Search Results

The PROMO is intended for use in obtaining human anatomical images of patients who cannot be moved to the radiology department for medical diagnosis.

The PROMO is based on predicate device TOPAZ and the x-ray detectors are the same as the predicate system. The PROMO is moved smoothly with manual by user. The core part of x-ray source adopts high quality tube assembly, x-ray collimator, HV cable assembly and High Voltage x-ray Generator with excellent performance, lifetime and stability. Digital flat panel detector with CsI screen provides excellent spatial resolution, MTF, DQE and stability based on fine pixel pitch. The core part of x-ray source adopts high quality tube assembly, x-ray collimator, HV cable assembly and High Voltage x-ray Generator which have worldwide reputation on excellent performance, lifetime and stability. Touch screen LCD based x-ray control console provides user-friendly interface and easy technique selection. Collimator supports high accuracy for selected x-ray field size over any SID. The PROMO include imaging software that is the RADMAX. The RADMAX software can perform processing the radiological image acquired from solid state x-ray imaging device. The RADMAX software is based on predicate device TOPAZ. The CTR function is a manual quantitative imaging feature that allows users to measure the cardiothoracic ratio by manually selecting points using a mouse. The software function has been verified and validated as safe and effective.

The provided FDA 510(k) clearance letter and summary for the PROMO Mobile X-ray System do not contain information about specific acceptance criteria, reported device performance metrics in relation to those criteria, or details of a clinical study that proves the device meets acceptance criteria.

The document primarily focuses on demonstrating substantial equivalence to a predicate device (TOPAZ) through non-clinical performance testing and compliance with various recognized standards and guidance documents. It confirms that the device's image performance was evaluated through bench testing.

Therefore, for the specific questions asked, most of the information is not available in the provided text.

Here's an breakdown of what can and cannot be answered based on the provided document:

Information that CANNOT be provided from the document:

• 1. A table of acceptance criteria and the reported device performance: The document mentions "bench testing was conducted to evaluate the image performance of the detector" and that "PROMO meets or exceeds TOPAZ in key image quality metrics such as uniformity, SNR, linearity, spatial resolution, and low contrast resolution." However, it does not provide specific numerical acceptance criteria for these metrics nor the quantitative reported performance of the device against them.
• 2. Sample size used for the test set and the data provenance: Since no clinical study or specific test set with patient data is described, this information is not available. The "test set" mentioned refers to non-clinical bench testing.
• 3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable as no clinical study involving expert interpretation is detailed.
• 4. Adjudication method (e.g. 2+1, 3+1, none) for the test set: Not applicable as no clinical study involving expert interpretation is 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: Not applicable. The PROMO is a mobile X-ray system, not an AI diagnostic tool, and the document does not describe any MRMC studies. The "CTR function" mentioned is a manual measurement tool, not an AI feature for diagnostic assistance.
• 6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not applicable, as this device itself is the imaging hardware, not an AI algorithm.
• 7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.): For the non-clinical bench testing mentioned, the "ground truth" would be objective physical measurements of image quality parameters (e.g., standard phantoms for linearity, resolution, etc.). The document does not describe clinical ground truths.
• 8. The sample size for the training set: The document does not describe any machine learning or AI models with a "training set."
• 9. How the ground truth for the training set was established: Not applicable, as no training set is mentioned.

Information that CAN be inferred or directly stated from the document (regarding non-clinical testing and general acceptance):

The document implicitly defines "acceptance criteria" by stating compliance with recognized national and international standards for medical electrical equipment, radiation protection, usability, software life cycle, risk management, and cybersecurity. The "study" that proves the device meets these (non-clinical) acceptance criteria is the bench testing and verification/validation processes conducted according to these standards.

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

Summary regarding the device performance study:

The PROMO Mobile X-ray System's substantial equivalence to its predicate (TOPAZ) and its safety and effectiveness are established through non-clinical performance testing (bench testing). This testing focused on comparing technical specifications and image quality metrics against the predicate and ensuring compliance with a comprehensive set of international and FDA-recognized standards and guidance documents. The document explicitly states: "Bench testing was conducted to evaluate the image performance of the detector. The results showed that PROMO meets or exceeds TOPAZ in key image quality metrics such as uniformity, SNR, linearity, spatial resolution, and low contrast resolution. Therefore, the substantial equivalence in image quality performance is supported by objective bench testing data."

Type of ground truth used (for bench testing):

For the non-clinical bench testing, the ground truth would be established by objective physical measurements using standardized phantoms and test objects to assess imaging characteristics (e.g., bar patterns for spatial resolution, step wedges for linearity, uniform fields for uniformity).

Ask a specific question about this device

The GXR-Series Diagnostic X-ray System is intended for use in obtaining human anatomical images for medical diagnostic by using X-rays.

The GXR Series Diagnostic X-ray System consists of a combination of an x-ray generator, and associated equipment such as tube stand, patient table, and, digital imaging system.

