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

VIVIX-S 4386W is indicated for digital imaging solution designed as a general radiographic system for human anatomy. It is intended to replace film or screen based radiographic systems in all general purposes of diagnostic procedures. It is not to be used for mammography. It is intended for both adult and pediatric populations.

VIVIX-S 4386W, a flat panel detector model named; FXRD-4386WB with imaging areas of 43cm x 86cm. The device intercepts x-ray photons and the scintillator emits visible spectrum photons that illuminate an array of photo (a-SI)-detectors that create electrical signals. After the electrical signals are generated, it is converted to digital value, and the Software which acquires and processes the data values from the detector. The resulting digital images will be displayed on monitors. These devices should be integrated with an operating PC and an X-Ray generator. It can be utilized to digitalize x-ray images and transfer for radiography diagnostic.

Here's a breakdown of the acceptance criteria and study information for the VIVIX-S 4386W device, based on the provided text:

Acceptance Criteria and Reported Device Performance

The provided text focuses on demonstrating substantial equivalence to a predicate device (VIVIX-S 1717V, K181003) rather than defining specific acceptance criteria for de novo performance. The acceptance criteria implicitly are that the device performs as well as or better than the predicate device for relevant metrics, and that any differences do not raise new safety or effectiveness concerns.

The comparison table below highlights the performance metrics reported and their relationship to the predicate device.

Study Details

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

   • Test Set Sample Size: The document does not explicitly state the number of images or cases used in the clinical study. It only mentions that "a single-blinded concurrence study was conducted."
   • Data Provenance: Not specified (e.g., country of origin). The study is described as a "concurrence clinical study," implying prospective data collection for the purpose of the study, but this is not definitively stated.

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

   • Number of Experts: Not specified.
   • Qualifications of Experts: Not specified (e.g., radiologist with 10 years of experience).

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

   • Adjudication Method: Not specified. The study is described as "single-blinded concurrence study," which suggests readers were evaluating images without knowing if they were from the subject or predicate device, but the method for reconciling disagreements or establishing a consensus ground truth 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:

   • MRMC Study: Yes, a "single-blinded concurrence study" was conducted comparing the subject device with the predicate. This is a form of comparative effectiveness study.
   • Effect Size (AI Assistance): Not applicable. This study evaluates a digital X-ray detector (hardware plus basic image processing software), not an AI-assisted diagnostic tool. The study aims to show equivalence between the subject device and the predicate device in terms of diagnostic capability, not to demonstrate improvement with AI assistance. The document states, "the study confirmed that the new VIVIX-S 4386W provides images of equivalent diagnostic capability to the predicate devices."

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

   • Yes, non-clinical performance evaluations (MTF, DQE, spatial resolution) were conducted in a standalone manner to assess the physical performance characteristics of the device. However, the "clinical study" aspect would inherently involve human readers to assess "diagnostic capability." The term "standalone" in the context of diagnostic algorithms typically refers to the algorithm making a direct diagnostic output without human review, which is not what this device does. This device is a diagnostic imaging system component, and its images are intended for human interpretation.

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

   • The ground truth for the clinical study is based on expert assessment of diagnostic capability via comparison of images from the subject device to those from the predicate device. The document states "provides images of equivalent diagnostic capability." It does not specify if an independent "ground truth" (e.g., pathology reports, follow-up outcomes) was established for the cases themselves, but rather the relative diagnostic utility of the images produced by the two devices.

7. The sample size for the training set:

   • Training Set Sample Size: Not applicable. This document describes a medical device (digital X-ray detector) and its associated image acquisition and processing software. It is not an AI/ML algorithm that typically requires a large, annotated training set in the conventional sense for learning specific diagnostic tasks. The "training" for such a system involves engineering and calibration to produce high-quality images.

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

   • Ground Truth for Training Set: Not applicable for the reasons mentioned above. The development of the VIVIX-S 4386W involves engineering design, physical measurements, and quality control, rather than machine learning training with labeled data.

Ask a specific question about this device

The NFLK-2501 Portable X-ray Unit is a portable X-ray device, intended for use by a qualified/trained physician or technician for the purpose of acquiring X-ray images of the desired parts of patient's anatomy (including head, cervical spine, chest, abdomen, lumbar spine, pelvis and extremities).

The device may be used for handheld diagnostic imaging of body extremities.

The system is subject to the following limitations of use when stand-mounted:

• The device may be used for diagnostic imaging of head, cervical spine, abdomen, lumbar spine, pelvis or extremities.
• The device may be used for imaging of the chest when used without a grid.

