Search Results

VIVIX-M detectors are flat panel detectors used in mammographic applications to acquire digital images for screening and diagnosis.

VIVIX-M, a series of flat panel detectors models named; FXMD-2430S, with imaging areas of 24cm x 30cm, 18cm x 24cm, 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 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.

VXvue Mammo is a digital X-ray imaging software designed for mammography applications. It acquires, processes, and transmits digital images from VIVIX-M detectors (FXMD-1008S and FXMD-2430S) while ensuring compliance with DICOM standards for seamless integration with PACS and other medical systems.

The provided document is a 510(k) summary for the VIVIX-M Digital X-ray detectors (models FXMD-2430S and FXMD-1008S). It states that the device is substantially equivalent to a predicate device (RSM 2430C, K170930).

However, the document does not contain the detailed acceptance criteria and a comprehensive study that proves the device meets those acceptance criteria in the format requested. Specifically:

• No explicit table of acceptance criteria and reported device performance for clinical endpoints. The document provides a table comparing the subject device to the predicate device for technical parameters (MTF, DQE) and states "Substantially Equivalent" but does not define numerical acceptance thresholds for these or for clinical performance.
• No details on sample size for the test set or data provenance for a clinical study. It mentions a "clinical image evaluation" was conducted but provides no specifics on the number of cases, patient demographics, or whether the data was retrospective or prospective, or its country of origin.
• No information on the number or qualifications of experts used for ground truth.
• No adjudication method specified for the test set.
• No Multi-Reader Multi-Case (MRMC) comparative effectiveness study details. There is no mention of human readers improving with AI assistance because this is a detector, not an AI-enabled device for interpretation.
• No "standalone (i.e. algorithm only without human-in-the-loop performance)" was done for clinical endpoints. This is a hardware device; its performance is assessed through image quality metrics (MTF, DQE, NPS, etc.) and clinical image evaluation for diagnostic capability, not an algorithm's standalone performance.
• The type of ground truth for clinical evaluation is not specified beyond "equivalent diagnostic capability."
• No training set size or ground truth establishment method for a training set. This device is a digital X-ray detector, not an AI/ML algorithm that is trained on a dataset. The performance evaluation is based on non-clinical technical measurements and a clinical image evaluation for diagnostic capability comparison to a predicate, not on a trained AI model.

The document primarily focuses on demonstrating substantial equivalence through:

• Technical performance metrics: MTF, DQE, NPS, Dynamic Range, Image Erasure, AEC Performance, and Phantom Testing. Acceptance for these is generally implied by being "equivalent to the predicate" or exceeding "specified thresholds."
• Clinical image evaluation: A general statement is made that a clinical image evaluation was conducted, confirming "equivalent diagnostic capability to the predicate device."

Therefore, based only on the provided text, I cannot complete the table or provide the requested details about a study proving clinical acceptance criteria. The information is limited to substantiating the device's equivalence to a predicate, not demonstrating it meets specific, predefined clinical acceptance criteria through a detailed study design as might be seen for a novel AI diagnostic device.

If this were an AI device, the "acceptance criteria" would be specific performance metrics (e.g., sensitivity, specificity, AUC) with predefined thresholds derived from clinical needs. For this detector, "acceptance" is framed in terms of substantial equivalence to a legally marketed predicate device.

What is present in the document relevant to performance and equivalence:

The document outlines a non-clinical testing summary and mentions a clinical image evaluation to demonstrate substantial equivalence to a predicate device, rather than meeting specific, numerical acceptance criteria for clinical performance that would typically be associated with an AI diagnostic study.

