Search Results

The PRORAD ATLAS ULTRAPORTABLE Digital X-ray system is intended to deliver high-quality, diagnostic radiographic images of the body extremities. It utilizes a portable X-ray unit, flat-panel detector and image acquisition software to produce clear digital images, enabling fast and accurate diagnosis. The portable X-ray unit is intended to be used only when stand/tripod mounted.

The PRORAD ATLAS ULTRAPORTABLE X-ray digital system is predominantly employed in various settings, including health-care centres, temporary and emergency health centres (established, especially in pandemic circumstances), outreach and field interventions (such as mobile clinics/vans, screening campaigns, and home care), and tele-radiology solutions in remote areas.

The primary users anticipated for the system include radiographers, radiological technologists, and medical professionals who are trained in safety, radiation protection, and image management.

The PRORAD ATLAS ULTRAPORTABLE PLUS Digital X-ray system is intended to deliver high-quality, diagnostic radiographic images of the body extremities. It utilizes a portable X-ray Unit, flat-panel detector and real-time image processing using software to produce clear digital images, enabling fast and accurate diagnosis. The portable X-ray unit is intended to be used only when stand/tripod mounted.

The PRORAD ATLAS ULTRAPORTABLE PLUS X-ray digital system is predominantly employed in various settings, including health-care centres, temporary and emergency health centres (established, especially in pandemic circumstances), outreach and field interventions (such as mobile clinics/vans, screening campaigns, and home care), and tele-radiology solutions in remote areas.

The primary users anticipated for the system include radiographers, radiological technologists, and medical professionals who are trained in safety, radiation protection, and image management.

The PRORAD ATLAS X-Ray system includes the ULTRAPORTABLE and ULTRAPORTABLE PLUS, which are portable diagnostic X-ray systems with fixed 70kV and 2mA tube current. These systems are intended to produce anatomical X-rays of the body extremities in both pediatric and adult patients. The PRORAD ATLAS X-Ray system was designed, developed, and manufactured by Prognosys Medical Systems Private Limited. The model numbers are listed below.

The PRORAD ATLAS X-ray system is a sophisticated, battery-powered X-ray generator offered in two versions: PRORAD ATLAS ULTRAPORTABLE and ULTRAPORTABLE PLUS. The main distinction between these models lies in their exposure time ranges and target anatomical areas. The ULTRAPORTABLE model provides exposure times ranging from 0.01 to 1.30 seconds, while the ULTRAPORTABLE PLUS model offers an extended exposure range of 0.01 to 2.5 seconds. Both models share identical internal components, software, algorithms, and operational features and are intended for imaging body extremities. The system includes a high-voltage tank with an X-ray tube mounted on an adjustable tripod stand, allowing users to adjust the height to the specific imaging area. Exposure parameters are configured through the X-ray generator's graphical user interface (GUI). After setting the parameters and positioning the patient on the detector, the X-ray is activated via an exposure switch. The detector captures the radiation, converts it into a digital signal, and transmits the data wirelessly to a computer equipped with compatible software. The images are processed and displayed on the computer for diagnostic review. The PRORAD ATLAS system is compatible with several 510(k)-cleared detectors and their associated software, listed below in Table 1. Prognosys includes one detector and its pre-configured software in the package, depending on availability. Fully battery-operated, the system does not support direct power connection but can seamlessly integrate with multiple detectors and compatible software as part of the package.

The provided FDA 510(k) clearance letter and supporting documentation for the PRORAD ATLAS ULTRAPORTABLE X-Ray Systems do not include acceptance criteria or a detailed study that proves the device meets specific performance criteria beyond general safety and effectiveness.

The document primarily focuses on demonstrating substantial equivalence to a predicate device (Remex KA6, K212144) rather than presenting a performance study with defined acceptance criteria. The "Summary of non-clinical testing" lists a series of international standards (IEC, ISO) and FDA guidance documents that were followed for design control, risk management, verification, and validation. The "Summary of clinical testing" mentions that clinical images were collected and reviewed by a qualified radiologist, confirming they are "clinically acceptable." However, specific quantitative acceptance criteria for image quality, diagnostic accuracy, or other performance metrics, along with the study design and results against those criteria, are not detailed in this document.

