Search Results

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.

The VIVIX-S 1751S, available in models FXRD-1751SA and FXRD-1751SB, features a 17x51 inch imaging area. This device intercepts x-ray photons and uses a scintillator to emit visible spectrum photons. The FXRD-1751SA model uses a Csl:Tl (Thallium doped Caesium lodide) scintillator, while the FXRD-1751SB model uses a Gadox (Gadolinium Oxysulfide) scintillator. These photons illuminate an array of photo (a-SI) detectors, creating electrical signals are then converted to digital values, which are processed by software to produce digital images displayed on monitors. The VIVIX-S 1751S must be integrated with an operating PC and an X-ray generator, and it can communicate with the generator via cable. It is designed for capturing and transferring digital x-ray images for radiography diagnosis. Note that the X-ray generator and imaging software are not included with the VIVIX-S 1751S.

The document describes a 510(k) submission for the VIVIX-S 1751S digital X-ray detector. The acceptance criteria and the study proving the device meets these criteria are primarily demonstrated through a comparison to a predicate device (K190611) and performance testing based on established standards.

Here's a breakdown of the requested information:

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria are implicitly defined by demonstrating substantial equivalence to the predicate device in terms of technological characteristics and performance metrics, as well as compliance with recognized standards. The "performance" column shows the subject device's reported values relative to the predicate device.

2. 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, "A-Qualified Expert Evaluation study according to CDRH's Guidance for the Submission of 510(k)'s for Solid State X-ray Imaging Devices was conducted..." However, it does not specify the sample size of cases/images used in this clinical evaluation study.
The data provenance (country of origin, retrospective/prospective) is not explicitly stated in the provided text.

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

The document mentions an "Expert Evaluation study" but does not specify the number of experts or their exact qualifications (e.g., "radiologist with 10 years of experience"). It only indicates that it was a "Qualified Expert Evaluation study."

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

The document does not describe the adjudication method used for the expert evaluation study.

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

A multi-reader multi-case (MRMC) study was conducted as part of the "Qualified Expert Evaluation study." The primary goal of this study was to confirm that the subject device (VIVIX-S 1751S - FXRD-1751SA) provides images of equivalent diagnostic capability to the predicate device (VIVIX-S 1751S - FXRD-1751SB).

The document does not mention the involvement of AI in this study, nor does it quantify any improvement of human readers with AI assistance. The study described is a comparison of two different X-ray detector technologies, not an AI-assisted reading study.

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

This device is an X-ray detector, not an AI algorithm. Therefore, the concept of "standalone (algorithm only)" performance without a human-in-the-loop is not applicable in the same way it would be for an AI diagnostic software. The performance metrics reported (MTF, DQE) are physical image quality parameters of the detector itself, which could be considered "standalone" in this context as they characterize the device's inherent imaging capability.

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

The ground truth for the "clinical test" (Expert Evaluation study) was established by "Qualified Expert Evaluation" to assess "equivalent diagnostic capability" of the images. This suggests a form of expert consensus or individual expert readings to determine the diagnostic quality of the images produced by the subject device compared to the predicate. It does not mention pathology or outcomes data as the primary ground truth.

8. The sample size for the training set

The document does not mention a training set in the context of this device because it is a hardware device (X-ray detector), not an AI algorithm that requires a training phase.

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

Since there is no mention of a training set for an AI algorithm, the question of how its ground truth was established is not applicable to this submission.

Ask a specific question about this device

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

VIVIX-S -FW, a series for of flat panel detectors models named; FXRD-2530FAW, FXRD-3643FAW, FXRD-4343FAW, with imaging areas of 25cm x 30cm, 36cm x 43cm, 43cm x 43cm, respectively. The detectors can acquire static images as well as fluoroscopic images up to 6fps.

The device intercepts x-ray photons and the scintillator (Cesium lodide) 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 is transmitted either by wire via cable or wirelessly through a system control unit (SCU), and the software called Vxvue acquires and processes the data values from the detector. The SW is of moderate level of concern. On the Vxvue, the use can view as well as perform basic manipulations such as (rotation, enlargement, etc.) on the acquired images. 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.

