Search Results

Flat Panel Digital X-ray Detector 17HK701G-W is indicated for digital imaging solution designed for general radiographic system for human anatomy. It is intended to replace film or screen based radiographic systems in general purpose diagnostic procedures all and not to be used for mammography.

The 17HK701G-W is the solid state x-ray imager, which can generate radiographic images of any part of the body. These devices intercept x-ray photons and the scintillator (CSI:TI) emits visible spectrum photons that illuminate an array of photo-detectors that create an electrical signals. After the electrical signals are generated, it is converted to digital value, and the images are displayed on monitors. The digital value can be communicated to the operator console via wiring connection. The 17HK701G-W consists of the following components: Flat Panel Detector, Control Box, battery Charger, 2 packs of battery, power adapter for charger, Calibration Software, power cord and cables. The 17HK701G-W can be used for general X-ray system excluding fluoroscopic, angiographic, and mammographic applications. The subject device is supported by software. The software is of Moderate level of concern and is identical to the predicate software.

This document pertains to the 510(k) premarket notification for the LG Electronics Inc. 17HK701G-W Flat Panel Digital X-ray Detector. The information provided outlines the device's characteristics and its substantial equivalence to a predicate device, K182348 (14HK701G-W).

Acceptance Criteria and Device Performance:

The document primarily focuses on demonstrating substantial equivalence to a predicate device rather than presenting a detailed independent study with specific acceptance criteria and a "reported device performance" table in the manner typically seen for new AI/CADe systems with diagnostic claims.

Instead, the acceptance for this device hinges on its technological characteristics being substantially equivalent to the predicate device, specifically regarding safety and effectiveness. The comparison table below highlights key technological characteristics:

Table of Acceptance Criteria and Reported Device Performance

The Study That Proves the Device Meets the Acceptance Criteria:

The document describes a submission for substantial equivalence to an existing predicate device (K182348, 14HK701G-W). This means the "study" is a collection of tests and comparisons designed to demonstrate that the new device (17HK701G-W) is as safe and effective as the predicate device, despite minor differences.

Here's the breakdown of the information requested:

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

   • The document states: "Clinical data has been provided according to FDA guidance document 'Guidance for the Submission of 510(k)s for Solid State X-ray Imaging Devices'. The data was not necessary to establish substantial equivalence based on the modifications to the device but provided further evidence in addition to the laboratory performance data to show that the device works as intended."
   • This implies that while clinical data was submitted, it wasn't the primary basis for the substantial equivalence determination due to the nature of the device (a digital X-ray detector, not an AI/CADe system with a diagnostic claim) and the similarity to the predicate. Therefore, detailed sample sizes, data provenance (country, retrospective/prospective), or ground truth methods for this clinical data are not explicitly provided in this summary. The focus was on non-clinical performance and technological equivalence.

2. 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):

   • As detailed above, the clinical data was not the primary driver for substantial equivalence, and therefore, details on expert ground truth establishment for a test set are not provided nor expected in this type of submission.

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

   • Not applicable/not provided as a formal reader study with adjudication for ground truth was not the primary method for demonstrating equivalence for this device.

4. 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 comparative effectiveness study was not done. This device is a diagnostic imaging component (a flat panel detector), not an AI/CADe system designed to assist human readers or make a diagnostic claim.

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

   • This question is generally relevant for AI/CADe systems. For this device (a flat panel detector), its "standalone performance" is assessed by electrical safety, EMC, and imaging performance tests (DQE, MTF, resolution), which were conducted. The device (detector) itself does not perform an "algorithm" making a diagnostic assessment.

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

   • For the non-clinical performance tests (DQE, MTF, resolution), the "ground truth" is established by physical measurement standards (e.g., IEC 62220-1). For the clinical data, if it was descriptive (e.g., image quality assessment), the ground truth would likely be expert interpretation, but specific details are not provided.

7. The sample size for the training set:

   • This device is a hardware component with associated firmware/software for image acquisition and processing. It is not an AI/Machine Learning model that undergoes "training" on a dataset in the conventional sense. The software validation refers to standard software development lifecycle processes, not machine learning model training. Therefore, a "training set sample size" is not applicable in this context.

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

   • As above, a "training set" in the context of machine learning is not applicable for this device. The software validation follows established engineering principles, ensuring the software performs its intended functions correctly and reliably, rather than learning from labeled data.

Ask a specific question about this device