Here's an analysis of the provided text regarding acceptance criteria and supporting studies for the GXR-series diagnostic x-ray system:

It's important to note that the provided document is a 510(k) Summary, which is a regulatory filing for a medical device seeking clearance from the FDA based on substantial equivalence to a predicate device. It typically focuses on demonstrating that the new device is as safe and effective as a legally marketed device, rather than proving absolute performance against specific clinical acceptance criteria in a comprehensive clinical study. Therefore, the details provided often lean towards non-clinical testing and comparison with established standards.

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly present a table of "acceptance criteria" for clinical performance. Instead, it relies on demonstrating adherence to recognized safety and performance standards, and comparison of technical characteristics to a predicate device. The "performance" is implicitly deemed acceptable if the device meets these standards and is substantially equivalent to the predicate.

Here's a generalized interpretation based on the document's content, focusing on what would typically be implied performance requirements for an X-ray system:

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

• Test Set Sample Size: The document does not specify a "test set" sample size in terms of clinical images or patient cases for performance evaluation against specific acceptance criteria. The testing discussed is primarily non-clinical, related to hardware and software verification and validation.
• Data Provenance: The document implies that the testing data is generated from laboratory testing and verification during the development and modification of the device. There is no mention of clinical data or patient data being used for the performance evaluation in this 510(k) summary. Given the context of a 510(k), particularly for an X-ray system, the primary focus is on engineering and performance testing against standards, rather than large-scale clinical studies. The data is thus likely prospective in terms of being generated specifically for this submission but is non-clinical in nature.

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

This information is not provided in the document. As the evaluation is non-clinical, there is no mention of "ground truth established by experts" in the context of diagnostic performance evaluation. The "ground truth" for non-clinical testing would typically be the expected technical output or adherence to a standard, rather than expert interpretation of images.

4. Adjudication Method for the Test Set

This information is not provided as the testing described and implied is non-clinical and does not involve expert adjudication of diagnostic findings.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done, and effect size

No, a multi-reader multi-case (MRMC) comparative effectiveness study was not explicitly mentioned or performed as part of this 510(k) submission. The document focuses on demonstrating substantial equivalence through technical comparisons and compliance with standards, not on proving improved reader performance with or without AI assistance.

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

This is not applicable in the sense of an AI algorithm's standalone performance. The device is a diagnostic X-ray system, which is inherently designed to be used with a human interpreter (a medical professional). While it has image processing software ("RADMAX"), this software enhances images for human diagnosis, not to provide an automated diagnosis itself.

7. The Type of Ground Truth Used

The "ground truth" for the non-clinical testing is adherence to technical specifications and international standards. For example, for radiation output, the ground truth is that the device delivers the specified kVp and mA, and for electrical safety, that it meets the requirements of IEC 60601-1. For image quality, it refers to intrinsic properties like spatial resolution, MTF, and DQE, which are measured objectively, not subjective expert consensus on diagnostic findings.

8. The Sample Size for the Training Set

This information is not applicable and therefore not provided. The device is an X-ray imaging system, not an AI/ML diagnostic algorithm that requires a training set of medical images in the conventional sense. The "training" for the device would involve calibration and configuration during manufacturing and installation to ensure it meets its technical specifications. The "RADMAX" software has image processing modules, but the document does not suggest these are deep learning models trained on vast datasets.

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

This information is not applicable for the same reasons as #8. If any parameters for the image processing modules are "learned" or optimized, the document does not elaborate on this process or the ground truth used for such optimization.

Ask a specific question about this device

The 'TOPAZ Mobile X-ray System' is intended for use in obtaining human anatomical images of patients who cannot be moved to the radiology department for medical diagnosis.

"TOPAZ" system is a system providing state-of-the-art image quality, user interface. "TOPAZ" system may be moved quietly and smoothly with motor drive mechanism "TOPAZ" system has a basic type column, and a collapsible type column option with a trendy design that allows driving without disturbing the front view. The core part of x-ray source adopts high quality tube assembly, motorized x-ray collimator. HV cable assembly and High Voltage X-Ray Generator. Touch screen LCD based x-ray control console provides user-friendly interface and easy technique selection. Collimator supports high accuracy for selected x-ray field size over any SID. Direct radiography via flat panel detector improves-exam speed and comfort with efficiency. Digital flat panel detector with Csl screen provides spatial resolution, MTF, DQE and stability based on fine pixel pitch. Selection of an anatomical study on the Digital Imaging Software automatically sets up the x-ray generator's preprogrammed exposure technique. The types of "TOPAZ" system are divided into TOPAZ-32D, and TOPAZ-40D according to maximum power and mA. The higher the maximum output, the wider the mA range to choose from, giving the user more technical options to choose from. The "TOPAZ Mobile X-ray System" consists of a tube assembly. x-ray collimator. High Voltage X-Rav Generator, detector and mechanical parts for mobility.

The provided text is a 510(k) Summary for the TOPAZ Mobile X-ray System, which focuses on demonstrating substantial equivalence to a predicate device rather than presenting a performance study with acceptance criteria in the format typically used for AI/CADe devices. This document describes the device, its intended use, technological characteristics, and differences from the predicate, along with non-clinical testing for safety and EMC standards.