The provided text describes a 510(k) summary for a digital flat panel X-ray detector, VIVIX-S FW, and its substantial equivalence to a predicate device, VIVIX-S VW. The study focuses on demonstrating that the new device provides images of equivalent diagnostic capability to the predicate devices.

Here's a breakdown of the requested information based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria for substantial equivalence are primarily based on demonstrating non-inferiority or equivalence to the predicate device in terms of "Performance (MTF)" and "Performance (DQE)," and meeting current spatial resolution standards. While the document states "similar performance," the exact acceptance thresholds (e.g., within a certain percentage point) for MTF and DQE are not explicitly quantified as absolute acceptance criteria values in the provided text. Instead, observed values are compared to the predicate.

Note on "Equivalence" Column in the provided table: The provided document's table includes an "Equivalence" column which states "Equivalent" for characteristics like Common Name, Classification Name, etc. For MTF, DQE, and Spatial Resolution, this column is blank in the source document, indicating a direct comparison rather than a simple "Equivalent" stamp. The text states "There is similar performance as follow" for MTF and DQE, and the table then lists the values.

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

The document states: "A single-blinded concurrence study according to CDRH's Guidance for the Submission of 510(k)'s for Solid State X-ray Imaging Devices was conducted, and the study confirmed that the new x-ray detectors VIVIX-S FW provide images of equivalent diagnostic capability to the predicate devices..."

• Sample Size: The specific sample size (number of images or cases) used for the clinical test set is not explicitly stated in the provided text.
• Data Provenance: The provenance (country of origin, retrospective/prospective) of the data used for the clinical study is not explicitly stated in the provided text.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications

The document mentions "a single-blinded concurrence study," which implies expert review. However:

• Number of Experts: The specific number of experts involved in establishing ground truth or evaluating images for the test set is not explicitly stated.
• Qualifications of Experts: The qualifications of these experts are not explicitly stated.

4. Adjudication Method for the Test Set

The document refers to a "single-blinded concurrence study." While this implies a comparison of images by readers, the specific adjudication method (e.g., 2+1, 3+1, none) for the test set is not explicitly stated. "Concurrence" suggests agreement among readers, but the process for resolving disagreements or establishing a definitive ground truth from the expert readings is not detailed.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and the Effect Size of Improvement with AI vs. Without AI Assistance

• MRMC Study: The document describes a "single-blinded concurrence study" comparing the VIVIX-S FW device to predicate devices. This sounds like it could be an MRMC-like study in its nature of comparing image quality or diagnostic capability, but it's focused on device equivalence rather than AI assistance.
• AI Assistance Effect Size: The device described (VIVIX-S FW) is a digital X-ray detector, not an AI-powered diagnostic tool. Therefore, the study is not assessing the improvement of human readers with AI assistance. The concept of "AI vs. without AI assistance" is not applicable to this device and study.

6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) Was Done

The device is an X-ray detector, which captures images. Its performance is evaluated through objective metrics like MTF and DQE, and through a clinical "concurrence study" involving human interpretation of the images produced by the device, comparing them to images from a predicate device. This is not an "algorithm-only" performance evaluation in the context of an AI algorithm, but rather a standalone evaluation of the image acquisition hardware. The non-clinical data (MTF, DQE, spatial resolution) are objective measures of the device's technical image quality, which can be seen as a form of standalone performance evaluation in the engineering sense.

7. The Type of Ground Truth Used

The clinical study is described as a "concurrence study" to confirm "equivalent diagnostic capability." This strongly suggests that the ground truth for diagnostic capability was established by expert consensus or through a process where experts evaluated the images for diagnostic equivalence. It does not mention pathology, outcomes data, or other definitive methods as the primary ground truth.