This device is not intended for mammography.

The NFLK-2501 consists of a LED display with up and down soft-keys for controlling kV, an X-ray generator (line-powered transformer), an X-ray tube assembly, a collimator. A cart or a stand can be used with the NFLK-2501. In addition, this unit has preset memory keys to store and select kV. The NFLK-2501 is used with a flat-panel detector.

This device is a mains-powered Mobile X-ray System, designed and manufactured by NEUF.

Compared with traditional X-ray products, this device has exquisite structure, compact design, light weight and easy operation.

The major components of the X-ray main unit include: handle, enclosure, control panel, system control (SYS) board, high-voltage tank, collimator (beam limiter), and system control software running on the SYS board. The system control software is for realtime interaction and control with various circuit modules inside the X-ray generator. The software responds to user operations on the control panel. The user can adjust and control the kV and mAs parameters, and the software will display the parameters or directly load the APR parameters. The software loads the control data from X-ray output into the high-voltage generation control circuit of the system control board, and control the high-voltage tank to generate high-voltage to excite the X-ray tube inside to emit X-rays, control the switch of the collimator indicator, and monitor the working status of the device, and control the display of the status indicators.

The system is for X-ray imaging and diagnosis in facilities with mobile or fixing sites.

This device is not intended for mammography.

The device can be used with an X-ray flat panel detector, a computer for receiving and detecting signal results and an image processing software. The NFLK-2501 is designed for handheld or stand-mounted imaging. The NFLK-2501 can be configured to an optional portable stand/rack (see optional stands in 4.2) or use a stand that complies with IEC 60601- 1 safety standard. The recommended maximum load that the stand can safely carry is 30kgs to ensure the mechanical stability and effectiveness of the device.

The cybersecurity risks of the NFLK-2501 have been addressed to assure that no new or increased cybersecurity risks were introduced as a part of device risk analysis. These risks are defined as sequence of events leading to a hazardous situation, and the controls for these risks were treated and implemented as proposed in the risk analysis (e.g., requirements, verification).

The provided FDA 510(k) summary for the NFLK-2501 Portable X-ray Unit primarily focuses on establishing substantial equivalence to a predicate device through technological comparison and compliance with electrical safety and performance standards. It does not present acceptance criteria or a study proving the device meets specific clinical performance criteria in the way typically seen for AI/ML-based devices.

The document is for a traditional X-ray unit, not an AI-powered diagnostic device. Therefore, the types of acceptance criteria and studies anticipated for AI/ML devices (e.g., sensitivity, specificity, AUC, MRMC studies) are not applicable or detailed here.

Instead, the "acceptance criteria" can be inferred from the non-clinical testing performed, which focuses on device safety, electrical performance, and compliance with general X-ray standards to demonstrate substantial equivalence.

Here's the information based on the provided document, interpreting "acceptance criteria" as compliance with relevant standards and "study" as the non-clinical testing performed:

Acceptance Criteria and Study for NFLK-2501 Portable X-ray Unit

The NFLK-2501 Portable X-ray Unit is a traditional X-ray device, and its acceptance criteria are primarily based on demonstrating substantial equivalence to a predicate device and compliance with established electrical safety, performance, and radiation protection standards. The "study" refers to the non-clinical bench testing conducted to meet these standards.

1. Table of Acceptance Criteria and Reported Device Performance

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

This is a traditional X-ray unit, not an AI/ML diagnostic device that relies on a "test set" of images or patient data for performance evaluation. The "testing" involved non-clinical bench tests to verify compliance with electrical, mechanical, and radiation safety standards. Therefore, the concept of a "sample size for a test set" and "data provenance" in the context of clinical performance data is not applicable here.

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

Not applicable. As this is not an AI/ML diagnostic device with a clinical "test set" requiring ground truth establishment, no experts were involved in this capacity. The "ground truth" for the device's acceptable performance is defined by compliance with the referenced industry and regulatory standards.

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

Not applicable for the reasons stated above.

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 portable X-ray unit, which is a hardware device for image acquisition, not an AI/ML-driven diagnostic aid for image interpretation. Therefore, no MRMC study comparing human readers with and without AI assistance was performed.

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

Not applicable. This device is an X-ray imaging system, not an algorithm, and does not have a standalone "algorithm-only" performance to evaluate.

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

The "ground truth" in this context is the successful demonstration of compliance with established international medical device standards (e.g., IEC 60601 series) and FDA regulations (21 CFR 1020). These standards define acceptable levels of safety, electrical performance, and radiation characteristics for X-ray equipment. It is not based on clinical "ground truth" such as pathology or outcomes data for diagnostic accuracy, as this is an imaging device, not a diagnostic algorithm.

