Search Results

The Definium Tempo Select 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.

This device is not intended for mammographic applications.

The Definium Tempo Select Radiography X-ray System is designed as a modular system with components that include an Overhead Tube Suspension (OTS) with a tube, an auto collimator and a depth camera, an elevating table, a motorized wall stand, a cabinet with X-ray high voltage generator, a wireless access point and wireless detectors in exam room and PC, monitor and control box with hand-switch in control room. The system generates diagnostic radiographic images which can be reviewed or managed locally and sent through a DICOM network for applications including reviewing, storage and printing.

By leveraging platform components/ design, Definium Tempo Select is similar to the predicate device Discovery XR656 HD (K191699) and the reference device Definium Pace Select (K231892) with regards to the user interface layout, patient worklist refresh and selection, protocol selection, image acquisition, and image processing based on the raw image. This product introduces a new high voltage generator which has the same key specifications as the predicate. A wireless detector used in referenced product Definium Pace Select is introduced. Image Pasting is improved with individual exposure parameter adjustable on images on both Table and Wall Stand Mode. Tube auto angulation is added for better auto positioning based on current auto-positioning. Camera Workflow is introduced based on existing depth camera. OTS is changed with 4 axis motorizations. An update was made to the previously cleared Tissue Equalization feature under K013481 to introduce a Deep Learning AI model that provides more consistent image presentations to the user which reduces additional workflow to adjust the image display parameters. The other minor changes including PC change, Wall Stand change and Table change.

The provided FDA 510(k) clearance letter and summary for the Definium Tempo Select offers some, but not all, of the requested information regarding the acceptance criteria and the study proving the device meets them. Notably, specific quantitative acceptance criteria for the AI Tissue Equalization feature are not explicitly stated.

Here's a breakdown of the available information and the identified gaps:

1. Table of Acceptance Criteria and Reported Device Performance

Note: The 510(k) summary does not explicitly list quantitative acceptance criteria for the AI Tissue Equalization algorithm. Instead, it states that "The verification tests confirmed that the algorithm meets the performance criteria, and the safety and efficacy of the device has not been affected." Without specific performance metrics or thresholds, a direct comparison in a table format is not possible for the AI component.

For the overall device, the acceptance criteria are implicitly performance metrics that ensure it functions comparably to the predicate device, as indicated by the "Equivalent" and "Identical" discussions in Table 1 (pages 7-11). However, these are primarily functional and technical equivalency statements rather than performance metrics for the AI feature.

Therefore, this section will focus on the AI Tissue Equalization feature as it's the part that underwent specific verification using a clinical image dataset.

AI Tissue Equalization Feature:

Missing Information:

• Specific quantitative metrics (e.g., AUC, sensitivity, specificity, image quality scores, expert rating differences) that define "more consistent image presentations" are not provided.
• The exact thresholds or target values for these metrics are not stated.

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

• Test Set Sample Size: Not explicitly stated as a number of images or cases. The document refers to "clinical images retrospectively collected across various anatomies...and Patient Sizes."
• Data Provenance: Retrospective collection from locations in the US, Europe, and Asia.

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

Missing Information. The document does not specify:

• The number of experts involved in establishing ground truth.
• Their qualifications (e.g., specific subspecialty, years of experience, board certification).
• Whether experts were even used to establish ground truth for this verification dataset, as the purpose was to confirm the AI met performance criteria rather than to directly compare its diagnostic accuracy against human readers or a different ground truth standard.

4. Adjudication Method for the Test Set

Missing Information. No adjudication method (e.g., 2+1, 3+1) is described for the test set.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done

No. A Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not explicitly mentioned or described in the provided document. The verification tests focused on the algorithm meeting performance criteria, not on comparing human reader performance with or without AI assistance.

• Effect Size: Not applicable, as no MRMC study was described.