8. The Sample Size for the Training Set

The provided text describes a 510(k) for a hardware device (digital X-ray detector) and its associated software for image processing and viewing (Vxvue). It does not mention machine learning or AI models requiring a "training set." Therefore, a training set sample size is not applicable and not provided in this document.

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

Since there is no mention of an AI model or training set, this question is not applicable based on the provided information.

Ask a specific question about this device

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

VIVIX-S VW, a series for of flat panel detectors models named; FXRD-2530VW, FXRD-2530VW PLUS, FXRD-3643VW, FXRD-3643VW PLUS, FXRD-4343VW, FXRD-4343VW PLUS, with imaging areas of 25cm x 30cm, 36cm x 43cm, 43cm, respectively. 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.

The retrieved text discusses the VIVIX-S VW digital flat panel X-ray detector, which is being reviewed for 510(k) clearance. The focus of the document is to demonstrate "substantial equivalence" of the device to previously cleared predicate devices, rather than establishing acceptance criteria for a new AI/CADe device with associated clinical studies that specifically prove these criteria are met.

Therefore, the provided text does not contain the detailed information required to fill out all the requested fields regarding acceptance criteria in the context of an AI/CADe device, as it is a 510(k) summary for a general X-ray detector. Specifically, it lacks information on:

• Specific acceptance criteria for clinical performance (e.g., sensitivity, specificity, AUC values with thresholds).
• The methodology for establishing ground truth for a test set (e.g., how experts determined disease presence/absence in a test set, number of experts, qualifications).
• Adjudication methods.
• MRMC comparative effectiveness study details (effect size of human readers with/without AI assistance).
• Standalone algorithm performance (since this is an X-ray detector, not an AI algorithm).
• Sample size and ground truth for a training set (which would be relevant for an AI model).

However, based on the information available, here's what can be extracted and inferred to the best extent possible for a general X-ray detector:

1. A table of acceptance criteria and the reported device performance

For an X-ray detector, acceptance criteria are primarily related to physical and imaging performance characteristics, not diagnostic accuracy in the way an AI algorithm would be evaluated. The text focuses on demonstrating equivalence to predicate devices using these metrics.

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

• Sample Size for Test Set: Not explicitly stated. The document mentions "a comparison test was conducted" for non-clinical data and "A single-blinded concurrence study" for clinical data, but without specific numbers of images or cases.
• Data Provenance: Not specified.

3. 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)

• Number of Experts: Not specified.
• Qualifications of Experts: Not specified. The study is described as a "single-blinded concurrence study," implying comparison between readers, but details on how ground truth was established are missing.

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

• Adjudication Method: Not specified. The term "concurrence study" implies agreement, but the method for resolving discrepancies or establishing a definitive ground truth is not detailed.

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

• MRMC Study: The document describes a "single-blinded concurrence study" to confirm "equivalent diagnostic capability to the predicate devices." This is not an MRMC study comparing human readers with and without AI assistance, but rather a study comparing the diagnostic capability of images produced by the subject device versus predicate devices.
• Effect Size of Human Reader Improvement: Not applicable, as this was not an AI-assisted diagnostic study.

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

• Standalone Study: Not applicable. This device is a digital X-ray detector, not an AI algorithm. Its performance is inherent in the image quality it produces, which is then interpreted by a human. The "standalone" concept typically applies to AI algorithms.

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

• Type of Ground Truth: Not explicitly stated. For a "concurrence study" comparing diagnostic capability of images, the ground truth would likely be established by expert radiologists, possibly through consensus or by reference to other clinical information, but the method is not described.

8. The sample size for the training set

• Sample Size for Training Set: Not applicable. This device is a hardware X-ray detector, not a machine learning algorithm that requires a training set.

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

• Ground Truth for Training Set: Not applicable, as there is no training set for a hardware device.

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

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

VIVIX-S 1417N Series is used for the general-purpose diagnostic procedures, and as well as intended to replace radiographic film / screen systems. The VIVIX-S 1417N Series is not intended for mammography applications.

