(122 days)
The Discovery XR656 is intended to generate digital radiographic imoges of the skull, spinal column, chest, abdomen, extremities, and other body parts in patients of all ages. Applications con be performed with the patient sitting, standing, or lying in the prone or supine position and is intended for use in all routine radiography exams.
When the VolumeRAD option is included on the system, the system can generate tomographic images of human anatomy including the skull, spinal column, chest, abdomen, extremities, and other body parts in patients of all ages.
When the VolumeRAD option is used for potients undergoing thorocic imaging, it is indicated for the detection of lung nodules. VolumeRad generates diagnostic images of the chest that aid the radiologist in achieving superior detectability of lung nodules versus posterior-anterior and left lateral views of the chest, at o comparable radiation level.
The device is not intended for mammographic applications.
The Discovery™ XR656 with VolumeRAD extended claims remains a radiographic X-ray system capable of generating radiographic and tomographic images of human anatomy.
The Discovery XR656 is designed to handle radiographic applications using GE's flat-panel wireless digital detector. The digital detector is comprised of amorphous silicon and cesium iodide scintillator. The resulting digital image can be sent through a DICOM network for applications such as printing, viewing and storage.
The Discovery XR656 Digital Radiographic Imaging system consists of a Wallstand, elevating table, overhead Tube support, X-ray tube, collimator, system controller, X-ray generator, and wireless/tethered digital detector. Various configurations are available to meet radiographic requirements. The Optima XR640 version of this product does not include advanced applications and uses the tethered version of the digital detector.
The Discovery XR656 offers a wide range of advanced clinical applications including GE's VolumeRAD™ (Digital Tomosynthesis), Dual Energy Subtraction, Tissue Equalization and Auto Image Paste.
This 510(k) is to expand our marketing claims for lung nodule detection using the VolumeRAD application. There is no change in design, manufacturing, materials or energy source of the already cleared device. All the abilities required to achieve the results of the extended claims during the clinical trial were available at the initial release of the system.
The provided text describes a 510(k) premarket notification for the GE Healthcare Discovery XR656 with VolumeRAD, seeking to expand its marketing claims for lung nodule detection. The relevant information to address your request is extracted and organized below.
1. Table of Acceptance Criteria and Reported Device Performance
The submission describes the goal of the clinical study, which implicitly sets the acceptance criteria: the device should increase physician accuracy in detecting lung nodules compared to conventional X-ray. The reported performance is that this goal was met.
| Acceptance Criteria (Implicit Goal) | Reported Device Performance |
|---|---|
| Increase physician accuracy in the detection of lung nodules (3-20mm) | "A Multi-centered clinical study was performed to demonstrate that the use of VolumeRAD increases physician accuracy in the detection of lung nodules 3-20mm in diameter, when compared to conventional two-view CxR (posterior-anterior (PA) and left lateral (LAT)), at an average effective dose less than 0.1mSv." |
| "With the extended VolumeRAD claims, the Discovery XR656 with VolumeRAD has demonstrated effectiveness beyond the original limited claims of the VolumeRAD feature." | |
| Comparable radiation level | "at a comparable radiation level." |
2. Sample Size Used for the Test Set and Data Provenance
The document states: "A Multi-centered clinical study was performed..." However, it does not specify the sample size used for the test set.
The data provenance is a "Multi-centered clinical study," implying prospective data collection across multiple sites. The document does not explicitly state the country of origin of the data.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications
The document does not specify the number of experts used to establish ground truth or their qualifications. It only refers to "physician accuracy."
4. Adjudication Method for the Test Set
The document does not describe any adjudication method used for the test set.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study and Effect Size
Yes, a comparative effectiveness study was done. The study aimed to demonstrate that "the use of VolumeRAD increases physician accuracy in the detection of lung nodules... when compared to conventional two-view CxR (posterior-anterior (PA) and left lateral (LAT))."
The document explicitly states that the study demonstrated an "increase[d] physician accuracy," implying a positive effect size. However, the exact effect size of how much human readers improve with AI (VolumeRAD) vs. without AI assistance (conventional CxR) is not quantified in the provided text (e.g., as a percentage increase in AUC, sensitivity, or specificity).
6. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study
The study described is focused on "physician accuracy," indicating a "human-in-the-loop" scenario where radiologists use the VolumeRAD system. A standalone (algorithm only without human-in-the-loop performance) study is not described in the provided text.
7. Type of Ground Truth Used
The document does not explicitly state the type of ground truth used. Given the focus on "lung nodule detection" and "physician accuracy," it is highly probable that the ground truth involved expert consensus, pathology, and/or follow-up imaging to confirm the presence or absence of lung nodules. However, this is an inference, not explicitly stated.
8. Sample Size for the Training Set
The document does not mention a training set sample size. The submission is for an expanded marketing claim for an existing device ("There is no change in design, manufacturing, materials or energy source of the already cleared device. All the abilities required to achieve the results of the extended claims during the clinical trial were available at the initial release of the system."). This suggests that the VolumeRAD feature was already developed, and this 510(k) is about validating its clinical utility for a specific indication (lung nodule detection), rather than the development of a new AI model requiring a separate training set description in this context.
9. How the Ground Truth for the Training Set Was Established
As no training set is described in the provided text (see point 8), how its ground truth was established is not applicable/described here.
§ 892.1740 Tomographic x-ray system.
(a)
Identification. A tomographic x-ray system is an x-ray device intended to be used to produce radiologic images of a specific cross-sectional plane of the body by blurring or eliminating detail from other planes. This generic type of device may include signal analysis and display equipment, patient and equipment supports, component parts, and accessories.(b)
Classification. Class II.