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

Yes, implicitly. The "AI Tissue Equalization algorithms verification dataset" was used to perform "verification tests" to confirm that "the algorithm meets the performance criteria, and the safety and efficacy of the device has not been affected." This suggests a standalone evaluation of the algorithm's output (image presentation consistency) against specific, albeit unstated, criteria. While human review of the output images was likely involved, the study's stated purpose was to verify the algorithm itself.

7. The Type of Ground Truth Used (Expert Consensus, Pathology, Outcomes Data, etc.)

Implied through image processing improvement, not diagnostic ground truth. For the AI Tissue Equalization feature, the "ground truth" is not in the traditional clinical diagnostic sense (e.g., disease presence confirmed by pathology). Instead, it appears to be related to the goal of "more consistent image presentations" and improving "contrast and visibility in over-penetrated and under-penetrated regions." This suggests the ground truth was an ideal or desired image presentation quality rather than a disease state. It's likely based on existing best practices for image processing and subjective assessment of image quality by experts, or perhaps a comparative assessment against the predicate's tissue equalization.

Missing Information: The precise method or criteria for this ground truth (e.g., a panel of radiologists rating image quality, a quantitative metric for contrast/visibility) is not specified.

8. The Sample Size for the Training Set

Missing Information. The document describes the "verification dataset" (test set) but does not provide any information on the sample size or composition of the training set used to develop the Deep Learning AI model for Tissue Equalization.

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

Missing Information. As the training set size and composition are not mentioned, neither is the method for establishing its ground truth. It can be inferred that the training process involved data labeled or optimized to achieve "more consistent image presentations" by dynamically estimating thick and thin regions, likely through expert-guided optimization or predefined image processing targets.

Ask a specific question about this device

The OEC One ASD mobile C-arm system is designed to provide fluoroscopic and digital spot images of adult and pediatic patient populations during diagnostic, interventional, and surgical procedures. Examples of a clinical application may include: orthopedic, gastrointestinal, endoscopic, urologic, vascular, critical care, and emergency procedures.

The OEC One ASD is a mobile C-arm X-ray system to provide fluoroscopic images of the patient during diagnostic, interventional, and surgical procedures such as orthopedic, gastrointestinal, endoscopic, urologic, neurologic, vascular, critical care, and emergency procedures. These images help the physician visualize the patient's anatomy and localize clinical regions of interest. The system consists of a mobile stand with an articulating arm attached to it to support an image display monitor (widescreen monitor) and a TechView tablet, and a "C" shaped apparatus that has a flat panel detector on the top of the C-arm and the X-ray Source assembly at the opposite end.

The OEC One ASD is capable of performing linear motions (vertical, horizontal) and rotational motions (orbital, lateral, wig-wag) that allows the user to position the X-ray image chain at various angles and distances with respect to the patient anatomy to be imaged. The C- arm is mechanically balanced allowing for ease of movement and capable of being "locked" in place using a manually activated lock.

The subject device is labelled as OEC One ASD.

The provided document is a 510(k) Summary of Safety and Effectiveness for the GE Hualun Medical Systems Co. Ltd. OEC One ASD, a mobile C-arm X-ray system. The document focuses on demonstrating substantial equivalence to a predicate device, OEC One (K182626), rather than presenting a study with specific acceptance criteria and detailed device performance results for a new AI/CAD feature.

The submission is for a modification of an existing device, primarily introducing an amorphous silicon (a-Si) flat panel detector as the image receptor and updating some hardware and software components. The changes are stated to enhance device performance and are discussed in terms of their impact on safety and effectiveness, concluding that no new hazards or concerns were raised.

Therefore, the information required for a detailed description of acceptance criteria and a study proving device performance, especially for AI/CAD features, is largely not present in this document. The document centers on demonstrating that the modified device maintains safety and effectiveness and is substantially equivalent to the predicate, rather than detailing a study against specific acceptance criteria for a novel functionality.

However, I can extract the available relevant information and highlight what is missing based on your request.