FXRD-1417NAW and FXRD-1417NBW are 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.

Models FXRD-1417NAW and FXRD-1417NBW 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, andimage information sharing on the network.

The provided document is a 510(k) premarket notification for a medical device, specifically a digital flat panel X-ray detector (VIVIX-S 1417N). It focuses on demonstrating substantial equivalence to a predicate device (VIVIX-S 1717N), rather than providing detailed acceptance criteria and a study to prove meeting those criteria for an AI/CADe device.

Therefore, this document does not contain the information required to answer the prompt regarding acceptance criteria and a study proving a device meets those criteria, especially for an AI/CADe device.

The document details the technical characteristics and non-clinical and clinical data used to support the substantial equivalence claim for a hardware device (an X-ray detector). It does not describe the performance of an AI or CADe algorithm or a study designed to evaluate such a system against specific performance metrics for diagnostic accuracy.

Here's why the requested information cannot be found in the provided text:

• No AI/CADe device: The VIVIX-S 1417N is an X-ray detector, which captures images. It is not an AI algorithm or a computer-aided detection (CADe) system that analyzes images for specific findings.
• Focus on Substantial Equivalence: The entire submission is built around proving the new device is "substantially equivalent" to an existing predicate device based on similar intended use, technological characteristics, and performance, primarily in terms of image quality metrics (MTF, DQE, etc.).
• "Clinical Data" section: While a "clinical data" section exists, it refers to a "single-blinded concurrence study" to confirm the new X-ray detectors provide "images of equivalent diagnostic capability" to the predicate devices. This is about image quality for human interpretation, not about the performance of an AI algorithm in detecting or diagnosing conditions, and it doesn't specify how "diagnostic capability" was quantified or what the acceptance criteria for it were. It serves to show the hardware works as intended for human readers.

To answer the prompt, I would need a document that describes the development and validation of an AI or CADe medical device, including:

• Specific diagnostic task: What condition is the AI designed to detect or diagnose (e.g., lung nodules, fractures, diabetic retinopathy)?
• Performance metrics: What metrics are used to measure the AI's accuracy (e.g., sensitivity, specificity, AUC, FROC, precision, recall)?
• Ground truth derivation: How was the definitive diagnosis for the test cases established (e.g., biopsy, follow-up, expert consensus with adjudication)?
• Study design for AI performance: Details of an MRMC study, standalone performance study, etc.

Since none of this is present, I cannot fill out the requested table or answer the specific questions about AI/CADe device performance directly from this document.

Ask a specific question about this device

VIVIX-S 1012N (FXRD-1012NA, FXRD-1012NB, FXRD-1012NAW and FXRD-1012NBW) 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.

Models FXRD-1012NA, FXRD-1012NB, FXRD-1012NAW and FXRD-1012NBW 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.

The provided text does not contain detailed acceptance criteria or a comprehensive study design that allows for the extraction of all requested information. The document is a 510(k) summary for a digital X-ray detector, focusing on demonstrating substantial equivalence to predicate devices rather than a detailed performance study against specific acceptance metrics derived independently.

However, based on the available information, here's a breakdown of what can be inferred and what is missing:

Missing Information:

• Detailed, explicit acceptance criteria values (e.g., specific thresholds for DQE, MTF that had to be met by the new device, beyond "similar"). The document states "...meet the acceptance criteria...", but these criteria themselves are not listed with numerical targets.
• The exact sample size for the clinical test set (only "a single-blinded concurrence study" is mentioned).
• Number and qualifications of experts for ground truth establishment.
• Adjudication method for the test set.
• Details of any Multi-Reader Multi-Case (MRMC) comparative effectiveness study, including effect size.
• Standalone algorithm performance (this device is a digital X-ray detector, not an AI algorithm, so this concept doesn't directly apply).
• Sample size for the training set (as this is a medical device, not an AI model, there isn't a "training set" in the typical sense of machine learning).
• How ground truth for the training set was established (again, not applicable to this type of device).