Therefore, I cannot provide a table of acceptance criteria and reported device performance, nor can I provide information about sample size, expert details, adjudication methods, MRMC studies, standalone performance, or training set specifics, as this information is not present in the provided text.

Based on the available text, here's what can be extracted:

• Overall Conclusion: The device is deemed "safe and effective when the device is used as labelled and is substantially equivalent to the predicate device."

Here's a breakdown of why the requested information cannot be fully provided based on the input:

1. A table of acceptance criteria and the reported device performance: This information is not explicitly stated in the document. The document confirms that "Validation of PRORAD ATLAS X-Ray System has demonstrated that the system enables optimal and quality imaging of anatomical structures" and that clinical images are "clinically acceptable," but no specific quantitative criteria or performance metrics are given.

2. Sample size used for the test set and the data provenance: The document states that "Clinical images of body extremities were collected from patients of varying ages, weights, and BMIs." However, the exact sample size and the provenance (e.g., country of origin, retrospective/prospective nature) of this clinical image test set are not specified.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts: The document mentions that images were "reviewed by a qualified radiologist." It does not specify the number of radiologists or their specific qualifications (e.g., years of experience, board certification).

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set: No adjudication method for the clinical image review is described.

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: An MRMC study is not mentioned. The device described is an X-ray system, not an AI software to assist human readers.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done: This is not applicable as the device is an X-ray system, not an algorithm, and it's intended to be used by trained medical professionals.

7. The type of ground truth used: The ground truth for the clinical images appears to be "clinical acceptability" as determined by a "qualified radiologist." This aligns with "expert consensus" in a general sense, but no more objective ground truth (e.g., pathology, outcomes data) is mentioned for the image quality assessment.

8. The sample size for the training set: The document does not mention a training set, as it describes an X-ray hardware system, not an AI-driven software that requires a training set.

9. How the ground truth for the training set was established: Not applicable, as no training set is mentioned.

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

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

The Discovery XR656 HD is intended to generate digital radiographic images of the skull, spinal column, chest, abdomen. extremities, and other body parts in patients of all ages. Applications can be performed with the patient sitting, standing. or lying in the prone or supine position and the system is intended for use in all routine radiography exams. Optional image pasting function enables the operator to stitch sequentially acquired radiographs into a single image.

The Discovery XR656 HD incorporates AutoGrid, which is an optional image processing software installed as a part of the systems Helix image processing software. AutoGrid can be used in lieu of an anti-scatter grid to improve image contrast in general radiographic images by reducing the effects of scatter radiation.

When the VolumeRAD option is included on the system can generate tomographic images of human anatomy including the skull, spinal column, chest, abdomen, extremities, and other body parts in patients of all ages.

When the VolumeRAD option is used for patients undergoing thoracic imaging, it is indicated for the detection of lung nodules. VolumeRad generates diagnostic images of the radiologist in achieving superior detectability of lung nodules versus posterior and left lateral views of the chest, at a comparable radiation level.

The device is not intended for mammographic applications.

The Discovery XR656 HD Radiography X-ray System is designed as a modular system with components that include an Overhead Tube Suspension with tube/collimator, wallstand, Table, X-ray generator, and cleared wireless digital detectors. The list of detectors verified and validated for use with the Discovery XR656 HD system, including their specifications, are provided in the user documentation. The System generates diagnostic radiographic images which can be sent through a DICOM network for applications including printing, viewing, and storage.
The components may be combined in different configurations to meet specific customer needs. In addition, upgrade configurations are available for predicate devices.
The optional image pasting function enables the operator to stitch sequentially acquired radiographs into a single image.
This 510(k) is to incorporate the VolumeRad advanced application that was currently available on the Discovery XR656 product onto the Discovery XR656 HD, as well as introduce a new Metal Artifact Reduction Algorithm, and an optional standalone console to take any Helix™ acquired images via DICOM (such as from a Discovery XR656 HD, Optima XR646 HD, or Optima XR240amx) and process the images independently of the system it was acquired on.

This document is a 510(k) Premarket Notification submission for the GE Healthcare Discovery XR656 HD with VolumeRad. The submission details the device's technical characteristics, intended use, and a comparison to predicate and reference devices to establish substantial equivalence.