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly define "acceptance criteria" in the context of a study demonstrating novel AI/CAD feature performance. Instead, it presents a comparison table of technical specifications between the proposed device (OEC One ASD) and the predicate device (OEC One K182626) to demonstrate substantial equivalence. The "Acceptance Criteria" here are implicitly derived from the predicate's performance and safety profiles.

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

This information is not provided in the document. The submission states, "comparative clinical images were evaluated to demonstrate substantial equivalence for the OEC One ASD compared to the cleared predicate," but no details on the sample size, data provenance (e.g., country of origin, retrospective/prospective nature), or specific evaluation methodology for these clinical images are given.

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)

This information is not provided in the document. The document states that "comparative clinical images were evaluated," but it does not specify the number or qualifications of experts involved in this evaluation or the establishment of ground truth.

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

This information is not provided in the document. The method used to resolve discrepancies or establish a consensus for the evaluation of comparative clinical images is not 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

A multi-reader multi-case (MRMC) comparative effectiveness study focusing on human reader improvement with AI assistance was not mentioned or described in this 510(k) submission. The document discusses device modifications and their impact on image quality and functionality, but not the comparative effectiveness of human readers utilizing AI.

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

This submission does not describe a standalone performance study for an AI algorithm. The device itself is an X-ray system, and while it has "Image Processing" features, these are not presented as standalone AI algorithms for diagnostic assistance but rather as integrated components affecting image generation and display characteristics. The update to ADRO from CPU to GPU based processing is noted for speed, but its standalone performance as an AI algorithm is not evaluated or presented.

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

The document mentions "comparative clinical images were evaluated," but it does not specify the type of ground truth against which these images were assessed. Since the primary focus is on demonstrating substantial equivalence of technical image characteristics rather than validating a diagnostic AI output, a traditional "ground truth" (like pathology or outcomes a specific AI would predict) is not explicitly detailed. The implicit ground truth would be the expected imaging performance and diagnostic utility comparable to the predicate device.

8. The sample size for the training set

This information is not provided in the document. The document describes modifications to an existing X-ray system, including software updates. It states, "Its software is based on the architecture, design and code base of the predicate device OEC One (K182626)," and underwent a standard software development lifecycle. There is no mention of a separate "training set" in the context of an AI/CAD algorithm as typically understood for deep learning models.

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

Since no training set for an AI/CAD algorithm is mentioned (refer to point 8), the method for establishing its ground truth is not applicable/provided in this document.

Ask a specific question about this device

The Definium Pace Select ET 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. This device is not intended for mammographic applications.

The Definium Pace Select ET Radiography X-ray System is designed as a modular system with components that include a 2-axis motorized tube stand with tube and auto collimator assembled on an elevating table, a motorized wall stand, a cabinet with X-ray high voltage generator, a wireless access point, wireless detectors, an acquisition workstation including a monitor and control box with hand-switch. The system generates diagnostic radiographic images which can be reviewed or managed locally and sent through a DICOM network for reviewing, storage and printing.

By leveraging platform components / design, Definium Pace Select ET is similar to the predicate Definium Pace Select (K231892) and the reference Discovery XR656 HD (K191699) with regards to the user interface layout, patient worklist refresh and selection, protocol selection, image acquisition, and image processing based on the raw image. This product introduces motorized tube stand (vertical and tube angulation) instead of manual tube stand of the predicate. The high voltage generator is new and is backwards compatible to the predicates high voltage generator. This product also introduced Image Pasting on Table and Wall Stand Mode, Auto tracking for Wall Stand, Auto Angulation, Camera Workflow, DAP software calculation, Siemens LED collimator and LCD touch screen console. The other minor changes include updates to components due to obsolescence.

The provided document is a 510(k) premarket notification for a medical device called "Definium Pace Select ET." It describes the device, its intended use, and compares its technological characteristics to a predicate device ("Definium Pace Select") and a reference device ("Discovery XR656 HD").

However, this document does not contain any performance data or details of a clinical study that proves the device meets specific acceptance criteria based on AI or human reading performance.