Therefore, the specific information about "acceptance criteria and the study that proves the device meets the acceptance criteria" as requested for AI/CADe devices (including details like sample size for test sets, data provenance, number of experts for ground truth, adjudication methods, MRMC studies, standalone performance, type of ground truth, and training set details) is not present in this 510(k) Summary.

This document primarily asserts that the "TOPAZ Mobile X-ray System" is substantially equivalent to the predicate device "TOPAZ Mobile DR System (K201124)" based on:

• Identical intended use.
• Similar technological characteristics, with modifications thoroughly tested for safety and effectiveness against international standards.
• Nonclinical testing results provided in the 510(k) demonstrating that predetermined acceptance criteria were met for safety (electrical safety, EMC, radiation protection) and software validation.

The "study that proves the device meets the acceptance criteria" in this context refers to the nonclinical testing against various recognized international and FDA standards, not a clinical performance study with human readers or pathology, as would be expected for AI/CADe systems.

Here's a summary of the available information regarding acceptance criteria and testing, tailored to what is provided in the document:

1. Table of Acceptance Criteria and Reported Device Performance:

The document does not explicitly present a table of acceptance criteria and reported device performance in the typical format for clinical accuracy for AI/CADe. Instead, it states that the device was assessed, tested, and passed predetermined testing criteria during validation testing, aligning with the risk analysis. It also confirms that the device meets "all the requirements listed in the Standards" (see the Standards table below). The "device performance" reported is its conformance to these standards and its substantial equivalence to the predicate.

Nonclinical Standards Met (acting as acceptance criteria for safety and effectiveness):

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

• Not Applicable/Not Provided. The document describes non-clinical engineering and software validation testing against standards, not a clinical study involving a "test set" of patient data for diagnostic performance. The focus is on the device's hardware, software (RADMAX), and new flat panel detectors meeting safety and electrical standards.

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):

• Not Applicable/Not Provided. Ground truth establishment by experts is relevant for clinical performance studies, which this document does not describe.

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

• Not Applicable/Not Provided. This is relevant for clinical performance studies.

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:

• No. This document describes a 510(k) for an X-ray system, not an AI/CADe system. No MRMC study was performed or is mentioned.

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

• Not Applicable/No. The device itself is an X-ray system, not an algorithm, and its performance is assessed in terms of meeting engineering and regulatory standards, not standalone diagnostic performance. The imaging software (RADMAX) is mentioned as identical to the predicate and has a "Basic Documentation Level" of concern, implying human interpretation of images.

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

• Not Applicable/Not Provided. For the non-clinical testing described, "ground truth" would relate to the correct functioning of the hardware and software according to specifications and standards, not clinical diagnostic accuracy.

8. The sample size for the training set:

• Not Applicable/Not Provided. This is relevant for AI/ML models. While the device contains software, it is not described as an AI/ML diagnostic algorithm needing a training set. The software changes are primarily GUI and image processing module updates, verified for impact on safety and effectiveness (not AI training).

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

• Not Applicable/Not Provided. As above, this is not an AI/ML submission requiring a training set.

In summary, the provided 510(k) document is for a mobile X-ray system and demonstrates substantial equivalence through nonclinical testing against recognized performance, safety, and EMC standards, rather than a clinical performance study with acceptance criteria related to diagnostic accuracy, which would be typical for AI-powered diagnostic devices.

Ask a specific question about this device

The "GXR-ES/ECS" System is intended for use in generating radiographic images of human anatomy. The Diagnostic Xray System consisting of a high voltage (HV) generator, a tube support unit, an X-ray beam limiting device, patient table, wall Bucky stand, and a tube, operates on a high-frequency inverter method, and is primarily used in a hospital for diagnosis of diseases in skeletal, respiratory and urinary systems. Such as the skull, spinal column, chest, abdomen, extremities, and other body parts. Applications can be performed with the patient sitting, standing, or lying in the prone or supine position

The "GXR-ES/ECS" System is intended for use in generating radiographic images of human anatomy. The Diagnostic Xray System consisting of a high voltage (HV) generator, a tube support unit, an X-ray beam limiting device, patient table, wall Bucky stand, and a tube, operates on a high-frequency inverter method, and is primarily used in a hospital for diagnosis of diseases in skeletal, respiratory and urinary systems. Such as the skull, spinal column, chest, abdomen, extremities, and other body parts. Applications can be performed with the patient sitting, standing, or lying in the prone or supine position. The system offers stable operation and good performance, delivering state-of-the-art image quality with good quality images. The flat-panel detectors are not part of the subject device. The operator control console is designed in two types: one with a large graphic LCD panel display and soft membrane switch, and the other with a large graphic LCD panel display and intuitive GUI configuration with Touch function. The high frequency X-ray generator features excellent accuracy, reproducibility and long-term stability with UPS functionality. APR (Anatomical Programming) and optional AEC (Automatic Exposure Control) features provide controlled exposure factors. Automatic Calibration function minimizes calibration time. The control console offers graphic waveform and data of x-ray exposure. Remote Diagnosis Software can make reports and transfer them via internet.