8. The sample size for the training set

Not applicable. The device is a hardware X-ray machine, not an AI/ML model trained on a dataset.

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

Not applicable for the reasons stated above.

Ask a specific question about this device

VIVIX-S 1751S series is used for the general-purpose diagnostic procedures, and as well as intended to replace radiographic film/ screen systems. The VIVIX-S 1751S series is not intended for mammography applications.

VIVIX-S 1751S, whose model name is VIVIX-S 1751S with 17X51 inches of imaging area. The device intercepts x-ray photons, and its Gadox (Gadolinium Oxysulfide) scintillator emits visible spectrum photons that illuminate an array of photo (a-SI)-detectors that create electrical signals. After the electrical signals are generated, it is converted to digital value, and the software acquires and processes the data values from the detector. The resulting digital images will be displayed on monitors. These devices should be integrated with an operating PC and an X-Ray generator. The detector can communicate with the generator by cable. It is utilized for capturing and transfer of digital x-ray images for radiography diagnosis. The X-ray generator and the imaging software are not part of the VIVIX-S 1751S.

Acceptance Criteria and Study for VIVIX-S 1751S Digital X-ray Detector

The VIVIX-S 1751S Digital X-ray detector was evaluated for substantial equivalence to its predicate device (K181003, VIVIX-S 1717V) through non-clinical performance testing and a clinical image concurrence study.

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria for the VIVIX-S 1751S are based on demonstrating performance equivalent to or better than the predicate device (VIVIX-S 1717V). Specifically, the device was tested against recognized performance metrics for X-ray detectors.

Note: While the exact DQE and MTF values vary for the specific FXRD-1751SB model compared to some predicate models (FXRD-1717VA vs FXRD-1717VB), the applicant states "Similar performance as follow" and declares the performance as "Equivalent," suggesting the overall performance is within an acceptable range for substantial equivalence.

2. Sample Size Used for the Test Set and Data Provenance

The provided summary does not explicitly state the specific sample size used for the clinical image concurrence study test set. It mentions "a single-blinded concurrence study." The data provenance (e.g., country of origin, retrospective or prospective) for this clinical study is also not detailed in the provided information.

3. Number of Experts and Qualifications for Ground Truth

The number of experts used to establish the ground truth for the clinical test set and their specific qualifications (e.g., "radiologist with 10 years of experience") are not specified in the provided 510(k) summary. It only indicates that "CDRH's Guidance for the Submission of 510(k)'s for Solid State X-ray Imaging Devices was conducted" and that it was a "single-blinded concurrence study."

4. Adjudication Method

The adjudication method for the test set is not explicitly stated. The summary mentions "a single-blinded concurrence study," which implies a comparison of images by experts, but the process for resolving disagreements or establishing a final ground truth is not described.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

There is no indication that a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was done to assess how much human readers improve with AI vs. without AI assistance. The device is a digital X-ray detector, not an AI-powered diagnostic tool, and the study described is a comparison of image diagnostic capability between two detector models.

6. Standalone (Algorithm Only) Performance Study

A standalone performance study of the algorithm only without human-in-the-loop performance is not applicable in the context of this device. The VIVIX-S 1751S is a digital X-ray detector, a hardware component that produces images for human interpretation, not an independent algorithm for diagnosis. The non-clinical performance (DQE, MTF, resolution) can be considered "standalone" in terms of objective image quality metrics of the device itself.

7. Type of Ground Truth Used

For the clinical study, the ground truth was established through expert concurrence. The summary states that the study "confirmed that the new x-ray detectors VIVIX-S 1751S provide images of equivalent diagnostic capability to the predicate devices." This implies that expert readers (though unspecified in number or qualifications) evaluated the images and concurred on their diagnostic equivalence. Pathology or outcomes data are not mentioned as the ground truth.

8. Sample Size for the Training Set

The provided 510(k) summary describes a digital X-ray detector, which is a hardware device for image acquisition. This device does not have a "training set" in the context of artificial intelligence or machine learning algorithms. Its design and performance are based on physical and technical specifications.

9. How the Ground Truth for the Training Set was Established

As clarified in point 8, the concept of a "training set" and associated "ground truth" for a training set is not applicable to this device as it is a digital X-ray detector, not an AI/ML diagnostic software. The performance evaluations are based on engineering specifications and clinical comparison to a predicate device.

Ask a specific question about this device