The "PERFORMANCE DATA" section explicitly states: "The Definium Pace Select ET does not contain clinical testing data." Instead, it lists non-clinical tests performed, such as Risk Analysis, Requirements Reviews, Design Reviews, and various levels of verification testing (unit, integration, performance, safety, simulated use). These non-clinical tests are aimed at confirming the safety and effectiveness of the device as it relates to changes from the predicate, rather than evaluating specific clinical diagnostic performance metrics with a test set, ground truth, and human readers.

Therefore, I cannot fulfill your request to describe the acceptance criteria and the study that proves the device meets the acceptance criteria, as the provided input does not contain this information.

Ask a specific question about this device

This product is intended to generate digital radiographic images of the skull, spinal column, 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. This device is not intended for mammographic applications.

The Definium Pace Select is a Digital Radiographic System designed as a modular system with components that includes fixed table with tube-stand, wallstand, cleared wireless digital detector, X-ray tube, collimator, high kV generator and acquisition workstation in control room. 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 grouped into different configurations to meet specific customer needs.

The FDA 510(k) summary for the Definium Pace Select, a Digital Radiographic System, indicates that clinical studies were not required to support substantial equivalence for this device. Therefore, a study proving the device meets specific acceptance criteria in terms of clinical performance (like sensitivity, specificity, or reader improvement with AI assistance) or a detailed clinical acceptance criteria table for such measures is not provided in this document.

The submission focuses primarily on demonstrating substantial equivalence to its predicate device (Discovery XR656 HD) based on non-clinical tests, technological characteristics, and safety/effectiveness data. The device's safety and effectiveness were confirmed through design verification and validation testing.

Here's a breakdown of the relevant information from the provided text:

1. Table of Acceptance Criteria and Reported Device Performance:

Since clinical studies were not deemed necessary for this 510(k) submission, there isn't a table presenting clinical acceptance criteria (e.g., sensitivity, specificity) and corresponding device performance metrics in the document. The acceptance criteria focused on compliance with voluntary standards and successful completion of verification and validation testing.

• ES 60601-1:2005/(R)2012 & A1:2012, C1:2009/(R)2012 & A2:2010/(R)2012
• IEC 60601-1-2:2014[Including AMD 1:2021]
• IEC 60601-1-3: 2021
• IEC 60601-1-6: 2020
• IEC 60601-2-54: 2018
• IEC 62366: 2015 + AMD1:2020
• ISO 10993-1: 2018
• ISO 10993-5: 2009/(R)2014
• ISO 10993-10: 2010/(R)2014
• ISO 10993-18 Second edition 2020-01
• PS 3.1 - 3.20: 2022d (DICOM set) |
  | Quality Assurance Measures | Applied: Risk Analysis, Requirements Reviews, Design Reviews, Unit level testing (Module verification), Integration testing (System verification), Performance testing (Verification), Safety testing (Verification), Simulated use testing (Validation). |
  | Risk Mitigation | Risks for new floor mounted positioners and image chain were evaluated, mitigated with design controls and labeling. Mitigations were verified and validated with acceptable results. |
  | Design Verification & Validation | Performed to confirm safety and effectiveness; test plans and results were executed with acceptable results. |

2. Sample Size for Test Set and Data Provenance:

No distinct "test set" in the context of clinical performance evaluation (e.g., images for diagnostic accuracy assessment) is mentioned because clinical studies were not required. The "testing" referred to in the document pertains to design verification and validation, which would involve hardware and software testing, rather than a clinical image dataset.

3. Number of Experts for Ground Truth and Qualifications:

Not applicable, as no clinical study requiring expert ground truth establishment for diagnostic accuracy was conducted for this submission.

4. Adjudication Method:

Not applicable, as no clinical study requiring adjudication of expert interpretations was conducted.

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

No MRMC study was conducted. The device is a digital radiographic system, and the submission emphasizes its substantial equivalence based on technological characteristics and safety, not on AI assistance to human readers.