The provided document, K232178, is a 510(k) summary for the DRGEM GXR-ES/ECS Diagnostic X-Ray System. It does not describe a study involving an AI/Machine Learning algorithm for diagnostic purposes, nor does it detail acceptance criteria for such an algorithm. Instead, it focuses on demonstrating substantial equivalence of a new X-ray hardware system to a predicate device based on non-clinical performance and safety standards.

Therefore, I cannot provide the requested information regarding acceptance criteria and a study proving an AI/Machine Learning device meets them, as this information is not present in the provided text. The document pertains to the clearance of a traditional X-ray imaging system.

The closest relevant information available in the document, which might be mistaken for "acceptance criteria" in the context of an AI study, are the non-clinical testing standards and their successful completion for the X-ray hardware system. However, these are general electrical, safety, and performance standards for an X-ray machine, not diagnostic accuracy metrics for an AI algorithm.

Here's a breakdown of why the requested information cannot be extracted from this document:

• No AI/Machine Learning Component: The device described is a "Diagnostic X-Ray System" which is a hardware unit (generator, tube support, beam limiter, table, Bucky stand, tube). It explicitly states that "The flat-panel detectors (a necessary component of a fully-functional diagnostic X-ray system) are not part of the subject device." and that the software is for "system control such as the collimation size, filter selection, Control of Generator." and is "identical to the predicate device". This indicates traditional X-ray equipment, not an AI-powered diagnostic tool.
• No Diagnostic Performance Study: The document describes non-clinical "Validation Test Plan" which "was designed to evaluate input functions, output functions, and actions performed by the subject device." It refers to meeting general safety and EMC standards (IEC 60601 series, ISO 14971, etc.) for an X-ray machine. There is no mention of a diagnostic performance study, reader studies, or ground truth establishment for diagnostic accuracy.
• "Acceptance Criteria" for Hardware: The "acceptance criteria" mentioned refer to successfully passing the listed safety, electrical, and performance standards for the X-ray system, not diagnostic accuracy of an algorithm.

In summary, the provided document is a 510(k) summary for an X-ray imaging device hardware, not an AI/Machine Learning diagnostic device. Therefore, the information requested about acceptance criteria and study data for an AI algorithm is not present.

Ask a specific question about this device

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

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

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

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

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

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

Ask a specific question about this device

DIAMOND-5A/6A/8A, is a stationary digital diagnostic x-ray system that is indicated for use in generating radiographic images of human anatomy. This device is not intended for mammography, bone density, fluoroscopy and angiography applications.

DIAMOND-5A/6A/8A, system is a digital radiographic system. There are 3 power output configurations which are reflected in the model designation "5A/6A/8A". The models have 3 different output power ratings: 52kW, 68kW, 82kW. DIAMOND 5A/6A/8A, incorporates digital flat panel detector technology, along with an automatic motorized U-arm radiographic stand and mobile patient table that can fit into smaller rooms without the need of ceiling support structures for X-Ray tube suspensions. The subject device comes in 2 hardware configurations; a Radiographic Stand configuration for a wired detector and a Radiographic Stand for removable detectors. The main components of the subject device are the same as the predicate. Components of the x-ray source are the tube assembly, motorized x-ray collimator, HV cable assembly and high frequency x-ray generator. A touch screen LCD based x-ray control console provides a user interface and technique selection. The automatic collimator supports high accuracy for selected x-ray field size over SID. Selection of an anatomical study on the imaging software automatically sets up the x-ray generator's pre-programmed exposure technique setting, motorized radiographic stand positioning, x-ray collimation and post image processing for selected study. Also, removable high-resolution grids which have 100 and 180cm (40 and 72 inch) focal distance. The integrated touch screen console located on the tube side, operator can easily control the radiographic techniques and stand positioning. Furthermore, the operator can verify the digital x-ray image on this screen. The GUI, automatically rotates corresponds to rotation angle of U-arm.

The provided text is a 510(k) summary for the DRGEM Corporation's DIAMOND-5A/6A/8A stationary digital diagnostic x-ray system. This summary focuses on demonstrating substantial equivalence to a predicate device rather than presenting a study of the device's diagnostic performance for measuring accuracy against a ground truth.

Therefore, much of the requested information (e.g., acceptance criteria for diagnostic capability, sample sizes for test/training sets, expert qualifications, MRMC studies, standalone performance, and ground truth types for diagnostic accuracy) is not available in this document. The document primarily addresses the safety and performance of the hardware components and software in comparison to a previously cleared device.

Here's the information that can be extracted from the provided text:

Acceptance Criteria and Reported Device Performance (as pertains to safety and technical function):

Detailed Study Information (as requested, with notes on unavailability):

1. Sample size used for the test set and the data provenance: Not applicable/available. The document describes non-clinical testing for safety and functionality, not a clinical study on diagnostic accuracy.

2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not applicable/available. No clinical test set requiring expert ground truth for diagnostic accuracy is described.

3. Adjudication method for the test set: Not applicable/available.

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: Not applicable/available. This device is a digital X-ray system, not an AI-powered diagnostic aide for human readers.

5. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: Not applicable/available. This refers to the performance of the X-ray system itself. The document states "The complete system has been assessed and tested at the factory and by Standards testing facilities. DIAMOND-5A/6A/8A, has passed all predetermined testing criteria." This indicates standalone testing for the system's technical function and safety.

