms like the i.b.a. Test Device DIGI-13). There was no clinical ground truth (expert consensus, pathology, or outcomes data) used in this particular substantial equivalence determination.

8. The sample size for the training set:

• Not applicable. This submission is for an X-ray imaging device, not an AI/ML algorithm that requires a training set.

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

• Not applicable. No AI/ML training set was used.

Ask a specific question about this device