6. Standalone (Algorithm Only) Performance:

Not explicitly detailed in terms of a standalone diagnostic performance study, as the device itself is an imaging system, not a standalone diagnostic algorithm. The "image processing with same algorithm" as the predicate device suggests the algorithms are part of the overall system functionality, not a separate AI diagnostic tool.

7. Type of Ground Truth Used:

For the non-clinical tests and design verification/validation, the "ground truth" would be established through engineering specifications, regulatory compliance standards, and functional requirements. For example, for radiation output, the ground truth would be the expected range defined by standards and the device's design. There is no mention of clinical ground truth (e.g., pathology, outcomes data) being used for this 510(k) submission.

8. Sample Size for Training Set:

Not applicable, as this device submission is for a digital radiographic system, not an AI/ML algorithm that typically requires a training set of data for development. The reference to "same algorithm" for image processing as the predicate implies existing, validated algorithms rather than newly trained ones.

9. How Ground Truth for Training Set Was Established:

Not applicable, as this device is not presented as an AI/ML system requiring a training set with established ground truth.

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

The OEC One™ mobile C-arm system is designed to provide fluoroscopic and digital spot images of adult and pediatric patient populations during diagnostic, interventional, and surgical procedures. Examples of a clinical application may include: orthopedic, gastrointestinal, endoscopic, urologic, neurologic, vascular, critical care, and emergency procedures.

The OEC One™ is a mobile C-arm x-ray system to provide fluoroscopic images of the patient during diagnostic, interventional, and surgical procedures such as orthopedic, gastrointestinal, endoscopic, urologic, vascular, neurologic, critical care, and emergency procedures. These images help the physician visualize the patient's anatomy and localize clinical regions of interest. The system consists of a mobile stand with an articulating arm attached to it to support an image display monitor (widescreen monitor) and a TechView tablet, and a "C" shaped apparatus that has an image intensifier on the top of the C-arm and the X-ray Source assembly at the opposite end.

The OEC One™ is capable of performing linear motions (vertical, horizontal) and rotational motions (orbital, lateral, wig-wag) that allow the user to position the X-ray image chain at various angles and distances with respect to the patient anatomy to be imaged. The C- arm is mechanically balanced allowing for ease of movement and capable of being "locked" in place using a manually activated lock.

The subject device is labelled as OEC One.

The provided text is a 510(k) Premarket Notification Submission for the OEC One with vascular option. This document primarily focuses on establishing substantial equivalence to a predicate device (OEC One, K172700) rather than presenting a detailed study with acceptance criteria for device performance in the context of an AI/algorithm-driven device.

The "device" in this context is an X-ray imaging system (OEC One™ mobile C-arm system), and the changes described are hardware and software modifications to enhance vascular imaging features. It is not an AI or algorithm-only device with specific performance metrics like sensitivity, specificity, or AUC.

Therefore, most of the requested information regarding acceptance criteria for AI performance, sample sizes for test/training sets, expert ground truth, adjudication methods, MRMC studies, or standalone algorithm performance is not applicable or cannot be extracted from this document.

However, I can extract information related to the device's technical specifications and the testing performed to demonstrate its safety and effectiveness.

Here is a summary of the information that can be extracted, addressing the closest relevant points:

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

The document does not provide a table of numerical acceptance criteria (e.g., sensitivity, specificity) for the device's imaging performance in relation to clinical outcomes. Instead, the acceptance criteria are generally implied by conformance to existing standards and successful completion of various engineering and verification tests. The "reported device performance" refers to the device meeting these design inputs and user needs.

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

• Test Set Sample Size: Not explicitly stated in terms of patient data. The testing involved "anthropomorphic phantoms" for image performance and various engineering/bench testing for functional validation. These are not "test sets" in the typical sense of a dataset for an AI algorithm.
• Data Provenance: Not applicable as it's not patient data for AI evaluation. The testing was conducted internally at GE Hualun Medical Systems Co., Ltd.

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

• Number of Experts: Not applicable. Ground truth from experts is not mentioned for this type of device evaluation.
• Qualifications of Experts: Not applicable.