6. The type of ground truth used (expert consensus, pathology, outcomes data, etc.): Not applicable/available for diagnostic accuracy. For safety and performance testing, the "ground truth" would be adherence to the cited international standards and predetermined testing criteria.

7. The sample size for the training set: Not applicable/available. The device is not an AI algorithm that requires a training set in the conventional sense for diagnostic tasks. Its software (RADMAX) is for image management and system control.

8. How the ground truth for the training set was established: Not applicable/available.

Summary of the Study (as described in the document):

The "study" described in the 510(k) summary is a non-clinical performance and safety assessment comparing the DIAMOND-5A/6A/8A system to its predicate device (also DIAMOND-5A/6A/8A, K192453). The primary purpose was to demonstrate that adding new digital flat panel detectors (Fujifilm, Varex, i-Ray models) and an updated version of the RADMAX image management software (version 1.01) did not negatively impact safety or efficacy and did not raise new safety risks.

The testing involved assessing the complete system's adherence to various international standards for medical electrical equipment, radiation protection, usability, software lifecycle processes, and risk management. The conclusion was that the device met all predetermined testing criteria and demonstrated a safe and effective profile similar to the predicate device. No clinical (diagnostic accuracy) studies are reported in this summary.

Ask a specific question about this device

The TOPAZ Mobile DR System, is a mobile X-ray imaging system, for the purpose of acquiring X-ray images of the desired parts of a patient's anatomy.

This device is not intended for mammography, bone density, fluoroscopy and angiography applications.

The TOPAZ Mobile DR System, (TOPAZ), is a mobile x-ray system and is a modification of the predicate device. There are 2 models for TOPAZ: TOPAZ-32D (32KW) and TOPAZ-40D (40KW). TOPAZ, may be moved quietly and smoothly with a motor drive mechanism.

The core part of x-ray source is a tube assembly, motorized x-ray collimator, HV cable assembly and high frequency x-ray generator. A touch screen LCD based x-ray control console provides a user-friendly interface and technique selection. The Collimator supports high accuracy for selected x-ray field size over any SID. Selection of an anatomical study on the imaging software automatically sets up the x-ray generator's pre-programmed exposure technique.

The X-ray passing through a patient's body is sent to the detector and then converted into electrical signals. These signals go through the process of amplification and digital data conversion in the signal process on the workstation and saved in a DICOM file for review on the device or on a Picture Archiving & Communication System (PACS) workstation.

The provided text is a 510(k) summary for the DRGEM TOPAZ Mobile DR System. It discusses the device, its intended use, and its substantial equivalence to a predicate device. However, it does not contain any information about a study that proves the device meets specific acceptance criteria related to a human-in-the-loop or standalone AI performance study.

The "PERFORMANCE DATA" section explicitly states that "Nonclinical testing results are provided in the 510(k). Validation testing indicated that as required by the risk analysis, designated individuals performed all verification and validation activities and that the results demonstrated that the predetermined acceptance criteria were met." This refers to engineering and safety testing against recognized standards (e.g., IEC 60601-2-54, ANSI AAMI ES60601-1, IEC 62304 for software), not clinical performance studies involving AI or human readers.

The key information missing to answer your request is data from a clinical performance study (e.g., diagnostic accuracy, reader study results). The device described is a mobile X-ray imaging system, which captures images. There is no mention of any integrated AI component that would require an AI-specific performance study with acceptance criteria for diagnostic performance.

Therefore, I cannot populate the table or answer most of your questions as the necessary information is not present in the provided document.

Here's what can be inferred or stated based on the provided text, and what cannot:

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

Cannot populate. The document focuses on regulatory compliance and engineering standards for the X-ray system itself, not diagnostic performance metrics (e.g., sensitivity, specificity, AUC) for an AI component. The "acceptance criteria" mentioned are for non-clinical engineering and safety tests, not clinical performance.

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

Not applicable/Not mentioned for clinical performance. The "test set" referenced in the document pertains to engineering validation and verification tests of the X-ray system's functions, not a clinical data set for evaluating diagnostic performance of an AI.

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)

Not applicable/Not mentioned. Ground truth establishment by experts (e.g., radiologists) is relevant for diagnostic performance studies. This document reports on non-clinical engineering tests.

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

Not applicable/Not mentioned. Adjudication methods are used in reader studies or for ground truth establishment in clinical performance. This document does not describe such studies.

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

No. The document does not describe any MRMC study.

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

No. The document does not describe any standalone algorithm performance testing related to diagnostic accuracy.

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

Not applicable/Not mentioned for clinical performance. For engineering tests, the "ground truth" would be the successful operation of the device according to its specifications and regulatory standards.

8. The sample size for the training set

Not applicable/Not mentioned. This information would be relevant for an AI device. The document describes an X-ray imaging system, not an AI.

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

Not applicable/Not mentioned. This information would be relevant for an AI device. The document describes an X-ray imaging system, not an AI.