Here's what can be extracted based on the provided text, and where information is missing:

Non-clinical Performance Comparisons (as presented in the 510(k) summary, specifically for FXMD-2430S model):
| Parameter | Predicate Device (RSM 2430C) | Subject Device (VIVIX-M FXMD-2430S) | Equivalence | Acceptanc

| MTF | 70% at 2lp/mm, 30% at 5lp/mm | 54.9% at 3lp/mm, 33.1% at 5lp/mm | Substantially Equivalent | Implied: Demonstrated spatial resolution equivalent to predicate, exceeding specified thresholds. | DQE | 43% at 2lp/mm, 30% at 5lp/mm | 59.0% at 3lp/mm, 42.5% at 5lp/mm | Substantially Equivalent | Implied: Comparable to predicate, confirming equivalent imaging performance. |
Other Non-Clinical Tests (Results are qualitative in the summary):

• Noise Power Spectrum (NPS): "confirmed consistent noise performance across tested exposure levels."
• Dynamic Range Testing: "exhibited a wide dynamic range suitable for mammographic imaging."
• Image Erasure and Fading Test (Ghosting): "No significant ghosting or residual artifacts were observed."
• Automatic Exposure Control (AEC) Performance: "met manufacturer-defined limits, ensuring consistent image quality."
• Phantom Testing (ACR, TE, CDMAM Phantoms): "All tests demonstrated diagnostic image quality equivalent to or better than the predicate device."

Clinical Performance:

• Overall Diagnostic Capability: "the study confirmed that the new x-ray detectors VIVIX-M provide images of equivalent diagnostic capability to the predicate device." |
  | 2. Sample Size (Test Set) & Data Provenance | Sample Size: Not specified. The document only states "A clinical image evaluation... was conducted."
  Data Provenance: Not specified (e.g., country of origin, retrospective/prospective). |
  | 3. Number of Experts & Qualifications for Ground Truth | Not specified. |
  | 4. Adjudication Method for Test Set | Not specified. |
  | 5. MRMC Comparative Effectiveness Study Effect Size | Not applicable. This is a medical imaging detector, not an AI-assisted diagnostic tool for human readers. There is no AI component that assists human readers. The clinical evaluation verifies equivalent diagnostic capability of the images produced by the detector. |
  | 6. Standalone (Algorithm Only) Performance | Not applicable in the context of an AI algorithm. This is a hardware device (X-ray detector). Its "standalone" performance is measured by its physical and image quality characteristics (MTF, DQE, NPS) and its ability to produce images comparable to a predicate for diagnostic purposes. These non-clinical tests were conducted. |
  | 7. Type of Ground Truth Used (for Clinical Evaluation) | The general statement is "equivalent diagnostic capability" to the predicate. The method for establishing this "diagnostic capability" as ground truth (e.g., expert consensus on clinical cases, pathological confirmation, long-term follow-up) is not explicitly detailed. It's likely based on radiologists' interpretation of the images produced by the device compared to the predicate in clinical scenarios. |
  | 8. Sample Size for Training Set | Not applicable. This device is a digital X-ray detector, not an AI/ML algorithm that requires a training set. |
  | 9. How Ground Truth for Training Set Was Established | Not applicable. (See #8) |

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.

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 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

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

The QXLink is a device that provides one or more capabilities relating to the acceptance, transfer, display, storage, and digital processing of medical images. The software components may provide functions for performing related to image manipulation, enhancement, compression or quantification. And images may be acquired from imaging devices such as CR, CT, MR and other devices. This device is not intended for mammographic operations.

The QXLink is a device that provides one or more capabilities relating to the acceptance, transfer, display, storage, and digital processing of medical images. The software components may provide functions for performing related to image manipulation, enhancement, compression or quantification.

I am sorry, but the provided text does not contain any information about acceptance criteria, device performance, study details, sample sizes, ground truth establishment, expert qualifications, or adjudication methods for a medical device study.

The document is an FDA 510(k) clearance letter for a device named "QXLink". It states that the device is substantially equivalent to a legally marketed predicate device. The letter primarily addresses regulatory compliance and provides indications for use for the QXLink device, which is a Picture Archiving and Communications System (PACS).

Therefore, I cannot fulfill your request to describe the acceptance criteria and the study proving the device meets those criteria based on the given information.

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