4. Adjudication method for the test set

• Adjudication Method: Not applicable. There was no expert adjudication process described for the testing performed.

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: No. This document describes a C-arm X-ray system, not an AI-assisted diagnostic tool that would typically undergo such a study.
• Effect Size of Human Readers: Not applicable.

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

• Standalone Performance: Not applicable. The device is an imaging system; its "performance" is inherently tied to image acquisition and display, which are used by a human operator/physician. The "vascular features" are software enhancements to the imaging workflow, not a standalone AI algorithm.

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

• Type of Ground Truth: For image quality, the ground truth was based on physical phantom characteristics and established technical standards (e.g., image resolution, contrast, noise, dose measurements). For functional aspects, it was based on meeting design inputs and user requirements validated through engineering tests. No expert consensus, pathology, or outcomes data were used as "ground truth" for this device's substantial equivalence declaration.

8. The sample size for the training set

• Training Set Sample Size: Not applicable. This document does not describe an AI model that requires a training set. The software updates are feature additions and modifications, not learned from a large dataset in the way a deep learning model would be.

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

• Ground Truth Establishment: Not applicable, as there is no mention of an AI model with a training set.

Ask a specific question about this device

The Optima XR646 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 device is not intended for mammographic applications.

The Optima XR646 HD is designed to be a lower cost version of the predicate device, the Discovery XR656 HD (K172869). Like the Discovery XR656 HD, the Optima XR646 HD is a radiographic X-ray system capable of generating radiographic images of human anatomy.
The Optima XR646 HD is designed to support radiographic applications using previously cleared flat panel wireless digital detectors. The system generates digital images for general radiography by means of its X-Ray image chain. The resulting digital image can be sent through a DICOM network for applications such as printing, viewing and storage.

The provided text is a 510(k) Premarket Notification from GE Healthcare for their Optima XR646 HD device. This document primarily focuses on demonstrating substantial equivalence to a predicate device, rather than presenting a detailed study of an AI/ML algorithm's performance against specific acceptance criteria.

The acceptance criteria described in the request are common for evaluations of AI/ML-driven medical devices (e.g., studies measuring diagnostic accuracy, reader performance improvement, etc.). However, the content of this 510(k) submission does not include such a study.

Instead, the submission for the Optima XR646 HD focuses on:

• Technological Equivalence: The device employs the same fundamental scientific technology as its predicate and reference devices (Discovery XR656 HD and Optima XR646, respectively).
• Identical Intended Use and Indications for Use: The new device is intended for the same purposes as the predicate.
• Hardware Changes: The primary difference is a change from five-axis motorized motion to one-axis motorized motion in the Overhead Tube Suspension (OTS), which affects the image pasting function's acquisition method (parallel sequence instead of rotating the x-ray tube).
• Compliance with Standards: The device complies with relevant IEC and DICOM standards.
• Quality Assurance Measures: Standard development processes like risk analysis, requirements reviews, design reviews, and various levels of testing (unit, integration, performance, safety, simulated use) were applied.
• No Clinical Studies Required: The submission explicitly states, "The subject of this premarket submission, Optima XR646 HD, does not require clinical studies to support substantial equivalence". This is a key point, as it indicates that no formal clinical trial or reader study (as implied by the questions regarding MRMC, human-in-the-loop, etc.) was deemed necessary by the manufacturer for this particular submission.

Therefore, I cannot provide the requested table and study details because the provided document does not contain an AI/ML device performance study. The device described is a traditional X-ray system, and its substantial equivalence is based on engineering changes and compliance with established standards, not on a new AI/ML algorithm requiring performance validation in the manner described by your questions.

In summary, there is no information in the provided document to answer the specific questions about acceptance criteria, test set details, expert ground truth, MRMC studies, or standalone algorithm performance, as these methodologies are typically applied to AI/ML software as a medical device (SaMD) or AI-augmented devices, which is not what this 510(k) describes.