Inferred Information based on the document:

The study primarily focuses on demonstrating substantial equivalence to predicate devices (K122865 and K122866) by comparing technological characteristics and performance metrics.

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly list "acceptance criteria" with numerical thresholds that the new device must meet. Instead, it compares the performance of the subject device (VIVIX-S 1012N models) to the predicate devices. The "acceptance" is implicitly that the performance of the new device is similar or better than the predicate devices, particularly in areas like DQE and MTF.

Here's a table showing the performance comparison provided, which serves as the "reported device performance" against the implicitly accepted "similar to predicate" standard:

Note: For DQE and MTF values, the table for the "Reference Predicate Devices" (K122865) shows "-" for these performance metrics, while the "Primary Predicate Devices" (K122866) has values. The "Comparison test" in section 9 explicitly states comparison was done with K122866.

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

• Sample Size: Not explicitly stated for the clinical test set, only mentioned as "a single-blinded concurrence study."
• Data Provenance: Not specified (e.g., country of origin). The study is described as a "clinical test" which "complied with the requirements specified in the CDRH's Guidance for the Submission of 510(k)'s for Solid State X-ray Imaging Devices," suggesting a prospective or collected dataset for the purpose of the submission. It's not explicitly stated as retrospective or prospective.

3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications

• Number of Experts: Not specified.
• Qualifications of Experts: Not specified.

4. Adjudication Method for the Test Set

• Adjudication Method: Not specified. The study is described as a "single-blinded concurrence study." This implies that evaluators were blinded to which images came from the new device versus the predicate, and their interpretations were compared for "concurrence," but the method of resolving discrepancies or establishing definitive ground truth from multiple readers is not detailed.

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

• Was it done?: The document describes a "single-blinded concurrence study" comparing images from the new device to the predicate device to confirm "equivalent diagnostic capability." This is a form of comparative study involving human readers (though the number of readers is not disclosed), but it is focused on demonstrating equivalence (non-inferiority) rather than improvement with AI assistance.
• Effect Size of Human Reader Improvement: Not applicable, as this is a comparison between two different X-ray detectors, not an AI-assisted workflow vs. unassisted human reading.

6. Standalone (Algorithm Only) Performance

• Was it done?: Not applicable. The device (VIVIX-S 1012N) is a digital X-ray detector, a hardware component that captures images. It is not an AI algorithm. The performance metrics (DQE, MTF, Resolution) are intrinsic to the image capture capabilities of the detector.

7. Type of Ground Truth Used

• Type of Ground Truth: For the "concurrence study," the ground truth was based on the "equivalent diagnostic capability" of the images as assessed by human readers ("experts"). This would typically mean that clinical interpretations of images from the new device were compared to interpretations of images from the predicate device to ensure they did not differ significantly in diagnostic content. It is a form of expert consensus on image diagnostic quality, rather than a definitive "true positive/negative" based on pathology or outcomes data.

8. The Sample Size for the Training Set

• Sample Size for Training Set: Not applicable. This device is a digital X-ray detector, not an AI model requiring a training set.

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

• How Ground Truth Established: Not applicable.

Ask a specific question about this device

VIVIX-S 1717N (FXRD-1717NA, FXRD-1717NB, FXRD-1717NAW and FXRD-1717NBW) 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.

Models FXRD-1717NA, FXRD-1717NB, FXRD-1717NAW and FXRD-1717NBW 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.

Models XRD-1717NA, FXRD-1717NB, FXRD-1717NAW and FXRD-1717NBW are digital X-ray flat panel detectors, and each model has a 10 x 12 inch imaging area.

FXRD-1717NA and FXRD-1717NB communicate by using a wired communication feature (Gigabit Ethernet communication method by connecting to a tether cable), while FXRD-1717NAW and FXRD-1717NBW communicate by using a wireless communication feature (IEEE 602.lla/b/g/n).

The scintillator used in FXRD-1717NA and FXRD-1717NAW is Csl. Gadox was used for FXRD-1717NB and FXRD-1717NBW.