Summary of the Device and its Testing as per the document:

The TOPAZ Mobile DR System is a mobile X-ray imaging system. The 510(k) submission primarily focuses on demonstrating its substantial equivalence to an existing predicate device (K183292, also a TOPAZ Mobile DR System from DRGEM). The main difference for this new 510(k) (K201124) is the addition of five previously cleared digital X-ray detectors to the TOPAZ system.

The "Performance Data" section details that the system underwent non-clinical testing against various recognized international and national standards (e.g., IEC 60601 series for medical electrical equipment safety, radiation protection, usability; IEC 62304 for medical device software; DICOM standards, JPEG standards, etc.). The acceptance criteria for these tests were met, demonstrating the device's safety and effectiveness as an X-ray imaging system, and its performance as well as the predicate device. This refers to the engineering and regulatory compliance of the hardware and integrated software for image acquisition and handling, not the diagnostic interpretation or AI assistance.

Ask a specific question about this device

DIAMOND-5A/6A/8A, is a stationary digital diagnostic x-ray system that is indicated for use in generating radiographic images of human anatomy. This device is not intended for mammographic applications.

DIAMOND-5A/6A/8A, system is a digital radiographic system. There are 3 power output configurations which are reflected in the model designation "5A/6A/8A". The models have 3 different output power ratings: 52kW, 68kW, 82kW. DIAMOND 5A/6A/8A. incorporates digital flat panel detector technology, along with an automatic motorized U-arm radiographic stand and mobile patient table that can fit into smaller rooms without the need of ceiling support structures for X-Ray tube suspensions. The digital flat panel digital detectors that are used in DIAMOND-5A/6A/8A, are the VAREX Model 4343Rv3 (Ethernet interface) and 4336Wv4 (wireless). The main components of the x-ray source are the tube assembly, motorized x-ray collimator, HV cable assembly and high frequency x-ray generator. A touch screen LCD based x-ray control console provides a user interface and technique selection. The automatic collimator supports high accuracy for selected x-ray field size over SID. Selection of an anatomical study on the imaging software automatically sets up the x-ray generator's pre-programmed exposure technique setting, motorized radiographic stand positioning, x-ray collimation and post image processing for selected study. Also, removable high-resolution grids which have 100 and 180cm (40 and 72 inch) focal distance supplies excellent image quality per each SID. The integrated touch screen console located in the tube side, operator can easily control the radiographic techniques and stand positioning. Furthermore, the operator can verify the digital x-ray image on this screen. The GUI, automatically rotates corresponds to rotation angle of U-arm. The Radiographic stand has four motorized joints, and automatic positioning can be accomplished by preprogrammed data which can be easily reprogrammed by operator. Total of seven safety sensors are located over U-arm, detector and tube side to protect. against collision with patient or obstacles to control the speed or stop the positioning. Also, a mobile patient table with heavy patient load is provided for radiographic study which needs table. A remote-control is provided for remote motorized control of the stand, and the movement will stop as soon as the key is no longer pressed. The predicate device contains image handling software that was designed at the same time the product was originally developed. The subject device will replace the original image handling module with the RADMAX Digital Image Software cleared under K182537. This will improve the software changeability when a change is needed and also will improve cyber security since there was no documented cyber security plan at the time of the original product development. RADMAX can also perform system control such as the collimation size, filter selection, etc. for the GXR series x-ray generators.

The provided document, a 510(k) summary for the DRGEM Corporation's DIAMOND-5A/6A/8A digital X-ray system, describes the device, its indications for use, and a comparison to predicate devices, along with performance data. However, it does not include detailed acceptance criteria or a study design for evaluating the diagnostic performance of the device, particularly for an AI component.

The document primarily focuses on demonstrating substantial equivalence to a predicate device, specifically regarding:

• Physical and functional characteristics (e.g., power output, detectors, image management software features).
• Compliance with various international safety and electromagnetic compatibility (EMC) standards for medical electrical equipment and software lifecycle processes.
• Risk management and usability engineering.

Therefore, I cannot extract specific information about acceptance criteria for diagnostic performance (e.g., sensitivity, specificity, or reader improvement with AI assistance) or a detailed diagnostic performance study (e.g., MRMC study, expert ground truth establishment) because that information is not present in the provided text.

The Performance Data section explicitly states: "The DIAMOND-5A/6A/8A system, has been assessed and tested and has passed predetermined testing criteria. The Validation Test Plan was designed to evaluate input functions, output functions, and actions performed by the subject device and followed the process documented in the System Validation Test Plan. Nonclinical testing results are provided in the 510(k). Validation testing indicated that as required by the risk analysis, designated individuals performed all verification and validation activities and that the results demonstrated that the predetermined acceptance criteria were met."

This phrasing suggests that the "testing criteria" and "acceptance criteria" referred to are for ensuring the functionality, safety, and compliance with standards of the X-ray system itself, and not necessarily for demonstrating specific diagnostic performance metrics (like the accuracy of an AI algorithm in detecting pathologies). The core of the submission seems to be the replacement of an older image handling module with "RADMAX Digital Image Software," and the impact of this change on the system's safety and efficacy, not the introduction of AI for diagnostic assistance.