Ask a specific question about this device

The OEC One™ mobile C-arm system is designed to provide fluoroscopic and digital spot/film images of adult and pediatric patient populations during diagnostic, interventional, and surgical procedures. Examples of a clinical application may include: orthopedic, gastrointestinal, endoscopic, urologic, neurologic, critical care, and emergency procedures.

The OEC One™ is a mobile C-arm x-ray system to provide fluoroscopic images of the patient during diagnostic, interventional, and surgical procedures such as orthopedic, gastrointestinal, endoscopic, urologic, neurologic, critical care, and emergency procedures. These images help the physician visualize the patient's anatomy and localize clinical regions of interest. The system consists of a mobile stand with an articulating arm attached to it to support an image display monitor (widescreen monitor) and a TechView tablet, and a "C" shaped

Based on the provided text, the device in question is the OEC One™ mobile C-arm system, which is an image-intensified fluoroscopic X-ray system. The document is a 510(k) Premarket Notification Submission, indicating that the manufacturer is seeking to demonstrate substantial equivalence to a legally marketed predicate device rather than provide evidence of a novel device's safety and effectiveness.

Therefore, the "acceptance criteria" and "study that proves the device meets the acceptance criteria" are framed within the context of demonstrating substantial equivalence to the predicate device (K123603 OEC Brivo), rather than proving the device's de novo performance against specific clinical metrics as one might expect for a new AI/CADx device.

Here's an analysis of the provided information in response to your specific questions:

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

The document does not present a table of specific performance acceptance criteria (e.g., sensitivity, specificity, accuracy) for a diagnostic output, as this is an imaging device rather than a diagnostic AI/CADx algorithm. Instead, the acceptance criteria are linked to demonstrating that the modified device maintains the same safety and effectiveness as the predicate device, especially considering the changes made (integration of mainframe/workstation, new display, software updates).

The "acceptance criteria" for this 510(k) appear to be:

• Conformance to relevant safety and performance standards: IEC 60601-1 Ed. 3 series (including IEC60601-2-54 and IEC 60601-2-43), and all applicable 21 CFR Subchapter J performance standards.
• Successful verification and validation: Demonstrating that the system met design input and user needs, including hazard mitigation.
• Maintenance of comparable image quality: Assessed through engineering bench testing using anthropomorphic phantoms.
• Compliance with software development requirements: For a "Moderate" level of concern device.

• All applicable 21CFR Subchapter J performance standards are met. |
  | Verification and Validation | - Verification and validation including hazard mitigation has been executed with results demonstrating the OEC One™ system met design input and user needs.
• Developed under GE Healthcare's Quality Management System, including design controls, risk management, and software development life cycle processes.
• Quality assurance measures applied: Risk Analysis, Required Reviews, Design Reviews, Unit Testing (Sub System verification), Integration testing (System verification), Performance testing (Verification), Safety testing (Verification), Simulated use testing (Validation). |
  | Image Quality/Performance (Non-Clinical) | - Additional engineering bench testing on image performance using anthropomorphic phantoms was performed.
• All the image quality/performance testing identified for fluoroscopy found in FDA's "Information for Industry: X-ray Imaging Devices - Laboratory Image Quality and Dose Assessment, Tests and Standards" was performed with acceptable results. |
  | Software Compliance | - Substantial equivalence was also based on software documentation for a "Moderate" level of concern device. |
  | Clinical Equivalence (No Clinical Study) | - "Because OEC One's modification based on the predicate device does not change the system's intended use and represent equivalent technological characteristics, clinical studies are not required to support substantial equivalence." This indicates the acceptance criterion for clinical performance was met by demonstrating the modifications did not impact the clinical function or safety relative to the predicate. |

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 applicable in the context of clinical images with human expert ground truth for an AI/CADx device. The testing described focuses on non-clinical engineering bench tests using anthropomorphic phantoms and system verification/validation against standards.
• Data Provenance: The document states "Additional engineering bench testing on image performance using anthropomorphic phantoms was also performed." This implies a prospective generation of test data using physical phantoms, rather than retrospective or prospective clinical patient data. The country of origin for this testing is not explicitly stated beyond the manufacturer's location (China).

