Search Results

The SKR 3000 is indicated for use in generating radiographic images of human anatomy. It is intended to replace radiographic film/screen system in general-purpose diagnostic procedures.

The SKR 3000 is not indicated for use in mammography, fluoroscopy and angiography applications.

The modified SKR 3000 employs additional peripheral units, the Detector Interface Unit 2 (DIU2) and the Generator Interface Units 3 (GIU3), to incorporate serial radiography operation that is an additional radiography acquisition sequence.

The system is intended for use replacing a radiographic film/screen system in general-purpose diagnostic procedures of human anatomy. The system can be used in conjunction with current cleared AeroDR FPDs. The P-61, P-71, P-81 and the other compatible FPDs availably used in SKR 3000 are lightweight, mobile FPD and they are formed in compatible size with the cassette of ISO standard size. The FPDs availably used for the serial radiography are P-61 and P-71.

The SKR 3000 performs radiography imaging of the human body using an X-ray planar detector (FPD) that outputs a digital signal, which is then input into an image processing device. The serial radiography is a function of multi-frame radiography simply repeating single still radiography multiple times. The acquired image is transmitted to a filing system, printer, and image display device as diagnostic image after applying image processing to the raw data of image by the image processing device, Console CS-7.

This document describes the SKR 3000 device, specifically modified with additional peripheral units (Detector Interface Unit 2 (DIU2) and Generator Interface Units 3 (GIU3)) to incorporate a serial radiography operation. The purpose of this submission is to demonstrate substantial equivalence to a predicate device (K172793).

Since the primary claim is substantial equivalence based on technological characteristics and performance tests, not a new clinical claim or improvement over human readers, much of the requested information regarding AI performance and comparative studies with human readers is not applicable or provided in this document.

Here's a breakdown of the available information:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly provide a table of acceptance criteria with specific numerical performance metrics. Instead, it states that:

• "All of the verification activities required by the specification and the risk analysis for the SKR 3000 were performed and the results demonstrated that the predetermined acceptance criteria were met."
• "The performance tests according to the 'Guidance for the Submission of 510(k)s for Solid State X-ray Imaging Devices' and the other verification and validation including the items required by the risk analysis for the SKR 3000 were performed and the results demonstrated that the predetermined acceptance criteria were met."

The acceptance criteria are implicitly tied to compliance with relevant standards and the risk analysis. Performance is reported as meeting these predetermined criteria.

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

The document does not specify a separate "test set" in the context of image analysis performance as typically seen with AI devices. The assessment relies on engineering and performance tests of the device's hardware and software functionalities for image acquisition and processing.

• No specific sample size of images or patients is provided for a "test set" in the context of diagnostic accuracy.
• The provenance of data (e.g., country of origin, retrospective/prospective) is not mentioned because the evaluation is based on technical verification and validation, rather than clinical data.

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

Not applicable. The ground truth for this device's performance demonstration appears to be defined by technical specifications, compliance with standards, and risk analysis, rather than expert consensus on diagnostic interpretations of images.

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

Not applicable, as no external expert adjudication of images 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

Not applicable. This device is a digital radiography system, not an AI-powered image analysis tool intended to assist human readers or improve their performance. The submission focuses on the safety and effectiveness of the imaging system itself.

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

Not applicable. The SKR 3000 is an X-ray imaging system, not a standalone algorithm.

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

The "ground truth" for the device's performance is established through:

• Technical Specifications: The device's ability to produce radiographic images of human anatomy according to defined parameters (e.g., pixel size, A/D conversion, frame rate for serial radiography).
• Compliance with Standards: Meeting established engineering and safety standards (AAMI/ANSI ES 60601-1, IEC 60601-1-2, ISO 10993-1).
• Risk Analysis: Demonstrating that identified risks, including those related to the new serial radiography function, are reduced to acceptable levels.
• Comparison to Predicate Device: The modified device maintains similar technological characteristics and operational principles to its legally marketed predicate, which implicitly serves as a benchmark for "ground truth" regarding general-purpose diagnostic imaging.

8. The sample size for the training set

Not applicable. This is not an AI/machine learning device that requires a training set of data.

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

Not applicable, as there is no training set for this device.

Ask a specific question about this device