The FXRD-1717N series is designed to be used with any certified X-ray generators that features DR Trigger mode and is marketed legally. When the DR Trigger mode is not desired, then the connection with the generator can be maintained with AED mode. FXRD-1717N is not designed to function as an X-ray control. The AED mode does not require integration procedure since there is no connection requirement between the X-ray System and the detector. The subject device can receive any types of x-ray signals without SW.

For the DR Trigger mode, the generator interface cable connects the SCU and the X-ray generator. The head of the cable is connected with one of the port (EXT-INF) of the SCU, and the other end of the cable (which is stripped) is connected to the generator's socket.

This document (K152894) describes a 510(k) premarket notification for the VIVIX-S 1717N digital flat panel X-ray detector. It focuses on demonstrating substantial equivalence to predicate devices rather than proving a specific clinical acceptance criterion with a novel AI device. Therefore, much of the requested information about AI performance, multi-reader multi-case studies, and detailed ground truth for training data is not applicable or available in this document.

However, I can extract and infer information about the acceptance criteria for a medical imaging device's performance through comparison to a predicate device, as well as the study conducted to demonstrate this equivalence.

Here's the breakdown based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The document doesn't explicitly state "acceptance criteria" for quantitative clinical performance metrics of the device in a table format as one might expect for a new AI diagnostic device. Instead, it demonstrates substantial equivalence to predicate devices based on technological characteristics and image quality assessments. The "acceptance criteria" are implicitly met if the device's performance metrics are comparable to or better than the predicate's.

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

• Test Set Sample Size: Not explicitly stated in terms of number of images or patients. The document only mentions "a single-blinded concurrence study."
• Data Provenance: Not specified in the document (e.g., country of origin). The study is described as a "clinical test, which complied with the requirements specified in the CDRH's Guidance for the Submission of 510(k)'s for Solid State X-ray Imaging Devices." This suggests a prospective or retrospective collection of images for the comparison, but details are not provided. The study confirms "equivalent diagnostic capability" of the new detectors to the predicate device.

3. Number of Experts Used to Establish Ground Truth for the Test Set and Their Qualifications

• Number of Experts: Not specified.
• Qualifications of Experts: Not specified.

4. Adjudication Method for the Test Set

• Adjudication Method: Not specified. The study is referred to as a "single-blinded concurrence study," which implies some form of assessment by experts, but the exact method of combining opinions or establishing ground truth isn't detailed.

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

• Was an MRMC study done? The document describes a "single-blinded concurrence study" to assess "equivalent diagnostic capability." While this involves readers and cases, the text does not indicate it was designed as a comparative effectiveness study comparing human readers with AI vs. without AI assistance. The device itself is an X-ray detector, not an AI interpretation algorithm.
• Effect Size of Human Readers with AI vs. without AI assistance: Not applicable, as this is a device for image acquisition, not AI for image interpretation.

6. Standalone Performance Study (Algorithm Only Without Human-in-the-Loop)

• Was a standalone study done? Not applicable in the context of an AI algorithm. This device is an X-ray detector. Its performance was evaluated based on physical detector characteristics (DQE, MTF, spatial resolution) and a "concurrence study" of its images against a predicate, implying human interpretation of the images produced by the detector.

7. Type of Ground Truth Used for the Test Set

• Type of Ground Truth: The "single-blinded concurrence study" evaluated "equivalent diagnostic capability." This implies that the ground truth for image quality was established through expert assessment of the diagnostic content of the images produced by the subject device compared to the predicate device. It is a form of expert consensus on image diagnosticity, rather than pathology or long-term outcomes data primarily.

8. Sample Size for the Training Set

• Sample Size for Training Set: Not applicable. This document describes a medical imaging device (X-ray detector), not an AI algorithm that requires a training set. The performance data relates to the physical characteristics of the detector and the quality of the images it produces.

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

• How Ground Truth for Training Set Was Established: Not applicable, as this is a medical imaging device, not an AI algorithm.