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. The testing described is primarily engineering and performance verification using phantoms and standards, not clinical image interpretation requiring expert radiologists to establish ground truth for a diagnostic task.

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

• Not applicable, as there is no clinical image-based test set requiring human adjudication.

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 MRMC study was done. The document explicitly states: "Clinical testing: Because OEC One’s modification based on the predicate device does not change the system’s intended use and represent equivalent technological characteristics, clinical studies are not required to support substantial equivalence." This is not a study of AI assistance.

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

• Not applicable. This is not an AI/CADx algorithm. The device itself is an X-ray imaging system. The software updates mentioned ("Adaptive Dynamic Range Optimization(ARDO) and motion artifact reduction") relate to image processing within the device itself, not a separate standalone diagnostic algorithm.

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

• The "ground truth" for the device's performance is established through:
  • Engineering benchmarks and physical phantom measurements: For image quality assessment against established standards (e.g., FDA's "Information for Industry: X-ray Imaging Devices - Laboratory Image Quality and Dose Assessment, Tests and Standards").
  • Compliance with international safety and performance standards: IEC 60601 series, 21 CFR Subchapter J.
  • Conformance to design specifications and user needs: Through verification and validation activities.

8. The sample size for the training set

• Not applicable. This is not a machine learning or AI device that requires a training set in the conventional sense. The "software updates" mentioned are more likely based on engineering principles and signal processing than machine learning training.

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

• Not applicable, as there is no explicit "training set" for an AI algorithm. Software development and calibration would typically rely on engineering specifications, physical models, and potentially empirical adjustments based on performance testing.

Ask a specific question about this device

The Optima XR646 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 is intended for use in all routine radiography exams.

The device is not intended for mammographic applications.

The Optima XR646 remains a radiographic X-ray system capable of generating radiographic images of human anatomy.

The Optima XR646 is designed to handle radiographic applications using GE's flat-panel wireless digital detector. The digital detector is comprised of amorphous silicon and cesium iodide scintillator. The resulting digital image can be sent through a DICOM network for applications such as printing, viewing and storage.

The Optima XR646 Digital Radiographic Imaging system consists of a WallStand, elevating table, overhead Tube support, X-ray tube, collimator, system controller, X-ray generator, and wireless or tethered digital detector. Various configurations such as Table only, WallStand only, or OTS only are available to meet customer radiographic requirements.

The provided document is a 510(k) Premarket Notification for the GE Optima XR646, a digital radiographic X-ray system. It focuses on demonstrating substantial equivalence to predicate devices rather than providing detailed acceptance criteria and a standalone study for a new AI-powered diagnostic device.

Therefore, the document does not contain the information required to answer your request fully. Specifically:

• No acceptance criteria for an AI device are mentioned. The document discusses regulatory compliance for an X-ray system.
• No study proving an AI device meets acceptance criteria. The document states that clinical studies were not required to support substantial equivalence for this X-ray system, and changes were verified and validated through bench testing.
• No information on sample size for test sets, data provenance, expert ground truth, adjudication methods, MRMC studies, standalone performance, or training set details for an AI algorithm. These are all concepts related to the evaluation of AI/ML-driven diagnostic devices, which is not the subject of this 510(k) submission.

The 510(k) submission details the device description, intended use, indications for use, and a comparison to predicate devices, focusing on the system's hardware and basic radiographic image generation capabilities. It highlights that the changes precipitating this 510(k) were related to hardware modifications and software control for the Image Pasting feature, and that these changes were validated through bench testing to ensure they did not introduce new safety or effectiveness issues.

In summary, this document is about the regulatory clearance of an X-ray imaging system, not an AI-powered diagnostic tool, and thus does not include the specific details you requested regarding AI acceptance criteria and studies.

Ask a specific question about this device