Based on the provided text, the device is a stationary digital diagnostic x-ray system, and the "AI component" referred to in your prompt (if it were present) would likely be part of the "RADMAX Digital Image Software" if it contained any AI-driven diagnostic features beyond basic image processing. However, the document does not elaborate on such diagnostic AI features or their performance evaluation.

Hypothetical Answer (if the document had contained the requested information for an AI-powered diagnostic device):

(Please note: The following is a hypothetical answer structured as if the document provided details for an AI-powered diagnostic device, which it does not. I've used placeholder values where specific information about diagnostic performance would typically be found in such a submission.)

Acceptance Criteria and Study for AI-Powered Diagnostic Device (Hypothetical)

This document describes the validation of a stationary digital diagnostic X-ray system. While the submission primarily focuses on functional safety and feature equivalence, if it were an AI-powered diagnostic device, the following hypothetical information would be expected for a performance study.

1. Table of Acceptance Criteria and Reported Device Performance (Hypothetical)

4. Adjudication Method for Test Set (Hypothetical)

• Method: [e.g., 2+1 Adjudication: Each case was initially reviewed independently by two experts. In cases of disagreement, a third, senior expert reviewed the case to establish the final ground truth. Alternatively, 3-reader consensus.]

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

• Was an MRMC study done? [e.g., Yes]
• Effect Size of Human Reader Improvement: [e.g., The MRMC study demonstrated that human readers, when assisted by the AI algorithm, showed an average XX% improvement in sensitivity for detecting condition X (e.g., from 75% to 85%), while maintaining specificity. The study used methods such as observer performance studies (e.g., ROC analysis) to quantify this improvement.]

6. Standalone Algorithm Performance (Hypothetical)

• Was a standalone performance evaluation done? [e.g., Yes]
• Metrics: The algorithm demonstrated a standalone sensitivity of Y% and specificity of Z% for condition X on the test set. (As per the table above).

7. Type of Ground Truth Used (Hypothetical)

• Ground Truth Type: [e.g., Expert consensus (as described in point 4), confirmed by available clinical outcomes data and/or pathology reports where possible.]

8. Sample Size for Training Set (Hypothetical)

• Sample Size: [e.g., 10,000 cases]

9. How Ground Truth for Training Set was Established (Hypothetical)

• Method: [e.g., A combination of initial annotations by trained technicians or junior radiologists, followed by review and verification by a single or small panel of senior radiologists. Cases were sometimes cross-referenced with electronic health records for clinical context and pathology reports if available.]

Ask a specific question about this device

The GXR-Series Diagnostic X-Ray System, (Models GXR-SD, GXR-S, SGXR-S, FDR Smart FGXR-S), is a stationary X-ray imaging system, for the purpose of acquiring X-ray images of the desired parts of a patient's anatomy. This device is not intended for mammography or bone density applications.

The GXR-Series Diagnostic X-Ray System, (Models GXR-SD, GXR-S, SGXR-S, FDR Smart FGXR-S) is comprised of 2 main configurations: GXR-SD and GXR-S, with SGXR-S, FDR Smart FGXR-S being different brand names for GXR-S. Both configurations are designed to diagnose the human body by providing radiographic x-ray image with anatomical structure.

GXR-S, SGXR-S, FDR Smart FGXR-S (analog) and GXR-SD (digital) have the same xray hardware components. However, the GXR-SD model contains image management (PACS) software and a flat panel digital detector. Interoperability is defined in the DICOM Conformance Statement which is part of the device labeling and is based upon NEMA PS 3.1 - 3.20 (2016). Digital Imaging and Communications in Medicine (DICOM) Set DICOM Standard.

The GXR-S does not have image management software and does not have a digital detector.

The GXR-SD, GXR-S, SGXR-S, FDR Smart FGXR-S, models consist of a high voltage (HV) generator, a tube support unit, an X-ray beam limiting device, patient table, wall Bucky stand, and an x-ray tube, that operates on a high-frequency inverter method.

The operator control console is designed to be simple and user-friendly, and the user can select or change x-ray parameters easily using a large graphic LCD panel display and a soft membrane switch. The GXR Series, high frequency X-ray generator features accuracy, reproducibility and long-term stability with capacitor assisted general line power supply. The APR (Anatomical Programming) and the optional AEC (Automatic Exposure Control) features gives the user control of exposure factors, automatically optimized for the radiological study selected.

RADMAX Digital Imaging Software (K182537) by DRGEM, is used in the GXR-SD model to serve as an interface to the hardware and images. Anatomical view-based digital image processing automatically optimizes and enhances the quality of the captured images.

The provided document, a 510(k) Premarket Notification summary for the GXR-Series Diagnostic X-Ray System, does not contain the detailed information typically presented in a study proving a device meets acceptance criteria for an AI/CADe (Computer-Aided Detection/Diagnosis) system.

This document describes a traditional X-ray system, not an AI software. The performance data highlighted is primarily related to non-clinical testing, electrical safety, EMC (Electromagnetic Compatibility), and conformance to various medical device standards (e.g., IEC 60601 series, ISO 14971, NEMA PS 3.1 DICOM). These are standard requirements for X-ray hardware, not for AI software performance in diagnostic tasks.

