Search Results

INNOVISION-EXII is a stationery X-ray system intended for obtaining radiographic images of various anatomical parts of the human body, both pediatrics and adults, in a clinical environment. INNOVISION-EXII is not intended for mammography, angiography, interventional, or fluoroscopy use.

INNOVISION-EXII can receive X-ray signals from X-ray irradiation and digitize them into X-ray images by converting digital images to DICOM image format using Elui imaging software. INNOVISION-EXII is a general radiography X-ray system and not for mammography nor fluoroscopy. In addition, the system must be operated by a user who is trained and licensed to handle a general radiography X-ray system to meet the regulatory requirements of a Radiologic Technologist. Target areas for examinations include the head, spine, chest, and abdomen for diagnostic screening of orthopedic, respiratory, or vertebral discs. The system can capture a patient's postures, such as sitting, standing, or lying. This system can be used for patients of all ages, but it should be used with care for pregnant women and infants. The INNOVISION-EXII system has no part directly touching the patient's body.

The provided text describes a 510(k) summary for the INNOVISION-EXII stationary X-ray system, asserting its substantial equivalence to a predicate device (GXR-Series Diagnostic X-Ray System). However, the document does not contain information about acceptance criteria or a detailed study proving the device meets specific acceptance criteria related to its performance metrics for diagnostic imaging or AI assistance.

The "Clinical testing" section on page 9 merely states: "Clinical image evaluation of INNOVISION-EXII has been performed. The evaluation results demonstrated that INNOVISION-EXII generated images are adequate and suitable for expressing contour and outlines. The image quality including contrast and density are appropriate and acceptable for diagnostic exams." This is a very general statement and does not provide specific acceptance criteria or detailed study results.

Similarly, there are no details regarding AI performance (standalone or human-in-the-loop), sample sizes, ground truth establishment, or expert qualifications for such studies. The document focuses on establishing substantial equivalence based on intended use, technological characteristics, and compliance with various safety and performance standards (electrical safety, EMC, software validation, risk analysis).

Therefore, based solely on the provided text, the requested information about acceptance criteria and a study proving the device meets these criteria cannot be extracted or inferred. The document is a 510(k) summary focused on demonstrating substantial equivalence, not a detailed clinical performance study report.

Here is a breakdown of why each requested point cannot be addressed from the given text:

1. A table of acceptance criteria and the reported device performance: Not present. The "clinical testing" section is too vague.
2. Sample sized used for the test set and the data provenance: Not present. No specific test set for clinical performance is detailed.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not present. No ground truth establishment process is described beyond a general "clinical image evaluation."
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set: Not present.
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 present. The document does not mention any AI component or MRMC study.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not present. No mention of an algorithm or standalone performance.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.): Not detailed. Only a general "clinical image evaluation" is mentioned.
8. The sample size for the training set: Not present. The document describes a medical imaging device, not a machine learning model requiring a training set.
9. How the ground truth for the training set was established: Not applicable, as there's no mention of a training set or machine learning components.

In summary, the provided FDA 510(k) summary largely focuses on engineering and regulatory compliance (electrical safety, EMC, software validation, comparison of technical specifications to a predicate device) to establish substantial equivalence, rather than detailed clinical performance metrics derived from a study with specific acceptance criteria and ground truth for diagnostic accuracy.

Ask a specific question about this device

GXR-Series Diagnostic X-Ray System, is a stationary X-ray imaging system, for the purpose of acquiring X-ray images of the desired parts of a patient's anatomy. This device is not intended for mammography or bone density applications.

GXR Series Diagnostic X-ray System is a digital radiographic system. There are 5 power output configurations which are reflected in the model's designation "GXR-XX". The models have 5 different output power ratings: 32kW, 40kW, 52kW, 68kW, 82kW. The subject device, GXR Series Diaqnostic X-ray System, is designed to diagnose the human body by providing radiographic x-ray image with anatomical structure. The subject device has the same x-ray hardware components and image management software as the predicate device. The subject device consists of a high voltage (HV) generator, a tube support unit, an X-ray beam limiting device, a patient table, wall Bucky stand, and an x-ray tube, that operates on a high-frequency inverter method. The operator control console is designed to be user-friendly, and the user can select or change x-ray parameters easily using a large graphic LCD panel display and a soft membrane switch. The GXR Series high frequency X-ray generator (manufactured by DRGEM) features accuracy, reproducibility and long-term stability with capacitor assisted general line power supply. The APR (Anatomical Programming) and the optional AEC (Automatic Exposure Control) features gives the user control of exposure factors, automatically optimized for the radiological study selected. The digital flat panel detectors provide spatial resolution, MTF, DQE and stability based on fine pixel pitch. Selection of an anatomical study on the imaging software automatically sets up the x-ray generator's pre-programmed exposure technique setting and post image processing for selected study. The subject device is able to use a total of 10 different digital detectors, (8 new plus 2 cleared in the predicate, which have been previously cleared by the 510(k) process. The GXR Series Diagnostic X-ray System consists of a combination of an x-ray generator. and associated equipment such as tube stand, patient table, and, digital imaging system. The main power cabinet contains the HT tank and control circuits, the filament drivers, the low speed starter, and interface connections to the room equipment. Tube stand and patient table allows the operator to position the patient. Full Featured Imaging Software & Digital Image Processing. Control console. The image manaqement software, RADMAX Digital Imaging Software (K182537) by DRGEM, is used in both the predicate and subject device to serve as a convenient interface to the hardware and images. Anatomical view-based digital image processing automatically optimizes and enhances the quality of the captured images. RADMAX (K182537) Digital Imaging Software is designed for acquiring images and processing the acquired images. The software can be used together with a digital X-ray detector and or an X-Ray generator. The main features of the RADMAX software are controlling and interfacing the detector, acquiring images after X-ray, storing acquired images, managing data, and image processing. It can also perform system control such as the collimation size, and filter selection.