Ask a specific question about this device

ViVIX-S wireless 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 all general purpose diagnostic procedures. Not to be used for mammography and/or for fluoroscopy.

The ViVIX-S Wireless is a digital X-ray flat panel detector which has 35.8cm x 43cm (FXRD-1417WA, FXRD-1417WB) imaging area and communicates via not only the wireless communication feature (IEEE 802.11a/b/g/n) but also wired communication feature (Giga-bit Ethernet communication method by connecting to a tether cable) optionally. The device intercepts 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, it is converted to a digital value, and an image will be displayed on the monitor. This device should be integrated with an operating PC and an X-Ray generator to utilize as digitalizing X-ray images and transfer for radiography diagnostic.

Here's an analysis of the provided text to extract information about acceptance criteria and the study proving the device meets them:

1. Table of Acceptance Criteria and Reported Device Performance

The provided text does not explicitly state quantitative acceptance criteria or a specific table for them in the traditional sense of performance metrics with thresholds. However, it implicitly uses a "substantial equivalence" framework. The performance data presented focuses on comparing the new device, ViVIX-S Wireless, to a predicate device, ViVIX-S.

• Quantum limited performance: No significant difference reported.
• Modulation Transfer Function (MTF): No significant difference reported.
• Effects of aliasing: No significant difference reported.
• Sensitivity linearity: No significant difference reported.
• Lag (Erasure thoroughness): No significant difference reported.
• Change in detection sensitivity: No significant difference reported.
• Dose requirement and reciprocity changes: No significant difference reported.
• Stability of device characteristics with time: No significant difference reported.
• Uniformity of device characteristic: No significant difference reported.
• Noise power spectrum (NPS): No significant difference reported.
• Spatial resolution: No significant difference reported.
• Minimum dose: No significant difference reported.
• Image Acquisition time: No significant difference reported.
• Black level: No significant difference reported. |
  | Clinical equivalence | - Comparison of Clinical Images: "No significant difference between the images of the ViVIX-S Wireless and those of the predicate device." |
  | Safety and EMC (Implicit) | - Electrical safety and EMC testing: "All test results were satisfactory" according to IEC 60601-1 and IEC 60601-1-2. |

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

• Sample Size for Test Set: 30 clinical images were used for the clinical study.
• Data Provenance: Not explicitly stated, but the company is based in South Korea. The study compares the new device to a predicate device, implying these images likely originated from a clinical setting where both devices could be used, or the predicate device was the source. This would likely be retrospective as it compares existing images or recent acquisitions for the purpose of demonstrating equivalence, rather than a planned prospective study where specific patient cohorts are followed.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts

The document does not specify the number of experts or their qualifications for establishing ground truth in either the non-clinical or clinical studies. The clinical study states a "concurrence study" was done, implying expert review, but details are absent.

4. Adjudication Method for the Test Set

The document does not explicitly state an adjudication method (e.g., 2+1, 3+1). The term "concurrence study" suggests some form of agreement or comparison, but the methodology for resolving discrepancies or establishing the "true" finding is not detailed.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and the Effect Size

The document describes a "concurrence study of 30 clinical images" to compare performance. While clinical images were used and a comparison was made, it does not explicitly describe an MRMC comparative effectiveness study with human readers improving with AI vs. without AI assistance. This device is an X-ray detector, not an AI diagnostic algorithm. The study's aim was device equivalence, not reader performance with AI. Therefore, no effect size for human reader improvement with AI is provided.

6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study Was Done

Yes, the "non-clinical study" can be considered a standalone performance evaluation of the device's technical specifications. It assessed intrinsic image quality metrics like DQE, MTF, NPS, spatial resolution, etc., independent of human interpretation for diagnostic tasks.