Therefore, I cannot extract the requested information regarding acceptance criteria and study details for an AI/CADe system from this document. The sections you asked for, such as sample sizes for test and training sets, expert qualifications, and MRMC studies, would be found in a submission for an AI-powered diagnostic device, which this is not.

The "Performance Data" section in the document specifically mentions "Nonclinical Testing" and lists several international standards for electrical safety and electromagnetic compatibility (EMC), as well as software lifecycle processes (IEC 62304) and risk management (ISO 14971). It concludes that "Validation testing indicated that as required by the risk analysis, designated individuals performed all verification and validation activities and that the results demonstrated that the predetermined acceptance criteria were met." However, it does not specify what those acceptance criteria for clinical performance are, as it is a hardware device.

If you have a document describing an AI/CADe device, please provide that, and I will be able to answer your questions.

Ask a specific question about this device

The TOPAZ Mobile DR System, is a mobile X-ray imaging system, for the purpose of acquiring X-ray images of the desired parts of a patient's anatomy.

This device is not intended for mammography, bone density, fluoroscopy and angiography applications.

The TOPAZ Mobile DR System. (TOPAZ), is a mobile x-ray system. There are 2 models for TOPAZ: TOPAZ-32D (32KW) and TOPAZ-40D (40KW). TOPAZ, may be moved quietly and smoothly with a motor drive mechanism.

The core part of x-ray source is a tube assembly, motorized x-ray collimator, HV cable assembly and high frequency x-ray generator. A touch screen LCD based x-ray control console provides a user-friendly interface and technique selection. The Collimator supports high accuracy for selected x-ray field size over any SID. Selection of an anatomical study on the imaging software automatically sets up the x-ray generator's pre-programmed exposure technique. Direct radiography via a flat panel detector improves workflow, exam speed and user comfort with efficiency. Digital flat panel detector with Csl screen provides good spatial resolution, MTF, DQE and stability based on a fine pixel pitch. The digital detector type used in TOPAZ is "VARIAN PacScan4336W" or "VARIAN PacScan4336W_V4 which was cleared as part of the Nexus DR™ Digital X-ray Imaging System (with PaxScan 4336Wv4), K161459.

The X-ray passing through a patient's body is sent to the detector and then converted into electrical signals. These signals go through the process of amplification and digital data conversion in the signal process on the workstation and saved in a DICOM file for review on the device or on a Picture Archiving & Communication System (PACS) workstation Image Management features and functions are:

• ROI: Default 13 ROI support .
• MARK: Unlimited support (User preset support) ●
• Horizontal Flip ●
• Vertical Flip .
• Rotate Clockwise (CW) ●
• . Rotate Counter Clockwise (CCW)
• Inverse (Black or White) .
• . Text Annotation
• Caliper / Ruler: Distance tool
• Angle: Angle measurement tool
• Zoom: Image zoom in/out ●
• . Magnify: Image magnify glass window
• . Pan: Image panning

The provided text does not describe acceptance criteria for a device's performance that is proven by a study. Instead, it is a 510(k) summary for the TOPAZ Mobile DR System, which is a mobile X-ray imaging system. The purpose of this document is to demonstrate "substantial equivalence" to a predicate device, meaning it's as safe and effective as a device already on the market.

Therefore, many of the requested points cannot be directly extracted from this document as it focuses on regulatory equivalence rather than specific performance acceptance criteria from a clinical or standalone study.

However, I can extract information related to the non-clinical testing performed to establish safety and effectiveness in comparison to the predicate device.

Here's an analysis based on the provided text, addressing the points where information is available:

1. Table of acceptance criteria and the reported device performance

The document does not provide a table of acceptance criteria for device performance in terms of diagnostic accuracy (e.g., sensitivity, specificity). Instead, it refers to fulfilling predetermined testing criteria based on regulatory standards for X-ray systems.

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

• Sample Size: Not applicable in the context of diagnostic performance. The testing mentioned is non-clinical, focusing on compliance with safety and performance standards of the physical device and its software.
• Data Provenance: Not applicable. The testing was conducted at the factory and by "Standards testing facilities."

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)

• Not applicable as this document details non-clinical testing for substantial equivalence, not a study evaluating diagnostic performance against a ground truth.

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

• Not applicable. The "test set" here refers to the system itself being tested against regulatory standards, not image data being adjudicated.

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

• No. A MRMC comparative effectiveness study was explicitly NOT done. The document states: "Clinical testing is not necessary for the TOPAZ Mobile DR system in order to demonstrate substantial equivalence to the predicate device." This device is a basic X-ray system, not an AI-powered diagnostic tool.

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

• Not applicable. This device is an X-ray imaging system, not an algorithm, and its performance is evaluated in the context of its function to acquire images, not analyze them.

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

• Not applicable. For the non-clinical testing, the "ground truth" was the specifications and requirements outlined by the various recognized international and national standards (e.g., IEC, ANSI AAMI, NEMA, ISO).

8. The sample size for the training set

• Not applicable. There is no mention of a "training set" as this is not an AI/algorithmic device.

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

• Not applicable.

Ask a specific question about this device