The provided text describes a 510(k) premarket notification for the "GXR-Series Diagnostic X-Ray System." This submission aims to demonstrate substantial equivalence to a predicate device, not to evaluate the performance of an AI algorithm with specific acceptance criteria that are typically statistical (e.g., sensitivity, specificity, AUC).

Therefore, based on the provided document, I cannot fulfill your request for:

• A table of acceptance criteria and the reported device performance (related to AI algorithm statistical performance).
• Sample size used for the test set and data provenance.
• Number of experts used to establish the ground truth for the test set and their qualifications.
• Adjudication method.
• If a multi reader multi case (MRMC) comparative effectiveness study was done.
• If a standalone (i.e. algorithm only without human-in-the-loop performance) was done.
• The type of ground truth used.
• The sample size for the training set.
• How the ground truth for the training set was established.

The document focuses on the device itself (an X-ray system), not an AI algorithm for image analysis. The "Performance Data" section describes nonclinical testing for general safety and effectiveness of the X-ray system as a whole, ensuring it meets standards for medical electrical equipment, radiation protection, and software lifecycle, and performs comparably to the predicate device. The only "difference" highlighted is the ability to interface with additional previously cleared digital flat panel detectors.

Ask a specific question about this device

VIVIX-S 1717V series is used for the general-purpose diagnostic procedures, and as well as intended to replace radiographic film/ screen systems. The VIVIX-S 1717V series is not intended for mammography applications.

VIVIX-S 1717V - Models FXRD-1717VA and FXRD-1717VB intercept X-ray photons, and the scintillator emits visible spectrum photons that illuminate an array of photo (a-SI)-detectors that create an electrical signals. After the electrical signals are generated, these are converted to a digital value, and an image will be displayed on the monitor.

These devices should be integrated with an operating PC and an X-Ray generator to digitalize Xray images and transfer the digitalized images for radiography diagnostic.

Advanced digital image processing allows considerably efficient diagnosis, all kinds of information management, and image information sharing on the network.

VIVIX-S 1717V - Models FXRD-1717VA and FXRD-1717VB are digital X-ray flat panel detectors, and each model has a 17 x 17 inch imaging area.

The scintillator used in FXRD-1717VA is Csl and Gadox was used for FXRD-1717VB.

Here's an analysis of the acceptance criteria and study detailed in the provided document:

Acceptance Criteria and Device Performance

The document doesn't explicitly state "acceptance criteria" in a separate, defined table with specific metrics that needed to be met to demonstrate equivalence. Instead, it relies on demonstrating substantial equivalence to a predicate device (VIVIX-S 1717N, K152894) through a comparison of technological characteristics and performance metrics, primarily DQE and MTF. The underlying acceptance criterion for these performance metrics is that they are "similar" to or within an acceptable range of the predicate device's performance.

Implicit Acceptance Criteria and Reported Device Performance:

The document concludes that "The results of these tests demonstrate that VIVIX-S 1717V - FXRD-1717VA and FXRD-1717VB Digital X-ray detectors meets the acceptance criteria and is adequate for this intended use."

Study Details

The primary study mentioned is a single-blinded concurrence study and a comparison test of non-clinical data.

1. Sample Size used for the test set and the data provenance:

   • Sample Size: Not explicitly stated for the clinical concurrence study. The document mentions "clinical images were provided," but doesn't quantify them. For the non-clinical data (DQE, MTF, spatial resolution), standard phantom images are typically used, but the quantity is not specified.
   • Data Provenance: Not specified (e.g., country of origin, retrospective/prospective). It's likely prospective data gathered for the submission.

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

   • This information is not provided in the document. The term "ground truth" is not used in the context of the clinical study; rather, it refers to a "concurrence study," implying comparison of image interpretations.

3. Adjudication method for the test set:

   • Not explicitly stated. A "single-blinded concurrence study" suggests that readers were unaware of which device generated the image, and their interpretations were compared. However, the method for resolving discrepancies or establishing an ultimate "truth" for evaluation is not detailed.

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 in the context of evaluating AI assistance. This study aims to demonstrate substantial equivalence between two X-ray detectors (subject device vs. predicate device), not the impact of AI on human reader performance.

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

   • No, this device is an X-ray detector, not an AI algorithm. Therefore, a standalone performance evaluation of an algorithm is not applicable. The device's performance is assessed through image quality metrics (DQE, MTF, resolution) and a clinical concurrence study with human readers.

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

   • The document implies expert consensus/interpretation for the clinical concurrence study ("provide images of equivalent diagnostic capability"). For the non-clinical performance data (DQE, MTF, Resolution), the "ground truth" is established by physical measurements and adherence to international standards (IEC 62220-1).

7. The sample size for the training set:

   • This device is an X-ray detector, not an AI or machine learning algorithm that requires a "training set." Therefore, this question is not applicable to the information provided.

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

   • As this device does not involve an AI algorithm with a training set, this question is not applicable.

Ask a specific question about this device