7. The Type of Ground Truth Used

• Non-clinical study: The "ground truth" for the non-clinical studies was based on objective, quantifiable physical and technical performance metrics of the X-ray detector itself (e.g., measured DQE, MTF, NPS, etc.) compared to established benchmarks or the predicate device's measured performance.
• Clinical study: For the clinical images, the "ground truth" or reference standard for comparison was the images from the predicate device. The study aimed to show "no significant difference" between images produced by the new device and the predicate device. This implies that the image quality and diagnostic information contained within the predicate device's images served as the de facto reference. The document does not mention pathology, outcomes data, or a separate expert consensus establishing specific diagnoses as ground truth for these 30 images, but rather the quality and equivalence of the images themselves.

8. The Sample Size for the Training Set

This information is not applicable and not provided. The ViVIX-S Wireless is a digital X-ray detector, a hardware device, not an AI algorithm that requires a training set of data.

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

This information is not applicable and not provided, as the device is a hardware component and not an AI algorithm requiring a training set.

Ask a specific question about this device

ViVIX-S with VXvue 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 all general purpose diagnostic procedures. Not to be used for mammography and/or for fluoroscopy.

ViVIX-S with VXvue is a digital X-ray flat panel detector which has 43x43cm (FXRD-1717SA, FXRD-1717SB) or 35.8x43cm (FXRD-1417SA, FXRD-1417SB) imaging area. The device intercepts 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, it is converted to digital value, and the images will be displayed on monitors. This device should be integrated with an operating PC and an X-Ray generator to utilize as digitalizing X-ray images and transfer for radiography diagnostic. Advanced digital imaging process allows considerably efficient diagnosis, all kind of information management, and sharing of image information on network.

Here's a breakdown of the acceptance criteria and study information based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

Note: The document states that the non-clinical and clinical studies "show that the ViVIX-S with VXvue is substantially equivalent to the predicate devices in the market." For the clinical study, it specifically notes "no significant differences between the images." This implies the acceptance criteria for these metrics were met by demonstrating equivalence or lack of significant difference compared to the predicate. The specific numerical thresholds for "acceptance criteria" are not provided in this document.

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

• Sample Size (Test Set): 30 clinical images.
• Data Provenance: Not explicitly stated regarding country of origin or whether it was retrospective or prospective. It is implied to be clinical data used for comparison.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications

• Number of Experts: Not specified.
• Qualifications of Experts: Not specified. The document only mentions a "concurrence study" comparing images, but does not detail the methodology for establishing ground truth or who performed the comparison.

4. Adjudication Method for the Test Set

• Not specified. The document simply states "A concurrence study of 30 clinical images was conducted to compare the performance... There were no significant differences." It doesn't describe the adjudication process if multiple reviewers were involved or how disagreements were resolved.

5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, and its effect size.

• No, a multi-reader multi-case (MRMC) comparative effectiveness study was not explicitly stated or described. The clinical study was a concurrence study comparing images from the new device to the predicate, not an assessment of human reader performance with or without AI assistance.

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

• While the device itself is a digital X-ray flat panel detector (hardware), and the "VXvue" part is advanced digital imaging process, the study described is a comparison of images produced by the device against a predicate, not an "algorithm-only" performance evaluation in the context of AI. The "advanced digital imaging process" implies software components, but its standalone diagnostic performance is not detailed separately from the hardware's image acquisition.

7. The type of ground truth used

• The implicit "ground truth" for the clinical study was the image quality and diagnostic information provided by the predicate device (K120020). The study aimed to show "no significant differences" between the images of the proposed device and those of the legally marketed predicate. It's a comparison to an established device, rather than an independent expert consensus, pathology, or outcomes data.

8. The sample size for the training set

• Not applicable/Not specified. This device is a digital X-ray detector, not an AI/ML algorithm that requires a training set in the conventional sense. The "advanced digital imaging process" is mentioned, but there is no indication of a machine learning component requiring a distinct training set. The study focuses on the performance of the imaging hardware and its processing in comparison to the predicate.

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

• Not applicable/Not specified, as no training set for an AI/ML algorithm is described in this submission.

Ask a specific question about this device