Based on the provided text, the device itself (Discovery XR656 HD with VolumeRad) is an X-ray system, not an AI or algorithm. Therefore, the questions related to AI performance metrics such as reader improvement with AI assistance, standalone algorithm performance, and sample sizes for training/test sets specifically for an AI component are not directly applicable.

However, the document does describe the "Metal Artifact Reduction algorithm for VolumeRad" and mentions its evaluation. This suggests an algorithmic component, though not an AI in the common sense of machine learning for diagnosis. The data provided focuses on demonstrating substantial equivalence to predicate devices for the overall system and its features, including the VolumeRad function with updated detectors and the metal artifact reduction algorithm.

Here's an analysis based on the information available, addressing the relevant points:

1. Table of Acceptance Criteria and Reported Device Performance:

The document primarily focuses on establishing substantial equivalence for the Discovery XR656 HD with VolumeRad to predicate devices, rather than defining specific acceptance criteria for a new AI algorithm and reporting its performance against those. The "performance" discussed is related to the overall system's safety and effectiveness, and the ability of the VolumeRad feature to generate diagnostic images comparable to or better than traditional views for lung nodule detection.

The statement regarding VolumeRad: "VolumeRad generates diagnostic images of the radiologist in achieving superior detectability of lung nodules versus posterior and left lateral views of the chest, at a comparable radiation level." acts as a performance claim for the VolumeRad feature itself, which is part of the device.

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

• Test Set for VolumeRad feature and Metal Artifact Reduction Algorithm: The document states that "bench testing using anthropomorphic phantoms was sufficient" for evaluating the Metal Artifact Reduction algorithm and for showing the equivalence of the VolumeRad feature with updated resolution detectors.
  • Sample Size: Not explicitly stated as a number of cases or patients from a clinical study for the test set. It refers to "anthropomorphic phantoms."
  • Data Provenance: Not human clinical data. The data originates from "anthropomorphic phantoms" used in bench testing. Given it's a GE Healthcare product, typically such testing occurs internally or at partner facilities. The location of the manufacturer is China.
  • Retrospective/Prospective: Not applicable as it's bench testing with phantoms.

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

• Since the testing was primarily bench testing with anthropomorphic phantoms, there is no mention of human experts establishing ground truth in the context of reading images from a test set. Evaluation would likely involve technical measurements and visual assessment by product development engineers or possibly consulting radiologists for image quality, but this isn't described as a formal ground truth process for a clinical test set.

4. Adjudication Method for the Test Set:

• Not applicable, as the evaluation was primarily bench testing with phantoms.

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

• No, a multi-reader multi-case (MRMC) comparative effectiveness study comparing human readers with and without AI assistance was not done. The submission explicitly states: "The subject of this premarket submission, Discovery XR656 HD with VolumeRad, did not require clinical studies to support substantial equivalence for the changes identified."
• Effect Size: Not determined, as no such study was performed.

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

• The document implies that the fundamental algorithm to create the VolumeRad image set is identical to the algorithm cleared under K132261. The Metal Artifact Reduction algorithm was evaluated via bench testing. While these are algorithmic components, the overall "device" is an X-ray system. The performance claims for VolumeRad are implicitly related to its ability to present images that aid the radiologist (human-in-the-loop). Bench testing of the algorithms was done, but not as a standalone diagnostic AI performance study in the typical sense for clinical claims.

7. Type of Ground Truth Used:

• For the technical evaluation of the VolumeRad feature and the Metal Artifact Reduction algorithm, the "ground truth" was established through bench testing using anthropomorphic phantoms. This means known conditions (e.g., presence/absence of nodules, specific metal artifacts) were simulated in the phantoms to assess the system's output.

8. Sample Size for the Training Set:

• The document does not describe the development of a new AI algorithm that would typically involve a "training set." The VolumeRad algorithm is stated to be "identical" to a previously cleared algorithm. The Metal Artifact Reduction algorithm is new, but its development process (including any training data if it were a machine learning algorithm) is not detailed. Therefore, the sample size for a training set is not provided.

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

• Not applicable as no specific "training set" for a new AI algorithm is described. For the general development of the overall system and its included algorithms, ground truth would be established through engineering specifications, phantom studies for image quality, and comparison against known physical properties.

Ask a specific question about this device